From 6f6ef07f412c5bfc37cde57e94b1fec789471907 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 20 Jul 2016 11:30:34 +0300 Subject: x86/insn: perf tools: Fix vcvtph2ps instruction decoding vcvtph2ps does not have an immediate operand, so remove the erroneous 'Ib' from its opcode map entry. Add vcvtph2ps to the perf tools new instructions test to verify it. Signed-off-by: Adrian Hunter Acked-by: Ingo Molnar Acked-by: Masami Hiramatsu Cc: Andy Lutomirski Cc: Dan Williams Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Thomas Gleixner Cc: X86 ML Link: http://lkml.kernel.org/r/1469003437-32706-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index d388de7..28082de 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -629,7 +629,7 @@ AVXcode: 2 10: pblendvb Vdq,Wdq (66) 11: 12: -13: vcvtph2ps Vx,Wx,Ib (66),(v) +13: vcvtph2ps Vx,Wx (66),(v) 14: blendvps Vdq,Wdq (66) 15: blendvpd Vdq,Wdq (66) 16: vpermps Vqq,Hqq,Wqq (66),(v) diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c index 3b491cf..ca08e6e 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -6,6 +6,8 @@ {{0x0f, 0x31, }, 2, 0, "", "", "0f 31 \trdtsc ",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "", +"c4 e2 7d 13 eb \tvcvtph2ps %xmm3,%ymm5",}, {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "", "f3 0f 1b 00 \tbndmk (%eax),%bnd0",}, {{0xf3, 0x0f, 0x1b, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", @@ -309,19 +311,19 @@ {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%eax,%ecx,1)",}, {{0xf2, 0xe8, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "call", "unconditional", -"f2 e8 fc ff ff ff \tbnd call 3c3 ",}, +"f2 e8 fc ff ff ff \tbnd call 3c8 ",}, {{0xf2, 0xff, 0x10, }, 3, 0, "call", "indirect", "f2 ff 10 \tbnd call *(%eax)",}, {{0xf2, 0xc3, }, 2, 0, "ret", "indirect", "f2 c3 \tbnd ret ",}, {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional", -"f2 e9 fc ff ff ff \tbnd jmp 3ce ",}, +"f2 e9 fc ff ff ff \tbnd jmp 3d3 ",}, {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional", -"f2 e9 fc ff ff ff \tbnd jmp 3d4 ",}, +"f2 e9 fc ff ff ff \tbnd jmp 3d9 ",}, {{0xf2, 0xff, 0x21, }, 3, 0, "jmp", "indirect", "f2 ff 21 \tbnd jmp *(%ecx)",}, {{0xf2, 0x0f, 0x85, 0xfc, 0xff, 0xff, 0xff, }, 7, 0xfffffffc, "jcc", "conditional", -"f2 0f 85 fc ff ff ff \tbnd jne 3de ",}, +"f2 0f 85 fc ff ff ff \tbnd jne 3e3 ",}, {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "", "0f 3a cc c1 00 \tsha1rnds4 $0x0,%xmm1,%xmm0",}, {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "", diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c index 4fe7cce..262d9d2 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -6,6 +6,8 @@ {{0x0f, 0x31, }, 2, 0, "", "", "0f 31 \trdtsc ",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "", +"c4 e2 7d 13 eb \tvcvtph2ps %xmm3,%ymm5",}, {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "", "f3 0f 1b 00 \tbndmk (%rax),%bnd0",}, {{0xf3, 0x41, 0x0f, 0x1b, 0x00, }, 5, 0, "", "", @@ -325,19 +327,19 @@ {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%rax,%rcx,1)",}, {{0xf2, 0xe8, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "call", "unconditional", -"f2 e8 00 00 00 00 \tbnd callq 3f6 ",}, +"f2 e8 00 00 00 00 \tbnd callq 3fb ",}, {{0x67, 0xf2, 0xff, 0x10, }, 4, 0, "call", "indirect", "67 f2 ff 10 \tbnd callq *(%eax)",}, {{0xf2, 0xc3, }, 2, 0, "ret", "indirect", "f2 c3 \tbnd retq ",}, {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional", -"f2 e9 00 00 00 00 \tbnd jmpq 402 ",}, +"f2 e9 00 00 00 00 \tbnd jmpq 407 ",}, {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional", -"f2 e9 00 00 00 00 \tbnd jmpq 408 ",}, +"f2 e9 00 00 00 00 \tbnd jmpq 40d ",}, {{0x67, 0xf2, 0xff, 0x21, }, 4, 0, "jmp", "indirect", "67 f2 ff 21 \tbnd jmpq *(%ecx)",}, {{0xf2, 0x0f, 0x85, 0x00, 0x00, 0x00, 0x00, }, 7, 0, "jcc", "conditional", -"f2 0f 85 00 00 00 00 \tbnd jne 413 ",}, +"f2 0f 85 00 00 00 00 \tbnd jne 418 ",}, {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "", "0f 3a cc c1 00 \tsha1rnds4 $0x0,%xmm1,%xmm0",}, {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "", diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c index 41b1b1c..3cd6775 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -19,6 +19,10 @@ int main(void) /* Following line is a marker for the awk script - do not change */ asm volatile("rdtsc"); /* Start here */ + /* Test fix for vcvtph2ps in x86-opcode-map.txt */ + + asm volatile("vcvtph2ps %xmm3,%ymm5"); + #ifdef __x86_64__ /* bndmk m64, bnd */ diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index d388de7..28082de 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -629,7 +629,7 @@ AVXcode: 2 10: pblendvb Vdq,Wdq (66) 11: 12: -13: vcvtph2ps Vx,Wx,Ib (66),(v) +13: vcvtph2ps Vx,Wx (66),(v) 14: blendvps Vdq,Wdq (66) 15: blendvpd Vdq,Wdq (66) 16: vpermps Vqq,Hqq,Wqq (66),(v) -- cgit v0.10.2 From 25af37f4e1e0a747824e3713b80d6b97dad28b7c Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 20 Jul 2016 11:30:35 +0300 Subject: x86/insn: Add AVX-512 support to the instruction decoder Add support for Intel's AVX-512 instructions to the instruction decoder. AVX-512 instructions are documented in Intel Architecture Instruction Set Extensions Programming Reference (February 2016). AVX-512 instructions are identified by a EVEX prefix which, for the purpose of instruction decoding, can be treated as though it were a 4-byte VEX prefix. Existing instructions which can now accept an EVEX prefix need not be further annotated in the op code map (x86-opcode-map.txt). In the case of new instructions, the op code map is updated accordingly. Also add associated Mask Instructions that are used to manipulate mask registers used in AVX-512 instructions. The 'perf tools' instruction decoder is updated in a subsequent patch. And a representative set of instructions is added to the perf tools new instructions test in a subsequent patch. Signed-off-by: Adrian Hunter Acked-by: Ingo Molnar Acked-by: Masami Hiramatsu Cc: Andy Lutomirski Cc: Dan Williams Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Thomas Gleixner Cc: X86 ML Link: http://lkml.kernel.org/r/1469003437-32706-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h index 74a2e31..02aff08 100644 --- a/arch/x86/include/asm/inat.h +++ b/arch/x86/include/asm/inat.h @@ -48,6 +48,7 @@ /* AVX VEX prefixes */ #define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ #define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ +#define INAT_PFX_EVEX 15 /* EVEX prefix */ #define INAT_LSTPFX_MAX 3 #define INAT_LGCPFX_MAX 11 @@ -89,6 +90,7 @@ #define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) #define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) #define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) +#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) /* Attribute making macros for attribute tables */ #define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) #define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) @@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr) static inline int inat_is_vex_prefix(insn_attr_t attr) { attr &= INAT_PFX_MASK; - return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3; + return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 || + attr == INAT_PFX_EVEX; +} + +static inline int inat_is_evex_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX; } static inline int inat_is_vex3_prefix(insn_attr_t attr) @@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr) static inline int inat_must_vex(insn_attr_t attr) { - return attr & INAT_VEXONLY; + return attr & (INAT_VEXONLY | INAT_EVEXONLY); +} + +static inline int inat_must_evex(insn_attr_t attr) +{ + return attr & INAT_EVEXONLY; } #endif diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index e7814b7..b3e32b0 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -91,6 +91,7 @@ struct insn { #define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ #define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ /* VEX bit fields */ +#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */ #define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ #define X86_VEX2_M 1 /* VEX2.M always 1 */ #define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ @@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn) return (insn->vex_prefix.value != 0); } +static inline int insn_is_evex(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return (insn->vex_prefix.nbytes == 4); +} + /* Ensure this instruction is decoded completely */ static inline int insn_complete(struct insn *insn) { @@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn) { if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ return X86_VEX2_M; - else + else if (insn->vex_prefix.nbytes == 3) /* 3 bytes VEX */ return X86_VEX3_M(insn->vex_prefix.bytes[1]); + else /* EVEX */ + return X86_EVEX_M(insn->vex_prefix.bytes[1]); } static inline insn_byte_t insn_vex_p_bits(struct insn *insn) diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 1a41693..1088eb8 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -155,14 +155,24 @@ found: /* * In 32-bits mode, if the [7:6] bits (mod bits of * ModRM) on the second byte are not 11b, it is - * LDS or LES. + * LDS or LES or BOUND. */ if (X86_MODRM_MOD(b2) != 3) goto vex_end; } insn->vex_prefix.bytes[0] = b; insn->vex_prefix.bytes[1] = b2; - if (inat_is_vex3_prefix(attr)) { + if (inat_is_evex_prefix(attr)) { + b2 = peek_nbyte_next(insn_byte_t, insn, 2); + insn->vex_prefix.bytes[2] = b2; + b2 = peek_nbyte_next(insn_byte_t, insn, 3); + insn->vex_prefix.bytes[3] = b2; + insn->vex_prefix.nbytes = 4; + insn->next_byte += 4; + if (insn->x86_64 && X86_VEX_W(b2)) + /* VEX.W overrides opnd_size */ + insn->opnd_bytes = 8; + } else if (inat_is_vex3_prefix(attr)) { b2 = peek_nbyte_next(insn_byte_t, insn, 2); insn->vex_prefix.bytes[2] = b2; insn->vex_prefix.nbytes = 3; @@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn) m = insn_vex_m_bits(insn); p = insn_vex_p_bits(insn); insn->attr = inat_get_avx_attribute(op, m, p); - if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr)) + if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || + (!inat_accept_vex(insn->attr) && + !inat_is_group(insn->attr))) insn->attr = 0; /* This instruction is bad */ goto end; /* VEX has only 1 byte for opcode */ } diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 28082de..ec378cd 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -13,12 +13,17 @@ # opcode: escape # escaped-name # EndTable # +# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix +# mnemonics that begin with lowercase 'k' accept a VEX prefix +# # # GrpTable: GrpXXX # reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] # EndTable # # AVX Superscripts +# (ev): this opcode requires EVEX prefix. +# (evo): this opcode is changed by EVEX prefix (EVEX opcode) # (v): this opcode requires VEX prefix. # (v1): this opcode only supports 128bit VEX. # @@ -137,7 +142,7 @@ AVXcode: # 0x60 - 0x6f 60: PUSHA/PUSHAD (i64) 61: POPA/POPAD (i64) -62: BOUND Gv,Ma (i64) +62: BOUND Gv,Ma (i64) | EVEX (Prefix) 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64) 64: SEG=FS (Prefix) 65: SEG=GS (Prefix) @@ -399,17 +404,17 @@ AVXcode: 1 3f: # 0x0f 0x40-0x4f 40: CMOVO Gv,Ev -41: CMOVNO Gv,Ev -42: CMOVB/C/NAE Gv,Ev +41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66) +42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66) 43: CMOVAE/NB/NC Gv,Ev -44: CMOVE/Z Gv,Ev -45: CMOVNE/NZ Gv,Ev -46: CMOVBE/NA Gv,Ev -47: CMOVA/NBE Gv,Ev +44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66) +45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66) +46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66) +47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66) 48: CMOVS Gv,Ev 49: CMOVNS Gv,Ev -4a: CMOVP/PE Gv,Ev -4b: CMOVNP/PO Gv,Ev +4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66) +4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk 4c: CMOVL/NGE Gv,Ev 4d: CMOVNL/GE Gv,Ev 4e: CMOVLE/NG Gv,Ev @@ -426,7 +431,7 @@ AVXcode: 1 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1) 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1) 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1) -5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) +5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1) 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1) 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1) @@ -447,7 +452,7 @@ AVXcode: 1 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1) 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1) 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1) -6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3) +6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev) # 0x0f 0x70-0x7f 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1) 71: Grp12 (1A) @@ -458,14 +463,14 @@ AVXcode: 1 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1) # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX. 77: emms | vzeroupper | vzeroall -78: VMREAD Ey,Gy -79: VMWRITE Gy,Ey -7a: -7b: +78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev) +79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev) +7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev) +7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev) 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2) 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2) 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1) -7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3) +7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev) # 0x0f 0x80-0x8f # Note: "forced64" is Intel CPU behavior (see comment about CALL insn). 80: JO Jz (f64) @@ -485,16 +490,16 @@ AVXcode: 1 8e: JLE/JNG Jz (f64) 8f: JNLE/JG Jz (f64) # 0x0f 0x90-0x9f -90: SETO Eb -91: SETNO Eb -92: SETB/C/NAE Eb -93: SETAE/NB/NC Eb +90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66) +91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66) +92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2) +93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2) 94: SETE/Z Eb 95: SETNE/NZ Eb 96: SETBE/NA Eb 97: SETA/NBE Eb -98: SETS Eb -99: SETNS Eb +98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66) +99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66) 9a: SETP/PE Eb 9b: SETNP/PO Eb 9c: SETL/NGE Eb @@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1) d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1) d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1) da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1) -db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) +db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo) dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1) dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1) de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1) -df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) +df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo) # 0x0f 0xe0-0xef e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1) e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1) @@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1) e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1) e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1) e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1) -e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2) +e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2) e7: movntq Mq,Pq | vmovntdq Mx,Vx (66) e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1) e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1) ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1) -eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) +eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo) ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1) ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1) ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1) -ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) +ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo) # 0x0f 0xf0-0xff f0: vlddqu Vx,Mx (F2) f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1) @@ -626,81 +631,105 @@ AVXcode: 2 0e: vtestps Vx,Wx (66),(v) 0f: vtestpd Vx,Wx (66),(v) # 0x0f 0x38 0x10-0x1f -10: pblendvb Vdq,Wdq (66) -11: -12: -13: vcvtph2ps Vx,Wx (66),(v) -14: blendvps Vdq,Wdq (66) -15: blendvpd Vdq,Wdq (66) -16: vpermps Vqq,Hqq,Wqq (66),(v) +10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev) +11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev) +12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev) +13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev) +14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo) +15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo) +16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo) 17: vptest Vx,Wx (66) 18: vbroadcastss Vx,Wd (66),(v) -19: vbroadcastsd Vqq,Wq (66),(v) -1a: vbroadcastf128 Vqq,Mdq (66),(v) -1b: +19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo) +1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo) +1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev) 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1) 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1) 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1) -1f: +1f: vpabsq Vx,Wx (66),(ev) # 0x0f 0x38 0x20-0x2f -20: vpmovsxbw Vx,Ux/Mq (66),(v1) -21: vpmovsxbd Vx,Ux/Md (66),(v1) -22: vpmovsxbq Vx,Ux/Mw (66),(v1) -23: vpmovsxwd Vx,Ux/Mq (66),(v1) -24: vpmovsxwq Vx,Ux/Md (66),(v1) -25: vpmovsxdq Vx,Ux/Mq (66),(v1) -26: -27: -28: vpmuldq Vx,Hx,Wx (66),(v1) -29: vpcmpeqq Vx,Hx,Wx (66),(v1) -2a: vmovntdqa Vx,Mx (66),(v1) +20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev) +21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev) +22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev) +23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev) +24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev) +25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev) +26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev) +27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev) +28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev) +29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev) +2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev) 2b: vpackusdw Vx,Hx,Wx (66),(v1) -2c: vmaskmovps Vx,Hx,Mx (66),(v) -2d: vmaskmovpd Vx,Hx,Mx (66),(v) +2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo) +2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo) 2e: vmaskmovps Mx,Hx,Vx (66),(v) 2f: vmaskmovpd Mx,Hx,Vx (66),(v) # 0x0f 0x38 0x30-0x3f -30: vpmovzxbw Vx,Ux/Mq (66),(v1) -31: vpmovzxbd Vx,Ux/Md (66),(v1) -32: vpmovzxbq Vx,Ux/Mw (66),(v1) -33: vpmovzxwd Vx,Ux/Mq (66),(v1) -34: vpmovzxwq Vx,Ux/Md (66),(v1) -35: vpmovzxdq Vx,Ux/Mq (66),(v1) -36: vpermd Vqq,Hqq,Wqq (66),(v) +30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev) +31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev) +32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev) +33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev) +34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev) +35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev) +36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo) 37: vpcmpgtq Vx,Hx,Wx (66),(v1) -38: vpminsb Vx,Hx,Wx (66),(v1) -39: vpminsd Vx,Hx,Wx (66),(v1) -3a: vpminuw Vx,Hx,Wx (66),(v1) -3b: vpminud Vx,Hx,Wx (66),(v1) +38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev) +39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev) +3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev) +3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo) 3c: vpmaxsb Vx,Hx,Wx (66),(v1) -3d: vpmaxsd Vx,Hx,Wx (66),(v1) +3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo) 3e: vpmaxuw Vx,Hx,Wx (66),(v1) -3f: vpmaxud Vx,Hx,Wx (66),(v1) +3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo) # 0x0f 0x38 0x40-0x8f -40: vpmulld Vx,Hx,Wx (66),(v1) +40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo) 41: vphminposuw Vdq,Wdq (66),(v1) -42: -43: -44: +42: vgetexpps/d Vx,Wx (66),(ev) +43: vgetexpss/d Vx,Hx,Wx (66),(ev) +44: vplzcntd/q Vx,Wx (66),(ev) 45: vpsrlvd/q Vx,Hx,Wx (66),(v) -46: vpsravd Vx,Hx,Wx (66),(v) +46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo) 47: vpsllvd/q Vx,Hx,Wx (66),(v) -# Skip 0x48-0x57 +# Skip 0x48-0x4b +4c: vrcp14ps/d Vpd,Wpd (66),(ev) +4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) +4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) +4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) +# Skip 0x50-0x57 58: vpbroadcastd Vx,Wx (66),(v) -59: vpbroadcastq Vx,Wx (66),(v) -5a: vbroadcasti128 Vqq,Mdq (66),(v) -# Skip 0x5b-0x77 +59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) +5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) +5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) +# Skip 0x5c-0x63 +64: vpblendmd/q Vx,Hx,Wx (66),(ev) +65: vblendmps/d Vx,Hx,Wx (66),(ev) +66: vpblendmb/w Vx,Hx,Wx (66),(ev) +# Skip 0x67-0x74 +75: vpermi2b/w Vx,Hx,Wx (66),(ev) +76: vpermi2d/q Vx,Hx,Wx (66),(ev) +77: vpermi2ps/d Vx,Hx,Wx (66),(ev) 78: vpbroadcastb Vx,Wx (66),(v) 79: vpbroadcastw Vx,Wx (66),(v) -# Skip 0x7a-0x7f +7a: vpbroadcastb Vx,Rv (66),(ev) +7b: vpbroadcastw Vx,Rv (66),(ev) +7c: vpbroadcastd/q Vx,Rv (66),(ev) +7d: vpermt2b/w Vx,Hx,Wx (66),(ev) +7e: vpermt2d/q Vx,Hx,Wx (66),(ev) +7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) 81: INVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) +83: vpmultishiftqb Vx,Hx,Wx (66),(ev) +88: vexpandps/d Vpd,Wpd (66),(ev) +89: vpexpandd/q Vx,Wx (66),(ev) +8a: vcompressps/d Wx,Vx (66),(ev) +8b: vpcompressd/q Wx,Vx (66),(ev) 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v) +8d: vpermb/w Vx,Hx,Wx (66),(ev) 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v) # 0x0f 0x38 0x90-0xbf (FMA) -90: vgatherdd/q Vx,Hx,Wx (66),(v) -91: vgatherqd/q Vx,Hx,Wx (66),(v) +90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo) +91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo) 92: vgatherdps/d Vx,Hx,Wx (66),(v) 93: vgatherqps/d Vx,Hx,Wx (66),(v) 94: @@ -715,6 +744,10 @@ AVXcode: 2 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1) 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v) 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1) +a0: vpscatterdd/q Wx,Vx (66),(ev) +a1: vpscatterqd/q Wx,Vx (66),(ev) +a2: vscatterdps/d Wx,Vx (66),(ev) +a3: vscatterqps/d Wx,Vx (66),(ev) a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v) a8: vfmadd213ps/d Vx,Hx,Wx (66),(v) @@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v) ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1) ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v) af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1) +b4: vpmadd52luq Vx,Hx,Wx (66),(ev) +b5: vpmadd52huq Vx,Hx,Wx (66),(ev) b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v) b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v) b8: vfmadd231ps/d Vx,Hx,Wx (66),(v) @@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1) be: vfnmsub231ps/d Vx,Hx,Wx (66),(v) bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1) # 0x0f 0x38 0xc0-0xff -c8: sha1nexte Vdq,Wdq +c4: vpconflictd/q Vx,Wx (66),(ev) +c6: Grp18 (1A) +c7: Grp19 (1A) +c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev) c9: sha1msg1 Vdq,Wdq -ca: sha1msg2 Vdq,Wdq -cb: sha256rnds2 Vdq,Wdq -cc: sha256msg1 Vdq,Wdq -cd: sha256msg2 Vdq,Wdq +ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) +cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) +cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) +cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) db: VAESIMC Vdq,Wdq (66),(v1) dc: VAESENC Vdq,Hdq,Wdq (66),(v1) dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) @@ -763,15 +801,15 @@ AVXcode: 3 00: vpermq Vqq,Wqq,Ib (66),(v) 01: vpermpd Vqq,Wqq,Ib (66),(v) 02: vpblendd Vx,Hx,Wx,Ib (66),(v) -03: +03: valignd/q Vx,Hx,Wx,Ib (66),(ev) 04: vpermilps Vx,Wx,Ib (66),(v) 05: vpermilpd Vx,Wx,Ib (66),(v) 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v) 07: -08: vroundps Vx,Wx,Ib (66) -09: vroundpd Vx,Wx,Ib (66) -0a: vroundss Vss,Wss,Ib (66),(v1) -0b: vroundsd Vsd,Wsd,Ib (66),(v1) +08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) +09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo) +0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) +0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo) 0c: vblendps Vx,Hx,Wx,Ib (66) 0d: vblendpd Vx,Hx,Wx,Ib (66) 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1) @@ -780,26 +818,51 @@ AVXcode: 3 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1) 16: vpextrd/q Ey,Vdq,Ib (66),(v1) 17: vextractps Ed,Vdq,Ib (66),(v1) -18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) -19: vextractf128 Wdq,Vqq,Ib (66),(v) +18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo) +1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev) 1d: vcvtps2ph Wx,Vx,Ib (66),(v) +1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev) +1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev) 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1) 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1) 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1) -38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) -39: vextracti128 Wdq,Vqq,Ib (66),(v) +23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) +25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev) +26: vgetmantps/d Vx,Wx,Ib (66),(ev) +27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) +30: kshiftrb/w Vk,Uk,Ib (66),(v) +31: kshiftrd/q Vk,Uk,Ib (66),(v) +32: kshiftlb/w Vk,Uk,Ib (66),(v) +33: kshiftld/q Vk,Uk,Ib (66),(v) +38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo) +3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev) +3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev) +3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev) 40: vdpps Vx,Hx,Wx,Ib (66) 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1) -42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) +42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo) +43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1) 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v) 4a: vblendvps Vx,Hx,Wx,Lx (66),(v) 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v) 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1) +50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev) +51: vrangess/d Vx,Hx,Wx,Ib (66),(ev) +54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev) +55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev) +56: vreduceps/d Vx,Wx,Ib (66),(ev) +57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1) 61: vpcmpestri Vdq,Wdq,Ib (66),(v1) 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) +66: vfpclassps/d Vk,Wx,Ib (66),(ev) +67: vfpclassss/d Vk,Wx,Ib (66),(ev) cc: sha1rnds4 Vdq,Wdq,Ib df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) f0: RORX Gy,Ey,Ib (F2),(v) @@ -927,8 +990,10 @@ GrpTable: Grp12 EndTable GrpTable: Grp13 +0: vprord/q Hx,Wx,Ib (66),(ev) +1: vprold/q Hx,Wx,Ib (66),(ev) 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1) -4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) +4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo) 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1) EndTable @@ -963,6 +1028,20 @@ GrpTable: Grp17 3: BLSI By,Ey (v) EndTable +GrpTable: Grp18 +1: vgatherpf0dps/d Wx (66),(ev) +2: vgatherpf1dps/d Wx (66),(ev) +5: vscatterpf0dps/d Wx (66),(ev) +6: vscatterpf1dps/d Wx (66),(ev) +EndTable + +GrpTable: Grp19 +1: vgatherpf0qps/d Wx (66),(ev) +2: vgatherpf1qps/d Wx (66),(ev) +5: vscatterpf0qps/d Wx (66),(ev) +6: vscatterpf1qps/d Wx (66),(ev) +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index 093a892..a3d2c62 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -72,12 +72,14 @@ BEGIN { lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 - # All opcodes starting with lower-case 'v' or with (v1) superscript + # All opcodes starting with lower-case 'v', 'k' or with (v1) superscript # accepts VEX prefix - vexok_opcode_expr = "^v.*" + vexok_opcode_expr = "^[vk].*" vexok_expr = "\\(v1\\)" # All opcodes with (v) superscript supports *only* VEX prefix vexonly_expr = "\\(v\\)" + # All opcodes with (ev) superscript supports *only* EVEX prefix + evexonly_expr = "\\(ev\\)" prefix_expr = "\\(Prefix\\)" prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" @@ -95,6 +97,7 @@ BEGIN { prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ" prefix_num["VEX+1byte"] = "INAT_PFX_VEX2" prefix_num["VEX+2byte"] = "INAT_PFX_VEX3" + prefix_num["EVEX"] = "INAT_PFX_EVEX" clear_vars() } @@ -319,7 +322,9 @@ function convert_operands(count,opnd, i,j,imm,mod) flags = add_flags(flags, "INAT_MODRM") # check VEX codes - if (match(ext, vexonly_expr)) + if (match(ext, evexonly_expr)) + flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY") + else if (match(ext, vexonly_expr)) flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY") else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr)) flags = add_flags(flags, "INAT_VEXOK") -- cgit v0.10.2 From c61f4d5ebaf05fbd90bf43aa2096690b85e34761 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 20 Jul 2016 11:30:36 +0300 Subject: perf tools: Add AVX-512 support to the instruction decoder used by Intel PT Add support for Intel's AVX-512 instructions to perf tools instruction decoder used by Intel PT. The kernel's instruction decoder was updated in a previous patch. AVX-512 instructions are documented in Intel Architecture Instruction Set Extensions Programming Reference (February 2016). AVX-512 instructions are identified by a EVEX prefix which, for the purpose of instruction decoding, can be treated as though it were a 4-byte VEX prefix. Existing instructions which can now accept an EVEX prefix need not be further annotated in the op code map (x86-opcode-map.txt). In the case of new instructions, the op code map is updated accordingly. Also add associated Mask Instructions that are used to manipulate mask registers used in AVX-512 instructions. A representative set of instructions is added to the perf tools new instructions test in a subsequent patch. Signed-off-by: Adrian Hunter Acked-by: Ingo Molnar Acked-by: Masami Hiramatsu Cc: Andy Lutomirski Cc: Dan Williams Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Thomas Gleixner Cc: X86 ML Link: http://lkml.kernel.org/r/1469003437-32706-4-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk index 51756734..54e9616 100644 --- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk +++ b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk @@ -72,12 +72,14 @@ BEGIN { lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 - # All opcodes starting with lower-case 'v' or with (v1) superscript + # All opcodes starting with lower-case 'v', 'k' or with (v1) superscript # accepts VEX prefix - vexok_opcode_expr = "^v.*" + vexok_opcode_expr = "^[vk].*" vexok_expr = "\\(v1\\)" # All opcodes with (v) superscript supports *only* VEX prefix vexonly_expr = "\\(v\\)" + # All opcodes with (ev) superscript supports *only* EVEX prefix + evexonly_expr = "\\(ev\\)" prefix_expr = "\\(Prefix\\)" prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" @@ -95,6 +97,7 @@ BEGIN { prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ" prefix_num["VEX+1byte"] = "INAT_PFX_VEX2" prefix_num["VEX+2byte"] = "INAT_PFX_VEX3" + prefix_num["EVEX"] = "INAT_PFX_EVEX" clear_vars() } @@ -319,7 +322,9 @@ function convert_operands(count,opnd, i,j,imm,mod) flags = add_flags(flags, "INAT_MODRM") # check VEX codes - if (match(ext, vexonly_expr)) + if (match(ext, evexonly_expr)) + flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY") + else if (match(ext, vexonly_expr)) flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY") else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr)) flags = add_flags(flags, "INAT_VEXOK") diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h index 611645e..125ecd2 100644 --- a/tools/perf/util/intel-pt-decoder/inat.h +++ b/tools/perf/util/intel-pt-decoder/inat.h @@ -48,6 +48,7 @@ /* AVX VEX prefixes */ #define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ #define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ +#define INAT_PFX_EVEX 15 /* EVEX prefix */ #define INAT_LSTPFX_MAX 3 #define INAT_LGCPFX_MAX 11 @@ -89,6 +90,7 @@ #define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) #define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) #define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) +#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) /* Attribute making macros for attribute tables */ #define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) #define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) @@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr) static inline int inat_is_vex_prefix(insn_attr_t attr) { attr &= INAT_PFX_MASK; - return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3; + return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 || + attr == INAT_PFX_EVEX; +} + +static inline int inat_is_evex_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX; } static inline int inat_is_vex3_prefix(insn_attr_t attr) @@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr) static inline int inat_must_vex(insn_attr_t attr) { - return attr & INAT_VEXONLY; + return attr & (INAT_VEXONLY | INAT_EVEXONLY); +} + +static inline int inat_must_evex(insn_attr_t attr) +{ + return attr & INAT_EVEXONLY; } #endif diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c index 9f26eae..ca983e2 100644 --- a/tools/perf/util/intel-pt-decoder/insn.c +++ b/tools/perf/util/intel-pt-decoder/insn.c @@ -155,14 +155,24 @@ found: /* * In 32-bits mode, if the [7:6] bits (mod bits of * ModRM) on the second byte are not 11b, it is - * LDS or LES. + * LDS or LES or BOUND. */ if (X86_MODRM_MOD(b2) != 3) goto vex_end; } insn->vex_prefix.bytes[0] = b; insn->vex_prefix.bytes[1] = b2; - if (inat_is_vex3_prefix(attr)) { + if (inat_is_evex_prefix(attr)) { + b2 = peek_nbyte_next(insn_byte_t, insn, 2); + insn->vex_prefix.bytes[2] = b2; + b2 = peek_nbyte_next(insn_byte_t, insn, 3); + insn->vex_prefix.bytes[3] = b2; + insn->vex_prefix.nbytes = 4; + insn->next_byte += 4; + if (insn->x86_64 && X86_VEX_W(b2)) + /* VEX.W overrides opnd_size */ + insn->opnd_bytes = 8; + } else if (inat_is_vex3_prefix(attr)) { b2 = peek_nbyte_next(insn_byte_t, insn, 2); insn->vex_prefix.bytes[2] = b2; insn->vex_prefix.nbytes = 3; @@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn) m = insn_vex_m_bits(insn); p = insn_vex_p_bits(insn); insn->attr = inat_get_avx_attribute(op, m, p); - if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr)) + if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || + (!inat_accept_vex(insn->attr) && + !inat_is_group(insn->attr))) insn->attr = 0; /* This instruction is bad */ goto end; /* VEX has only 1 byte for opcode */ } diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h index dd12da0..e23578c 100644 --- a/tools/perf/util/intel-pt-decoder/insn.h +++ b/tools/perf/util/intel-pt-decoder/insn.h @@ -91,6 +91,7 @@ struct insn { #define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ #define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ /* VEX bit fields */ +#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */ #define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ #define X86_VEX2_M 1 /* VEX2.M always 1 */ #define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ @@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn) return (insn->vex_prefix.value != 0); } +static inline int insn_is_evex(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return (insn->vex_prefix.nbytes == 4); +} + /* Ensure this instruction is decoded completely */ static inline int insn_complete(struct insn *insn) { @@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn) { if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ return X86_VEX2_M; - else + else if (insn->vex_prefix.nbytes == 3) /* 3 bytes VEX */ return X86_VEX3_M(insn->vex_prefix.bytes[1]); + else /* EVEX */ + return X86_EVEX_M(insn->vex_prefix.bytes[1]); } static inline insn_byte_t insn_vex_p_bits(struct insn *insn) diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index 28082de..ec378cd 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -13,12 +13,17 @@ # opcode: escape # escaped-name # EndTable # +# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix +# mnemonics that begin with lowercase 'k' accept a VEX prefix +# # # GrpTable: GrpXXX # reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] # EndTable # # AVX Superscripts +# (ev): this opcode requires EVEX prefix. +# (evo): this opcode is changed by EVEX prefix (EVEX opcode) # (v): this opcode requires VEX prefix. # (v1): this opcode only supports 128bit VEX. # @@ -137,7 +142,7 @@ AVXcode: # 0x60 - 0x6f 60: PUSHA/PUSHAD (i64) 61: POPA/POPAD (i64) -62: BOUND Gv,Ma (i64) +62: BOUND Gv,Ma (i64) | EVEX (Prefix) 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64) 64: SEG=FS (Prefix) 65: SEG=GS (Prefix) @@ -399,17 +404,17 @@ AVXcode: 1 3f: # 0x0f 0x40-0x4f 40: CMOVO Gv,Ev -41: CMOVNO Gv,Ev -42: CMOVB/C/NAE Gv,Ev +41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66) +42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66) 43: CMOVAE/NB/NC Gv,Ev -44: CMOVE/Z Gv,Ev -45: CMOVNE/NZ Gv,Ev -46: CMOVBE/NA Gv,Ev -47: CMOVA/NBE Gv,Ev +44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66) +45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66) +46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66) +47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66) 48: CMOVS Gv,Ev 49: CMOVNS Gv,Ev -4a: CMOVP/PE Gv,Ev -4b: CMOVNP/PO Gv,Ev +4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66) +4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk 4c: CMOVL/NGE Gv,Ev 4d: CMOVNL/GE Gv,Ev 4e: CMOVLE/NG Gv,Ev @@ -426,7 +431,7 @@ AVXcode: 1 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1) 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1) 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1) -5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) +5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1) 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1) 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1) @@ -447,7 +452,7 @@ AVXcode: 1 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1) 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1) 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1) -6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3) +6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev) # 0x0f 0x70-0x7f 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1) 71: Grp12 (1A) @@ -458,14 +463,14 @@ AVXcode: 1 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1) # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX. 77: emms | vzeroupper | vzeroall -78: VMREAD Ey,Gy -79: VMWRITE Gy,Ey -7a: -7b: +78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev) +79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev) +7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev) +7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev) 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2) 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2) 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1) -7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3) +7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev) # 0x0f 0x80-0x8f # Note: "forced64" is Intel CPU behavior (see comment about CALL insn). 80: JO Jz (f64) @@ -485,16 +490,16 @@ AVXcode: 1 8e: JLE/JNG Jz (f64) 8f: JNLE/JG Jz (f64) # 0x0f 0x90-0x9f -90: SETO Eb -91: SETNO Eb -92: SETB/C/NAE Eb -93: SETAE/NB/NC Eb +90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66) +91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66) +92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2) +93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2) 94: SETE/Z Eb 95: SETNE/NZ Eb 96: SETBE/NA Eb 97: SETA/NBE Eb -98: SETS Eb -99: SETNS Eb +98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66) +99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66) 9a: SETP/PE Eb 9b: SETNP/PO Eb 9c: SETL/NGE Eb @@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1) d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1) d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1) da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1) -db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) +db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo) dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1) dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1) de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1) -df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) +df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo) # 0x0f 0xe0-0xef e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1) e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1) @@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1) e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1) e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1) e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1) -e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2) +e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2) e7: movntq Mq,Pq | vmovntdq Mx,Vx (66) e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1) e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1) ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1) -eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) +eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo) ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1) ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1) ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1) -ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) +ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo) # 0x0f 0xf0-0xff f0: vlddqu Vx,Mx (F2) f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1) @@ -626,81 +631,105 @@ AVXcode: 2 0e: vtestps Vx,Wx (66),(v) 0f: vtestpd Vx,Wx (66),(v) # 0x0f 0x38 0x10-0x1f -10: pblendvb Vdq,Wdq (66) -11: -12: -13: vcvtph2ps Vx,Wx (66),(v) -14: blendvps Vdq,Wdq (66) -15: blendvpd Vdq,Wdq (66) -16: vpermps Vqq,Hqq,Wqq (66),(v) +10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev) +11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev) +12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev) +13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev) +14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo) +15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo) +16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo) 17: vptest Vx,Wx (66) 18: vbroadcastss Vx,Wd (66),(v) -19: vbroadcastsd Vqq,Wq (66),(v) -1a: vbroadcastf128 Vqq,Mdq (66),(v) -1b: +19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo) +1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo) +1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev) 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1) 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1) 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1) -1f: +1f: vpabsq Vx,Wx (66),(ev) # 0x0f 0x38 0x20-0x2f -20: vpmovsxbw Vx,Ux/Mq (66),(v1) -21: vpmovsxbd Vx,Ux/Md (66),(v1) -22: vpmovsxbq Vx,Ux/Mw (66),(v1) -23: vpmovsxwd Vx,Ux/Mq (66),(v1) -24: vpmovsxwq Vx,Ux/Md (66),(v1) -25: vpmovsxdq Vx,Ux/Mq (66),(v1) -26: -27: -28: vpmuldq Vx,Hx,Wx (66),(v1) -29: vpcmpeqq Vx,Hx,Wx (66),(v1) -2a: vmovntdqa Vx,Mx (66),(v1) +20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev) +21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev) +22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev) +23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev) +24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev) +25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev) +26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev) +27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev) +28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev) +29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev) +2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev) 2b: vpackusdw Vx,Hx,Wx (66),(v1) -2c: vmaskmovps Vx,Hx,Mx (66),(v) -2d: vmaskmovpd Vx,Hx,Mx (66),(v) +2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo) +2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo) 2e: vmaskmovps Mx,Hx,Vx (66),(v) 2f: vmaskmovpd Mx,Hx,Vx (66),(v) # 0x0f 0x38 0x30-0x3f -30: vpmovzxbw Vx,Ux/Mq (66),(v1) -31: vpmovzxbd Vx,Ux/Md (66),(v1) -32: vpmovzxbq Vx,Ux/Mw (66),(v1) -33: vpmovzxwd Vx,Ux/Mq (66),(v1) -34: vpmovzxwq Vx,Ux/Md (66),(v1) -35: vpmovzxdq Vx,Ux/Mq (66),(v1) -36: vpermd Vqq,Hqq,Wqq (66),(v) +30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev) +31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev) +32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev) +33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev) +34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev) +35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev) +36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo) 37: vpcmpgtq Vx,Hx,Wx (66),(v1) -38: vpminsb Vx,Hx,Wx (66),(v1) -39: vpminsd Vx,Hx,Wx (66),(v1) -3a: vpminuw Vx,Hx,Wx (66),(v1) -3b: vpminud Vx,Hx,Wx (66),(v1) +38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev) +39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev) +3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev) +3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo) 3c: vpmaxsb Vx,Hx,Wx (66),(v1) -3d: vpmaxsd Vx,Hx,Wx (66),(v1) +3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo) 3e: vpmaxuw Vx,Hx,Wx (66),(v1) -3f: vpmaxud Vx,Hx,Wx (66),(v1) +3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo) # 0x0f 0x38 0x40-0x8f -40: vpmulld Vx,Hx,Wx (66),(v1) +40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo) 41: vphminposuw Vdq,Wdq (66),(v1) -42: -43: -44: +42: vgetexpps/d Vx,Wx (66),(ev) +43: vgetexpss/d Vx,Hx,Wx (66),(ev) +44: vplzcntd/q Vx,Wx (66),(ev) 45: vpsrlvd/q Vx,Hx,Wx (66),(v) -46: vpsravd Vx,Hx,Wx (66),(v) +46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo) 47: vpsllvd/q Vx,Hx,Wx (66),(v) -# Skip 0x48-0x57 +# Skip 0x48-0x4b +4c: vrcp14ps/d Vpd,Wpd (66),(ev) +4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) +4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) +4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) +# Skip 0x50-0x57 58: vpbroadcastd Vx,Wx (66),(v) -59: vpbroadcastq Vx,Wx (66),(v) -5a: vbroadcasti128 Vqq,Mdq (66),(v) -# Skip 0x5b-0x77 +59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) +5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) +5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) +# Skip 0x5c-0x63 +64: vpblendmd/q Vx,Hx,Wx (66),(ev) +65: vblendmps/d Vx,Hx,Wx (66),(ev) +66: vpblendmb/w Vx,Hx,Wx (66),(ev) +# Skip 0x67-0x74 +75: vpermi2b/w Vx,Hx,Wx (66),(ev) +76: vpermi2d/q Vx,Hx,Wx (66),(ev) +77: vpermi2ps/d Vx,Hx,Wx (66),(ev) 78: vpbroadcastb Vx,Wx (66),(v) 79: vpbroadcastw Vx,Wx (66),(v) -# Skip 0x7a-0x7f +7a: vpbroadcastb Vx,Rv (66),(ev) +7b: vpbroadcastw Vx,Rv (66),(ev) +7c: vpbroadcastd/q Vx,Rv (66),(ev) +7d: vpermt2b/w Vx,Hx,Wx (66),(ev) +7e: vpermt2d/q Vx,Hx,Wx (66),(ev) +7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) 81: INVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) +83: vpmultishiftqb Vx,Hx,Wx (66),(ev) +88: vexpandps/d Vpd,Wpd (66),(ev) +89: vpexpandd/q Vx,Wx (66),(ev) +8a: vcompressps/d Wx,Vx (66),(ev) +8b: vpcompressd/q Wx,Vx (66),(ev) 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v) +8d: vpermb/w Vx,Hx,Wx (66),(ev) 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v) # 0x0f 0x38 0x90-0xbf (FMA) -90: vgatherdd/q Vx,Hx,Wx (66),(v) -91: vgatherqd/q Vx,Hx,Wx (66),(v) +90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo) +91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo) 92: vgatherdps/d Vx,Hx,Wx (66),(v) 93: vgatherqps/d Vx,Hx,Wx (66),(v) 94: @@ -715,6 +744,10 @@ AVXcode: 2 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1) 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v) 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1) +a0: vpscatterdd/q Wx,Vx (66),(ev) +a1: vpscatterqd/q Wx,Vx (66),(ev) +a2: vscatterdps/d Wx,Vx (66),(ev) +a3: vscatterqps/d Wx,Vx (66),(ev) a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v) a8: vfmadd213ps/d Vx,Hx,Wx (66),(v) @@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v) ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1) ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v) af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1) +b4: vpmadd52luq Vx,Hx,Wx (66),(ev) +b5: vpmadd52huq Vx,Hx,Wx (66),(ev) b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v) b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v) b8: vfmadd231ps/d Vx,Hx,Wx (66),(v) @@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1) be: vfnmsub231ps/d Vx,Hx,Wx (66),(v) bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1) # 0x0f 0x38 0xc0-0xff -c8: sha1nexte Vdq,Wdq +c4: vpconflictd/q Vx,Wx (66),(ev) +c6: Grp18 (1A) +c7: Grp19 (1A) +c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev) c9: sha1msg1 Vdq,Wdq -ca: sha1msg2 Vdq,Wdq -cb: sha256rnds2 Vdq,Wdq -cc: sha256msg1 Vdq,Wdq -cd: sha256msg2 Vdq,Wdq +ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) +cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) +cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) +cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) db: VAESIMC Vdq,Wdq (66),(v1) dc: VAESENC Vdq,Hdq,Wdq (66),(v1) dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) @@ -763,15 +801,15 @@ AVXcode: 3 00: vpermq Vqq,Wqq,Ib (66),(v) 01: vpermpd Vqq,Wqq,Ib (66),(v) 02: vpblendd Vx,Hx,Wx,Ib (66),(v) -03: +03: valignd/q Vx,Hx,Wx,Ib (66),(ev) 04: vpermilps Vx,Wx,Ib (66),(v) 05: vpermilpd Vx,Wx,Ib (66),(v) 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v) 07: -08: vroundps Vx,Wx,Ib (66) -09: vroundpd Vx,Wx,Ib (66) -0a: vroundss Vss,Wss,Ib (66),(v1) -0b: vroundsd Vsd,Wsd,Ib (66),(v1) +08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) +09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo) +0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) +0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo) 0c: vblendps Vx,Hx,Wx,Ib (66) 0d: vblendpd Vx,Hx,Wx,Ib (66) 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1) @@ -780,26 +818,51 @@ AVXcode: 3 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1) 16: vpextrd/q Ey,Vdq,Ib (66),(v1) 17: vextractps Ed,Vdq,Ib (66),(v1) -18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) -19: vextractf128 Wdq,Vqq,Ib (66),(v) +18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo) +1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev) 1d: vcvtps2ph Wx,Vx,Ib (66),(v) +1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev) +1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev) 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1) 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1) 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1) -38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) -39: vextracti128 Wdq,Vqq,Ib (66),(v) +23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) +25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev) +26: vgetmantps/d Vx,Wx,Ib (66),(ev) +27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) +30: kshiftrb/w Vk,Uk,Ib (66),(v) +31: kshiftrd/q Vk,Uk,Ib (66),(v) +32: kshiftlb/w Vk,Uk,Ib (66),(v) +33: kshiftld/q Vk,Uk,Ib (66),(v) +38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo) +3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev) +3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev) +3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev) 40: vdpps Vx,Hx,Wx,Ib (66) 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1) -42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) +42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo) +43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1) 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v) 4a: vblendvps Vx,Hx,Wx,Lx (66),(v) 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v) 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1) +50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev) +51: vrangess/d Vx,Hx,Wx,Ib (66),(ev) +54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev) +55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev) +56: vreduceps/d Vx,Wx,Ib (66),(ev) +57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1) 61: vpcmpestri Vdq,Wdq,Ib (66),(v1) 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) +66: vfpclassps/d Vk,Wx,Ib (66),(ev) +67: vfpclassss/d Vk,Wx,Ib (66),(ev) cc: sha1rnds4 Vdq,Wdq,Ib df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) f0: RORX Gy,Ey,Ib (F2),(v) @@ -927,8 +990,10 @@ GrpTable: Grp12 EndTable GrpTable: Grp13 +0: vprord/q Hx,Wx,Ib (66),(ev) +1: vprold/q Hx,Wx,Ib (66),(ev) 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1) -4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) +4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo) 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1) EndTable @@ -963,6 +1028,20 @@ GrpTable: Grp17 3: BLSI By,Ey (v) EndTable +GrpTable: Grp18 +1: vgatherpf0dps/d Wx (66),(ev) +2: vgatherpf1dps/d Wx (66),(ev) +5: vscatterpf0dps/d Wx (66),(ev) +6: vscatterpf1dps/d Wx (66),(ev) +EndTable + +GrpTable: Grp19 +1: vgatherpf0qps/d Wx (66),(ev) +2: vgatherpf1qps/d Wx (66),(ev) +5: vscatterpf0qps/d Wx (66),(ev) +6: vscatterpf1qps/d Wx (66),(ev) +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH -- cgit v0.10.2 From 6c4d0b41ce3e61fe87e6195582c66cd262399b82 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 20 Jul 2016 11:30:37 +0300 Subject: perf tools: Add AVX-512 instructions to the new instructions test Previous patches added support for Intel's AVX-512 instructions to the kernel and perf tools instruction decoders. AVX-512 instructions are documented in Intel Architecture Instruction Set Extensions Programming Reference (February 2016). Add a representative set of instructions to perf's "new instructions" test. e.g. perf test "new instructions" Or to view a particular instruction: perf test -v "new instructions" 2>&1 | grep vbroadcasti64x4 Signed-off-by: Adrian Hunter Acked-by: Ingo Molnar Acked-by: Masami Hiramatsu Tested-by: Arnaldo Carvalho de Melo Cc: Andy Lutomirski Cc: Dan Williams Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Thomas Gleixner Cc: X86 ML Link: http://lkml.kernel.org/r/1469003437-32706-5-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c index ca08e6e..3918dd5 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -8,6 +8,1014 @@ "0f 31 \trdtsc ",}, {{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "", "c4 e2 7d 13 eb \tvcvtph2ps %xmm3,%ymm5",}, +{{0x62, 0x81, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 81 78 56 34 12 \tbound %eax,0x12345678(%ecx)",}, +{{0x62, 0x88, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 88 78 56 34 12 \tbound %ecx,0x12345678(%eax)",}, +{{0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 90 78 56 34 12 \tbound %edx,0x12345678(%eax)",}, +{{0x62, 0x98, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 98 78 56 34 12 \tbound %ebx,0x12345678(%eax)",}, +{{0x62, 0xa0, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 a0 78 56 34 12 \tbound %esp,0x12345678(%eax)",}, +{{0x62, 0xa8, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 a8 78 56 34 12 \tbound %ebp,0x12345678(%eax)",}, +{{0x62, 0xb0, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 b0 78 56 34 12 \tbound %esi,0x12345678(%eax)",}, +{{0x62, 0xb8, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 b8 78 56 34 12 \tbound %edi,0x12345678(%eax)",}, +{{0x62, 0x08, }, 2, 0, "", "", +"62 08 \tbound %ecx,(%eax)",}, +{{0x62, 0x05, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 05 78 56 34 12 \tbound %eax,0x12345678",}, +{{0x62, 0x14, 0x01, }, 3, 0, "", "", +"62 14 01 \tbound %edx,(%ecx,%eax,1)",}, +{{0x62, 0x14, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"62 14 05 78 56 34 12 \tbound %edx,0x12345678(,%eax,1)",}, +{{0x62, 0x14, 0x08, }, 3, 0, "", "", +"62 14 08 \tbound %edx,(%eax,%ecx,1)",}, +{{0x62, 0x14, 0xc8, }, 3, 0, "", "", +"62 14 c8 \tbound %edx,(%eax,%ecx,8)",}, +{{0x62, 0x50, 0x12, }, 3, 0, "", "", +"62 50 12 \tbound %edx,0x12(%eax)",}, +{{0x62, 0x55, 0x12, }, 3, 0, "", "", +"62 55 12 \tbound %edx,0x12(%ebp)",}, +{{0x62, 0x54, 0x01, 0x12, }, 4, 0, "", "", +"62 54 01 12 \tbound %edx,0x12(%ecx,%eax,1)",}, +{{0x62, 0x54, 0x05, 0x12, }, 4, 0, "", "", +"62 54 05 12 \tbound %edx,0x12(%ebp,%eax,1)",}, +{{0x62, 0x54, 0x08, 0x12, }, 4, 0, "", "", +"62 54 08 12 \tbound %edx,0x12(%eax,%ecx,1)",}, +{{0x62, 0x54, 0xc8, 0x12, }, 4, 0, "", "", +"62 54 c8 12 \tbound %edx,0x12(%eax,%ecx,8)",}, +{{0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 90 78 56 34 12 \tbound %edx,0x12345678(%eax)",}, +{{0x62, 0x95, 0x78, 0x56, 0x34, 0x12, }, 6, 0, "", "", +"62 95 78 56 34 12 \tbound %edx,0x12345678(%ebp)",}, +{{0x62, 0x94, 0x01, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"62 94 01 78 56 34 12 \tbound %edx,0x12345678(%ecx,%eax,1)",}, +{{0x62, 0x94, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"62 94 05 78 56 34 12 \tbound %edx,0x12345678(%ebp,%eax,1)",}, +{{0x62, 0x94, 0x08, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"62 94 08 78 56 34 12 \tbound %edx,0x12345678(%eax,%ecx,1)",}, +{{0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"62 94 c8 78 56 34 12 \tbound %edx,0x12345678(%eax,%ecx,8)",}, +{{0x66, 0x62, 0x81, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 81 78 56 34 12 \tbound %ax,0x12345678(%ecx)",}, +{{0x66, 0x62, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 88 78 56 34 12 \tbound %cx,0x12345678(%eax)",}, +{{0x66, 0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 90 78 56 34 12 \tbound %dx,0x12345678(%eax)",}, +{{0x66, 0x62, 0x98, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 98 78 56 34 12 \tbound %bx,0x12345678(%eax)",}, +{{0x66, 0x62, 0xa0, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 a0 78 56 34 12 \tbound %sp,0x12345678(%eax)",}, +{{0x66, 0x62, 0xa8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 a8 78 56 34 12 \tbound %bp,0x12345678(%eax)",}, +{{0x66, 0x62, 0xb0, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 b0 78 56 34 12 \tbound %si,0x12345678(%eax)",}, +{{0x66, 0x62, 0xb8, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 b8 78 56 34 12 \tbound %di,0x12345678(%eax)",}, +{{0x66, 0x62, 0x08, }, 3, 0, "", "", +"66 62 08 \tbound %cx,(%eax)",}, +{{0x66, 0x62, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 05 78 56 34 12 \tbound %ax,0x12345678",}, +{{0x66, 0x62, 0x14, 0x01, }, 4, 0, "", "", +"66 62 14 01 \tbound %dx,(%ecx,%eax,1)",}, +{{0x66, 0x62, 0x14, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"66 62 14 05 78 56 34 12 \tbound %dx,0x12345678(,%eax,1)",}, +{{0x66, 0x62, 0x14, 0x08, }, 4, 0, "", "", +"66 62 14 08 \tbound %dx,(%eax,%ecx,1)",}, +{{0x66, 0x62, 0x14, 0xc8, }, 4, 0, "", "", +"66 62 14 c8 \tbound %dx,(%eax,%ecx,8)",}, +{{0x66, 0x62, 0x50, 0x12, }, 4, 0, "", "", +"66 62 50 12 \tbound %dx,0x12(%eax)",}, +{{0x66, 0x62, 0x55, 0x12, }, 4, 0, "", "", +"66 62 55 12 \tbound %dx,0x12(%ebp)",}, +{{0x66, 0x62, 0x54, 0x01, 0x12, }, 5, 0, "", "", +"66 62 54 01 12 \tbound %dx,0x12(%ecx,%eax,1)",}, +{{0x66, 0x62, 0x54, 0x05, 0x12, }, 5, 0, "", "", +"66 62 54 05 12 \tbound %dx,0x12(%ebp,%eax,1)",}, +{{0x66, 0x62, 0x54, 0x08, 0x12, }, 5, 0, "", "", +"66 62 54 08 12 \tbound %dx,0x12(%eax,%ecx,1)",}, +{{0x66, 0x62, 0x54, 0xc8, 0x12, }, 5, 0, "", "", +"66 62 54 c8 12 \tbound %dx,0x12(%eax,%ecx,8)",}, +{{0x66, 0x62, 0x90, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 90 78 56 34 12 \tbound %dx,0x12345678(%eax)",}, +{{0x66, 0x62, 0x95, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"66 62 95 78 56 34 12 \tbound %dx,0x12345678(%ebp)",}, +{{0x66, 0x62, 0x94, 0x01, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"66 62 94 01 78 56 34 12 \tbound %dx,0x12345678(%ecx,%eax,1)",}, +{{0x66, 0x62, 0x94, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"66 62 94 05 78 56 34 12 \tbound %dx,0x12345678(%ebp,%eax,1)",}, +{{0x66, 0x62, 0x94, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"66 62 94 08 78 56 34 12 \tbound %dx,0x12345678(%eax,%ecx,1)",}, +{{0x66, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"66 62 94 c8 78 56 34 12 \tbound %dx,0x12345678(%eax,%ecx,8)",}, +{{0x0f, 0x41, 0xd8, }, 3, 0, "", "", +"0f 41 d8 \tcmovno %eax,%ebx",}, +{{0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 41 88 78 56 34 12 \tcmovno 0x12345678(%eax),%ecx",}, +{{0x66, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"66 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%eax),%cx",}, +{{0x0f, 0x44, 0xd8, }, 3, 0, "", "", +"0f 44 d8 \tcmove %eax,%ebx",}, +{{0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 44 88 78 56 34 12 \tcmove 0x12345678(%eax),%ecx",}, +{{0x66, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"66 0f 44 88 78 56 34 12 \tcmove 0x12345678(%eax),%cx",}, +{{0x0f, 0x90, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 90 80 78 56 34 12 \tseto 0x12345678(%eax)",}, +{{0x0f, 0x91, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 91 80 78 56 34 12 \tsetno 0x12345678(%eax)",}, +{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 92 80 78 56 34 12 \tsetb 0x12345678(%eax)",}, +{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 92 80 78 56 34 12 \tsetb 0x12345678(%eax)",}, +{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 92 80 78 56 34 12 \tsetb 0x12345678(%eax)",}, +{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 93 80 78 56 34 12 \tsetae 0x12345678(%eax)",}, +{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 93 80 78 56 34 12 \tsetae 0x12345678(%eax)",}, +{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 93 80 78 56 34 12 \tsetae 0x12345678(%eax)",}, +{{0x0f, 0x98, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 98 80 78 56 34 12 \tsets 0x12345678(%eax)",}, +{{0x0f, 0x99, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 99 80 78 56 34 12 \tsetns 0x12345678(%eax)",}, +{{0xc5, 0xcc, 0x41, 0xef, }, 4, 0, "", "", +"c5 cc 41 ef \tkandw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x41, 0xef, }, 5, 0, "", "", +"c4 e1 cc 41 ef \tkandq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x41, 0xef, }, 4, 0, "", "", +"c5 cd 41 ef \tkandb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x41, 0xef, }, 5, 0, "", "", +"c4 e1 cd 41 ef \tkandd %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x42, 0xef, }, 4, 0, "", "", +"c5 cc 42 ef \tkandnw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x42, 0xef, }, 5, 0, "", "", +"c4 e1 cc 42 ef \tkandnq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x42, 0xef, }, 4, 0, "", "", +"c5 cd 42 ef \tkandnb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x42, 0xef, }, 5, 0, "", "", +"c4 e1 cd 42 ef \tkandnd %k7,%k6,%k5",}, +{{0xc5, 0xf8, 0x44, 0xf7, }, 4, 0, "", "", +"c5 f8 44 f7 \tknotw %k7,%k6",}, +{{0xc4, 0xe1, 0xf8, 0x44, 0xf7, }, 5, 0, "", "", +"c4 e1 f8 44 f7 \tknotq %k7,%k6",}, +{{0xc5, 0xf9, 0x44, 0xf7, }, 4, 0, "", "", +"c5 f9 44 f7 \tknotb %k7,%k6",}, +{{0xc4, 0xe1, 0xf9, 0x44, 0xf7, }, 5, 0, "", "", +"c4 e1 f9 44 f7 \tknotd %k7,%k6",}, +{{0xc5, 0xcc, 0x45, 0xef, }, 4, 0, "", "", +"c5 cc 45 ef \tkorw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x45, 0xef, }, 5, 0, "", "", +"c4 e1 cc 45 ef \tkorq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x45, 0xef, }, 4, 0, "", "", +"c5 cd 45 ef \tkorb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x45, 0xef, }, 5, 0, "", "", +"c4 e1 cd 45 ef \tkord %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x46, 0xef, }, 4, 0, "", "", +"c5 cc 46 ef \tkxnorw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x46, 0xef, }, 5, 0, "", "", +"c4 e1 cc 46 ef \tkxnorq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x46, 0xef, }, 4, 0, "", "", +"c5 cd 46 ef \tkxnorb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x46, 0xef, }, 5, 0, "", "", +"c4 e1 cd 46 ef \tkxnord %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x47, 0xef, }, 4, 0, "", "", +"c5 cc 47 ef \tkxorw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x47, 0xef, }, 5, 0, "", "", +"c4 e1 cc 47 ef \tkxorq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x47, 0xef, }, 4, 0, "", "", +"c5 cd 47 ef \tkxorb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x47, 0xef, }, 5, 0, "", "", +"c4 e1 cd 47 ef \tkxord %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x4a, 0xef, }, 4, 0, "", "", +"c5 cc 4a ef \tkaddw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x4a, 0xef, }, 5, 0, "", "", +"c4 e1 cc 4a ef \tkaddq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x4a, 0xef, }, 4, 0, "", "", +"c5 cd 4a ef \tkaddb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x4a, 0xef, }, 5, 0, "", "", +"c4 e1 cd 4a ef \tkaddd %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x4b, 0xef, }, 4, 0, "", "", +"c5 cd 4b ef \tkunpckbw %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x4b, 0xef, }, 4, 0, "", "", +"c5 cc 4b ef \tkunpckwd %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x4b, 0xef, }, 5, 0, "", "", +"c4 e1 cc 4b ef \tkunpckdq %k7,%k6,%k5",}, +{{0xc5, 0xf8, 0x90, 0xee, }, 4, 0, "", "", +"c5 f8 90 ee \tkmovw %k6,%k5",}, +{{0xc5, 0xf8, 0x90, 0x29, }, 4, 0, "", "", +"c5 f8 90 29 \tkmovw (%ecx),%k5",}, +{{0xc5, 0xf8, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "", +"c5 f8 90 ac c8 23 01 00 00 \tkmovw 0x123(%eax,%ecx,8),%k5",}, +{{0xc5, 0xf8, 0x91, 0x29, }, 4, 0, "", "", +"c5 f8 91 29 \tkmovw %k5,(%ecx)",}, +{{0xc5, 0xf8, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "", +"c5 f8 91 ac c8 23 01 00 00 \tkmovw %k5,0x123(%eax,%ecx,8)",}, +{{0xc5, 0xf8, 0x92, 0xe8, }, 4, 0, "", "", +"c5 f8 92 e8 \tkmovw %eax,%k5",}, +{{0xc5, 0xf8, 0x92, 0xed, }, 4, 0, "", "", +"c5 f8 92 ed \tkmovw %ebp,%k5",}, +{{0xc5, 0xf8, 0x93, 0xc5, }, 4, 0, "", "", +"c5 f8 93 c5 \tkmovw %k5,%eax",}, +{{0xc5, 0xf8, 0x93, 0xed, }, 4, 0, "", "", +"c5 f8 93 ed \tkmovw %k5,%ebp",}, +{{0xc4, 0xe1, 0xf8, 0x90, 0xee, }, 5, 0, "", "", +"c4 e1 f8 90 ee \tkmovq %k6,%k5",}, +{{0xc4, 0xe1, 0xf8, 0x90, 0x29, }, 5, 0, "", "", +"c4 e1 f8 90 29 \tkmovq (%ecx),%k5",}, +{{0xc4, 0xe1, 0xf8, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 e1 f8 90 ac c8 23 01 00 00 \tkmovq 0x123(%eax,%ecx,8),%k5",}, +{{0xc4, 0xe1, 0xf8, 0x91, 0x29, }, 5, 0, "", "", +"c4 e1 f8 91 29 \tkmovq %k5,(%ecx)",}, +{{0xc4, 0xe1, 0xf8, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 e1 f8 91 ac c8 23 01 00 00 \tkmovq %k5,0x123(%eax,%ecx,8)",}, +{{0xc5, 0xf9, 0x90, 0xee, }, 4, 0, "", "", +"c5 f9 90 ee \tkmovb %k6,%k5",}, +{{0xc5, 0xf9, 0x90, 0x29, }, 4, 0, "", "", +"c5 f9 90 29 \tkmovb (%ecx),%k5",}, +{{0xc5, 0xf9, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "", +"c5 f9 90 ac c8 23 01 00 00 \tkmovb 0x123(%eax,%ecx,8),%k5",}, +{{0xc5, 0xf9, 0x91, 0x29, }, 4, 0, "", "", +"c5 f9 91 29 \tkmovb %k5,(%ecx)",}, +{{0xc5, 0xf9, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 9, 0, "", "", +"c5 f9 91 ac c8 23 01 00 00 \tkmovb %k5,0x123(%eax,%ecx,8)",}, +{{0xc5, 0xf9, 0x92, 0xe8, }, 4, 0, "", "", +"c5 f9 92 e8 \tkmovb %eax,%k5",}, +{{0xc5, 0xf9, 0x92, 0xed, }, 4, 0, "", "", +"c5 f9 92 ed \tkmovb %ebp,%k5",}, +{{0xc5, 0xf9, 0x93, 0xc5, }, 4, 0, "", "", +"c5 f9 93 c5 \tkmovb %k5,%eax",}, +{{0xc5, 0xf9, 0x93, 0xed, }, 4, 0, "", "", +"c5 f9 93 ed \tkmovb %k5,%ebp",}, +{{0xc4, 0xe1, 0xf9, 0x90, 0xee, }, 5, 0, "", "", +"c4 e1 f9 90 ee \tkmovd %k6,%k5",}, +{{0xc4, 0xe1, 0xf9, 0x90, 0x29, }, 5, 0, "", "", +"c4 e1 f9 90 29 \tkmovd (%ecx),%k5",}, +{{0xc4, 0xe1, 0xf9, 0x90, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 e1 f9 90 ac c8 23 01 00 00 \tkmovd 0x123(%eax,%ecx,8),%k5",}, +{{0xc4, 0xe1, 0xf9, 0x91, 0x29, }, 5, 0, "", "", +"c4 e1 f9 91 29 \tkmovd %k5,(%ecx)",}, +{{0xc4, 0xe1, 0xf9, 0x91, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 e1 f9 91 ac c8 23 01 00 00 \tkmovd %k5,0x123(%eax,%ecx,8)",}, +{{0xc5, 0xfb, 0x92, 0xe8, }, 4, 0, "", "", +"c5 fb 92 e8 \tkmovd %eax,%k5",}, +{{0xc5, 0xfb, 0x92, 0xed, }, 4, 0, "", "", +"c5 fb 92 ed \tkmovd %ebp,%k5",}, +{{0xc5, 0xfb, 0x93, 0xc5, }, 4, 0, "", "", +"c5 fb 93 c5 \tkmovd %k5,%eax",}, +{{0xc5, 0xfb, 0x93, 0xed, }, 4, 0, "", "", +"c5 fb 93 ed \tkmovd %k5,%ebp",}, +{{0xc5, 0xf8, 0x98, 0xee, }, 4, 0, "", "", +"c5 f8 98 ee \tkortestw %k6,%k5",}, +{{0xc4, 0xe1, 0xf8, 0x98, 0xee, }, 5, 0, "", "", +"c4 e1 f8 98 ee \tkortestq %k6,%k5",}, +{{0xc5, 0xf9, 0x98, 0xee, }, 4, 0, "", "", +"c5 f9 98 ee \tkortestb %k6,%k5",}, +{{0xc4, 0xe1, 0xf9, 0x98, 0xee, }, 5, 0, "", "", +"c4 e1 f9 98 ee \tkortestd %k6,%k5",}, +{{0xc5, 0xf8, 0x99, 0xee, }, 4, 0, "", "", +"c5 f8 99 ee \tktestw %k6,%k5",}, +{{0xc4, 0xe1, 0xf8, 0x99, 0xee, }, 5, 0, "", "", +"c4 e1 f8 99 ee \tktestq %k6,%k5",}, +{{0xc5, 0xf9, 0x99, 0xee, }, 4, 0, "", "", +"c5 f9 99 ee \tktestb %k6,%k5",}, +{{0xc4, 0xe1, 0xf9, 0x99, 0xee, }, 5, 0, "", "", +"c4 e1 f9 99 ee \tktestd %k6,%k5",}, +{{0xc4, 0xe3, 0xf9, 0x30, 0xee, 0x12, }, 6, 0, "", "", +"c4 e3 f9 30 ee 12 \tkshiftrw $0x12,%k6,%k5",}, +{{0xc4, 0xe3, 0xf9, 0x31, 0xee, 0x5b, }, 6, 0, "", "", +"c4 e3 f9 31 ee 5b \tkshiftrq $0x5b,%k6,%k5",}, +{{0xc4, 0xe3, 0xf9, 0x32, 0xee, 0x12, }, 6, 0, "", "", +"c4 e3 f9 32 ee 12 \tkshiftlw $0x12,%k6,%k5",}, +{{0xc4, 0xe3, 0xf9, 0x33, 0xee, 0x5b, }, 6, 0, "", "", +"c4 e3 f9 33 ee 5b \tkshiftlq $0x5b,%k6,%k5",}, +{{0xc5, 0xf8, 0x5b, 0xf5, }, 4, 0, "", "", +"c5 f8 5b f5 \tvcvtdq2ps %xmm5,%xmm6",}, +{{0x62, 0xf1, 0xfc, 0x4f, 0x5b, 0xf5, }, 6, 0, "", "", +"62 f1 fc 4f 5b f5 \tvcvtqq2ps %zmm5,%ymm6{%k7}",}, +{{0xc5, 0xf9, 0x5b, 0xf5, }, 4, 0, "", "", +"c5 f9 5b f5 \tvcvtps2dq %xmm5,%xmm6",}, +{{0xc5, 0xfa, 0x5b, 0xf5, }, 4, 0, "", "", +"c5 fa 5b f5 \tvcvttps2dq %xmm5,%xmm6",}, +{{0x0f, 0x6f, 0xe0, }, 3, 0, "", "", +"0f 6f e0 \tmovq %mm0,%mm4",}, +{{0xc5, 0xfd, 0x6f, 0xf4, }, 4, 0, "", "", +"c5 fd 6f f4 \tvmovdqa %ymm4,%ymm6",}, +{{0x62, 0xf1, 0x7d, 0x48, 0x6f, 0xf5, }, 6, 0, "", "", +"62 f1 7d 48 6f f5 \tvmovdqa32 %zmm5,%zmm6",}, +{{0x62, 0xf1, 0xfd, 0x48, 0x6f, 0xf5, }, 6, 0, "", "", +"62 f1 fd 48 6f f5 \tvmovdqa64 %zmm5,%zmm6",}, +{{0xc5, 0xfe, 0x6f, 0xf4, }, 4, 0, "", "", +"c5 fe 6f f4 \tvmovdqu %ymm4,%ymm6",}, +{{0x62, 0xf1, 0x7e, 0x48, 0x6f, 0xf5, }, 6, 0, "", "", +"62 f1 7e 48 6f f5 \tvmovdqu32 %zmm5,%zmm6",}, +{{0x62, 0xf1, 0xfe, 0x48, 0x6f, 0xf5, }, 6, 0, "", "", +"62 f1 fe 48 6f f5 \tvmovdqu64 %zmm5,%zmm6",}, +{{0x62, 0xf1, 0x7f, 0x48, 0x6f, 0xf5, }, 6, 0, "", "", +"62 f1 7f 48 6f f5 \tvmovdqu8 %zmm5,%zmm6",}, +{{0x62, 0xf1, 0xff, 0x48, 0x6f, 0xf5, }, 6, 0, "", "", +"62 f1 ff 48 6f f5 \tvmovdqu16 %zmm5,%zmm6",}, +{{0x0f, 0x78, 0xc3, }, 3, 0, "", "", +"0f 78 c3 \tvmread %eax,%ebx",}, +{{0x62, 0xf1, 0x7c, 0x48, 0x78, 0xf5, }, 6, 0, "", "", +"62 f1 7c 48 78 f5 \tvcvttps2udq %zmm5,%zmm6",}, +{{0x62, 0xf1, 0xfc, 0x4f, 0x78, 0xf5, }, 6, 0, "", "", +"62 f1 fc 4f 78 f5 \tvcvttpd2udq %zmm5,%ymm6{%k7}",}, +{{0x62, 0xf1, 0x7f, 0x08, 0x78, 0xc6, }, 6, 0, "", "", +"62 f1 7f 08 78 c6 \tvcvttsd2usi %xmm6,%eax",}, +{{0x62, 0xf1, 0x7e, 0x08, 0x78, 0xc6, }, 6, 0, "", "", +"62 f1 7e 08 78 c6 \tvcvttss2usi %xmm6,%eax",}, +{{0x62, 0xf1, 0x7d, 0x4f, 0x78, 0xf5, }, 6, 0, "", "", +"62 f1 7d 4f 78 f5 \tvcvttps2uqq %ymm5,%zmm6{%k7}",}, +{{0x62, 0xf1, 0xfd, 0x48, 0x78, 0xf5, }, 6, 0, "", "", +"62 f1 fd 48 78 f5 \tvcvttpd2uqq %zmm5,%zmm6",}, +{{0x0f, 0x79, 0xd8, }, 3, 0, "", "", +"0f 79 d8 \tvmwrite %eax,%ebx",}, +{{0x62, 0xf1, 0x7c, 0x48, 0x79, 0xf5, }, 6, 0, "", "", +"62 f1 7c 48 79 f5 \tvcvtps2udq %zmm5,%zmm6",}, +{{0x62, 0xf1, 0xfc, 0x4f, 0x79, 0xf5, }, 6, 0, "", "", +"62 f1 fc 4f 79 f5 \tvcvtpd2udq %zmm5,%ymm6{%k7}",}, +{{0x62, 0xf1, 0x7f, 0x08, 0x79, 0xc6, }, 6, 0, "", "", +"62 f1 7f 08 79 c6 \tvcvtsd2usi %xmm6,%eax",}, +{{0x62, 0xf1, 0x7e, 0x08, 0x79, 0xc6, }, 6, 0, "", "", +"62 f1 7e 08 79 c6 \tvcvtss2usi %xmm6,%eax",}, +{{0x62, 0xf1, 0x7d, 0x4f, 0x79, 0xf5, }, 6, 0, "", "", +"62 f1 7d 4f 79 f5 \tvcvtps2uqq %ymm5,%zmm6{%k7}",}, +{{0x62, 0xf1, 0xfd, 0x48, 0x79, 0xf5, }, 6, 0, "", "", +"62 f1 fd 48 79 f5 \tvcvtpd2uqq %zmm5,%zmm6",}, +{{0x62, 0xf1, 0x7e, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "", +"62 f1 7e 4f 7a f5 \tvcvtudq2pd %ymm5,%zmm6{%k7}",}, +{{0x62, 0xf1, 0xfe, 0x48, 0x7a, 0xf5, }, 6, 0, "", "", +"62 f1 fe 48 7a f5 \tvcvtuqq2pd %zmm5,%zmm6",}, +{{0x62, 0xf1, 0x7f, 0x48, 0x7a, 0xf5, }, 6, 0, "", "", +"62 f1 7f 48 7a f5 \tvcvtudq2ps %zmm5,%zmm6",}, +{{0x62, 0xf1, 0xff, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "", +"62 f1 ff 4f 7a f5 \tvcvtuqq2ps %zmm5,%ymm6{%k7}",}, +{{0x62, 0xf1, 0x7d, 0x4f, 0x7a, 0xf5, }, 6, 0, "", "", +"62 f1 7d 4f 7a f5 \tvcvttps2qq %ymm5,%zmm6{%k7}",}, +{{0x62, 0xf1, 0xfd, 0x48, 0x7a, 0xf5, }, 6, 0, "", "", +"62 f1 fd 48 7a f5 \tvcvttpd2qq %zmm5,%zmm6",}, +{{0x62, 0xf1, 0x57, 0x08, 0x7b, 0xf0, }, 6, 0, "", "", +"62 f1 57 08 7b f0 \tvcvtusi2sd %eax,%xmm5,%xmm6",}, +{{0x62, 0xf1, 0x56, 0x08, 0x7b, 0xf0, }, 6, 0, "", "", +"62 f1 56 08 7b f0 \tvcvtusi2ss %eax,%xmm5,%xmm6",}, +{{0x62, 0xf1, 0x7d, 0x4f, 0x7b, 0xf5, }, 6, 0, "", "", +"62 f1 7d 4f 7b f5 \tvcvtps2qq %ymm5,%zmm6{%k7}",}, +{{0x62, 0xf1, 0xfd, 0x48, 0x7b, 0xf5, }, 6, 0, "", "", +"62 f1 fd 48 7b f5 \tvcvtpd2qq %zmm5,%zmm6",}, +{{0x0f, 0x7f, 0xc4, }, 3, 0, "", "", +"0f 7f c4 \tmovq %mm0,%mm4",}, +{{0xc5, 0xfd, 0x7f, 0xee, }, 4, 0, "", "", +"c5 fd 7f ee \tvmovdqa %ymm5,%ymm6",}, +{{0x62, 0xf1, 0x7d, 0x48, 0x7f, 0xee, }, 6, 0, "", "", +"62 f1 7d 48 7f ee \tvmovdqa32 %zmm5,%zmm6",}, +{{0x62, 0xf1, 0xfd, 0x48, 0x7f, 0xee, }, 6, 0, "", "", +"62 f1 fd 48 7f ee \tvmovdqa64 %zmm5,%zmm6",}, +{{0xc5, 0xfe, 0x7f, 0xee, }, 4, 0, "", "", +"c5 fe 7f ee \tvmovdqu %ymm5,%ymm6",}, +{{0x62, 0xf1, 0x7e, 0x48, 0x7f, 0xee, }, 6, 0, "", "", +"62 f1 7e 48 7f ee \tvmovdqu32 %zmm5,%zmm6",}, +{{0x62, 0xf1, 0xfe, 0x48, 0x7f, 0xee, }, 6, 0, "", "", +"62 f1 fe 48 7f ee \tvmovdqu64 %zmm5,%zmm6",}, +{{0x62, 0xf1, 0x7f, 0x48, 0x7f, 0xee, }, 6, 0, "", "", +"62 f1 7f 48 7f ee \tvmovdqu8 %zmm5,%zmm6",}, +{{0x62, 0xf1, 0xff, 0x48, 0x7f, 0xee, }, 6, 0, "", "", +"62 f1 ff 48 7f ee \tvmovdqu16 %zmm5,%zmm6",}, +{{0x0f, 0xdb, 0xd1, }, 3, 0, "", "", +"0f db d1 \tpand %mm1,%mm2",}, +{{0x66, 0x0f, 0xdb, 0xd1, }, 4, 0, "", "", +"66 0f db d1 \tpand %xmm1,%xmm2",}, +{{0xc5, 0xcd, 0xdb, 0xd4, }, 4, 0, "", "", +"c5 cd db d4 \tvpand %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf1, 0x55, 0x48, 0xdb, 0xf4, }, 6, 0, "", "", +"62 f1 55 48 db f4 \tvpandd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x48, 0xdb, 0xf4, }, 6, 0, "", "", +"62 f1 d5 48 db f4 \tvpandq %zmm4,%zmm5,%zmm6",}, +{{0x0f, 0xdf, 0xd1, }, 3, 0, "", "", +"0f df d1 \tpandn %mm1,%mm2",}, +{{0x66, 0x0f, 0xdf, 0xd1, }, 4, 0, "", "", +"66 0f df d1 \tpandn %xmm1,%xmm2",}, +{{0xc5, 0xcd, 0xdf, 0xd4, }, 4, 0, "", "", +"c5 cd df d4 \tvpandn %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf1, 0x55, 0x48, 0xdf, 0xf4, }, 6, 0, "", "", +"62 f1 55 48 df f4 \tvpandnd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x48, 0xdf, 0xf4, }, 6, 0, "", "", +"62 f1 d5 48 df f4 \tvpandnq %zmm4,%zmm5,%zmm6",}, +{{0xc5, 0xf9, 0xe6, 0xd1, }, 4, 0, "", "", +"c5 f9 e6 d1 \tvcvttpd2dq %xmm1,%xmm2",}, +{{0xc5, 0xfa, 0xe6, 0xf5, }, 4, 0, "", "", +"c5 fa e6 f5 \tvcvtdq2pd %xmm5,%xmm6",}, +{{0x62, 0xf1, 0x7e, 0x4f, 0xe6, 0xf5, }, 6, 0, "", "", +"62 f1 7e 4f e6 f5 \tvcvtdq2pd %ymm5,%zmm6{%k7}",}, +{{0x62, 0xf1, 0xfe, 0x48, 0xe6, 0xf5, }, 6, 0, "", "", +"62 f1 fe 48 e6 f5 \tvcvtqq2pd %zmm5,%zmm6",}, +{{0xc5, 0xfb, 0xe6, 0xd1, }, 4, 0, "", "", +"c5 fb e6 d1 \tvcvtpd2dq %xmm1,%xmm2",}, +{{0x0f, 0xeb, 0xf4, }, 3, 0, "", "", +"0f eb f4 \tpor %mm4,%mm6",}, +{{0xc5, 0xcd, 0xeb, 0xd4, }, 4, 0, "", "", +"c5 cd eb d4 \tvpor %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf1, 0x55, 0x48, 0xeb, 0xf4, }, 6, 0, "", "", +"62 f1 55 48 eb f4 \tvpord %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x48, 0xeb, 0xf4, }, 6, 0, "", "", +"62 f1 d5 48 eb f4 \tvporq %zmm4,%zmm5,%zmm6",}, +{{0x0f, 0xef, 0xf4, }, 3, 0, "", "", +"0f ef f4 \tpxor %mm4,%mm6",}, +{{0xc5, 0xcd, 0xef, 0xd4, }, 4, 0, "", "", +"c5 cd ef d4 \tvpxor %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf1, 0x55, 0x48, 0xef, 0xf4, }, 6, 0, "", "", +"62 f1 55 48 ef f4 \tvpxord %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x48, 0xef, 0xf4, }, 6, 0, "", "", +"62 f1 d5 48 ef f4 \tvpxorq %zmm4,%zmm5,%zmm6",}, +{{0x66, 0x0f, 0x38, 0x10, 0xc1, }, 5, 0, "", "", +"66 0f 38 10 c1 \tpblendvb %xmm0,%xmm1,%xmm0",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x10, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 10 f4 \tvpsrlvw %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x10, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 10 ee \tvpmovuswb %zmm5,%ymm6{%k7}",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x11, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 11 ee \tvpmovusdb %zmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x11, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 11 f4 \tvpsravw %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x12, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 12 ee \tvpmovusqb %zmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x12, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 12 f4 \tvpsllvw %zmm4,%zmm5,%zmm6",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "", +"c4 e2 7d 13 eb \tvcvtph2ps %xmm3,%ymm5",}, +{{0x62, 0xf2, 0x7d, 0x4f, 0x13, 0xf5, }, 6, 0, "", "", +"62 f2 7d 4f 13 f5 \tvcvtph2ps %ymm5,%zmm6{%k7}",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x13, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 13 ee \tvpmovusdw %zmm5,%ymm6{%k7}",}, +{{0x66, 0x0f, 0x38, 0x14, 0xc1, }, 5, 0, "", "", +"66 0f 38 14 c1 \tblendvps %xmm0,%xmm1,%xmm0",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x14, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 14 ee \tvpmovusqw %zmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0x55, 0x48, 0x14, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 14 f4 \tvprorvd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x14, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 14 f4 \tvprorvq %zmm4,%zmm5,%zmm6",}, +{{0x66, 0x0f, 0x38, 0x15, 0xc1, }, 5, 0, "", "", +"66 0f 38 15 c1 \tblendvpd %xmm0,%xmm1,%xmm0",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x15, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 15 ee \tvpmovusqd %zmm5,%ymm6{%k7}",}, +{{0x62, 0xf2, 0x55, 0x48, 0x15, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 15 f4 \tvprolvd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x15, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 15 f4 \tvprolvq %zmm4,%zmm5,%zmm6",}, +{{0xc4, 0xe2, 0x4d, 0x16, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 16 d4 \tvpermps %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x4d, 0x2f, 0x16, 0xd4, }, 6, 0, "", "", +"62 f2 4d 2f 16 d4 \tvpermps %ymm4,%ymm6,%ymm2{%k7}",}, +{{0x62, 0xf2, 0xcd, 0x2f, 0x16, 0xd4, }, 6, 0, "", "", +"62 f2 cd 2f 16 d4 \tvpermpd %ymm4,%ymm6,%ymm2{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x19, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 19 f4 \tvbroadcastsd %xmm4,%ymm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x19, 0xf7, }, 6, 0, "", "", +"62 f2 7d 48 19 f7 \tvbroadcastf32x2 %xmm7,%zmm6",}, +{{0xc4, 0xe2, 0x7d, 0x1a, 0x21, }, 5, 0, "", "", +"c4 e2 7d 1a 21 \tvbroadcastf128 (%ecx),%ymm4",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x1a, 0x31, }, 6, 0, "", "", +"62 f2 7d 48 1a 31 \tvbroadcastf32x4 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x1a, 0x31, }, 6, 0, "", "", +"62 f2 fd 48 1a 31 \tvbroadcastf64x2 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x1b, 0x31, }, 6, 0, "", "", +"62 f2 7d 48 1b 31 \tvbroadcastf32x8 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x1b, 0x31, }, 6, 0, "", "", +"62 f2 fd 48 1b 31 \tvbroadcastf64x4 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x1f, 0xf4, }, 6, 0, "", "", +"62 f2 fd 48 1f f4 \tvpabsq %zmm4,%zmm6",}, +{{0xc4, 0xe2, 0x79, 0x20, 0xec, }, 5, 0, "", "", +"c4 e2 79 20 ec \tvpmovsxbw %xmm4,%xmm5",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x20, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 20 ee \tvpmovswb %zmm5,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x21, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 21 f4 \tvpmovsxbd %xmm4,%ymm6",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x21, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 21 ee \tvpmovsdb %zmm5,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x22, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 22 e4 \tvpmovsxbq %xmm4,%ymm4",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x22, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 22 ee \tvpmovsqb %zmm5,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x23, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 23 e4 \tvpmovsxwd %xmm4,%ymm4",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x23, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 23 ee \tvpmovsdw %zmm5,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x24, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 24 f4 \tvpmovsxwq %xmm4,%ymm6",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x24, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 24 ee \tvpmovsqw %zmm5,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x25, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 25 e4 \tvpmovsxdq %xmm4,%ymm4",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x25, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 25 ee \tvpmovsqd %zmm5,%ymm6{%k7}",}, +{{0x62, 0xf2, 0x4d, 0x48, 0x26, 0xed, }, 6, 0, "", "", +"62 f2 4d 48 26 ed \tvptestmb %zmm5,%zmm6,%k5",}, +{{0x62, 0xf2, 0xcd, 0x48, 0x26, 0xed, }, 6, 0, "", "", +"62 f2 cd 48 26 ed \tvptestmw %zmm5,%zmm6,%k5",}, +{{0x62, 0xf2, 0x56, 0x48, 0x26, 0xec, }, 6, 0, "", "", +"62 f2 56 48 26 ec \tvptestnmb %zmm4,%zmm5,%k5",}, +{{0x62, 0xf2, 0xd6, 0x48, 0x26, 0xec, }, 6, 0, "", "", +"62 f2 d6 48 26 ec \tvptestnmw %zmm4,%zmm5,%k5",}, +{{0x62, 0xf2, 0x4d, 0x48, 0x27, 0xed, }, 6, 0, "", "", +"62 f2 4d 48 27 ed \tvptestmd %zmm5,%zmm6,%k5",}, +{{0x62, 0xf2, 0xcd, 0x48, 0x27, 0xed, }, 6, 0, "", "", +"62 f2 cd 48 27 ed \tvptestmq %zmm5,%zmm6,%k5",}, +{{0x62, 0xf2, 0x56, 0x48, 0x27, 0xec, }, 6, 0, "", "", +"62 f2 56 48 27 ec \tvptestnmd %zmm4,%zmm5,%k5",}, +{{0x62, 0xf2, 0xd6, 0x48, 0x27, 0xec, }, 6, 0, "", "", +"62 f2 d6 48 27 ec \tvptestnmq %zmm4,%zmm5,%k5",}, +{{0xc4, 0xe2, 0x4d, 0x28, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 28 d4 \tvpmuldq %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x28, 0xf5, }, 6, 0, "", "", +"62 f2 7e 48 28 f5 \tvpmovm2b %k5,%zmm6",}, +{{0x62, 0xf2, 0xfe, 0x48, 0x28, 0xf5, }, 6, 0, "", "", +"62 f2 fe 48 28 f5 \tvpmovm2w %k5,%zmm6",}, +{{0xc4, 0xe2, 0x4d, 0x29, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 29 d4 \tvpcmpeqq %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x29, 0xee, }, 6, 0, "", "", +"62 f2 7e 48 29 ee \tvpmovb2m %zmm6,%k5",}, +{{0x62, 0xf2, 0xfe, 0x48, 0x29, 0xee, }, 6, 0, "", "", +"62 f2 fe 48 29 ee \tvpmovw2m %zmm6,%k5",}, +{{0xc4, 0xe2, 0x7d, 0x2a, 0x21, }, 5, 0, "", "", +"c4 e2 7d 2a 21 \tvmovntdqa (%ecx),%ymm4",}, +{{0x62, 0xf2, 0xfe, 0x48, 0x2a, 0xce, }, 6, 0, "", "", +"62 f2 fe 48 2a ce \tvpbroadcastmb2q %k6,%zmm1",}, +{{0xc4, 0xe2, 0x5d, 0x2c, 0x31, }, 5, 0, "", "", +"c4 e2 5d 2c 31 \tvmaskmovps (%ecx),%ymm4,%ymm6",}, +{{0x62, 0xf2, 0x55, 0x48, 0x2c, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 2c f4 \tvscalefps %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x2c, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 2c f4 \tvscalefpd %zmm4,%zmm5,%zmm6",}, +{{0xc4, 0xe2, 0x5d, 0x2d, 0x31, }, 5, 0, "", "", +"c4 e2 5d 2d 31 \tvmaskmovpd (%ecx),%ymm4,%ymm6",}, +{{0x62, 0xf2, 0x55, 0x0f, 0x2d, 0xf4, }, 6, 0, "", "", +"62 f2 55 0f 2d f4 \tvscalefss %xmm4,%xmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0xd5, 0x0f, 0x2d, 0xf4, }, 6, 0, "", "", +"62 f2 d5 0f 2d f4 \tvscalefsd %xmm4,%xmm5,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x30, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 30 e4 \tvpmovzxbw %xmm4,%ymm4",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x30, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 30 ee \tvpmovwb %zmm5,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x31, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 31 f4 \tvpmovzxbd %xmm4,%ymm6",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x31, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 31 ee \tvpmovdb %zmm5,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x32, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 32 e4 \tvpmovzxbq %xmm4,%ymm4",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x32, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 32 ee \tvpmovqb %zmm5,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x33, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 33 e4 \tvpmovzxwd %xmm4,%ymm4",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x33, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 33 ee \tvpmovdw %zmm5,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x34, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 34 f4 \tvpmovzxwq %xmm4,%ymm6",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x34, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 34 ee \tvpmovqw %zmm5,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x35, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 35 e4 \tvpmovzxdq %xmm4,%ymm4",}, +{{0x62, 0xf2, 0x7e, 0x4f, 0x35, 0xee, }, 6, 0, "", "", +"62 f2 7e 4f 35 ee \tvpmovqd %zmm5,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x4d, 0x36, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 36 d4 \tvpermd %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x4d, 0x2f, 0x36, 0xd4, }, 6, 0, "", "", +"62 f2 4d 2f 36 d4 \tvpermd %ymm4,%ymm6,%ymm2{%k7}",}, +{{0x62, 0xf2, 0xcd, 0x2f, 0x36, 0xd4, }, 6, 0, "", "", +"62 f2 cd 2f 36 d4 \tvpermq %ymm4,%ymm6,%ymm2{%k7}",}, +{{0xc4, 0xe2, 0x4d, 0x38, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 38 d4 \tvpminsb %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x38, 0xf5, }, 6, 0, "", "", +"62 f2 7e 48 38 f5 \tvpmovm2d %k5,%zmm6",}, +{{0x62, 0xf2, 0xfe, 0x48, 0x38, 0xf5, }, 6, 0, "", "", +"62 f2 fe 48 38 f5 \tvpmovm2q %k5,%zmm6",}, +{{0xc4, 0xe2, 0x69, 0x39, 0xd9, }, 5, 0, "", "", +"c4 e2 69 39 d9 \tvpminsd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x55, 0x48, 0x39, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 39 f4 \tvpminsd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x39, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 39 f4 \tvpminsq %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x39, 0xee, }, 6, 0, "", "", +"62 f2 7e 48 39 ee \tvpmovd2m %zmm6,%k5",}, +{{0x62, 0xf2, 0xfe, 0x48, 0x39, 0xee, }, 6, 0, "", "", +"62 f2 fe 48 39 ee \tvpmovq2m %zmm6,%k5",}, +{{0xc4, 0xe2, 0x4d, 0x3a, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 3a d4 \tvpminuw %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x3a, 0xf6, }, 6, 0, "", "", +"62 f2 7e 48 3a f6 \tvpbroadcastmw2d %k6,%zmm6",}, +{{0xc4, 0xe2, 0x4d, 0x3b, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 3b d4 \tvpminud %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x55, 0x48, 0x3b, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 3b f4 \tvpminud %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x3b, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 3b f4 \tvpminuq %zmm4,%zmm5,%zmm6",}, +{{0xc4, 0xe2, 0x4d, 0x3d, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 3d d4 \tvpmaxsd %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x55, 0x48, 0x3d, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 3d f4 \tvpmaxsd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x3d, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 3d f4 \tvpmaxsq %zmm4,%zmm5,%zmm6",}, +{{0xc4, 0xe2, 0x4d, 0x3f, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 3f d4 \tvpmaxud %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x55, 0x48, 0x3f, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 3f f4 \tvpmaxud %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x3f, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 3f f4 \tvpmaxuq %zmm4,%zmm5,%zmm6",}, +{{0xc4, 0xe2, 0x4d, 0x40, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 40 d4 \tvpmulld %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x55, 0x48, 0x40, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 40 f4 \tvpmulld %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x40, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 40 f4 \tvpmullq %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x42, 0xf5, }, 6, 0, "", "", +"62 f2 7d 48 42 f5 \tvgetexpps %zmm5,%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x42, 0xf5, }, 6, 0, "", "", +"62 f2 fd 48 42 f5 \tvgetexppd %zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x0f, 0x43, 0xf4, }, 6, 0, "", "", +"62 f2 55 0f 43 f4 \tvgetexpss %xmm4,%xmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0xe5, 0x0f, 0x43, 0xe2, }, 6, 0, "", "", +"62 f2 e5 0f 43 e2 \tvgetexpsd %xmm2,%xmm3,%xmm4{%k7}",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x44, 0xf5, }, 6, 0, "", "", +"62 f2 7d 48 44 f5 \tvplzcntd %zmm5,%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x44, 0xf5, }, 6, 0, "", "", +"62 f2 fd 48 44 f5 \tvplzcntq %zmm5,%zmm6",}, +{{0xc4, 0xe2, 0x4d, 0x46, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 46 d4 \tvpsravd %ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf2, 0x55, 0x48, 0x46, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 46 f4 \tvpsravd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x46, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 46 f4 \tvpsravq %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x4c, 0xf5, }, 6, 0, "", "", +"62 f2 7d 48 4c f5 \tvrcp14ps %zmm5,%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x4c, 0xf5, }, 6, 0, "", "", +"62 f2 fd 48 4c f5 \tvrcp14pd %zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x0f, 0x4d, 0xf4, }, 6, 0, "", "", +"62 f2 55 0f 4d f4 \tvrcp14ss %xmm4,%xmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0xd5, 0x0f, 0x4d, 0xf4, }, 6, 0, "", "", +"62 f2 d5 0f 4d f4 \tvrcp14sd %xmm4,%xmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x4e, 0xf5, }, 6, 0, "", "", +"62 f2 7d 48 4e f5 \tvrsqrt14ps %zmm5,%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x4e, 0xf5, }, 6, 0, "", "", +"62 f2 fd 48 4e f5 \tvrsqrt14pd %zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "", +"62 f2 55 0f 4f f4 \tvrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0xd5, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "", +"62 f2 d5 0f 4f f4 \tvrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "", +"c4 e2 79 59 f4 \tvpbroadcastq %xmm4,%xmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x59, 0xf7, }, 6, 0, "", "", +"62 f2 7d 48 59 f7 \tvbroadcasti32x2 %xmm7,%zmm6",}, +{{0xc4, 0xe2, 0x7d, 0x5a, 0x21, }, 5, 0, "", "", +"c4 e2 7d 5a 21 \tvbroadcasti128 (%ecx),%ymm4",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x5a, 0x31, }, 6, 0, "", "", +"62 f2 7d 48 5a 31 \tvbroadcasti32x4 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x5a, 0x31, }, 6, 0, "", "", +"62 f2 fd 48 5a 31 \tvbroadcasti64x2 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x5b, 0x31, }, 6, 0, "", "", +"62 f2 7d 48 5b 31 \tvbroadcasti32x8 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x5b, 0x31, }, 6, 0, "", "", +"62 f2 fd 48 5b 31 \tvbroadcasti64x4 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0x55, 0x48, 0x64, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 64 f4 \tvpblendmd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x64, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 64 f4 \tvpblendmq %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x48, 0x65, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 65 f4 \tvblendmps %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x65, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 65 f4 \tvblendmpd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x48, 0x66, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 66 f4 \tvpblendmb %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x66, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 66 f4 \tvpblendmw %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x48, 0x75, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 75 f4 \tvpermi2b %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x75, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 75 f4 \tvpermi2w %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x48, 0x76, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 76 f4 \tvpermi2d %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x76, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 76 f4 \tvpermi2q %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x48, 0x77, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 77 f4 \tvpermi2ps %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x77, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 77 f4 \tvpermi2pd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x7a, 0xd8, }, 6, 0, "", "", +"62 f2 7d 08 7a d8 \tvpbroadcastb %eax,%xmm3",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x7b, 0xd8, }, 6, 0, "", "", +"62 f2 7d 08 7b d8 \tvpbroadcastw %eax,%xmm3",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x7c, 0xd8, }, 6, 0, "", "", +"62 f2 7d 08 7c d8 \tvpbroadcastd %eax,%xmm3",}, +{{0x62, 0xf2, 0x55, 0x48, 0x7d, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 7d f4 \tvpermt2b %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x7d, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 7d f4 \tvpermt2w %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x48, 0x7e, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 7e f4 \tvpermt2d %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x7e, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 7e f4 \tvpermt2q %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x55, 0x48, 0x7f, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 7f f4 \tvpermt2ps %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x7f, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 7f f4 \tvpermt2pd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x83, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 83 f4 \tvpmultishiftqb %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x88, 0x31, }, 6, 0, "", "", +"62 f2 7d 48 88 31 \tvexpandps (%ecx),%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x88, 0x31, }, 6, 0, "", "", +"62 f2 fd 48 88 31 \tvexpandpd (%ecx),%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x89, 0x31, }, 6, 0, "", "", +"62 f2 7d 48 89 31 \tvpexpandd (%ecx),%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x89, 0x31, }, 6, 0, "", "", +"62 f2 fd 48 89 31 \tvpexpandq (%ecx),%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x8a, 0x31, }, 6, 0, "", "", +"62 f2 7d 48 8a 31 \tvcompressps %zmm6,(%ecx)",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x8a, 0x31, }, 6, 0, "", "", +"62 f2 fd 48 8a 31 \tvcompresspd %zmm6,(%ecx)",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x8b, 0x31, }, 6, 0, "", "", +"62 f2 7d 48 8b 31 \tvpcompressd %zmm6,(%ecx)",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x8b, 0x31, }, 6, 0, "", "", +"62 f2 fd 48 8b 31 \tvpcompressq %zmm6,(%ecx)",}, +{{0x62, 0xf2, 0x55, 0x48, 0x8d, 0xf4, }, 6, 0, "", "", +"62 f2 55 48 8d f4 \tvpermb %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0x8d, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 8d f4 \tvpermw %zmm4,%zmm5,%zmm6",}, +{{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", +"c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",}, +{{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "", +"c4 e2 e9 90 4c 7d 04 \tvpgatherdq %xmm2,0x4(%ebp,%xmm7,2),%xmm1",}, +{{0x62, 0xf2, 0x7d, 0x49, 0x90, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 90 b4 fd 7b 00 00 00 \tvpgatherdd 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0x90, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 90 b4 fd 7b 00 00 00 \tvpgatherdq 0x7b(%ebp,%ymm7,8),%zmm6{%k1}",}, +{{0xc4, 0xe2, 0x69, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", +"c4 e2 69 91 4c 7d 02 \tvpgatherqd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",}, +{{0xc4, 0xe2, 0xe9, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", +"c4 e2 e9 91 4c 7d 02 \tvpgatherqq %xmm2,0x2(%ebp,%xmm7,2),%xmm1",}, +{{0x62, 0xf2, 0x7d, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 91 b4 fd 7b 00 00 00 \tvpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 91 b4 fd 7b 00 00 00 \tvpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 a0 b4 fd 7b 00 00 00 \tvpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 a0 b4 fd 7b 00 00 00 \tvpscatterdq %zmm6,0x7b(%ebp,%ymm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xa1, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 a1 b4 fd 7b 00 00 00 \tvpscatterqd %ymm6,0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x29, 0xa1, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 29 a1 b4 fd 7b 00 00 00 \tvpscatterqq %ymm6,0x7b(%ebp,%ymm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xa2, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 a2 b4 fd 7b 00 00 00 \tvscatterdps %zmm6,0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xa2, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 a2 b4 fd 7b 00 00 00 \tvscatterdpd %zmm6,0x7b(%ebp,%ymm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 a3 b4 fd 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 a3 b4 fd 7b 00 00 00 \tvscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xd5, 0x48, 0xb4, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 b4 f4 \tvpmadd52luq %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0xd5, 0x48, 0xb5, 0xf4, }, 6, 0, "", "", +"62 f2 d5 48 b5 f4 \tvpmadd52huq %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0xc4, 0xf5, }, 6, 0, "", "", +"62 f2 7d 48 c4 f5 \tvpconflictd %zmm5,%zmm6",}, +{{0x62, 0xf2, 0xfd, 0x48, 0xc4, 0xf5, }, 6, 0, "", "", +"62 f2 fd 48 c4 f5 \tvpconflictq %zmm5,%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x48, 0xc8, 0xfe, }, 6, 0, "", "", +"62 f2 7d 48 c8 fe \tvexp2ps %zmm6,%zmm7",}, +{{0x62, 0xf2, 0xfd, 0x48, 0xc8, 0xfe, }, 6, 0, "", "", +"62 f2 fd 48 c8 fe \tvexp2pd %zmm6,%zmm7",}, +{{0x62, 0xf2, 0x7d, 0x48, 0xca, 0xfe, }, 6, 0, "", "", +"62 f2 7d 48 ca fe \tvrcp28ps %zmm6,%zmm7",}, +{{0x62, 0xf2, 0xfd, 0x48, 0xca, 0xfe, }, 6, 0, "", "", +"62 f2 fd 48 ca fe \tvrcp28pd %zmm6,%zmm7",}, +{{0x62, 0xf2, 0x4d, 0x0f, 0xcb, 0xfd, }, 6, 0, "", "", +"62 f2 4d 0f cb fd \tvrcp28ss %xmm5,%xmm6,%xmm7{%k7}",}, +{{0x62, 0xf2, 0xcd, 0x0f, 0xcb, 0xfd, }, 6, 0, "", "", +"62 f2 cd 0f cb fd \tvrcp28sd %xmm5,%xmm6,%xmm7{%k7}",}, +{{0x62, 0xf2, 0x7d, 0x48, 0xcc, 0xfe, }, 6, 0, "", "", +"62 f2 7d 48 cc fe \tvrsqrt28ps %zmm6,%zmm7",}, +{{0x62, 0xf2, 0xfd, 0x48, 0xcc, 0xfe, }, 6, 0, "", "", +"62 f2 fd 48 cc fe \tvrsqrt28pd %zmm6,%zmm7",}, +{{0x62, 0xf2, 0x4d, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "", +"62 f2 4d 0f cd fd \tvrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}",}, +{{0x62, 0xf2, 0xcd, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "", +"62 f2 cd 0f cd fd \tvrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}",}, +{{0x62, 0xf3, 0x4d, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 48 03 fd 12 \tvalignd $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0xcd, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 48 03 fd 12 \tvalignq $0x12,%zmm5,%zmm6,%zmm7",}, +{{0xc4, 0xe3, 0x7d, 0x08, 0xd6, 0x05, }, 6, 0, "", "", +"c4 e3 7d 08 d6 05 \tvroundps $0x5,%ymm6,%ymm2",}, +{{0x62, 0xf3, 0x7d, 0x48, 0x08, 0xf5, 0x12, }, 7, 0, "", "", +"62 f3 7d 48 08 f5 12 \tvrndscaleps $0x12,%zmm5,%zmm6",}, +{{0xc4, 0xe3, 0x7d, 0x09, 0xd6, 0x05, }, 6, 0, "", "", +"c4 e3 7d 09 d6 05 \tvroundpd $0x5,%ymm6,%ymm2",}, +{{0x62, 0xf3, 0xfd, 0x48, 0x09, 0xf5, 0x12, }, 7, 0, "", "", +"62 f3 fd 48 09 f5 12 \tvrndscalepd $0x12,%zmm5,%zmm6",}, +{{0xc4, 0xe3, 0x49, 0x0a, 0xd4, 0x05, }, 6, 0, "", "", +"c4 e3 49 0a d4 05 \tvroundss $0x5,%xmm4,%xmm6,%xmm2",}, +{{0x62, 0xf3, 0x55, 0x0f, 0x0a, 0xf4, 0x12, }, 7, 0, "", "", +"62 f3 55 0f 0a f4 12 \tvrndscaless $0x12,%xmm4,%xmm5,%xmm6{%k7}",}, +{{0xc4, 0xe3, 0x49, 0x0b, 0xd4, 0x05, }, 6, 0, "", "", +"c4 e3 49 0b d4 05 \tvroundsd $0x5,%xmm4,%xmm6,%xmm2",}, +{{0x62, 0xf3, 0xd5, 0x0f, 0x0b, 0xf4, 0x12, }, 7, 0, "", "", +"62 f3 d5 0f 0b f4 12 \tvrndscalesd $0x12,%xmm4,%xmm5,%xmm6{%k7}",}, +{{0xc4, 0xe3, 0x5d, 0x18, 0xf4, 0x05, }, 6, 0, "", "", +"c4 e3 5d 18 f4 05 \tvinsertf128 $0x5,%xmm4,%ymm4,%ymm6",}, +{{0x62, 0xf3, 0x55, 0x4f, 0x18, 0xf4, 0x12, }, 7, 0, "", "", +"62 f3 55 4f 18 f4 12 \tvinsertf32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}",}, +{{0x62, 0xf3, 0xd5, 0x4f, 0x18, 0xf4, 0x12, }, 7, 0, "", "", +"62 f3 d5 4f 18 f4 12 \tvinsertf64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}",}, +{{0xc4, 0xe3, 0x7d, 0x19, 0xe4, 0x05, }, 6, 0, "", "", +"c4 e3 7d 19 e4 05 \tvextractf128 $0x5,%ymm4,%xmm4",}, +{{0x62, 0xf3, 0x7d, 0x4f, 0x19, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 7d 4f 19 ee 12 \tvextractf32x4 $0x12,%zmm5,%xmm6{%k7}",}, +{{0x62, 0xf3, 0xfd, 0x4f, 0x19, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 fd 4f 19 ee 12 \tvextractf64x2 $0x12,%zmm5,%xmm6{%k7}",}, +{{0x62, 0xf3, 0x4d, 0x4f, 0x1a, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 4f 1a fd 12 \tvinsertf32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}",}, +{{0x62, 0xf3, 0xcd, 0x4f, 0x1a, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 4f 1a fd 12 \tvinsertf64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}",}, +{{0x62, 0xf3, 0x7d, 0x4f, 0x1b, 0xf7, 0x12, }, 7, 0, "", "", +"62 f3 7d 4f 1b f7 12 \tvextractf32x8 $0x12,%zmm6,%ymm7{%k7}",}, +{{0x62, 0xf3, 0xfd, 0x4f, 0x1b, 0xf7, 0x12, }, 7, 0, "", "", +"62 f3 fd 4f 1b f7 12 \tvextractf64x4 $0x12,%zmm6,%ymm7{%k7}",}, +{{0x62, 0xf3, 0x45, 0x48, 0x1e, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 45 48 1e ee 12 \tvpcmpud $0x12,%zmm6,%zmm7,%k5",}, +{{0x62, 0xf3, 0xc5, 0x48, 0x1e, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 c5 48 1e ee 12 \tvpcmpuq $0x12,%zmm6,%zmm7,%k5",}, +{{0x62, 0xf3, 0x45, 0x48, 0x1f, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 45 48 1f ee 12 \tvpcmpd $0x12,%zmm6,%zmm7,%k5",}, +{{0x62, 0xf3, 0xc5, 0x48, 0x1f, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 c5 48 1f ee 12 \tvpcmpq $0x12,%zmm6,%zmm7,%k5",}, +{{0x62, 0xf3, 0x4d, 0x48, 0x23, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 48 23 fd 12 \tvshuff32x4 $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0xcd, 0x48, 0x23, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 48 23 fd 12 \tvshuff64x2 $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0x4d, 0x48, 0x25, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 48 25 fd 12 \tvpternlogd $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0xcd, 0x48, 0x25, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 48 25 fd 12 \tvpternlogq $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0x7d, 0x48, 0x26, 0xfe, 0x12, }, 7, 0, "", "", +"62 f3 7d 48 26 fe 12 \tvgetmantps $0x12,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0xfd, 0x48, 0x26, 0xfe, 0x12, }, 7, 0, "", "", +"62 f3 fd 48 26 fe 12 \tvgetmantpd $0x12,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0x4d, 0x0f, 0x27, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 0f 27 fd 12 \tvgetmantss $0x12,%xmm5,%xmm6,%xmm7{%k7}",}, +{{0x62, 0xf3, 0xcd, 0x0f, 0x27, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 0f 27 fd 12 \tvgetmantsd $0x12,%xmm5,%xmm6,%xmm7{%k7}",}, +{{0xc4, 0xe3, 0x5d, 0x38, 0xf4, 0x05, }, 6, 0, "", "", +"c4 e3 5d 38 f4 05 \tvinserti128 $0x5,%xmm4,%ymm4,%ymm6",}, +{{0x62, 0xf3, 0x55, 0x4f, 0x38, 0xf4, 0x12, }, 7, 0, "", "", +"62 f3 55 4f 38 f4 12 \tvinserti32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}",}, +{{0x62, 0xf3, 0xd5, 0x4f, 0x38, 0xf4, 0x12, }, 7, 0, "", "", +"62 f3 d5 4f 38 f4 12 \tvinserti64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}",}, +{{0xc4, 0xe3, 0x7d, 0x39, 0xe6, 0x05, }, 6, 0, "", "", +"c4 e3 7d 39 e6 05 \tvextracti128 $0x5,%ymm4,%xmm6",}, +{{0x62, 0xf3, 0x7d, 0x4f, 0x39, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 7d 4f 39 ee 12 \tvextracti32x4 $0x12,%zmm5,%xmm6{%k7}",}, +{{0x62, 0xf3, 0xfd, 0x4f, 0x39, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 fd 4f 39 ee 12 \tvextracti64x2 $0x12,%zmm5,%xmm6{%k7}",}, +{{0x62, 0xf3, 0x4d, 0x4f, 0x3a, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 4f 3a fd 12 \tvinserti32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}",}, +{{0x62, 0xf3, 0xcd, 0x4f, 0x3a, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 4f 3a fd 12 \tvinserti64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}",}, +{{0x62, 0xf3, 0x7d, 0x4f, 0x3b, 0xf7, 0x12, }, 7, 0, "", "", +"62 f3 7d 4f 3b f7 12 \tvextracti32x8 $0x12,%zmm6,%ymm7{%k7}",}, +{{0x62, 0xf3, 0xfd, 0x4f, 0x3b, 0xf7, 0x12, }, 7, 0, "", "", +"62 f3 fd 4f 3b f7 12 \tvextracti64x4 $0x12,%zmm6,%ymm7{%k7}",}, +{{0x62, 0xf3, 0x45, 0x48, 0x3e, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 45 48 3e ee 12 \tvpcmpub $0x12,%zmm6,%zmm7,%k5",}, +{{0x62, 0xf3, 0xc5, 0x48, 0x3e, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 c5 48 3e ee 12 \tvpcmpuw $0x12,%zmm6,%zmm7,%k5",}, +{{0x62, 0xf3, 0x45, 0x48, 0x3f, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 45 48 3f ee 12 \tvpcmpb $0x12,%zmm6,%zmm7,%k5",}, +{{0x62, 0xf3, 0xc5, 0x48, 0x3f, 0xee, 0x12, }, 7, 0, "", "", +"62 f3 c5 48 3f ee 12 \tvpcmpw $0x12,%zmm6,%zmm7,%k5",}, +{{0xc4, 0xe3, 0x4d, 0x42, 0xd4, 0x05, }, 6, 0, "", "", +"c4 e3 4d 42 d4 05 \tvmpsadbw $0x5,%ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf3, 0x55, 0x48, 0x42, 0xf4, 0x12, }, 7, 0, "", "", +"62 f3 55 48 42 f4 12 \tvdbpsadbw $0x12,%zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf3, 0x4d, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 48 43 fd 12 \tvshufi32x4 $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0xcd, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 48 43 fd 12 \tvshufi64x2 $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0x4d, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 48 50 fd 12 \tvrangeps $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0xcd, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 48 50 fd 12 \tvrangepd $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0x4d, 0x08, 0x51, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 08 51 fd 12 \tvrangess $0x12,%xmm5,%xmm6,%xmm7",}, +{{0x62, 0xf3, 0xcd, 0x08, 0x51, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 08 51 fd 12 \tvrangesd $0x12,%xmm5,%xmm6,%xmm7",}, +{{0x62, 0xf3, 0x4d, 0x48, 0x54, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 48 54 fd 12 \tvfixupimmps $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0xcd, 0x48, 0x54, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 48 54 fd 12 \tvfixupimmpd $0x12,%zmm5,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0x4d, 0x0f, 0x55, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 0f 55 fd 12 \tvfixupimmss $0x12,%xmm5,%xmm6,%xmm7{%k7}",}, +{{0x62, 0xf3, 0xcd, 0x0f, 0x55, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 0f 55 fd 12 \tvfixupimmsd $0x12,%xmm5,%xmm6,%xmm7{%k7}",}, +{{0x62, 0xf3, 0x7d, 0x48, 0x56, 0xfe, 0x12, }, 7, 0, "", "", +"62 f3 7d 48 56 fe 12 \tvreduceps $0x12,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0xfd, 0x48, 0x56, 0xfe, 0x12, }, 7, 0, "", "", +"62 f3 fd 48 56 fe 12 \tvreducepd $0x12,%zmm6,%zmm7",}, +{{0x62, 0xf3, 0x4d, 0x08, 0x57, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 4d 08 57 fd 12 \tvreducess $0x12,%xmm5,%xmm6,%xmm7",}, +{{0x62, 0xf3, 0xcd, 0x08, 0x57, 0xfd, 0x12, }, 7, 0, "", "", +"62 f3 cd 08 57 fd 12 \tvreducesd $0x12,%xmm5,%xmm6,%xmm7",}, +{{0x62, 0xf3, 0x7d, 0x48, 0x66, 0xef, 0x12, }, 7, 0, "", "", +"62 f3 7d 48 66 ef 12 \tvfpclassps $0x12,%zmm7,%k5",}, +{{0x62, 0xf3, 0xfd, 0x48, 0x66, 0xef, 0x12, }, 7, 0, "", "", +"62 f3 fd 48 66 ef 12 \tvfpclasspd $0x12,%zmm7,%k5",}, +{{0x62, 0xf3, 0x7d, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "", +"62 f3 7d 08 67 ef 12 \tvfpclassss $0x12,%xmm7,%k5",}, +{{0x62, 0xf3, 0xfd, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "", +"62 f3 fd 08 67 ef 12 \tvfpclasssd $0x12,%xmm7,%k5",}, +{{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "", +"62 f1 4d 48 72 c5 12 \tvprord $0x12,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "", +"62 f1 cd 48 72 c5 12 \tvprorq $0x12,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xcd, 0x12, }, 7, 0, "", "", +"62 f1 4d 48 72 cd 12 \tvprold $0x12,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xcd, 0x12, }, 7, 0, "", "", +"62 f1 cd 48 72 cd 12 \tvprolq $0x12,%zmm5,%zmm6",}, +{{0x0f, 0x72, 0xe6, 0x02, }, 4, 0, "", "", +"0f 72 e6 02 \tpsrad $0x2,%mm6",}, +{{0xc5, 0xed, 0x72, 0xe6, 0x05, }, 5, 0, "", "", +"c5 ed 72 e6 05 \tvpsrad $0x5,%ymm6,%ymm2",}, +{{0x62, 0xf1, 0x6d, 0x48, 0x72, 0xe6, 0x05, }, 7, 0, "", "", +"62 f1 6d 48 72 e6 05 \tvpsrad $0x5,%zmm6,%zmm2",}, +{{0x62, 0xf1, 0xed, 0x48, 0x72, 0xe6, 0x05, }, 7, 0, "", "", +"62 f1 ed 48 72 e6 05 \tvpsraq $0x5,%zmm6,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 c6 8c fd 7b 00 00 00 \tvgatherpf0dps 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 c6 8c fd 7b 00 00 00 \tvgatherpf0dpd 0x7b(%ebp,%ymm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 c6 94 fd 7b 00 00 00 \tvgatherpf1dps 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 c6 94 fd 7b 00 00 00 \tvgatherpf1dpd 0x7b(%ebp,%ymm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 c6 ac fd 7b 00 00 00 \tvscatterpf0dps 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 c6 ac fd 7b 00 00 00 \tvscatterpf0dpd 0x7b(%ebp,%ymm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xc6, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 c6 b4 fd 7b 00 00 00 \tvscatterpf1dps 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xc6, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 c6 b4 fd 7b 00 00 00 \tvscatterpf1dpd 0x7b(%ebp,%ymm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 c7 8c fd 7b 00 00 00 \tvgatherpf0qps 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0x8c, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 c7 8c fd 7b 00 00 00 \tvgatherpf0qpd 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 c7 94 fd 7b 00 00 00 \tvgatherpf1qps 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0x94, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 c7 94 fd 7b 00 00 00 \tvgatherpf1qpd 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 c7 ac fd 7b 00 00 00 \tvscatterpf0qps 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0xac, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 c7 ac fd 7b 00 00 00 \tvscatterpf0qpd 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0x7d, 0x49, 0xc7, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 7d 49 c7 b4 fd 7b 00 00 00 \tvscatterpf1qps 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf2, 0xfd, 0x49, 0xc7, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 f2 fd 49 c7 b4 fd 7b 00 00 00 \tvscatterpf1qpd 0x7b(%ebp,%zmm7,8){%k1}",}, +{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0xf4, }, 6, 0, "", "", +"62 f1 d5 48 58 f4 \tvaddpd %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x4f, 0x58, 0xf4, }, 6, 0, "", "", +"62 f1 d5 4f 58 f4 \tvaddpd %zmm4,%zmm5,%zmm6{%k7}",}, +{{0x62, 0xf1, 0xd5, 0xcf, 0x58, 0xf4, }, 6, 0, "", "", +"62 f1 d5 cf 58 f4 \tvaddpd %zmm4,%zmm5,%zmm6{%k7}{z}",}, +{{0x62, 0xf1, 0xd5, 0x18, 0x58, 0xf4, }, 6, 0, "", "", +"62 f1 d5 18 58 f4 \tvaddpd {rn-sae},%zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0xf4, }, 6, 0, "", "", +"62 f1 d5 58 58 f4 \tvaddpd {ru-sae},%zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x38, 0x58, 0xf4, }, 6, 0, "", "", +"62 f1 d5 38 58 f4 \tvaddpd {rd-sae},%zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x78, 0x58, 0xf4, }, 6, 0, "", "", +"62 f1 d5 78 58 f4 \tvaddpd {rz-sae},%zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0x31, }, 6, 0, "", "", +"62 f1 d5 48 58 31 \tvaddpd (%ecx),%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0xb4, 0xc8, 0x23, 0x01, 0x00, 0x00, }, 11, 0, "", "", +"62 f1 d5 48 58 b4 c8 23 01 00 00 \tvaddpd 0x123(%eax,%ecx,8),%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0x31, }, 6, 0, "", "", +"62 f1 d5 58 58 31 \tvaddpd (%ecx){1to8},%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x48, 0x58, 0x72, 0x7f, }, 7, 0, "", "", +"62 f1 d5 48 58 72 7f \tvaddpd 0x1fc0(%edx),%zmm5,%zmm6",}, +{{0x62, 0xf1, 0xd5, 0x58, 0x58, 0x72, 0x7f, }, 7, 0, "", "", +"62 f1 d5 58 58 72 7f \tvaddpd 0x3f8(%edx){1to8},%zmm5,%zmm6",}, +{{0x62, 0xf1, 0x4c, 0x58, 0xc2, 0x6a, 0x7f, 0x08, }, 8, 0, "", "", +"62 f1 4c 58 c2 6a 7f 08 \tvcmpeq_uqps 0x1fc(%edx){1to16},%zmm6,%k5",}, +{{0x62, 0xf1, 0xe7, 0x0f, 0xc2, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, 0x01, }, 12, 0, "", "", +"62 f1 e7 0f c2 ac c8 23 01 00 00 01 \tvcmpltsd 0x123(%eax,%ecx,8),%xmm3,%k5{%k7}",}, +{{0x62, 0xf1, 0xd7, 0x1f, 0xc2, 0xec, 0x02, }, 7, 0, "", "", +"62 f1 d7 1f c2 ec 02 \tvcmplesd {sae},%xmm4,%xmm5,%k5{%k7}",}, +{{0x62, 0xf3, 0x5d, 0x0f, 0x27, 0xac, 0xc8, 0x23, 0x01, 0x00, 0x00, 0x5b, }, 12, 0, "", "", +"62 f3 5d 0f 27 ac c8 23 01 00 00 5b \tvgetmantss $0x5b,0x123(%eax,%ecx,8),%xmm4,%xmm5{%k7}",}, {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "", "f3 0f 1b 00 \tbndmk (%eax),%bnd0",}, {{0xf3, 0x0f, 0x1b, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", @@ -311,19 +1319,19 @@ {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%eax,%ecx,1)",}, {{0xf2, 0xe8, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "call", "unconditional", -"f2 e8 fc ff ff ff \tbnd call 3c8 ",}, +"f2 e8 fc ff ff ff \tbnd call fce ",}, {{0xf2, 0xff, 0x10, }, 3, 0, "call", "indirect", "f2 ff 10 \tbnd call *(%eax)",}, {{0xf2, 0xc3, }, 2, 0, "ret", "indirect", "f2 c3 \tbnd ret ",}, {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional", -"f2 e9 fc ff ff ff \tbnd jmp 3d3 ",}, +"f2 e9 fc ff ff ff \tbnd jmp fd9 ",}, {{0xf2, 0xe9, 0xfc, 0xff, 0xff, 0xff, }, 6, 0xfffffffc, "jmp", "unconditional", -"f2 e9 fc ff ff ff \tbnd jmp 3d9 ",}, +"f2 e9 fc ff ff ff \tbnd jmp fdf ",}, {{0xf2, 0xff, 0x21, }, 3, 0, "jmp", "indirect", "f2 ff 21 \tbnd jmp *(%ecx)",}, {{0xf2, 0x0f, 0x85, 0xfc, 0xff, 0xff, 0xff, }, 7, 0xfffffffc, "jcc", "conditional", -"f2 0f 85 fc ff ff ff \tbnd jne 3e3 ",}, +"f2 0f 85 fc ff ff ff \tbnd jne fe9 ",}, {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "", "0f 3a cc c1 00 \tsha1rnds4 $0x0,%xmm1,%xmm0",}, {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "", diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c index 262d9d2..9c8c61e 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -8,6 +8,936 @@ "0f 31 \trdtsc ",}, {{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "", "c4 e2 7d 13 eb \tvcvtph2ps %xmm3,%ymm5",}, +{{0x48, 0x0f, 0x41, 0xd8, }, 4, 0, "", "", +"48 0f 41 d8 \tcmovno %rax,%rbx",}, +{{0x48, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"48 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%rax),%rcx",}, +{{0x66, 0x0f, 0x41, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"66 0f 41 88 78 56 34 12 \tcmovno 0x12345678(%rax),%cx",}, +{{0x48, 0x0f, 0x44, 0xd8, }, 4, 0, "", "", +"48 0f 44 d8 \tcmove %rax,%rbx",}, +{{0x48, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"48 0f 44 88 78 56 34 12 \tcmove 0x12345678(%rax),%rcx",}, +{{0x66, 0x0f, 0x44, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"66 0f 44 88 78 56 34 12 \tcmove 0x12345678(%rax),%cx",}, +{{0x0f, 0x90, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 90 80 78 56 34 12 \tseto 0x12345678(%rax)",}, +{{0x0f, 0x91, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 91 80 78 56 34 12 \tsetno 0x12345678(%rax)",}, +{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 92 80 78 56 34 12 \tsetb 0x12345678(%rax)",}, +{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 92 80 78 56 34 12 \tsetb 0x12345678(%rax)",}, +{{0x0f, 0x92, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 92 80 78 56 34 12 \tsetb 0x12345678(%rax)",}, +{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 93 80 78 56 34 12 \tsetae 0x12345678(%rax)",}, +{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 93 80 78 56 34 12 \tsetae 0x12345678(%rax)",}, +{{0x0f, 0x93, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 93 80 78 56 34 12 \tsetae 0x12345678(%rax)",}, +{{0x0f, 0x98, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 98 80 78 56 34 12 \tsets 0x12345678(%rax)",}, +{{0x0f, 0x99, 0x80, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 99 80 78 56 34 12 \tsetns 0x12345678(%rax)",}, +{{0xc5, 0xcc, 0x41, 0xef, }, 4, 0, "", "", +"c5 cc 41 ef \tkandw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x41, 0xef, }, 5, 0, "", "", +"c4 e1 cc 41 ef \tkandq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x41, 0xef, }, 4, 0, "", "", +"c5 cd 41 ef \tkandb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x41, 0xef, }, 5, 0, "", "", +"c4 e1 cd 41 ef \tkandd %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x42, 0xef, }, 4, 0, "", "", +"c5 cc 42 ef \tkandnw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x42, 0xef, }, 5, 0, "", "", +"c4 e1 cc 42 ef \tkandnq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x42, 0xef, }, 4, 0, "", "", +"c5 cd 42 ef \tkandnb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x42, 0xef, }, 5, 0, "", "", +"c4 e1 cd 42 ef \tkandnd %k7,%k6,%k5",}, +{{0xc5, 0xf8, 0x44, 0xf7, }, 4, 0, "", "", +"c5 f8 44 f7 \tknotw %k7,%k6",}, +{{0xc4, 0xe1, 0xf8, 0x44, 0xf7, }, 5, 0, "", "", +"c4 e1 f8 44 f7 \tknotq %k7,%k6",}, +{{0xc5, 0xf9, 0x44, 0xf7, }, 4, 0, "", "", +"c5 f9 44 f7 \tknotb %k7,%k6",}, +{{0xc4, 0xe1, 0xf9, 0x44, 0xf7, }, 5, 0, "", "", +"c4 e1 f9 44 f7 \tknotd %k7,%k6",}, +{{0xc5, 0xcc, 0x45, 0xef, }, 4, 0, "", "", +"c5 cc 45 ef \tkorw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x45, 0xef, }, 5, 0, "", "", +"c4 e1 cc 45 ef \tkorq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x45, 0xef, }, 4, 0, "", "", +"c5 cd 45 ef \tkorb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x45, 0xef, }, 5, 0, "", "", +"c4 e1 cd 45 ef \tkord %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x46, 0xef, }, 4, 0, "", "", +"c5 cc 46 ef \tkxnorw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x46, 0xef, }, 5, 0, "", "", +"c4 e1 cc 46 ef \tkxnorq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x46, 0xef, }, 4, 0, "", "", +"c5 cd 46 ef \tkxnorb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x46, 0xef, }, 5, 0, "", "", +"c4 e1 cd 46 ef \tkxnord %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x47, 0xef, }, 4, 0, "", "", +"c5 cc 47 ef \tkxorw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x47, 0xef, }, 5, 0, "", "", +"c4 e1 cc 47 ef \tkxorq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x47, 0xef, }, 4, 0, "", "", +"c5 cd 47 ef \tkxorb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x47, 0xef, }, 5, 0, "", "", +"c4 e1 cd 47 ef \tkxord %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x4a, 0xef, }, 4, 0, "", "", +"c5 cc 4a ef \tkaddw %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x4a, 0xef, }, 5, 0, "", "", +"c4 e1 cc 4a ef \tkaddq %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x4a, 0xef, }, 4, 0, "", "", +"c5 cd 4a ef \tkaddb %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcd, 0x4a, 0xef, }, 5, 0, "", "", +"c4 e1 cd 4a ef \tkaddd %k7,%k6,%k5",}, +{{0xc5, 0xcd, 0x4b, 0xef, }, 4, 0, "", "", +"c5 cd 4b ef \tkunpckbw %k7,%k6,%k5",}, +{{0xc5, 0xcc, 0x4b, 0xef, }, 4, 0, "", "", +"c5 cc 4b ef \tkunpckwd %k7,%k6,%k5",}, +{{0xc4, 0xe1, 0xcc, 0x4b, 0xef, }, 5, 0, "", "", +"c4 e1 cc 4b ef \tkunpckdq %k7,%k6,%k5",}, +{{0xc5, 0xf8, 0x90, 0xee, }, 4, 0, "", "", +"c5 f8 90 ee \tkmovw %k6,%k5",}, +{{0xc5, 0xf8, 0x90, 0x29, }, 4, 0, "", "", +"c5 f8 90 29 \tkmovw (%rcx),%k5",}, +{{0xc4, 0xa1, 0x78, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 a1 78 90 ac f0 23 01 00 00 \tkmovw 0x123(%rax,%r14,8),%k5",}, +{{0xc5, 0xf8, 0x91, 0x29, }, 4, 0, "", "", +"c5 f8 91 29 \tkmovw %k5,(%rcx)",}, +{{0xc4, 0xa1, 0x78, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 a1 78 91 ac f0 23 01 00 00 \tkmovw %k5,0x123(%rax,%r14,8)",}, +{{0xc5, 0xf8, 0x92, 0xe8, }, 4, 0, "", "", +"c5 f8 92 e8 \tkmovw %eax,%k5",}, +{{0xc5, 0xf8, 0x92, 0xed, }, 4, 0, "", "", +"c5 f8 92 ed \tkmovw %ebp,%k5",}, +{{0xc4, 0xc1, 0x78, 0x92, 0xed, }, 5, 0, "", "", +"c4 c1 78 92 ed \tkmovw %r13d,%k5",}, +{{0xc5, 0xf8, 0x93, 0xc5, }, 4, 0, "", "", +"c5 f8 93 c5 \tkmovw %k5,%eax",}, +{{0xc5, 0xf8, 0x93, 0xed, }, 4, 0, "", "", +"c5 f8 93 ed \tkmovw %k5,%ebp",}, +{{0xc5, 0x78, 0x93, 0xed, }, 4, 0, "", "", +"c5 78 93 ed \tkmovw %k5,%r13d",}, +{{0xc4, 0xe1, 0xf8, 0x90, 0xee, }, 5, 0, "", "", +"c4 e1 f8 90 ee \tkmovq %k6,%k5",}, +{{0xc4, 0xe1, 0xf8, 0x90, 0x29, }, 5, 0, "", "", +"c4 e1 f8 90 29 \tkmovq (%rcx),%k5",}, +{{0xc4, 0xa1, 0xf8, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 a1 f8 90 ac f0 23 01 00 00 \tkmovq 0x123(%rax,%r14,8),%k5",}, +{{0xc4, 0xe1, 0xf8, 0x91, 0x29, }, 5, 0, "", "", +"c4 e1 f8 91 29 \tkmovq %k5,(%rcx)",}, +{{0xc4, 0xa1, 0xf8, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 a1 f8 91 ac f0 23 01 00 00 \tkmovq %k5,0x123(%rax,%r14,8)",}, +{{0xc4, 0xe1, 0xfb, 0x92, 0xe8, }, 5, 0, "", "", +"c4 e1 fb 92 e8 \tkmovq %rax,%k5",}, +{{0xc4, 0xe1, 0xfb, 0x92, 0xed, }, 5, 0, "", "", +"c4 e1 fb 92 ed \tkmovq %rbp,%k5",}, +{{0xc4, 0xc1, 0xfb, 0x92, 0xed, }, 5, 0, "", "", +"c4 c1 fb 92 ed \tkmovq %r13,%k5",}, +{{0xc4, 0xe1, 0xfb, 0x93, 0xc5, }, 5, 0, "", "", +"c4 e1 fb 93 c5 \tkmovq %k5,%rax",}, +{{0xc4, 0xe1, 0xfb, 0x93, 0xed, }, 5, 0, "", "", +"c4 e1 fb 93 ed \tkmovq %k5,%rbp",}, +{{0xc4, 0x61, 0xfb, 0x93, 0xed, }, 5, 0, "", "", +"c4 61 fb 93 ed \tkmovq %k5,%r13",}, +{{0xc5, 0xf9, 0x90, 0xee, }, 4, 0, "", "", +"c5 f9 90 ee \tkmovb %k6,%k5",}, +{{0xc5, 0xf9, 0x90, 0x29, }, 4, 0, "", "", +"c5 f9 90 29 \tkmovb (%rcx),%k5",}, +{{0xc4, 0xa1, 0x79, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 a1 79 90 ac f0 23 01 00 00 \tkmovb 0x123(%rax,%r14,8),%k5",}, +{{0xc5, 0xf9, 0x91, 0x29, }, 4, 0, "", "", +"c5 f9 91 29 \tkmovb %k5,(%rcx)",}, +{{0xc4, 0xa1, 0x79, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 a1 79 91 ac f0 23 01 00 00 \tkmovb %k5,0x123(%rax,%r14,8)",}, +{{0xc5, 0xf9, 0x92, 0xe8, }, 4, 0, "", "", +"c5 f9 92 e8 \tkmovb %eax,%k5",}, +{{0xc5, 0xf9, 0x92, 0xed, }, 4, 0, "", "", +"c5 f9 92 ed \tkmovb %ebp,%k5",}, +{{0xc4, 0xc1, 0x79, 0x92, 0xed, }, 5, 0, "", "", +"c4 c1 79 92 ed \tkmovb %r13d,%k5",}, +{{0xc5, 0xf9, 0x93, 0xc5, }, 4, 0, "", "", +"c5 f9 93 c5 \tkmovb %k5,%eax",}, +{{0xc5, 0xf9, 0x93, 0xed, }, 4, 0, "", "", +"c5 f9 93 ed \tkmovb %k5,%ebp",}, +{{0xc5, 0x79, 0x93, 0xed, }, 4, 0, "", "", +"c5 79 93 ed \tkmovb %k5,%r13d",}, +{{0xc4, 0xe1, 0xf9, 0x90, 0xee, }, 5, 0, "", "", +"c4 e1 f9 90 ee \tkmovd %k6,%k5",}, +{{0xc4, 0xe1, 0xf9, 0x90, 0x29, }, 5, 0, "", "", +"c4 e1 f9 90 29 \tkmovd (%rcx),%k5",}, +{{0xc4, 0xa1, 0xf9, 0x90, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 a1 f9 90 ac f0 23 01 00 00 \tkmovd 0x123(%rax,%r14,8),%k5",}, +{{0xc4, 0xe1, 0xf9, 0x91, 0x29, }, 5, 0, "", "", +"c4 e1 f9 91 29 \tkmovd %k5,(%rcx)",}, +{{0xc4, 0xa1, 0xf9, 0x91, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 10, 0, "", "", +"c4 a1 f9 91 ac f0 23 01 00 00 \tkmovd %k5,0x123(%rax,%r14,8)",}, +{{0xc5, 0xfb, 0x92, 0xe8, }, 4, 0, "", "", +"c5 fb 92 e8 \tkmovd %eax,%k5",}, +{{0xc5, 0xfb, 0x92, 0xed, }, 4, 0, "", "", +"c5 fb 92 ed \tkmovd %ebp,%k5",}, +{{0xc4, 0xc1, 0x7b, 0x92, 0xed, }, 5, 0, "", "", +"c4 c1 7b 92 ed \tkmovd %r13d,%k5",}, +{{0xc5, 0xfb, 0x93, 0xc5, }, 4, 0, "", "", +"c5 fb 93 c5 \tkmovd %k5,%eax",}, +{{0xc5, 0xfb, 0x93, 0xed, }, 4, 0, "", "", +"c5 fb 93 ed \tkmovd %k5,%ebp",}, +{{0xc5, 0x7b, 0x93, 0xed, }, 4, 0, "", "", +"c5 7b 93 ed \tkmovd %k5,%r13d",}, +{{0xc5, 0xf8, 0x98, 0xee, }, 4, 0, "", "", +"c5 f8 98 ee \tkortestw %k6,%k5",}, +{{0xc4, 0xe1, 0xf8, 0x98, 0xee, }, 5, 0, "", "", +"c4 e1 f8 98 ee \tkortestq %k6,%k5",}, +{{0xc5, 0xf9, 0x98, 0xee, }, 4, 0, "", "", +"c5 f9 98 ee \tkortestb %k6,%k5",}, +{{0xc4, 0xe1, 0xf9, 0x98, 0xee, }, 5, 0, "", "", +"c4 e1 f9 98 ee \tkortestd %k6,%k5",}, +{{0xc5, 0xf8, 0x99, 0xee, }, 4, 0, "", "", +"c5 f8 99 ee \tktestw %k6,%k5",}, +{{0xc4, 0xe1, 0xf8, 0x99, 0xee, }, 5, 0, "", "", +"c4 e1 f8 99 ee \tktestq %k6,%k5",}, +{{0xc5, 0xf9, 0x99, 0xee, }, 4, 0, "", "", +"c5 f9 99 ee \tktestb %k6,%k5",}, +{{0xc4, 0xe1, 0xf9, 0x99, 0xee, }, 5, 0, "", "", +"c4 e1 f9 99 ee \tktestd %k6,%k5",}, +{{0xc4, 0xe3, 0xf9, 0x30, 0xee, 0x12, }, 6, 0, "", "", +"c4 e3 f9 30 ee 12 \tkshiftrw $0x12,%k6,%k5",}, +{{0xc4, 0xe3, 0xf9, 0x31, 0xee, 0x5b, }, 6, 0, "", "", +"c4 e3 f9 31 ee 5b \tkshiftrq $0x5b,%k6,%k5",}, +{{0xc4, 0xe3, 0xf9, 0x32, 0xee, 0x12, }, 6, 0, "", "", +"c4 e3 f9 32 ee 12 \tkshiftlw $0x12,%k6,%k5",}, +{{0xc4, 0xe3, 0xf9, 0x33, 0xee, 0x5b, }, 6, 0, "", "", +"c4 e3 f9 33 ee 5b \tkshiftlq $0x5b,%k6,%k5",}, +{{0xc5, 0xf8, 0x5b, 0xf5, }, 4, 0, "", "", +"c5 f8 5b f5 \tvcvtdq2ps %xmm5,%xmm6",}, +{{0x62, 0x91, 0xfc, 0x4f, 0x5b, 0xf5, }, 6, 0, "", "", +"62 91 fc 4f 5b f5 \tvcvtqq2ps %zmm29,%ymm6{%k7}",}, +{{0xc5, 0xf9, 0x5b, 0xf5, }, 4, 0, "", "", +"c5 f9 5b f5 \tvcvtps2dq %xmm5,%xmm6",}, +{{0xc5, 0xfa, 0x5b, 0xf5, }, 4, 0, "", "", +"c5 fa 5b f5 \tvcvttps2dq %xmm5,%xmm6",}, +{{0x0f, 0x6f, 0xe0, }, 3, 0, "", "", +"0f 6f e0 \tmovq %mm0,%mm4",}, +{{0xc5, 0xfd, 0x6f, 0xf4, }, 4, 0, "", "", +"c5 fd 6f f4 \tvmovdqa %ymm4,%ymm6",}, +{{0x62, 0x01, 0x7d, 0x48, 0x6f, 0xd1, }, 6, 0, "", "", +"62 01 7d 48 6f d1 \tvmovdqa32 %zmm25,%zmm26",}, +{{0x62, 0x01, 0xfd, 0x48, 0x6f, 0xd1, }, 6, 0, "", "", +"62 01 fd 48 6f d1 \tvmovdqa64 %zmm25,%zmm26",}, +{{0xc5, 0xfe, 0x6f, 0xf4, }, 4, 0, "", "", +"c5 fe 6f f4 \tvmovdqu %ymm4,%ymm6",}, +{{0x62, 0x01, 0x7e, 0x48, 0x6f, 0xf5, }, 6, 0, "", "", +"62 01 7e 48 6f f5 \tvmovdqu32 %zmm29,%zmm30",}, +{{0x62, 0x01, 0xfe, 0x48, 0x6f, 0xd1, }, 6, 0, "", "", +"62 01 fe 48 6f d1 \tvmovdqu64 %zmm25,%zmm26",}, +{{0x62, 0x01, 0x7f, 0x48, 0x6f, 0xf5, }, 6, 0, "", "", +"62 01 7f 48 6f f5 \tvmovdqu8 %zmm29,%zmm30",}, +{{0x62, 0x01, 0xff, 0x48, 0x6f, 0xd1, }, 6, 0, "", "", +"62 01 ff 48 6f d1 \tvmovdqu16 %zmm25,%zmm26",}, +{{0x0f, 0x78, 0xc3, }, 3, 0, "", "", +"0f 78 c3 \tvmread %rax,%rbx",}, +{{0x62, 0x01, 0x7c, 0x48, 0x78, 0xd1, }, 6, 0, "", "", +"62 01 7c 48 78 d1 \tvcvttps2udq %zmm25,%zmm26",}, +{{0x62, 0x91, 0xfc, 0x4f, 0x78, 0xf5, }, 6, 0, "", "", +"62 91 fc 4f 78 f5 \tvcvttpd2udq %zmm29,%ymm6{%k7}",}, +{{0x62, 0xf1, 0xff, 0x08, 0x78, 0xc6, }, 6, 0, "", "", +"62 f1 ff 08 78 c6 \tvcvttsd2usi %xmm6,%rax",}, +{{0x62, 0xf1, 0xfe, 0x08, 0x78, 0xc6, }, 6, 0, "", "", +"62 f1 fe 08 78 c6 \tvcvttss2usi %xmm6,%rax",}, +{{0x62, 0x61, 0x7d, 0x4f, 0x78, 0xd5, }, 6, 0, "", "", +"62 61 7d 4f 78 d5 \tvcvttps2uqq %ymm5,%zmm26{%k7}",}, +{{0x62, 0x01, 0xfd, 0x48, 0x78, 0xf5, }, 6, 0, "", "", +"62 01 fd 48 78 f5 \tvcvttpd2uqq %zmm29,%zmm30",}, +{{0x0f, 0x79, 0xd8, }, 3, 0, "", "", +"0f 79 d8 \tvmwrite %rax,%rbx",}, +{{0x62, 0x01, 0x7c, 0x48, 0x79, 0xd1, }, 6, 0, "", "", +"62 01 7c 48 79 d1 \tvcvtps2udq %zmm25,%zmm26",}, +{{0x62, 0x91, 0xfc, 0x4f, 0x79, 0xf5, }, 6, 0, "", "", +"62 91 fc 4f 79 f5 \tvcvtpd2udq %zmm29,%ymm6{%k7}",}, +{{0x62, 0xf1, 0xff, 0x08, 0x79, 0xc6, }, 6, 0, "", "", +"62 f1 ff 08 79 c6 \tvcvtsd2usi %xmm6,%rax",}, +{{0x62, 0xf1, 0xfe, 0x08, 0x79, 0xc6, }, 6, 0, "", "", +"62 f1 fe 08 79 c6 \tvcvtss2usi %xmm6,%rax",}, +{{0x62, 0x61, 0x7d, 0x4f, 0x79, 0xd5, }, 6, 0, "", "", +"62 61 7d 4f 79 d5 \tvcvtps2uqq %ymm5,%zmm26{%k7}",}, +{{0x62, 0x01, 0xfd, 0x48, 0x79, 0xf5, }, 6, 0, "", "", +"62 01 fd 48 79 f5 \tvcvtpd2uqq %zmm29,%zmm30",}, +{{0x62, 0x61, 0x7e, 0x4f, 0x7a, 0xed, }, 6, 0, "", "", +"62 61 7e 4f 7a ed \tvcvtudq2pd %ymm5,%zmm29{%k7}",}, +{{0x62, 0x01, 0xfe, 0x48, 0x7a, 0xd1, }, 6, 0, "", "", +"62 01 fe 48 7a d1 \tvcvtuqq2pd %zmm25,%zmm26",}, +{{0x62, 0x01, 0x7f, 0x48, 0x7a, 0xf5, }, 6, 0, "", "", +"62 01 7f 48 7a f5 \tvcvtudq2ps %zmm29,%zmm30",}, +{{0x62, 0x01, 0xff, 0x4f, 0x7a, 0xd1, }, 6, 0, "", "", +"62 01 ff 4f 7a d1 \tvcvtuqq2ps %zmm25,%ymm26{%k7}",}, +{{0x62, 0x01, 0x7d, 0x4f, 0x7a, 0xd1, }, 6, 0, "", "", +"62 01 7d 4f 7a d1 \tvcvttps2qq %ymm25,%zmm26{%k7}",}, +{{0x62, 0x01, 0xfd, 0x48, 0x7a, 0xf5, }, 6, 0, "", "", +"62 01 fd 48 7a f5 \tvcvttpd2qq %zmm29,%zmm30",}, +{{0x62, 0xf1, 0x57, 0x08, 0x7b, 0xf0, }, 6, 0, "", "", +"62 f1 57 08 7b f0 \tvcvtusi2sd %eax,%xmm5,%xmm6",}, +{{0x62, 0xf1, 0x56, 0x08, 0x7b, 0xf0, }, 6, 0, "", "", +"62 f1 56 08 7b f0 \tvcvtusi2ss %eax,%xmm5,%xmm6",}, +{{0x62, 0x61, 0x7d, 0x4f, 0x7b, 0xd5, }, 6, 0, "", "", +"62 61 7d 4f 7b d5 \tvcvtps2qq %ymm5,%zmm26{%k7}",}, +{{0x62, 0x01, 0xfd, 0x48, 0x7b, 0xf5, }, 6, 0, "", "", +"62 01 fd 48 7b f5 \tvcvtpd2qq %zmm29,%zmm30",}, +{{0x0f, 0x7f, 0xc4, }, 3, 0, "", "", +"0f 7f c4 \tmovq %mm0,%mm4",}, +{{0xc5, 0x7d, 0x7f, 0xc6, }, 4, 0, "", "", +"c5 7d 7f c6 \tvmovdqa %ymm8,%ymm6",}, +{{0x62, 0x01, 0x7d, 0x48, 0x7f, 0xca, }, 6, 0, "", "", +"62 01 7d 48 7f ca \tvmovdqa32 %zmm25,%zmm26",}, +{{0x62, 0x01, 0xfd, 0x48, 0x7f, 0xca, }, 6, 0, "", "", +"62 01 fd 48 7f ca \tvmovdqa64 %zmm25,%zmm26",}, +{{0xc5, 0x7e, 0x7f, 0xc6, }, 4, 0, "", "", +"c5 7e 7f c6 \tvmovdqu %ymm8,%ymm6",}, +{{0x62, 0x01, 0x7e, 0x48, 0x7f, 0xca, }, 6, 0, "", "", +"62 01 7e 48 7f ca \tvmovdqu32 %zmm25,%zmm26",}, +{{0x62, 0x01, 0xfe, 0x48, 0x7f, 0xca, }, 6, 0, "", "", +"62 01 fe 48 7f ca \tvmovdqu64 %zmm25,%zmm26",}, +{{0x62, 0x61, 0x7f, 0x48, 0x7f, 0x31, }, 6, 0, "", "", +"62 61 7f 48 7f 31 \tvmovdqu8 %zmm30,(%rcx)",}, +{{0x62, 0x01, 0xff, 0x48, 0x7f, 0xca, }, 6, 0, "", "", +"62 01 ff 48 7f ca \tvmovdqu16 %zmm25,%zmm26",}, +{{0x0f, 0xdb, 0xd1, }, 3, 0, "", "", +"0f db d1 \tpand %mm1,%mm2",}, +{{0x66, 0x0f, 0xdb, 0xd1, }, 4, 0, "", "", +"66 0f db d1 \tpand %xmm1,%xmm2",}, +{{0xc5, 0xcd, 0xdb, 0xd4, }, 4, 0, "", "", +"c5 cd db d4 \tvpand %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x01, 0x35, 0x40, 0xdb, 0xd0, }, 6, 0, "", "", +"62 01 35 40 db d0 \tvpandd %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x01, 0xb5, 0x40, 0xdb, 0xd0, }, 6, 0, "", "", +"62 01 b5 40 db d0 \tvpandq %zmm24,%zmm25,%zmm26",}, +{{0x0f, 0xdf, 0xd1, }, 3, 0, "", "", +"0f df d1 \tpandn %mm1,%mm2",}, +{{0x66, 0x0f, 0xdf, 0xd1, }, 4, 0, "", "", +"66 0f df d1 \tpandn %xmm1,%xmm2",}, +{{0xc5, 0xcd, 0xdf, 0xd4, }, 4, 0, "", "", +"c5 cd df d4 \tvpandn %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x01, 0x35, 0x40, 0xdf, 0xd0, }, 6, 0, "", "", +"62 01 35 40 df d0 \tvpandnd %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x01, 0xb5, 0x40, 0xdf, 0xd0, }, 6, 0, "", "", +"62 01 b5 40 df d0 \tvpandnq %zmm24,%zmm25,%zmm26",}, +{{0xc5, 0xf9, 0xe6, 0xd1, }, 4, 0, "", "", +"c5 f9 e6 d1 \tvcvttpd2dq %xmm1,%xmm2",}, +{{0xc5, 0xfa, 0xe6, 0xf5, }, 4, 0, "", "", +"c5 fa e6 f5 \tvcvtdq2pd %xmm5,%xmm6",}, +{{0x62, 0x61, 0x7e, 0x4f, 0xe6, 0xd5, }, 6, 0, "", "", +"62 61 7e 4f e6 d5 \tvcvtdq2pd %ymm5,%zmm26{%k7}",}, +{{0x62, 0x01, 0xfe, 0x48, 0xe6, 0xd1, }, 6, 0, "", "", +"62 01 fe 48 e6 d1 \tvcvtqq2pd %zmm25,%zmm26",}, +{{0xc5, 0xfb, 0xe6, 0xd1, }, 4, 0, "", "", +"c5 fb e6 d1 \tvcvtpd2dq %xmm1,%xmm2",}, +{{0x0f, 0xeb, 0xf4, }, 3, 0, "", "", +"0f eb f4 \tpor %mm4,%mm6",}, +{{0xc5, 0xcd, 0xeb, 0xd4, }, 4, 0, "", "", +"c5 cd eb d4 \tvpor %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x01, 0x35, 0x40, 0xeb, 0xd0, }, 6, 0, "", "", +"62 01 35 40 eb d0 \tvpord %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x01, 0xb5, 0x40, 0xeb, 0xd0, }, 6, 0, "", "", +"62 01 b5 40 eb d0 \tvporq %zmm24,%zmm25,%zmm26",}, +{{0x0f, 0xef, 0xf4, }, 3, 0, "", "", +"0f ef f4 \tpxor %mm4,%mm6",}, +{{0xc5, 0xcd, 0xef, 0xd4, }, 4, 0, "", "", +"c5 cd ef d4 \tvpxor %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x01, 0x35, 0x40, 0xef, 0xd0, }, 6, 0, "", "", +"62 01 35 40 ef d0 \tvpxord %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x01, 0xb5, 0x40, 0xef, 0xd0, }, 6, 0, "", "", +"62 01 b5 40 ef d0 \tvpxorq %zmm24,%zmm25,%zmm26",}, +{{0x66, 0x0f, 0x38, 0x10, 0xc1, }, 5, 0, "", "", +"66 0f 38 10 c1 \tpblendvb %xmm0,%xmm1,%xmm0",}, +{{0x62, 0x02, 0x9d, 0x40, 0x10, 0xeb, }, 6, 0, "", "", +"62 02 9d 40 10 eb \tvpsrlvw %zmm27,%zmm28,%zmm29",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x10, 0xe6, }, 6, 0, "", "", +"62 62 7e 4f 10 e6 \tvpmovuswb %zmm28,%ymm6{%k7}",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x11, 0xe6, }, 6, 0, "", "", +"62 62 7e 4f 11 e6 \tvpmovusdb %zmm28,%xmm6{%k7}",}, +{{0x62, 0x02, 0x9d, 0x40, 0x11, 0xeb, }, 6, 0, "", "", +"62 02 9d 40 11 eb \tvpsravw %zmm27,%zmm28,%zmm29",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x12, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 12 de \tvpmovusqb %zmm27,%xmm6{%k7}",}, +{{0x62, 0x02, 0x9d, 0x40, 0x12, 0xeb, }, 6, 0, "", "", +"62 02 9d 40 12 eb \tvpsllvw %zmm27,%zmm28,%zmm29",}, +{{0xc4, 0xe2, 0x7d, 0x13, 0xeb, }, 5, 0, "", "", +"c4 e2 7d 13 eb \tvcvtph2ps %xmm3,%ymm5",}, +{{0x62, 0x62, 0x7d, 0x4f, 0x13, 0xdd, }, 6, 0, "", "", +"62 62 7d 4f 13 dd \tvcvtph2ps %ymm5,%zmm27{%k7}",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x13, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 13 de \tvpmovusdw %zmm27,%ymm6{%k7}",}, +{{0x66, 0x0f, 0x38, 0x14, 0xc1, }, 5, 0, "", "", +"66 0f 38 14 c1 \tblendvps %xmm0,%xmm1,%xmm0",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x14, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 14 de \tvpmovusqw %zmm27,%xmm6{%k7}",}, +{{0x62, 0x02, 0x1d, 0x40, 0x14, 0xeb, }, 6, 0, "", "", +"62 02 1d 40 14 eb \tvprorvd %zmm27,%zmm28,%zmm29",}, +{{0x62, 0x02, 0x9d, 0x40, 0x14, 0xeb, }, 6, 0, "", "", +"62 02 9d 40 14 eb \tvprorvq %zmm27,%zmm28,%zmm29",}, +{{0x66, 0x0f, 0x38, 0x15, 0xc1, }, 5, 0, "", "", +"66 0f 38 15 c1 \tblendvpd %xmm0,%xmm1,%xmm0",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x15, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 15 de \tvpmovusqd %zmm27,%ymm6{%k7}",}, +{{0x62, 0x02, 0x1d, 0x40, 0x15, 0xeb, }, 6, 0, "", "", +"62 02 1d 40 15 eb \tvprolvd %zmm27,%zmm28,%zmm29",}, +{{0x62, 0x02, 0x9d, 0x40, 0x15, 0xeb, }, 6, 0, "", "", +"62 02 9d 40 15 eb \tvprolvq %zmm27,%zmm28,%zmm29",}, +{{0xc4, 0xe2, 0x4d, 0x16, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 16 d4 \tvpermps %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x82, 0x2d, 0x27, 0x16, 0xf0, }, 6, 0, "", "", +"62 82 2d 27 16 f0 \tvpermps %ymm24,%ymm26,%ymm22{%k7}",}, +{{0x62, 0x82, 0xad, 0x27, 0x16, 0xf0, }, 6, 0, "", "", +"62 82 ad 27 16 f0 \tvpermpd %ymm24,%ymm26,%ymm22{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x19, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 19 f4 \tvbroadcastsd %xmm4,%ymm6",}, +{{0x62, 0x02, 0x7d, 0x48, 0x19, 0xd3, }, 6, 0, "", "", +"62 02 7d 48 19 d3 \tvbroadcastf32x2 %xmm27,%zmm26",}, +{{0xc4, 0xe2, 0x7d, 0x1a, 0x21, }, 5, 0, "", "", +"c4 e2 7d 1a 21 \tvbroadcastf128 (%rcx),%ymm4",}, +{{0x62, 0x62, 0x7d, 0x48, 0x1a, 0x11, }, 6, 0, "", "", +"62 62 7d 48 1a 11 \tvbroadcastf32x4 (%rcx),%zmm26",}, +{{0x62, 0x62, 0xfd, 0x48, 0x1a, 0x11, }, 6, 0, "", "", +"62 62 fd 48 1a 11 \tvbroadcastf64x2 (%rcx),%zmm26",}, +{{0x62, 0x62, 0x7d, 0x48, 0x1b, 0x19, }, 6, 0, "", "", +"62 62 7d 48 1b 19 \tvbroadcastf32x8 (%rcx),%zmm27",}, +{{0x62, 0x62, 0xfd, 0x48, 0x1b, 0x11, }, 6, 0, "", "", +"62 62 fd 48 1b 11 \tvbroadcastf64x4 (%rcx),%zmm26",}, +{{0x62, 0x02, 0xfd, 0x48, 0x1f, 0xe3, }, 6, 0, "", "", +"62 02 fd 48 1f e3 \tvpabsq %zmm27,%zmm28",}, +{{0xc4, 0xe2, 0x79, 0x20, 0xec, }, 5, 0, "", "", +"c4 e2 79 20 ec \tvpmovsxbw %xmm4,%xmm5",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x20, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 20 de \tvpmovswb %zmm27,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x21, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 21 f4 \tvpmovsxbd %xmm4,%ymm6",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x21, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 21 de \tvpmovsdb %zmm27,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x22, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 22 e4 \tvpmovsxbq %xmm4,%ymm4",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x22, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 22 de \tvpmovsqb %zmm27,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x23, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 23 e4 \tvpmovsxwd %xmm4,%ymm4",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x23, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 23 de \tvpmovsdw %zmm27,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x24, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 24 f4 \tvpmovsxwq %xmm4,%ymm6",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x24, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 24 de \tvpmovsqw %zmm27,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x25, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 25 e4 \tvpmovsxdq %xmm4,%ymm4",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x25, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 25 de \tvpmovsqd %zmm27,%ymm6{%k7}",}, +{{0x62, 0x92, 0x1d, 0x40, 0x26, 0xeb, }, 6, 0, "", "", +"62 92 1d 40 26 eb \tvptestmb %zmm27,%zmm28,%k5",}, +{{0x62, 0x92, 0x9d, 0x40, 0x26, 0xeb, }, 6, 0, "", "", +"62 92 9d 40 26 eb \tvptestmw %zmm27,%zmm28,%k5",}, +{{0x62, 0x92, 0x26, 0x40, 0x26, 0xea, }, 6, 0, "", "", +"62 92 26 40 26 ea \tvptestnmb %zmm26,%zmm27,%k5",}, +{{0x62, 0x92, 0xa6, 0x40, 0x26, 0xea, }, 6, 0, "", "", +"62 92 a6 40 26 ea \tvptestnmw %zmm26,%zmm27,%k5",}, +{{0x62, 0x92, 0x1d, 0x40, 0x27, 0xeb, }, 6, 0, "", "", +"62 92 1d 40 27 eb \tvptestmd %zmm27,%zmm28,%k5",}, +{{0x62, 0x92, 0x9d, 0x40, 0x27, 0xeb, }, 6, 0, "", "", +"62 92 9d 40 27 eb \tvptestmq %zmm27,%zmm28,%k5",}, +{{0x62, 0x92, 0x26, 0x40, 0x27, 0xea, }, 6, 0, "", "", +"62 92 26 40 27 ea \tvptestnmd %zmm26,%zmm27,%k5",}, +{{0x62, 0x92, 0xa6, 0x40, 0x27, 0xea, }, 6, 0, "", "", +"62 92 a6 40 27 ea \tvptestnmq %zmm26,%zmm27,%k5",}, +{{0xc4, 0xe2, 0x4d, 0x28, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 28 d4 \tvpmuldq %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x62, 0x7e, 0x48, 0x28, 0xe5, }, 6, 0, "", "", +"62 62 7e 48 28 e5 \tvpmovm2b %k5,%zmm28",}, +{{0x62, 0x62, 0xfe, 0x48, 0x28, 0xe5, }, 6, 0, "", "", +"62 62 fe 48 28 e5 \tvpmovm2w %k5,%zmm28",}, +{{0xc4, 0xe2, 0x4d, 0x29, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 29 d4 \tvpcmpeqq %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x92, 0x7e, 0x48, 0x29, 0xec, }, 6, 0, "", "", +"62 92 7e 48 29 ec \tvpmovb2m %zmm28,%k5",}, +{{0x62, 0x92, 0xfe, 0x48, 0x29, 0xec, }, 6, 0, "", "", +"62 92 fe 48 29 ec \tvpmovw2m %zmm28,%k5",}, +{{0xc4, 0xe2, 0x7d, 0x2a, 0x21, }, 5, 0, "", "", +"c4 e2 7d 2a 21 \tvmovntdqa (%rcx),%ymm4",}, +{{0x62, 0x62, 0xfe, 0x48, 0x2a, 0xf6, }, 6, 0, "", "", +"62 62 fe 48 2a f6 \tvpbroadcastmb2q %k6,%zmm30",}, +{{0xc4, 0xe2, 0x5d, 0x2c, 0x31, }, 5, 0, "", "", +"c4 e2 5d 2c 31 \tvmaskmovps (%rcx),%ymm4,%ymm6",}, +{{0x62, 0x02, 0x35, 0x40, 0x2c, 0xd0, }, 6, 0, "", "", +"62 02 35 40 2c d0 \tvscalefps %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0xb5, 0x40, 0x2c, 0xd0, }, 6, 0, "", "", +"62 02 b5 40 2c d0 \tvscalefpd %zmm24,%zmm25,%zmm26",}, +{{0xc4, 0xe2, 0x5d, 0x2d, 0x31, }, 5, 0, "", "", +"c4 e2 5d 2d 31 \tvmaskmovpd (%rcx),%ymm4,%ymm6",}, +{{0x62, 0x02, 0x35, 0x07, 0x2d, 0xd0, }, 6, 0, "", "", +"62 02 35 07 2d d0 \tvscalefss %xmm24,%xmm25,%xmm26{%k7}",}, +{{0x62, 0x02, 0xb5, 0x07, 0x2d, 0xd0, }, 6, 0, "", "", +"62 02 b5 07 2d d0 \tvscalefsd %xmm24,%xmm25,%xmm26{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x30, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 30 e4 \tvpmovzxbw %xmm4,%ymm4",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x30, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 30 de \tvpmovwb %zmm27,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x31, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 31 f4 \tvpmovzxbd %xmm4,%ymm6",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x31, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 31 de \tvpmovdb %zmm27,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x32, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 32 e4 \tvpmovzxbq %xmm4,%ymm4",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x32, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 32 de \tvpmovqb %zmm27,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x33, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 33 e4 \tvpmovzxwd %xmm4,%ymm4",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x33, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 33 de \tvpmovdw %zmm27,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x34, 0xf4, }, 5, 0, "", "", +"c4 e2 7d 34 f4 \tvpmovzxwq %xmm4,%ymm6",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x34, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 34 de \tvpmovqw %zmm27,%xmm6{%k7}",}, +{{0xc4, 0xe2, 0x7d, 0x35, 0xe4, }, 5, 0, "", "", +"c4 e2 7d 35 e4 \tvpmovzxdq %xmm4,%ymm4",}, +{{0x62, 0x62, 0x7e, 0x4f, 0x35, 0xde, }, 6, 0, "", "", +"62 62 7e 4f 35 de \tvpmovqd %zmm27,%ymm6{%k7}",}, +{{0xc4, 0xe2, 0x4d, 0x36, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 36 d4 \tvpermd %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x82, 0x2d, 0x27, 0x36, 0xf0, }, 6, 0, "", "", +"62 82 2d 27 36 f0 \tvpermd %ymm24,%ymm26,%ymm22{%k7}",}, +{{0x62, 0x82, 0xad, 0x27, 0x36, 0xf0, }, 6, 0, "", "", +"62 82 ad 27 36 f0 \tvpermq %ymm24,%ymm26,%ymm22{%k7}",}, +{{0xc4, 0xe2, 0x4d, 0x38, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 38 d4 \tvpminsb %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x62, 0x7e, 0x48, 0x38, 0xe5, }, 6, 0, "", "", +"62 62 7e 48 38 e5 \tvpmovm2d %k5,%zmm28",}, +{{0x62, 0x62, 0xfe, 0x48, 0x38, 0xe5, }, 6, 0, "", "", +"62 62 fe 48 38 e5 \tvpmovm2q %k5,%zmm28",}, +{{0xc4, 0xe2, 0x69, 0x39, 0xd9, }, 5, 0, "", "", +"c4 e2 69 39 d9 \tvpminsd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0x02, 0x35, 0x40, 0x39, 0xd0, }, 6, 0, "", "", +"62 02 35 40 39 d0 \tvpminsd %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0xb5, 0x40, 0x39, 0xd0, }, 6, 0, "", "", +"62 02 b5 40 39 d0 \tvpminsq %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x92, 0x7e, 0x48, 0x39, 0xec, }, 6, 0, "", "", +"62 92 7e 48 39 ec \tvpmovd2m %zmm28,%k5",}, +{{0x62, 0x92, 0xfe, 0x48, 0x39, 0xec, }, 6, 0, "", "", +"62 92 fe 48 39 ec \tvpmovq2m %zmm28,%k5",}, +{{0xc4, 0xe2, 0x4d, 0x3a, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 3a d4 \tvpminuw %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x62, 0x7e, 0x48, 0x3a, 0xe6, }, 6, 0, "", "", +"62 62 7e 48 3a e6 \tvpbroadcastmw2d %k6,%zmm28",}, +{{0xc4, 0xe2, 0x4d, 0x3b, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 3b d4 \tvpminud %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x02, 0x35, 0x40, 0x3b, 0xd0, }, 6, 0, "", "", +"62 02 35 40 3b d0 \tvpminud %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0xb5, 0x40, 0x3b, 0xd0, }, 6, 0, "", "", +"62 02 b5 40 3b d0 \tvpminuq %zmm24,%zmm25,%zmm26",}, +{{0xc4, 0xe2, 0x4d, 0x3d, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 3d d4 \tvpmaxsd %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x02, 0x35, 0x40, 0x3d, 0xd0, }, 6, 0, "", "", +"62 02 35 40 3d d0 \tvpmaxsd %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0xb5, 0x40, 0x3d, 0xd0, }, 6, 0, "", "", +"62 02 b5 40 3d d0 \tvpmaxsq %zmm24,%zmm25,%zmm26",}, +{{0xc4, 0xe2, 0x4d, 0x3f, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 3f d4 \tvpmaxud %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x02, 0x35, 0x40, 0x3f, 0xd0, }, 6, 0, "", "", +"62 02 35 40 3f d0 \tvpmaxud %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0xb5, 0x40, 0x3f, 0xd0, }, 6, 0, "", "", +"62 02 b5 40 3f d0 \tvpmaxuq %zmm24,%zmm25,%zmm26",}, +{{0xc4, 0xe2, 0x4d, 0x40, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 40 d4 \tvpmulld %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x02, 0x35, 0x40, 0x40, 0xd0, }, 6, 0, "", "", +"62 02 35 40 40 d0 \tvpmulld %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0xb5, 0x40, 0x40, 0xd0, }, 6, 0, "", "", +"62 02 b5 40 40 d0 \tvpmullq %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0x7d, 0x48, 0x42, 0xd1, }, 6, 0, "", "", +"62 02 7d 48 42 d1 \tvgetexpps %zmm25,%zmm26",}, +{{0x62, 0x02, 0xfd, 0x48, 0x42, 0xe3, }, 6, 0, "", "", +"62 02 fd 48 42 e3 \tvgetexppd %zmm27,%zmm28",}, +{{0x62, 0x02, 0x35, 0x07, 0x43, 0xd0, }, 6, 0, "", "", +"62 02 35 07 43 d0 \tvgetexpss %xmm24,%xmm25,%xmm26{%k7}",}, +{{0x62, 0x02, 0x95, 0x07, 0x43, 0xf4, }, 6, 0, "", "", +"62 02 95 07 43 f4 \tvgetexpsd %xmm28,%xmm29,%xmm30{%k7}",}, +{{0x62, 0x02, 0x7d, 0x48, 0x44, 0xe3, }, 6, 0, "", "", +"62 02 7d 48 44 e3 \tvplzcntd %zmm27,%zmm28",}, +{{0x62, 0x02, 0xfd, 0x48, 0x44, 0xe3, }, 6, 0, "", "", +"62 02 fd 48 44 e3 \tvplzcntq %zmm27,%zmm28",}, +{{0xc4, 0xe2, 0x4d, 0x46, 0xd4, }, 5, 0, "", "", +"c4 e2 4d 46 d4 \tvpsravd %ymm4,%ymm6,%ymm2",}, +{{0x62, 0x02, 0x35, 0x40, 0x46, 0xd0, }, 6, 0, "", "", +"62 02 35 40 46 d0 \tvpsravd %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0xb5, 0x40, 0x46, 0xd0, }, 6, 0, "", "", +"62 02 b5 40 46 d0 \tvpsravq %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0x7d, 0x48, 0x4c, 0xd1, }, 6, 0, "", "", +"62 02 7d 48 4c d1 \tvrcp14ps %zmm25,%zmm26",}, +{{0x62, 0x02, 0xfd, 0x48, 0x4c, 0xe3, }, 6, 0, "", "", +"62 02 fd 48 4c e3 \tvrcp14pd %zmm27,%zmm28",}, +{{0x62, 0x02, 0x35, 0x07, 0x4d, 0xd0, }, 6, 0, "", "", +"62 02 35 07 4d d0 \tvrcp14ss %xmm24,%xmm25,%xmm26{%k7}",}, +{{0x62, 0x02, 0xb5, 0x07, 0x4d, 0xd0, }, 6, 0, "", "", +"62 02 b5 07 4d d0 \tvrcp14sd %xmm24,%xmm25,%xmm26{%k7}",}, +{{0x62, 0x02, 0x7d, 0x48, 0x4e, 0xd1, }, 6, 0, "", "", +"62 02 7d 48 4e d1 \tvrsqrt14ps %zmm25,%zmm26",}, +{{0x62, 0x02, 0xfd, 0x48, 0x4e, 0xe3, }, 6, 0, "", "", +"62 02 fd 48 4e e3 \tvrsqrt14pd %zmm27,%zmm28",}, +{{0x62, 0x02, 0x35, 0x07, 0x4f, 0xd0, }, 6, 0, "", "", +"62 02 35 07 4f d0 \tvrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}",}, +{{0x62, 0x02, 0xb5, 0x07, 0x4f, 0xd0, }, 6, 0, "", "", +"62 02 b5 07 4f d0 \tvrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}",}, +{{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "", +"c4 e2 79 59 f4 \tvpbroadcastq %xmm4,%xmm6",}, +{{0x62, 0x02, 0x7d, 0x48, 0x59, 0xd3, }, 6, 0, "", "", +"62 02 7d 48 59 d3 \tvbroadcasti32x2 %xmm27,%zmm26",}, +{{0xc4, 0xe2, 0x7d, 0x5a, 0x21, }, 5, 0, "", "", +"c4 e2 7d 5a 21 \tvbroadcasti128 (%rcx),%ymm4",}, +{{0x62, 0x62, 0x7d, 0x48, 0x5a, 0x11, }, 6, 0, "", "", +"62 62 7d 48 5a 11 \tvbroadcasti32x4 (%rcx),%zmm26",}, +{{0x62, 0x62, 0xfd, 0x48, 0x5a, 0x11, }, 6, 0, "", "", +"62 62 fd 48 5a 11 \tvbroadcasti64x2 (%rcx),%zmm26",}, +{{0x62, 0x62, 0x7d, 0x48, 0x5b, 0x21, }, 6, 0, "", "", +"62 62 7d 48 5b 21 \tvbroadcasti32x8 (%rcx),%zmm28",}, +{{0x62, 0x62, 0xfd, 0x48, 0x5b, 0x11, }, 6, 0, "", "", +"62 62 fd 48 5b 11 \tvbroadcasti64x4 (%rcx),%zmm26",}, +{{0x62, 0x02, 0x25, 0x40, 0x64, 0xe2, }, 6, 0, "", "", +"62 02 25 40 64 e2 \tvpblendmd %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0x64, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 64 e2 \tvpblendmq %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0x35, 0x40, 0x65, 0xd0, }, 6, 0, "", "", +"62 02 35 40 65 d0 \tvblendmps %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0xa5, 0x40, 0x65, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 65 e2 \tvblendmpd %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0x25, 0x40, 0x66, 0xe2, }, 6, 0, "", "", +"62 02 25 40 66 e2 \tvpblendmb %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0x66, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 66 e2 \tvpblendmw %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0x35, 0x40, 0x75, 0xd0, }, 6, 0, "", "", +"62 02 35 40 75 d0 \tvpermi2b %zmm24,%zmm25,%zmm26",}, +{{0x62, 0x02, 0xa5, 0x40, 0x75, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 75 e2 \tvpermi2w %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0x25, 0x40, 0x76, 0xe2, }, 6, 0, "", "", +"62 02 25 40 76 e2 \tvpermi2d %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0x76, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 76 e2 \tvpermi2q %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0x25, 0x40, 0x77, 0xe2, }, 6, 0, "", "", +"62 02 25 40 77 e2 \tvpermi2ps %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0x77, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 77 e2 \tvpermi2pd %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x62, 0x7d, 0x08, 0x7a, 0xf0, }, 6, 0, "", "", +"62 62 7d 08 7a f0 \tvpbroadcastb %eax,%xmm30",}, +{{0x62, 0x62, 0x7d, 0x08, 0x7b, 0xf0, }, 6, 0, "", "", +"62 62 7d 08 7b f0 \tvpbroadcastw %eax,%xmm30",}, +{{0x62, 0x62, 0x7d, 0x08, 0x7c, 0xf0, }, 6, 0, "", "", +"62 62 7d 08 7c f0 \tvpbroadcastd %eax,%xmm30",}, +{{0x62, 0x62, 0xfd, 0x48, 0x7c, 0xf0, }, 6, 0, "", "", +"62 62 fd 48 7c f0 \tvpbroadcastq %rax,%zmm30",}, +{{0x62, 0x02, 0x25, 0x40, 0x7d, 0xe2, }, 6, 0, "", "", +"62 02 25 40 7d e2 \tvpermt2b %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0x7d, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 7d e2 \tvpermt2w %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0x25, 0x40, 0x7e, 0xe2, }, 6, 0, "", "", +"62 02 25 40 7e e2 \tvpermt2d %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0x7e, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 7e e2 \tvpermt2q %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0x25, 0x40, 0x7f, 0xe2, }, 6, 0, "", "", +"62 02 25 40 7f e2 \tvpermt2ps %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0x7f, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 7f e2 \tvpermt2pd %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0x83, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 83 e2 \tvpmultishiftqb %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x62, 0x7d, 0x48, 0x88, 0x11, }, 6, 0, "", "", +"62 62 7d 48 88 11 \tvexpandps (%rcx),%zmm26",}, +{{0x62, 0x62, 0xfd, 0x48, 0x88, 0x21, }, 6, 0, "", "", +"62 62 fd 48 88 21 \tvexpandpd (%rcx),%zmm28",}, +{{0x62, 0x62, 0x7d, 0x48, 0x89, 0x21, }, 6, 0, "", "", +"62 62 7d 48 89 21 \tvpexpandd (%rcx),%zmm28",}, +{{0x62, 0x62, 0xfd, 0x48, 0x89, 0x11, }, 6, 0, "", "", +"62 62 fd 48 89 11 \tvpexpandq (%rcx),%zmm26",}, +{{0x62, 0x62, 0x7d, 0x48, 0x8a, 0x21, }, 6, 0, "", "", +"62 62 7d 48 8a 21 \tvcompressps %zmm28,(%rcx)",}, +{{0x62, 0x62, 0xfd, 0x48, 0x8a, 0x21, }, 6, 0, "", "", +"62 62 fd 48 8a 21 \tvcompresspd %zmm28,(%rcx)",}, +{{0x62, 0x62, 0x7d, 0x48, 0x8b, 0x21, }, 6, 0, "", "", +"62 62 7d 48 8b 21 \tvpcompressd %zmm28,(%rcx)",}, +{{0x62, 0x62, 0xfd, 0x48, 0x8b, 0x11, }, 6, 0, "", "", +"62 62 fd 48 8b 11 \tvpcompressq %zmm26,(%rcx)",}, +{{0x62, 0x02, 0x25, 0x40, 0x8d, 0xe2, }, 6, 0, "", "", +"62 02 25 40 8d e2 \tvpermb %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0x8d, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 8d e2 \tvpermw %zmm26,%zmm27,%zmm28",}, +{{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", +"c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",}, +{{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "", +"c4 e2 e9 90 4c 7d 04 \tvpgatherdq %xmm2,0x4(%rbp,%xmm7,2),%xmm1",}, +{{0x62, 0x22, 0x7d, 0x41, 0x90, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 22 7d 41 90 94 dd 7b 00 00 00 \tvpgatherdd 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",}, +{{0x62, 0x22, 0xfd, 0x41, 0x90, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 22 fd 41 90 94 dd 7b 00 00 00 \tvpgatherdq 0x7b(%rbp,%ymm27,8),%zmm26{%k1}",}, +{{0xc4, 0xe2, 0x69, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", +"c4 e2 69 91 4c 7d 02 \tvpgatherqd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",}, +{{0xc4, 0xe2, 0xe9, 0x91, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", +"c4 e2 e9 91 4c 7d 02 \tvpgatherqq %xmm2,0x2(%rbp,%xmm7,2),%xmm1",}, +{{0x62, 0x22, 0x7d, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 22 7d 41 91 94 dd 7b 00 00 00 \tvpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}",}, +{{0x62, 0x22, 0xfd, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 22 fd 41 91 94 dd 7b 00 00 00 \tvpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",}, +{{0x62, 0x22, 0x7d, 0x41, 0xa0, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 22 7d 41 a0 a4 ed 7b 00 00 00 \tvpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",}, +{{0x62, 0x22, 0xfd, 0x41, 0xa0, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 22 fd 41 a0 94 dd 7b 00 00 00 \tvpscatterdq %zmm26,0x7b(%rbp,%ymm27,8){%k1}",}, +{{0x62, 0xb2, 0x7d, 0x41, 0xa1, 0xb4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 b2 7d 41 a1 b4 ed 7b 00 00 00 \tvpscatterqd %ymm6,0x7b(%rbp,%zmm29,8){%k1}",}, +{{0x62, 0xb2, 0xfd, 0x21, 0xa1, 0xb4, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 b2 fd 21 a1 b4 dd 7b 00 00 00 \tvpscatterqq %ymm6,0x7b(%rbp,%ymm27,8){%k1}",}, +{{0x62, 0x22, 0x7d, 0x41, 0xa2, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 22 7d 41 a2 a4 ed 7b 00 00 00 \tvscatterdps %zmm28,0x7b(%rbp,%zmm29,8){%k1}",}, +{{0x62, 0x22, 0xfd, 0x41, 0xa2, 0xa4, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 22 fd 41 a2 a4 dd 7b 00 00 00 \tvscatterdpd %zmm28,0x7b(%rbp,%ymm27,8){%k1}",}, +{{0x62, 0xb2, 0x7d, 0x41, 0xa3, 0xb4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 b2 7d 41 a3 b4 ed 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}",}, +{{0x62, 0x22, 0xfd, 0x41, 0xa3, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 22 fd 41 a3 a4 ed 7b 00 00 00 \tvscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",}, +{{0x62, 0x02, 0xa5, 0x40, 0xb4, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 b4 e2 \tvpmadd52luq %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0xa5, 0x40, 0xb5, 0xe2, }, 6, 0, "", "", +"62 02 a5 40 b5 e2 \tvpmadd52huq %zmm26,%zmm27,%zmm28",}, +{{0x62, 0x02, 0x7d, 0x48, 0xc4, 0xda, }, 6, 0, "", "", +"62 02 7d 48 c4 da \tvpconflictd %zmm26,%zmm27",}, +{{0x62, 0x02, 0xfd, 0x48, 0xc4, 0xda, }, 6, 0, "", "", +"62 02 fd 48 c4 da \tvpconflictq %zmm26,%zmm27",}, +{{0x62, 0x02, 0x7d, 0x48, 0xc8, 0xf5, }, 6, 0, "", "", +"62 02 7d 48 c8 f5 \tvexp2ps %zmm29,%zmm30",}, +{{0x62, 0x02, 0xfd, 0x48, 0xc8, 0xda, }, 6, 0, "", "", +"62 02 fd 48 c8 da \tvexp2pd %zmm26,%zmm27",}, +{{0x62, 0x02, 0x7d, 0x48, 0xca, 0xf5, }, 6, 0, "", "", +"62 02 7d 48 ca f5 \tvrcp28ps %zmm29,%zmm30",}, +{{0x62, 0x02, 0xfd, 0x48, 0xca, 0xda, }, 6, 0, "", "", +"62 02 fd 48 ca da \tvrcp28pd %zmm26,%zmm27",}, +{{0x62, 0x02, 0x15, 0x07, 0xcb, 0xf4, }, 6, 0, "", "", +"62 02 15 07 cb f4 \tvrcp28ss %xmm28,%xmm29,%xmm30{%k7}",}, +{{0x62, 0x02, 0xad, 0x07, 0xcb, 0xd9, }, 6, 0, "", "", +"62 02 ad 07 cb d9 \tvrcp28sd %xmm25,%xmm26,%xmm27{%k7}",}, +{{0x62, 0x02, 0x7d, 0x48, 0xcc, 0xf5, }, 6, 0, "", "", +"62 02 7d 48 cc f5 \tvrsqrt28ps %zmm29,%zmm30",}, +{{0x62, 0x02, 0xfd, 0x48, 0xcc, 0xda, }, 6, 0, "", "", +"62 02 fd 48 cc da \tvrsqrt28pd %zmm26,%zmm27",}, +{{0x62, 0x02, 0x15, 0x07, 0xcd, 0xf4, }, 6, 0, "", "", +"62 02 15 07 cd f4 \tvrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}",}, +{{0x62, 0x02, 0xad, 0x07, 0xcd, 0xd9, }, 6, 0, "", "", +"62 02 ad 07 cd d9 \tvrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}",}, +{{0x62, 0x03, 0x15, 0x40, 0x03, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 15 40 03 f4 12 \tvalignd $0x12,%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x03, 0xad, 0x40, 0x03, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 03 d9 12 \tvalignq $0x12,%zmm25,%zmm26,%zmm27",}, +{{0xc4, 0xe3, 0x7d, 0x08, 0xd6, 0x05, }, 6, 0, "", "", +"c4 e3 7d 08 d6 05 \tvroundps $0x5,%ymm6,%ymm2",}, +{{0x62, 0x03, 0x7d, 0x48, 0x08, 0xd1, 0x12, }, 7, 0, "", "", +"62 03 7d 48 08 d1 12 \tvrndscaleps $0x12,%zmm25,%zmm26",}, +{{0xc4, 0xe3, 0x7d, 0x09, 0xd6, 0x05, }, 6, 0, "", "", +"c4 e3 7d 09 d6 05 \tvroundpd $0x5,%ymm6,%ymm2",}, +{{0x62, 0x03, 0xfd, 0x48, 0x09, 0xd1, 0x12, }, 7, 0, "", "", +"62 03 fd 48 09 d1 12 \tvrndscalepd $0x12,%zmm25,%zmm26",}, +{{0xc4, 0xe3, 0x49, 0x0a, 0xd4, 0x05, }, 6, 0, "", "", +"c4 e3 49 0a d4 05 \tvroundss $0x5,%xmm4,%xmm6,%xmm2",}, +{{0x62, 0x03, 0x35, 0x07, 0x0a, 0xd0, 0x12, }, 7, 0, "", "", +"62 03 35 07 0a d0 12 \tvrndscaless $0x12,%xmm24,%xmm25,%xmm26{%k7}",}, +{{0xc4, 0xe3, 0x49, 0x0b, 0xd4, 0x05, }, 6, 0, "", "", +"c4 e3 49 0b d4 05 \tvroundsd $0x5,%xmm4,%xmm6,%xmm2",}, +{{0x62, 0x03, 0xb5, 0x07, 0x0b, 0xd0, 0x12, }, 7, 0, "", "", +"62 03 b5 07 0b d0 12 \tvrndscalesd $0x12,%xmm24,%xmm25,%xmm26{%k7}",}, +{{0xc4, 0xe3, 0x5d, 0x18, 0xf4, 0x05, }, 6, 0, "", "", +"c4 e3 5d 18 f4 05 \tvinsertf128 $0x5,%xmm4,%ymm4,%ymm6",}, +{{0x62, 0x03, 0x35, 0x47, 0x18, 0xd0, 0x12, }, 7, 0, "", "", +"62 03 35 47 18 d0 12 \tvinsertf32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}",}, +{{0x62, 0x03, 0xb5, 0x47, 0x18, 0xd0, 0x12, }, 7, 0, "", "", +"62 03 b5 47 18 d0 12 \tvinsertf64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}",}, +{{0xc4, 0xe3, 0x7d, 0x19, 0xe4, 0x05, }, 6, 0, "", "", +"c4 e3 7d 19 e4 05 \tvextractf128 $0x5,%ymm4,%xmm4",}, +{{0x62, 0x03, 0x7d, 0x4f, 0x19, 0xca, 0x12, }, 7, 0, "", "", +"62 03 7d 4f 19 ca 12 \tvextractf32x4 $0x12,%zmm25,%xmm26{%k7}",}, +{{0x62, 0x03, 0xfd, 0x4f, 0x19, 0xca, 0x12, }, 7, 0, "", "", +"62 03 fd 4f 19 ca 12 \tvextractf64x2 $0x12,%zmm25,%xmm26{%k7}",}, +{{0x62, 0x03, 0x2d, 0x47, 0x1a, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 47 1a d9 12 \tvinsertf32x8 $0x12,%ymm25,%zmm26,%zmm27{%k7}",}, +{{0x62, 0x03, 0x95, 0x47, 0x1a, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 95 47 1a f4 12 \tvinsertf64x4 $0x12,%ymm28,%zmm29,%zmm30{%k7}",}, +{{0x62, 0x03, 0x7d, 0x4f, 0x1b, 0xee, 0x12, }, 7, 0, "", "", +"62 03 7d 4f 1b ee 12 \tvextractf32x8 $0x12,%zmm29,%ymm30{%k7}",}, +{{0x62, 0x03, 0xfd, 0x4f, 0x1b, 0xd3, 0x12, }, 7, 0, "", "", +"62 03 fd 4f 1b d3 12 \tvextractf64x4 $0x12,%zmm26,%ymm27{%k7}",}, +{{0x62, 0x93, 0x0d, 0x40, 0x1e, 0xed, 0x12, }, 7, 0, "", "", +"62 93 0d 40 1e ed 12 \tvpcmpud $0x12,%zmm29,%zmm30,%k5",}, +{{0x62, 0x93, 0xa5, 0x40, 0x1e, 0xea, 0x12, }, 7, 0, "", "", +"62 93 a5 40 1e ea 12 \tvpcmpuq $0x12,%zmm26,%zmm27,%k5",}, +{{0x62, 0x93, 0x0d, 0x40, 0x1f, 0xed, 0x12, }, 7, 0, "", "", +"62 93 0d 40 1f ed 12 \tvpcmpd $0x12,%zmm29,%zmm30,%k5",}, +{{0x62, 0x93, 0xa5, 0x40, 0x1f, 0xea, 0x12, }, 7, 0, "", "", +"62 93 a5 40 1f ea 12 \tvpcmpq $0x12,%zmm26,%zmm27,%k5",}, +{{0x62, 0x03, 0x15, 0x40, 0x23, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 15 40 23 f4 12 \tvshuff32x4 $0x12,%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x03, 0xad, 0x40, 0x23, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 23 d9 12 \tvshuff64x2 $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0x03, 0x15, 0x40, 0x25, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 15 40 25 f4 12 \tvpternlogd $0x12,%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x03, 0x95, 0x40, 0x25, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 95 40 25 f4 12 \tvpternlogq $0x12,%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x03, 0x7d, 0x48, 0x26, 0xda, 0x12, }, 7, 0, "", "", +"62 03 7d 48 26 da 12 \tvgetmantps $0x12,%zmm26,%zmm27",}, +{{0x62, 0x03, 0xfd, 0x48, 0x26, 0xf5, 0x12, }, 7, 0, "", "", +"62 03 fd 48 26 f5 12 \tvgetmantpd $0x12,%zmm29,%zmm30",}, +{{0x62, 0x03, 0x2d, 0x07, 0x27, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 07 27 d9 12 \tvgetmantss $0x12,%xmm25,%xmm26,%xmm27{%k7}",}, +{{0x62, 0x03, 0x95, 0x07, 0x27, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 95 07 27 f4 12 \tvgetmantsd $0x12,%xmm28,%xmm29,%xmm30{%k7}",}, +{{0xc4, 0xe3, 0x5d, 0x38, 0xf4, 0x05, }, 6, 0, "", "", +"c4 e3 5d 38 f4 05 \tvinserti128 $0x5,%xmm4,%ymm4,%ymm6",}, +{{0x62, 0x03, 0x35, 0x47, 0x38, 0xd0, 0x12, }, 7, 0, "", "", +"62 03 35 47 38 d0 12 \tvinserti32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}",}, +{{0x62, 0x03, 0xb5, 0x47, 0x38, 0xd0, 0x12, }, 7, 0, "", "", +"62 03 b5 47 38 d0 12 \tvinserti64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}",}, +{{0xc4, 0xe3, 0x7d, 0x39, 0xe6, 0x05, }, 6, 0, "", "", +"c4 e3 7d 39 e6 05 \tvextracti128 $0x5,%ymm4,%xmm6",}, +{{0x62, 0x03, 0x7d, 0x4f, 0x39, 0xca, 0x12, }, 7, 0, "", "", +"62 03 7d 4f 39 ca 12 \tvextracti32x4 $0x12,%zmm25,%xmm26{%k7}",}, +{{0x62, 0x03, 0xfd, 0x4f, 0x39, 0xca, 0x12, }, 7, 0, "", "", +"62 03 fd 4f 39 ca 12 \tvextracti64x2 $0x12,%zmm25,%xmm26{%k7}",}, +{{0x62, 0x03, 0x15, 0x47, 0x3a, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 15 47 3a f4 12 \tvinserti32x8 $0x12,%ymm28,%zmm29,%zmm30{%k7}",}, +{{0x62, 0x03, 0xad, 0x47, 0x3a, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 47 3a d9 12 \tvinserti64x4 $0x12,%ymm25,%zmm26,%zmm27{%k7}",}, +{{0x62, 0x03, 0x7d, 0x4f, 0x3b, 0xee, 0x12, }, 7, 0, "", "", +"62 03 7d 4f 3b ee 12 \tvextracti32x8 $0x12,%zmm29,%ymm30{%k7}",}, +{{0x62, 0x03, 0xfd, 0x4f, 0x3b, 0xd3, 0x12, }, 7, 0, "", "", +"62 03 fd 4f 3b d3 12 \tvextracti64x4 $0x12,%zmm26,%ymm27{%k7}",}, +{{0x62, 0x93, 0x0d, 0x40, 0x3e, 0xed, 0x12, }, 7, 0, "", "", +"62 93 0d 40 3e ed 12 \tvpcmpub $0x12,%zmm29,%zmm30,%k5",}, +{{0x62, 0x93, 0xa5, 0x40, 0x3e, 0xea, 0x12, }, 7, 0, "", "", +"62 93 a5 40 3e ea 12 \tvpcmpuw $0x12,%zmm26,%zmm27,%k5",}, +{{0x62, 0x93, 0x0d, 0x40, 0x3f, 0xed, 0x12, }, 7, 0, "", "", +"62 93 0d 40 3f ed 12 \tvpcmpb $0x12,%zmm29,%zmm30,%k5",}, +{{0x62, 0x93, 0xa5, 0x40, 0x3f, 0xea, 0x12, }, 7, 0, "", "", +"62 93 a5 40 3f ea 12 \tvpcmpw $0x12,%zmm26,%zmm27,%k5",}, +{{0xc4, 0xe3, 0x4d, 0x42, 0xd4, 0x05, }, 6, 0, "", "", +"c4 e3 4d 42 d4 05 \tvmpsadbw $0x5,%ymm4,%ymm6,%ymm2",}, +{{0x62, 0xf3, 0x55, 0x48, 0x42, 0xf4, 0x12, }, 7, 0, "", "", +"62 f3 55 48 42 f4 12 \tvdbpsadbw $0x12,%zmm4,%zmm5,%zmm6",}, +{{0x62, 0x03, 0x2d, 0x40, 0x43, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 40 43 d9 12 \tvshufi32x4 $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0x03, 0x95, 0x40, 0x43, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 95 40 43 f4 12 \tvshufi64x2 $0x12,%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x03, 0x2d, 0x40, 0x50, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 40 50 d9 12 \tvrangeps $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0x03, 0x95, 0x40, 0x50, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 95 40 50 f4 12 \tvrangepd $0x12,%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x03, 0x2d, 0x00, 0x51, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 00 51 d9 12 \tvrangess $0x12,%xmm25,%xmm26,%xmm27",}, +{{0x62, 0x03, 0x95, 0x00, 0x51, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 95 00 51 f4 12 \tvrangesd $0x12,%xmm28,%xmm29,%xmm30",}, +{{0x62, 0x03, 0x15, 0x40, 0x54, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 15 40 54 f4 12 \tvfixupimmps $0x12,%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x03, 0xad, 0x40, 0x54, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 54 d9 12 \tvfixupimmpd $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0x03, 0x15, 0x07, 0x55, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 15 07 55 f4 12 \tvfixupimmss $0x12,%xmm28,%xmm29,%xmm30{%k7}",}, +{{0x62, 0x03, 0xad, 0x07, 0x55, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 07 55 d9 12 \tvfixupimmsd $0x12,%xmm25,%xmm26,%xmm27{%k7}",}, +{{0x62, 0x03, 0x7d, 0x48, 0x56, 0xda, 0x12, }, 7, 0, "", "", +"62 03 7d 48 56 da 12 \tvreduceps $0x12,%zmm26,%zmm27",}, +{{0x62, 0x03, 0xfd, 0x48, 0x56, 0xf5, 0x12, }, 7, 0, "", "", +"62 03 fd 48 56 f5 12 \tvreducepd $0x12,%zmm29,%zmm30",}, +{{0x62, 0x03, 0x2d, 0x00, 0x57, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 00 57 d9 12 \tvreducess $0x12,%xmm25,%xmm26,%xmm27",}, +{{0x62, 0x03, 0x95, 0x00, 0x57, 0xf4, 0x12, }, 7, 0, "", "", +"62 03 95 00 57 f4 12 \tvreducesd $0x12,%xmm28,%xmm29,%xmm30",}, +{{0x62, 0x93, 0x7d, 0x48, 0x66, 0xeb, 0x12, }, 7, 0, "", "", +"62 93 7d 48 66 eb 12 \tvfpclassps $0x12,%zmm27,%k5",}, +{{0x62, 0x93, 0xfd, 0x48, 0x66, 0xee, 0x12, }, 7, 0, "", "", +"62 93 fd 48 66 ee 12 \tvfpclasspd $0x12,%zmm30,%k5",}, +{{0x62, 0x93, 0x7d, 0x08, 0x67, 0xeb, 0x12, }, 7, 0, "", "", +"62 93 7d 08 67 eb 12 \tvfpclassss $0x12,%xmm27,%k5",}, +{{0x62, 0x93, 0xfd, 0x08, 0x67, 0xee, 0x12, }, 7, 0, "", "", +"62 93 fd 08 67 ee 12 \tvfpclasssd $0x12,%xmm30,%k5",}, +{{0x62, 0x91, 0x2d, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "", +"62 91 2d 40 72 c1 12 \tvprord $0x12,%zmm25,%zmm26",}, +{{0x62, 0x91, 0xad, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "", +"62 91 ad 40 72 c1 12 \tvprorq $0x12,%zmm25,%zmm26",}, +{{0x62, 0x91, 0x0d, 0x40, 0x72, 0xcd, 0x12, }, 7, 0, "", "", +"62 91 0d 40 72 cd 12 \tvprold $0x12,%zmm29,%zmm30",}, +{{0x62, 0x91, 0x8d, 0x40, 0x72, 0xcd, 0x12, }, 7, 0, "", "", +"62 91 8d 40 72 cd 12 \tvprolq $0x12,%zmm29,%zmm30",}, +{{0x0f, 0x72, 0xe6, 0x02, }, 4, 0, "", "", +"0f 72 e6 02 \tpsrad $0x2,%mm6",}, +{{0xc5, 0xed, 0x72, 0xe6, 0x05, }, 5, 0, "", "", +"c5 ed 72 e6 05 \tvpsrad $0x5,%ymm6,%ymm2",}, +{{0x62, 0x91, 0x4d, 0x40, 0x72, 0xe2, 0x05, }, 7, 0, "", "", +"62 91 4d 40 72 e2 05 \tvpsrad $0x5,%zmm26,%zmm22",}, +{{0x62, 0x91, 0xcd, 0x40, 0x72, 0xe2, 0x05, }, 7, 0, "", "", +"62 91 cd 40 72 e2 05 \tvpsraq $0x5,%zmm26,%zmm22",}, +{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 7d 41 c6 8c fe 7b 00 00 00 \tvgatherpf0dps 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 fd 41 c6 8c fe 7b 00 00 00 \tvgatherpf0dpd 0x7b(%r14,%ymm31,8){%k1}",}, +{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 7d 41 c6 94 fe 7b 00 00 00 \tvgatherpf1dps 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 fd 41 c6 94 fe 7b 00 00 00 \tvgatherpf1dpd 0x7b(%r14,%ymm31,8){%k1}",}, +{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 7d 41 c6 ac fe 7b 00 00 00 \tvscatterpf0dps 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 fd 41 c6 ac fe 7b 00 00 00 \tvscatterpf0dpd 0x7b(%r14,%ymm31,8){%k1}",}, +{{0x62, 0x92, 0x7d, 0x41, 0xc6, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 7d 41 c6 b4 fe 7b 00 00 00 \tvscatterpf1dps 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0xfd, 0x41, 0xc6, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 fd 41 c6 b4 fe 7b 00 00 00 \tvscatterpf1dpd 0x7b(%r14,%ymm31,8){%k1}",}, +{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 7d 41 c7 8c fe 7b 00 00 00 \tvgatherpf0qps 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0x8c, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 fd 41 c7 8c fe 7b 00 00 00 \tvgatherpf0qpd 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 7d 41 c7 94 fe 7b 00 00 00 \tvgatherpf1qps 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0x94, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 fd 41 c7 94 fe 7b 00 00 00 \tvgatherpf1qpd 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 7d 41 c7 ac fe 7b 00 00 00 \tvscatterpf0qps 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0xac, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 fd 41 c7 ac fe 7b 00 00 00 \tvscatterpf0qpd 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0x7d, 0x41, 0xc7, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 7d 41 c7 b4 fe 7b 00 00 00 \tvscatterpf1qps 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x92, 0xfd, 0x41, 0xc7, 0xb4, 0xfe, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", +"62 92 fd 41 c7 b4 fe 7b 00 00 00 \tvscatterpf1qpd 0x7b(%r14,%zmm31,8){%k1}",}, +{{0x62, 0x01, 0x95, 0x40, 0x58, 0xf4, }, 6, 0, "", "", +"62 01 95 40 58 f4 \tvaddpd %zmm28,%zmm29,%zmm30",}, +{{0x62, 0x01, 0x95, 0x47, 0x58, 0xf4, }, 6, 0, "", "", +"62 01 95 47 58 f4 \tvaddpd %zmm28,%zmm29,%zmm30{%k7}",}, +{{0x62, 0x01, 0x95, 0xc7, 0x58, 0xf4, }, 6, 0, "", "", +"62 01 95 c7 58 f4 \tvaddpd %zmm28,%zmm29,%zmm30{%k7}{z}",}, +{{0x62, 0x01, 0x95, 0x10, 0x58, 0xf4, }, 6, 0, "", "", +"62 01 95 10 58 f4 \tvaddpd {rn-sae},%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x01, 0x95, 0x50, 0x58, 0xf4, }, 6, 0, "", "", +"62 01 95 50 58 f4 \tvaddpd {ru-sae},%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x01, 0x95, 0x30, 0x58, 0xf4, }, 6, 0, "", "", +"62 01 95 30 58 f4 \tvaddpd {rd-sae},%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x01, 0x95, 0x70, 0x58, 0xf4, }, 6, 0, "", "", +"62 01 95 70 58 f4 \tvaddpd {rz-sae},%zmm28,%zmm29,%zmm30",}, +{{0x62, 0x61, 0x95, 0x40, 0x58, 0x31, }, 6, 0, "", "", +"62 61 95 40 58 31 \tvaddpd (%rcx),%zmm29,%zmm30",}, +{{0x62, 0x21, 0x95, 0x40, 0x58, 0xb4, 0xf0, 0x23, 0x01, 0x00, 0x00, }, 11, 0, "", "", +"62 21 95 40 58 b4 f0 23 01 00 00 \tvaddpd 0x123(%rax,%r14,8),%zmm29,%zmm30",}, +{{0x62, 0x61, 0x95, 0x50, 0x58, 0x31, }, 6, 0, "", "", +"62 61 95 50 58 31 \tvaddpd (%rcx){1to8},%zmm29,%zmm30",}, +{{0x62, 0x61, 0x95, 0x40, 0x58, 0x72, 0x7f, }, 7, 0, "", "", +"62 61 95 40 58 72 7f \tvaddpd 0x1fc0(%rdx),%zmm29,%zmm30",}, +{{0x62, 0x61, 0x95, 0x50, 0x58, 0x72, 0x7f, }, 7, 0, "", "", +"62 61 95 50 58 72 7f \tvaddpd 0x3f8(%rdx){1to8},%zmm29,%zmm30",}, +{{0x62, 0xf1, 0x0c, 0x50, 0xc2, 0x6a, 0x7f, 0x08, }, 8, 0, "", "", +"62 f1 0c 50 c2 6a 7f 08 \tvcmpeq_uqps 0x1fc(%rdx){1to16},%zmm30,%k5",}, +{{0x62, 0xb1, 0x97, 0x07, 0xc2, 0xac, 0xf0, 0x23, 0x01, 0x00, 0x00, 0x01, }, 12, 0, "", "", +"62 b1 97 07 c2 ac f0 23 01 00 00 01 \tvcmpltsd 0x123(%rax,%r14,8),%xmm29,%k5{%k7}",}, +{{0x62, 0x91, 0x97, 0x17, 0xc2, 0xec, 0x02, }, 7, 0, "", "", +"62 91 97 17 c2 ec 02 \tvcmplesd {sae},%xmm28,%xmm29,%k5{%k7}",}, +{{0x62, 0x23, 0x15, 0x07, 0x27, 0xb4, 0xf0, 0x23, 0x01, 0x00, 0x00, 0x5b, }, 12, 0, "", "", +"62 23 15 07 27 b4 f0 23 01 00 00 5b \tvgetmantss $0x5b,0x123(%rax,%r14,8),%xmm29,%xmm30{%k7}",}, {{0xf3, 0x0f, 0x1b, 0x00, }, 4, 0, "", "", "f3 0f 1b 00 \tbndmk (%rax),%bnd0",}, {{0xf3, 0x41, 0x0f, 0x1b, 0x00, }, 5, 0, "", "", @@ -327,19 +1257,19 @@ {{0x0f, 0x1b, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", "0f 1b 84 08 78 56 34 12 \tbndstx %bnd0,0x12345678(%rax,%rcx,1)",}, {{0xf2, 0xe8, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "call", "unconditional", -"f2 e8 00 00 00 00 \tbnd callq 3fb ",}, +"f2 e8 00 00 00 00 \tbnd callq f22 ",}, {{0x67, 0xf2, 0xff, 0x10, }, 4, 0, "call", "indirect", "67 f2 ff 10 \tbnd callq *(%eax)",}, {{0xf2, 0xc3, }, 2, 0, "ret", "indirect", "f2 c3 \tbnd retq ",}, {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional", -"f2 e9 00 00 00 00 \tbnd jmpq 407 ",}, +"f2 e9 00 00 00 00 \tbnd jmpq f2e ",}, {{0xf2, 0xe9, 0x00, 0x00, 0x00, 0x00, }, 6, 0, "jmp", "unconditional", -"f2 e9 00 00 00 00 \tbnd jmpq 40d ",}, +"f2 e9 00 00 00 00 \tbnd jmpq f34 ",}, {{0x67, 0xf2, 0xff, 0x21, }, 4, 0, "jmp", "indirect", "67 f2 ff 21 \tbnd jmpq *(%ecx)",}, {{0xf2, 0x0f, 0x85, 0x00, 0x00, 0x00, 0x00, }, 7, 0, "jcc", "conditional", -"f2 0f 85 00 00 00 00 \tbnd jne 418 ",}, +"f2 0f 85 00 00 00 00 \tbnd jne f3f ",}, {{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "", "0f 3a cc c1 00 \tsha1rnds4 $0x0,%xmm1,%xmm0",}, {{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "", diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c index 3cd6775..76e0ec3 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -25,6 +25,876 @@ int main(void) #ifdef __x86_64__ + /* AVX-512: Instructions with the same op codes as Mask Instructions */ + + asm volatile("cmovno %rax,%rbx"); + asm volatile("cmovno 0x12345678(%rax),%rcx"); + asm volatile("cmovno 0x12345678(%rax),%cx"); + + asm volatile("cmove %rax,%rbx"); + asm volatile("cmove 0x12345678(%rax),%rcx"); + asm volatile("cmove 0x12345678(%rax),%cx"); + + asm volatile("seto 0x12345678(%rax)"); + asm volatile("setno 0x12345678(%rax)"); + asm volatile("setb 0x12345678(%rax)"); + asm volatile("setc 0x12345678(%rax)"); + asm volatile("setnae 0x12345678(%rax)"); + asm volatile("setae 0x12345678(%rax)"); + asm volatile("setnb 0x12345678(%rax)"); + asm volatile("setnc 0x12345678(%rax)"); + asm volatile("sets 0x12345678(%rax)"); + asm volatile("setns 0x12345678(%rax)"); + + /* AVX-512: Mask Instructions */ + + asm volatile("kandw %k7,%k6,%k5"); + asm volatile("kandq %k7,%k6,%k5"); + asm volatile("kandb %k7,%k6,%k5"); + asm volatile("kandd %k7,%k6,%k5"); + + asm volatile("kandnw %k7,%k6,%k5"); + asm volatile("kandnq %k7,%k6,%k5"); + asm volatile("kandnb %k7,%k6,%k5"); + asm volatile("kandnd %k7,%k6,%k5"); + + asm volatile("knotw %k7,%k6"); + asm volatile("knotq %k7,%k6"); + asm volatile("knotb %k7,%k6"); + asm volatile("knotd %k7,%k6"); + + asm volatile("korw %k7,%k6,%k5"); + asm volatile("korq %k7,%k6,%k5"); + asm volatile("korb %k7,%k6,%k5"); + asm volatile("kord %k7,%k6,%k5"); + + asm volatile("kxnorw %k7,%k6,%k5"); + asm volatile("kxnorq %k7,%k6,%k5"); + asm volatile("kxnorb %k7,%k6,%k5"); + asm volatile("kxnord %k7,%k6,%k5"); + + asm volatile("kxorw %k7,%k6,%k5"); + asm volatile("kxorq %k7,%k6,%k5"); + asm volatile("kxorb %k7,%k6,%k5"); + asm volatile("kxord %k7,%k6,%k5"); + + asm volatile("kaddw %k7,%k6,%k5"); + asm volatile("kaddq %k7,%k6,%k5"); + asm volatile("kaddb %k7,%k6,%k5"); + asm volatile("kaddd %k7,%k6,%k5"); + + asm volatile("kunpckbw %k7,%k6,%k5"); + asm volatile("kunpckwd %k7,%k6,%k5"); + asm volatile("kunpckdq %k7,%k6,%k5"); + + asm volatile("kmovw %k6,%k5"); + asm volatile("kmovw (%rcx),%k5"); + asm volatile("kmovw 0x123(%rax,%r14,8),%k5"); + asm volatile("kmovw %k5,(%rcx)"); + asm volatile("kmovw %k5,0x123(%rax,%r14,8)"); + asm volatile("kmovw %eax,%k5"); + asm volatile("kmovw %ebp,%k5"); + asm volatile("kmovw %r13d,%k5"); + asm volatile("kmovw %k5,%eax"); + asm volatile("kmovw %k5,%ebp"); + asm volatile("kmovw %k5,%r13d"); + + asm volatile("kmovq %k6,%k5"); + asm volatile("kmovq (%rcx),%k5"); + asm volatile("kmovq 0x123(%rax,%r14,8),%k5"); + asm volatile("kmovq %k5,(%rcx)"); + asm volatile("kmovq %k5,0x123(%rax,%r14,8)"); + asm volatile("kmovq %rax,%k5"); + asm volatile("kmovq %rbp,%k5"); + asm volatile("kmovq %r13,%k5"); + asm volatile("kmovq %k5,%rax"); + asm volatile("kmovq %k5,%rbp"); + asm volatile("kmovq %k5,%r13"); + + asm volatile("kmovb %k6,%k5"); + asm volatile("kmovb (%rcx),%k5"); + asm volatile("kmovb 0x123(%rax,%r14,8),%k5"); + asm volatile("kmovb %k5,(%rcx)"); + asm volatile("kmovb %k5,0x123(%rax,%r14,8)"); + asm volatile("kmovb %eax,%k5"); + asm volatile("kmovb %ebp,%k5"); + asm volatile("kmovb %r13d,%k5"); + asm volatile("kmovb %k5,%eax"); + asm volatile("kmovb %k5,%ebp"); + asm volatile("kmovb %k5,%r13d"); + + asm volatile("kmovd %k6,%k5"); + asm volatile("kmovd (%rcx),%k5"); + asm volatile("kmovd 0x123(%rax,%r14,8),%k5"); + asm volatile("kmovd %k5,(%rcx)"); + asm volatile("kmovd %k5,0x123(%rax,%r14,8)"); + asm volatile("kmovd %eax,%k5"); + asm volatile("kmovd %ebp,%k5"); + asm volatile("kmovd %r13d,%k5"); + asm volatile("kmovd %k5,%eax"); + asm volatile("kmovd %k5,%ebp"); + asm volatile("kmovd %k5,%r13d"); + + asm volatile("kortestw %k6,%k5"); + asm volatile("kortestq %k6,%k5"); + asm volatile("kortestb %k6,%k5"); + asm volatile("kortestd %k6,%k5"); + + asm volatile("ktestw %k6,%k5"); + asm volatile("ktestq %k6,%k5"); + asm volatile("ktestb %k6,%k5"); + asm volatile("ktestd %k6,%k5"); + + asm volatile("kshiftrw $0x12,%k6,%k5"); + asm volatile("kshiftrq $0x5b,%k6,%k5"); + asm volatile("kshiftlw $0x12,%k6,%k5"); + asm volatile("kshiftlq $0x5b,%k6,%k5"); + + /* AVX-512: Op code 0f 5b */ + asm volatile("vcvtdq2ps %xmm5,%xmm6"); + asm volatile("vcvtqq2ps %zmm29,%ymm6{%k7}"); + asm volatile("vcvtps2dq %xmm5,%xmm6"); + asm volatile("vcvttps2dq %xmm5,%xmm6"); + + /* AVX-512: Op code 0f 6f */ + + asm volatile("movq %mm0,%mm4"); + asm volatile("vmovdqa %ymm4,%ymm6"); + asm volatile("vmovdqa32 %zmm25,%zmm26"); + asm volatile("vmovdqa64 %zmm25,%zmm26"); + asm volatile("vmovdqu %ymm4,%ymm6"); + asm volatile("vmovdqu32 %zmm29,%zmm30"); + asm volatile("vmovdqu64 %zmm25,%zmm26"); + asm volatile("vmovdqu8 %zmm29,%zmm30"); + asm volatile("vmovdqu16 %zmm25,%zmm26"); + + /* AVX-512: Op code 0f 78 */ + + asm volatile("vmread %rax,%rbx"); + asm volatile("vcvttps2udq %zmm25,%zmm26"); + asm volatile("vcvttpd2udq %zmm29,%ymm6{%k7}"); + asm volatile("vcvttsd2usi %xmm6,%rax"); + asm volatile("vcvttss2usi %xmm6,%rax"); + asm volatile("vcvttps2uqq %ymm5,%zmm26{%k7}"); + asm volatile("vcvttpd2uqq %zmm29,%zmm30"); + + /* AVX-512: Op code 0f 79 */ + + asm volatile("vmwrite %rax,%rbx"); + asm volatile("vcvtps2udq %zmm25,%zmm26"); + asm volatile("vcvtpd2udq %zmm29,%ymm6{%k7}"); + asm volatile("vcvtsd2usi %xmm6,%rax"); + asm volatile("vcvtss2usi %xmm6,%rax"); + asm volatile("vcvtps2uqq %ymm5,%zmm26{%k7}"); + asm volatile("vcvtpd2uqq %zmm29,%zmm30"); + + /* AVX-512: Op code 0f 7a */ + + asm volatile("vcvtudq2pd %ymm5,%zmm29{%k7}"); + asm volatile("vcvtuqq2pd %zmm25,%zmm26"); + asm volatile("vcvtudq2ps %zmm29,%zmm30"); + asm volatile("vcvtuqq2ps %zmm25,%ymm26{%k7}"); + asm volatile("vcvttps2qq %ymm25,%zmm26{%k7}"); + asm volatile("vcvttpd2qq %zmm29,%zmm30"); + + /* AVX-512: Op code 0f 7b */ + + asm volatile("vcvtusi2sd %eax,%xmm5,%xmm6"); + asm volatile("vcvtusi2ss %eax,%xmm5,%xmm6"); + asm volatile("vcvtps2qq %ymm5,%zmm26{%k7}"); + asm volatile("vcvtpd2qq %zmm29,%zmm30"); + + /* AVX-512: Op code 0f 7f */ + + asm volatile("movq.s %mm0,%mm4"); + asm volatile("vmovdqa %ymm8,%ymm6"); + asm volatile("vmovdqa32.s %zmm25,%zmm26"); + asm volatile("vmovdqa64.s %zmm25,%zmm26"); + asm volatile("vmovdqu %ymm8,%ymm6"); + asm volatile("vmovdqu32.s %zmm25,%zmm26"); + asm volatile("vmovdqu64.s %zmm25,%zmm26"); + asm volatile("vmovdqu8.s %zmm30,(%rcx)"); + asm volatile("vmovdqu16.s %zmm25,%zmm26"); + + /* AVX-512: Op code 0f db */ + + asm volatile("pand %mm1,%mm2"); + asm volatile("pand %xmm1,%xmm2"); + asm volatile("vpand %ymm4,%ymm6,%ymm2"); + asm volatile("vpandd %zmm24,%zmm25,%zmm26"); + asm volatile("vpandq %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f df */ + + asm volatile("pandn %mm1,%mm2"); + asm volatile("pandn %xmm1,%xmm2"); + asm volatile("vpandn %ymm4,%ymm6,%ymm2"); + asm volatile("vpandnd %zmm24,%zmm25,%zmm26"); + asm volatile("vpandnq %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f e6 */ + + asm volatile("vcvttpd2dq %xmm1,%xmm2"); + asm volatile("vcvtdq2pd %xmm5,%xmm6"); + asm volatile("vcvtdq2pd %ymm5,%zmm26{%k7}"); + asm volatile("vcvtqq2pd %zmm25,%zmm26"); + asm volatile("vcvtpd2dq %xmm1,%xmm2"); + + /* AVX-512: Op code 0f eb */ + + asm volatile("por %mm4,%mm6"); + asm volatile("vpor %ymm4,%ymm6,%ymm2"); + asm volatile("vpord %zmm24,%zmm25,%zmm26"); + asm volatile("vporq %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f ef */ + + asm volatile("pxor %mm4,%mm6"); + asm volatile("vpxor %ymm4,%ymm6,%ymm2"); + asm volatile("vpxord %zmm24,%zmm25,%zmm26"); + asm volatile("vpxorq %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f 38 10 */ + + asm volatile("pblendvb %xmm1,%xmm0"); + asm volatile("vpsrlvw %zmm27,%zmm28,%zmm29"); + asm volatile("vpmovuswb %zmm28,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 11 */ + + asm volatile("vpmovusdb %zmm28,%xmm6{%k7}"); + asm volatile("vpsravw %zmm27,%zmm28,%zmm29"); + + /* AVX-512: Op code 0f 38 12 */ + + asm volatile("vpmovusqb %zmm27,%xmm6{%k7}"); + asm volatile("vpsllvw %zmm27,%zmm28,%zmm29"); + + /* AVX-512: Op code 0f 38 13 */ + + asm volatile("vcvtph2ps %xmm3,%ymm5"); + asm volatile("vcvtph2ps %ymm5,%zmm27{%k7}"); + asm volatile("vpmovusdw %zmm27,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 14 */ + + asm volatile("blendvps %xmm1,%xmm0"); + asm volatile("vpmovusqw %zmm27,%xmm6{%k7}"); + asm volatile("vprorvd %zmm27,%zmm28,%zmm29"); + asm volatile("vprorvq %zmm27,%zmm28,%zmm29"); + + /* AVX-512: Op code 0f 38 15 */ + + asm volatile("blendvpd %xmm1,%xmm0"); + asm volatile("vpmovusqd %zmm27,%ymm6{%k7}"); + asm volatile("vprolvd %zmm27,%zmm28,%zmm29"); + asm volatile("vprolvq %zmm27,%zmm28,%zmm29"); + + /* AVX-512: Op code 0f 38 16 */ + + asm volatile("vpermps %ymm4,%ymm6,%ymm2"); + asm volatile("vpermps %ymm24,%ymm26,%ymm22{%k7}"); + asm volatile("vpermpd %ymm24,%ymm26,%ymm22{%k7}"); + + /* AVX-512: Op code 0f 38 19 */ + + asm volatile("vbroadcastsd %xmm4,%ymm6"); + asm volatile("vbroadcastf32x2 %xmm27,%zmm26"); + + /* AVX-512: Op code 0f 38 1a */ + + asm volatile("vbroadcastf128 (%rcx),%ymm4"); + asm volatile("vbroadcastf32x4 (%rcx),%zmm26"); + asm volatile("vbroadcastf64x2 (%rcx),%zmm26"); + + /* AVX-512: Op code 0f 38 1b */ + + asm volatile("vbroadcastf32x8 (%rcx),%zmm27"); + asm volatile("vbroadcastf64x4 (%rcx),%zmm26"); + + /* AVX-512: Op code 0f 38 1f */ + + asm volatile("vpabsq %zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 20 */ + + asm volatile("vpmovsxbw %xmm4,%xmm5"); + asm volatile("vpmovswb %zmm27,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 21 */ + + asm volatile("vpmovsxbd %xmm4,%ymm6"); + asm volatile("vpmovsdb %zmm27,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 22 */ + + asm volatile("vpmovsxbq %xmm4,%ymm4"); + asm volatile("vpmovsqb %zmm27,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 23 */ + + asm volatile("vpmovsxwd %xmm4,%ymm4"); + asm volatile("vpmovsdw %zmm27,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 24 */ + + asm volatile("vpmovsxwq %xmm4,%ymm6"); + asm volatile("vpmovsqw %zmm27,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 25 */ + + asm volatile("vpmovsxdq %xmm4,%ymm4"); + asm volatile("vpmovsqd %zmm27,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 26 */ + + asm volatile("vptestmb %zmm27,%zmm28,%k5"); + asm volatile("vptestmw %zmm27,%zmm28,%k5"); + asm volatile("vptestnmb %zmm26,%zmm27,%k5"); + asm volatile("vptestnmw %zmm26,%zmm27,%k5"); + + /* AVX-512: Op code 0f 38 27 */ + + asm volatile("vptestmd %zmm27,%zmm28,%k5"); + asm volatile("vptestmq %zmm27,%zmm28,%k5"); + asm volatile("vptestnmd %zmm26,%zmm27,%k5"); + asm volatile("vptestnmq %zmm26,%zmm27,%k5"); + + /* AVX-512: Op code 0f 38 28 */ + + asm volatile("vpmuldq %ymm4,%ymm6,%ymm2"); + asm volatile("vpmovm2b %k5,%zmm28"); + asm volatile("vpmovm2w %k5,%zmm28"); + + /* AVX-512: Op code 0f 38 29 */ + + asm volatile("vpcmpeqq %ymm4,%ymm6,%ymm2"); + asm volatile("vpmovb2m %zmm28,%k5"); + asm volatile("vpmovw2m %zmm28,%k5"); + + /* AVX-512: Op code 0f 38 2a */ + + asm volatile("vmovntdqa (%rcx),%ymm4"); + asm volatile("vpbroadcastmb2q %k6,%zmm30"); + + /* AVX-512: Op code 0f 38 2c */ + + asm volatile("vmaskmovps (%rcx),%ymm4,%ymm6"); + asm volatile("vscalefps %zmm24,%zmm25,%zmm26"); + asm volatile("vscalefpd %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f 38 2d */ + + asm volatile("vmaskmovpd (%rcx),%ymm4,%ymm6"); + asm volatile("vscalefss %xmm24,%xmm25,%xmm26{%k7}"); + asm volatile("vscalefsd %xmm24,%xmm25,%xmm26{%k7}"); + + /* AVX-512: Op code 0f 38 30 */ + + asm volatile("vpmovzxbw %xmm4,%ymm4"); + asm volatile("vpmovwb %zmm27,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 31 */ + + asm volatile("vpmovzxbd %xmm4,%ymm6"); + asm volatile("vpmovdb %zmm27,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 32 */ + + asm volatile("vpmovzxbq %xmm4,%ymm4"); + asm volatile("vpmovqb %zmm27,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 33 */ + + asm volatile("vpmovzxwd %xmm4,%ymm4"); + asm volatile("vpmovdw %zmm27,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 34 */ + + asm volatile("vpmovzxwq %xmm4,%ymm6"); + asm volatile("vpmovqw %zmm27,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 35 */ + + asm volatile("vpmovzxdq %xmm4,%ymm4"); + asm volatile("vpmovqd %zmm27,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 38 */ + + asm volatile("vpermd %ymm4,%ymm6,%ymm2"); + asm volatile("vpermd %ymm24,%ymm26,%ymm22{%k7}"); + asm volatile("vpermq %ymm24,%ymm26,%ymm22{%k7}"); + + /* AVX-512: Op code 0f 38 38 */ + + asm volatile("vpminsb %ymm4,%ymm6,%ymm2"); + asm volatile("vpmovm2d %k5,%zmm28"); + asm volatile("vpmovm2q %k5,%zmm28"); + + /* AVX-512: Op code 0f 38 39 */ + + asm volatile("vpminsd %xmm1,%xmm2,%xmm3"); + asm volatile("vpminsd %zmm24,%zmm25,%zmm26"); + asm volatile("vpminsq %zmm24,%zmm25,%zmm26"); + asm volatile("vpmovd2m %zmm28,%k5"); + asm volatile("vpmovq2m %zmm28,%k5"); + + /* AVX-512: Op code 0f 38 3a */ + + asm volatile("vpminuw %ymm4,%ymm6,%ymm2"); + asm volatile("vpbroadcastmw2d %k6,%zmm28"); + + /* AVX-512: Op code 0f 38 3b */ + + asm volatile("vpminud %ymm4,%ymm6,%ymm2"); + asm volatile("vpminud %zmm24,%zmm25,%zmm26"); + asm volatile("vpminuq %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f 38 3d */ + + asm volatile("vpmaxsd %ymm4,%ymm6,%ymm2"); + asm volatile("vpmaxsd %zmm24,%zmm25,%zmm26"); + asm volatile("vpmaxsq %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f 38 3f */ + + asm volatile("vpmaxud %ymm4,%ymm6,%ymm2"); + asm volatile("vpmaxud %zmm24,%zmm25,%zmm26"); + asm volatile("vpmaxuq %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f 38 42 */ + + asm volatile("vpmulld %ymm4,%ymm6,%ymm2"); + asm volatile("vpmulld %zmm24,%zmm25,%zmm26"); + asm volatile("vpmullq %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f 38 42 */ + + asm volatile("vgetexpps %zmm25,%zmm26"); + asm volatile("vgetexppd %zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 43 */ + + asm volatile("vgetexpss %xmm24,%xmm25,%xmm26{%k7}"); + asm volatile("vgetexpsd %xmm28,%xmm29,%xmm30{%k7}"); + + /* AVX-512: Op code 0f 38 44 */ + + asm volatile("vplzcntd %zmm27,%zmm28"); + asm volatile("vplzcntq %zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 46 */ + + asm volatile("vpsravd %ymm4,%ymm6,%ymm2"); + asm volatile("vpsravd %zmm24,%zmm25,%zmm26"); + asm volatile("vpsravq %zmm24,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f 38 4c */ + + asm volatile("vrcp14ps %zmm25,%zmm26"); + asm volatile("vrcp14pd %zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 4d */ + + asm volatile("vrcp14ss %xmm24,%xmm25,%xmm26{%k7}"); + asm volatile("vrcp14sd %xmm24,%xmm25,%xmm26{%k7}"); + + /* AVX-512: Op code 0f 38 4e */ + + asm volatile("vrsqrt14ps %zmm25,%zmm26"); + asm volatile("vrsqrt14pd %zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 4f */ + + asm volatile("vrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}"); + asm volatile("vrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}"); + + /* AVX-512: Op code 0f 38 59 */ + + asm volatile("vpbroadcastq %xmm4,%xmm6"); + asm volatile("vbroadcasti32x2 %xmm27,%zmm26"); + + /* AVX-512: Op code 0f 38 5a */ + + asm volatile("vbroadcasti128 (%rcx),%ymm4"); + asm volatile("vbroadcasti32x4 (%rcx),%zmm26"); + asm volatile("vbroadcasti64x2 (%rcx),%zmm26"); + + /* AVX-512: Op code 0f 38 5b */ + + asm volatile("vbroadcasti32x8 (%rcx),%zmm28"); + asm volatile("vbroadcasti64x4 (%rcx),%zmm26"); + + /* AVX-512: Op code 0f 38 64 */ + + asm volatile("vpblendmd %zmm26,%zmm27,%zmm28"); + asm volatile("vpblendmq %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 65 */ + + asm volatile("vblendmps %zmm24,%zmm25,%zmm26"); + asm volatile("vblendmpd %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 66 */ + + asm volatile("vpblendmb %zmm26,%zmm27,%zmm28"); + asm volatile("vpblendmw %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 75 */ + + asm volatile("vpermi2b %zmm24,%zmm25,%zmm26"); + asm volatile("vpermi2w %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 76 */ + + asm volatile("vpermi2d %zmm26,%zmm27,%zmm28"); + asm volatile("vpermi2q %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 77 */ + + asm volatile("vpermi2ps %zmm26,%zmm27,%zmm28"); + asm volatile("vpermi2pd %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 7a */ + + asm volatile("vpbroadcastb %eax,%xmm30"); + + /* AVX-512: Op code 0f 38 7b */ + + asm volatile("vpbroadcastw %eax,%xmm30"); + + /* AVX-512: Op code 0f 38 7c */ + + asm volatile("vpbroadcastd %eax,%xmm30"); + asm volatile("vpbroadcastq %rax,%zmm30"); + + /* AVX-512: Op code 0f 38 7d */ + + asm volatile("vpermt2b %zmm26,%zmm27,%zmm28"); + asm volatile("vpermt2w %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 7e */ + + asm volatile("vpermt2d %zmm26,%zmm27,%zmm28"); + asm volatile("vpermt2q %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 7f */ + + asm volatile("vpermt2ps %zmm26,%zmm27,%zmm28"); + asm volatile("vpermt2pd %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 83 */ + + asm volatile("vpmultishiftqb %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 88 */ + + asm volatile("vexpandps (%rcx),%zmm26"); + asm volatile("vexpandpd (%rcx),%zmm28"); + + /* AVX-512: Op code 0f 38 89 */ + + asm volatile("vpexpandd (%rcx),%zmm28"); + asm volatile("vpexpandq (%rcx),%zmm26"); + + /* AVX-512: Op code 0f 38 8a */ + + asm volatile("vcompressps %zmm28,(%rcx)"); + asm volatile("vcompresspd %zmm28,(%rcx)"); + + /* AVX-512: Op code 0f 38 8b */ + + asm volatile("vpcompressd %zmm28,(%rcx)"); + asm volatile("vpcompressq %zmm26,(%rcx)"); + + /* AVX-512: Op code 0f 38 8d */ + + asm volatile("vpermb %zmm26,%zmm27,%zmm28"); + asm volatile("vpermw %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 90 */ + + asm volatile("vpgatherdd %xmm2,0x02(%rbp,%xmm7,2),%xmm1"); + asm volatile("vpgatherdq %xmm2,0x04(%rbp,%xmm7,2),%xmm1"); + asm volatile("vpgatherdd 0x7b(%rbp,%zmm27,8),%zmm26{%k1}"); + asm volatile("vpgatherdq 0x7b(%rbp,%ymm27,8),%zmm26{%k1}"); + + /* AVX-512: Op code 0f 38 91 */ + + asm volatile("vpgatherqd %xmm2,0x02(%rbp,%xmm7,2),%xmm1"); + asm volatile("vpgatherqq %xmm2,0x02(%rbp,%xmm7,2),%xmm1"); + asm volatile("vpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}"); + asm volatile("vpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}"); + + /* AVX-512: Op code 0f 38 a0 */ + + asm volatile("vpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}"); + asm volatile("vpscatterdq %zmm26,0x7b(%rbp,%ymm27,8){%k1}"); + + /* AVX-512: Op code 0f 38 a1 */ + + asm volatile("vpscatterqd %ymm6,0x7b(%rbp,%zmm29,8){%k1}"); + asm volatile("vpscatterqq %ymm6,0x7b(%rbp,%ymm27,8){%k1}"); + + /* AVX-512: Op code 0f 38 a2 */ + + asm volatile("vscatterdps %zmm28,0x7b(%rbp,%zmm29,8){%k1}"); + asm volatile("vscatterdpd %zmm28,0x7b(%rbp,%ymm27,8){%k1}"); + + /* AVX-512: Op code 0f 38 a3 */ + + asm volatile("vscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}"); + asm volatile("vscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}"); + + /* AVX-512: Op code 0f 38 b4 */ + + asm volatile("vpmadd52luq %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 b5 */ + + asm volatile("vpmadd52huq %zmm26,%zmm27,%zmm28"); + + /* AVX-512: Op code 0f 38 c4 */ + + asm volatile("vpconflictd %zmm26,%zmm27"); + asm volatile("vpconflictq %zmm26,%zmm27"); + + /* AVX-512: Op code 0f 38 c8 */ + + asm volatile("vexp2ps %zmm29,%zmm30"); + asm volatile("vexp2pd %zmm26,%zmm27"); + + /* AVX-512: Op code 0f 38 ca */ + + asm volatile("vrcp28ps %zmm29,%zmm30"); + asm volatile("vrcp28pd %zmm26,%zmm27"); + + /* AVX-512: Op code 0f 38 cb */ + + asm volatile("vrcp28ss %xmm28,%xmm29,%xmm30{%k7}"); + asm volatile("vrcp28sd %xmm25,%xmm26,%xmm27{%k7}"); + + /* AVX-512: Op code 0f 38 cc */ + + asm volatile("vrsqrt28ps %zmm29,%zmm30"); + asm volatile("vrsqrt28pd %zmm26,%zmm27"); + + /* AVX-512: Op code 0f 38 cd */ + + asm volatile("vrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}"); + asm volatile("vrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}"); + + /* AVX-512: Op code 0f 3a 03 */ + + asm volatile("valignd $0x12,%zmm28,%zmm29,%zmm30"); + asm volatile("valignq $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a 08 */ + + asm volatile("vroundps $0x5,%ymm6,%ymm2"); + asm volatile("vrndscaleps $0x12,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f 3a 09 */ + + asm volatile("vroundpd $0x5,%ymm6,%ymm2"); + asm volatile("vrndscalepd $0x12,%zmm25,%zmm26"); + + /* AVX-512: Op code 0f 3a 1a */ + + asm volatile("vroundss $0x5,%xmm4,%xmm6,%xmm2"); + asm volatile("vrndscaless $0x12,%xmm24,%xmm25,%xmm26{%k7}"); + + /* AVX-512: Op code 0f 3a 0b */ + + asm volatile("vroundsd $0x5,%xmm4,%xmm6,%xmm2"); + asm volatile("vrndscalesd $0x12,%xmm24,%xmm25,%xmm26{%k7}"); + + /* AVX-512: Op code 0f 3a 18 */ + + asm volatile("vinsertf128 $0x5,%xmm4,%ymm4,%ymm6"); + asm volatile("vinsertf32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}"); + asm volatile("vinsertf64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}"); + + /* AVX-512: Op code 0f 3a 19 */ + + asm volatile("vextractf128 $0x5,%ymm4,%xmm4"); + asm volatile("vextractf32x4 $0x12,%zmm25,%xmm26{%k7}"); + asm volatile("vextractf64x2 $0x12,%zmm25,%xmm26{%k7}"); + + /* AVX-512: Op code 0f 3a 1a */ + + asm volatile("vinsertf32x8 $0x12,%ymm25,%zmm26,%zmm27{%k7}"); + asm volatile("vinsertf64x4 $0x12,%ymm28,%zmm29,%zmm30{%k7}"); + + /* AVX-512: Op code 0f 3a 1b */ + + asm volatile("vextractf32x8 $0x12,%zmm29,%ymm30{%k7}"); + asm volatile("vextractf64x4 $0x12,%zmm26,%ymm27{%k7}"); + + /* AVX-512: Op code 0f 3a 1e */ + + asm volatile("vpcmpud $0x12,%zmm29,%zmm30,%k5"); + asm volatile("vpcmpuq $0x12,%zmm26,%zmm27,%k5"); + + /* AVX-512: Op code 0f 3a 1f */ + + asm volatile("vpcmpd $0x12,%zmm29,%zmm30,%k5"); + asm volatile("vpcmpq $0x12,%zmm26,%zmm27,%k5"); + + /* AVX-512: Op code 0f 3a 23 */ + + asm volatile("vshuff32x4 $0x12,%zmm28,%zmm29,%zmm30"); + asm volatile("vshuff64x2 $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a 25 */ + + asm volatile("vpternlogd $0x12,%zmm28,%zmm29,%zmm30"); + asm volatile("vpternlogq $0x12,%zmm28,%zmm29,%zmm30"); + + /* AVX-512: Op code 0f 3a 26 */ + + asm volatile("vgetmantps $0x12,%zmm26,%zmm27"); + asm volatile("vgetmantpd $0x12,%zmm29,%zmm30"); + + /* AVX-512: Op code 0f 3a 27 */ + + asm volatile("vgetmantss $0x12,%xmm25,%xmm26,%xmm27{%k7}"); + asm volatile("vgetmantsd $0x12,%xmm28,%xmm29,%xmm30{%k7}"); + + /* AVX-512: Op code 0f 3a 38 */ + + asm volatile("vinserti128 $0x5,%xmm4,%ymm4,%ymm6"); + asm volatile("vinserti32x4 $0x12,%xmm24,%zmm25,%zmm26{%k7}"); + asm volatile("vinserti64x2 $0x12,%xmm24,%zmm25,%zmm26{%k7}"); + + /* AVX-512: Op code 0f 3a 39 */ + + asm volatile("vextracti128 $0x5,%ymm4,%xmm6"); + asm volatile("vextracti32x4 $0x12,%zmm25,%xmm26{%k7}"); + asm volatile("vextracti64x2 $0x12,%zmm25,%xmm26{%k7}"); + + /* AVX-512: Op code 0f 3a 3a */ + + asm volatile("vinserti32x8 $0x12,%ymm28,%zmm29,%zmm30{%k7}"); + asm volatile("vinserti64x4 $0x12,%ymm25,%zmm26,%zmm27{%k7}"); + + /* AVX-512: Op code 0f 3a 3b */ + + asm volatile("vextracti32x8 $0x12,%zmm29,%ymm30{%k7}"); + asm volatile("vextracti64x4 $0x12,%zmm26,%ymm27{%k7}"); + + /* AVX-512: Op code 0f 3a 3e */ + + asm volatile("vpcmpub $0x12,%zmm29,%zmm30,%k5"); + asm volatile("vpcmpuw $0x12,%zmm26,%zmm27,%k5"); + + /* AVX-512: Op code 0f 3a 3f */ + + asm volatile("vpcmpb $0x12,%zmm29,%zmm30,%k5"); + asm volatile("vpcmpw $0x12,%zmm26,%zmm27,%k5"); + + /* AVX-512: Op code 0f 3a 43 */ + + asm volatile("vmpsadbw $0x5,%ymm4,%ymm6,%ymm2"); + asm volatile("vdbpsadbw $0x12,%zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 3a 43 */ + + asm volatile("vshufi32x4 $0x12,%zmm25,%zmm26,%zmm27"); + asm volatile("vshufi64x2 $0x12,%zmm28,%zmm29,%zmm30"); + + /* AVX-512: Op code 0f 3a 50 */ + + asm volatile("vrangeps $0x12,%zmm25,%zmm26,%zmm27"); + asm volatile("vrangepd $0x12,%zmm28,%zmm29,%zmm30"); + + /* AVX-512: Op code 0f 3a 51 */ + + asm volatile("vrangess $0x12,%xmm25,%xmm26,%xmm27"); + asm volatile("vrangesd $0x12,%xmm28,%xmm29,%xmm30"); + + /* AVX-512: Op code 0f 3a 54 */ + + asm volatile("vfixupimmps $0x12,%zmm28,%zmm29,%zmm30"); + asm volatile("vfixupimmpd $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a 55 */ + + asm volatile("vfixupimmss $0x12,%xmm28,%xmm29,%xmm30{%k7}"); + asm volatile("vfixupimmsd $0x12,%xmm25,%xmm26,%xmm27{%k7}"); + + /* AVX-512: Op code 0f 3a 56 */ + + asm volatile("vreduceps $0x12,%zmm26,%zmm27"); + asm volatile("vreducepd $0x12,%zmm29,%zmm30"); + + /* AVX-512: Op code 0f 3a 57 */ + + asm volatile("vreducess $0x12,%xmm25,%xmm26,%xmm27"); + asm volatile("vreducesd $0x12,%xmm28,%xmm29,%xmm30"); + + /* AVX-512: Op code 0f 3a 66 */ + + asm volatile("vfpclassps $0x12,%zmm27,%k5"); + asm volatile("vfpclasspd $0x12,%zmm30,%k5"); + + /* AVX-512: Op code 0f 3a 67 */ + + asm volatile("vfpclassss $0x12,%xmm27,%k5"); + asm volatile("vfpclasssd $0x12,%xmm30,%k5"); + + /* AVX-512: Op code 0f 72 (Grp13) */ + + asm volatile("vprord $0x12,%zmm25,%zmm26"); + asm volatile("vprorq $0x12,%zmm25,%zmm26"); + asm volatile("vprold $0x12,%zmm29,%zmm30"); + asm volatile("vprolq $0x12,%zmm29,%zmm30"); + asm volatile("psrad $0x2,%mm6"); + asm volatile("vpsrad $0x5,%ymm6,%ymm2"); + asm volatile("vpsrad $0x5,%zmm26,%zmm22"); + asm volatile("vpsraq $0x5,%zmm26,%zmm22"); + + /* AVX-512: Op code 0f 38 c6 (Grp18) */ + + asm volatile("vgatherpf0dps 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vgatherpf0dpd 0x7b(%r14,%ymm31,8){%k1}"); + asm volatile("vgatherpf1dps 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vgatherpf1dpd 0x7b(%r14,%ymm31,8){%k1}"); + asm volatile("vscatterpf0dps 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vscatterpf0dpd 0x7b(%r14,%ymm31,8){%k1}"); + asm volatile("vscatterpf1dps 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vscatterpf1dpd 0x7b(%r14,%ymm31,8){%k1}"); + + /* AVX-512: Op code 0f 38 c7 (Grp19) */ + + asm volatile("vgatherpf0qps 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vgatherpf0qpd 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vgatherpf1qps 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vgatherpf1qpd 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vscatterpf0qps 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vscatterpf0qpd 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vscatterpf1qps 0x7b(%r14,%zmm31,8){%k1}"); + asm volatile("vscatterpf1qpd 0x7b(%r14,%zmm31,8){%k1}"); + + /* AVX-512: Examples */ + + asm volatile("vaddpd %zmm28,%zmm29,%zmm30"); + asm volatile("vaddpd %zmm28,%zmm29,%zmm30{%k7}"); + asm volatile("vaddpd %zmm28,%zmm29,%zmm30{%k7}{z}"); + asm volatile("vaddpd {rn-sae},%zmm28,%zmm29,%zmm30"); + asm volatile("vaddpd {ru-sae},%zmm28,%zmm29,%zmm30"); + asm volatile("vaddpd {rd-sae},%zmm28,%zmm29,%zmm30"); + asm volatile("vaddpd {rz-sae},%zmm28,%zmm29,%zmm30"); + asm volatile("vaddpd (%rcx),%zmm29,%zmm30"); + asm volatile("vaddpd 0x123(%rax,%r14,8),%zmm29,%zmm30"); + asm volatile("vaddpd (%rcx){1to8},%zmm29,%zmm30"); + asm volatile("vaddpd 0x1fc0(%rdx),%zmm29,%zmm30"); + asm volatile("vaddpd 0x3f8(%rdx){1to8},%zmm29,%zmm30"); + asm volatile("vcmpeq_uqps 0x1fc(%rdx){1to16},%zmm30,%k5"); + asm volatile("vcmpltsd 0x123(%rax,%r14,8),%xmm29,%k5{%k7}"); + asm volatile("vcmplesd {sae},%xmm28,%xmm29,%k5{%k7}"); + asm volatile("vgetmantss $0x5b,0x123(%rax,%r14,8),%xmm29,%xmm30{%k7}"); + /* bndmk m64, bnd */ asm volatile("bndmk (%rax), %bnd0"); @@ -475,6 +1345,921 @@ int main(void) #else /* #ifdef __x86_64__ */ + /* bound r32, mem (same op code as EVEX prefix) */ + + asm volatile("bound %eax, 0x12345678(%ecx)"); + asm volatile("bound %ecx, 0x12345678(%eax)"); + asm volatile("bound %edx, 0x12345678(%eax)"); + asm volatile("bound %ebx, 0x12345678(%eax)"); + asm volatile("bound %esp, 0x12345678(%eax)"); + asm volatile("bound %ebp, 0x12345678(%eax)"); + asm volatile("bound %esi, 0x12345678(%eax)"); + asm volatile("bound %edi, 0x12345678(%eax)"); + asm volatile("bound %ecx, (%eax)"); + asm volatile("bound %eax, (0x12345678)"); + asm volatile("bound %edx, (%ecx,%eax,1)"); + asm volatile("bound %edx, 0x12345678(,%eax,1)"); + asm volatile("bound %edx, (%eax,%ecx,1)"); + asm volatile("bound %edx, (%eax,%ecx,8)"); + asm volatile("bound %edx, 0x12(%eax)"); + asm volatile("bound %edx, 0x12(%ebp)"); + asm volatile("bound %edx, 0x12(%ecx,%eax,1)"); + asm volatile("bound %edx, 0x12(%ebp,%eax,1)"); + asm volatile("bound %edx, 0x12(%eax,%ecx,1)"); + asm volatile("bound %edx, 0x12(%eax,%ecx,8)"); + asm volatile("bound %edx, 0x12345678(%eax)"); + asm volatile("bound %edx, 0x12345678(%ebp)"); + asm volatile("bound %edx, 0x12345678(%ecx,%eax,1)"); + asm volatile("bound %edx, 0x12345678(%ebp,%eax,1)"); + asm volatile("bound %edx, 0x12345678(%eax,%ecx,1)"); + asm volatile("bound %edx, 0x12345678(%eax,%ecx,8)"); + + /* bound r16, mem (same op code as EVEX prefix) */ + + asm volatile("bound %ax, 0x12345678(%ecx)"); + asm volatile("bound %cx, 0x12345678(%eax)"); + asm volatile("bound %dx, 0x12345678(%eax)"); + asm volatile("bound %bx, 0x12345678(%eax)"); + asm volatile("bound %sp, 0x12345678(%eax)"); + asm volatile("bound %bp, 0x12345678(%eax)"); + asm volatile("bound %si, 0x12345678(%eax)"); + asm volatile("bound %di, 0x12345678(%eax)"); + asm volatile("bound %cx, (%eax)"); + asm volatile("bound %ax, (0x12345678)"); + asm volatile("bound %dx, (%ecx,%eax,1)"); + asm volatile("bound %dx, 0x12345678(,%eax,1)"); + asm volatile("bound %dx, (%eax,%ecx,1)"); + asm volatile("bound %dx, (%eax,%ecx,8)"); + asm volatile("bound %dx, 0x12(%eax)"); + asm volatile("bound %dx, 0x12(%ebp)"); + asm volatile("bound %dx, 0x12(%ecx,%eax,1)"); + asm volatile("bound %dx, 0x12(%ebp,%eax,1)"); + asm volatile("bound %dx, 0x12(%eax,%ecx,1)"); + asm volatile("bound %dx, 0x12(%eax,%ecx,8)"); + asm volatile("bound %dx, 0x12345678(%eax)"); + asm volatile("bound %dx, 0x12345678(%ebp)"); + asm volatile("bound %dx, 0x12345678(%ecx,%eax,1)"); + asm volatile("bound %dx, 0x12345678(%ebp,%eax,1)"); + asm volatile("bound %dx, 0x12345678(%eax,%ecx,1)"); + asm volatile("bound %dx, 0x12345678(%eax,%ecx,8)"); + + /* AVX-512: Instructions with the same op codes as Mask Instructions */ + + asm volatile("cmovno %eax,%ebx"); + asm volatile("cmovno 0x12345678(%eax),%ecx"); + asm volatile("cmovno 0x12345678(%eax),%cx"); + + asm volatile("cmove %eax,%ebx"); + asm volatile("cmove 0x12345678(%eax),%ecx"); + asm volatile("cmove 0x12345678(%eax),%cx"); + + asm volatile("seto 0x12345678(%eax)"); + asm volatile("setno 0x12345678(%eax)"); + asm volatile("setb 0x12345678(%eax)"); + asm volatile("setc 0x12345678(%eax)"); + asm volatile("setnae 0x12345678(%eax)"); + asm volatile("setae 0x12345678(%eax)"); + asm volatile("setnb 0x12345678(%eax)"); + asm volatile("setnc 0x12345678(%eax)"); + asm volatile("sets 0x12345678(%eax)"); + asm volatile("setns 0x12345678(%eax)"); + + /* AVX-512: Mask Instructions */ + + asm volatile("kandw %k7,%k6,%k5"); + asm volatile("kandq %k7,%k6,%k5"); + asm volatile("kandb %k7,%k6,%k5"); + asm volatile("kandd %k7,%k6,%k5"); + + asm volatile("kandnw %k7,%k6,%k5"); + asm volatile("kandnq %k7,%k6,%k5"); + asm volatile("kandnb %k7,%k6,%k5"); + asm volatile("kandnd %k7,%k6,%k5"); + + asm volatile("knotw %k7,%k6"); + asm volatile("knotq %k7,%k6"); + asm volatile("knotb %k7,%k6"); + asm volatile("knotd %k7,%k6"); + + asm volatile("korw %k7,%k6,%k5"); + asm volatile("korq %k7,%k6,%k5"); + asm volatile("korb %k7,%k6,%k5"); + asm volatile("kord %k7,%k6,%k5"); + + asm volatile("kxnorw %k7,%k6,%k5"); + asm volatile("kxnorq %k7,%k6,%k5"); + asm volatile("kxnorb %k7,%k6,%k5"); + asm volatile("kxnord %k7,%k6,%k5"); + + asm volatile("kxorw %k7,%k6,%k5"); + asm volatile("kxorq %k7,%k6,%k5"); + asm volatile("kxorb %k7,%k6,%k5"); + asm volatile("kxord %k7,%k6,%k5"); + + asm volatile("kaddw %k7,%k6,%k5"); + asm volatile("kaddq %k7,%k6,%k5"); + asm volatile("kaddb %k7,%k6,%k5"); + asm volatile("kaddd %k7,%k6,%k5"); + + asm volatile("kunpckbw %k7,%k6,%k5"); + asm volatile("kunpckwd %k7,%k6,%k5"); + asm volatile("kunpckdq %k7,%k6,%k5"); + + asm volatile("kmovw %k6,%k5"); + asm volatile("kmovw (%ecx),%k5"); + asm volatile("kmovw 0x123(%eax,%ecx,8),%k5"); + asm volatile("kmovw %k5,(%ecx)"); + asm volatile("kmovw %k5,0x123(%eax,%ecx,8)"); + asm volatile("kmovw %eax,%k5"); + asm volatile("kmovw %ebp,%k5"); + asm volatile("kmovw %k5,%eax"); + asm volatile("kmovw %k5,%ebp"); + + asm volatile("kmovq %k6,%k5"); + asm volatile("kmovq (%ecx),%k5"); + asm volatile("kmovq 0x123(%eax,%ecx,8),%k5"); + asm volatile("kmovq %k5,(%ecx)"); + asm volatile("kmovq %k5,0x123(%eax,%ecx,8)"); + + asm volatile("kmovb %k6,%k5"); + asm volatile("kmovb (%ecx),%k5"); + asm volatile("kmovb 0x123(%eax,%ecx,8),%k5"); + asm volatile("kmovb %k5,(%ecx)"); + asm volatile("kmovb %k5,0x123(%eax,%ecx,8)"); + asm volatile("kmovb %eax,%k5"); + asm volatile("kmovb %ebp,%k5"); + asm volatile("kmovb %k5,%eax"); + asm volatile("kmovb %k5,%ebp"); + + asm volatile("kmovd %k6,%k5"); + asm volatile("kmovd (%ecx),%k5"); + asm volatile("kmovd 0x123(%eax,%ecx,8),%k5"); + asm volatile("kmovd %k5,(%ecx)"); + asm volatile("kmovd %k5,0x123(%eax,%ecx,8)"); + asm volatile("kmovd %eax,%k5"); + asm volatile("kmovd %ebp,%k5"); + asm volatile("kmovd %k5,%eax"); + asm volatile("kmovd %k5,%ebp"); + + asm volatile("kortestw %k6,%k5"); + asm volatile("kortestq %k6,%k5"); + asm volatile("kortestb %k6,%k5"); + asm volatile("kortestd %k6,%k5"); + + asm volatile("ktestw %k6,%k5"); + asm volatile("ktestq %k6,%k5"); + asm volatile("ktestb %k6,%k5"); + asm volatile("ktestd %k6,%k5"); + + asm volatile("kshiftrw $0x12,%k6,%k5"); + asm volatile("kshiftrq $0x5b,%k6,%k5"); + asm volatile("kshiftlw $0x12,%k6,%k5"); + asm volatile("kshiftlq $0x5b,%k6,%k5"); + + /* AVX-512: Op code 0f 5b */ + asm volatile("vcvtdq2ps %xmm5,%xmm6"); + asm volatile("vcvtqq2ps %zmm5,%ymm6{%k7}"); + asm volatile("vcvtps2dq %xmm5,%xmm6"); + asm volatile("vcvttps2dq %xmm5,%xmm6"); + + /* AVX-512: Op code 0f 6f */ + + asm volatile("movq %mm0,%mm4"); + asm volatile("vmovdqa %ymm4,%ymm6"); + asm volatile("vmovdqa32 %zmm5,%zmm6"); + asm volatile("vmovdqa64 %zmm5,%zmm6"); + asm volatile("vmovdqu %ymm4,%ymm6"); + asm volatile("vmovdqu32 %zmm5,%zmm6"); + asm volatile("vmovdqu64 %zmm5,%zmm6"); + asm volatile("vmovdqu8 %zmm5,%zmm6"); + asm volatile("vmovdqu16 %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 78 */ + + asm volatile("vmread %eax,%ebx"); + asm volatile("vcvttps2udq %zmm5,%zmm6"); + asm volatile("vcvttpd2udq %zmm5,%ymm6{%k7}"); + asm volatile("vcvttsd2usi %xmm6,%eax"); + asm volatile("vcvttss2usi %xmm6,%eax"); + asm volatile("vcvttps2uqq %ymm5,%zmm6{%k7}"); + asm volatile("vcvttpd2uqq %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 79 */ + + asm volatile("vmwrite %eax,%ebx"); + asm volatile("vcvtps2udq %zmm5,%zmm6"); + asm volatile("vcvtpd2udq %zmm5,%ymm6{%k7}"); + asm volatile("vcvtsd2usi %xmm6,%eax"); + asm volatile("vcvtss2usi %xmm6,%eax"); + asm volatile("vcvtps2uqq %ymm5,%zmm6{%k7}"); + asm volatile("vcvtpd2uqq %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 7a */ + + asm volatile("vcvtudq2pd %ymm5,%zmm6{%k7}"); + asm volatile("vcvtuqq2pd %zmm5,%zmm6"); + asm volatile("vcvtudq2ps %zmm5,%zmm6"); + asm volatile("vcvtuqq2ps %zmm5,%ymm6{%k7}"); + asm volatile("vcvttps2qq %ymm5,%zmm6{%k7}"); + asm volatile("vcvttpd2qq %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 7b */ + + asm volatile("vcvtusi2sd %eax,%xmm5,%xmm6"); + asm volatile("vcvtusi2ss %eax,%xmm5,%xmm6"); + asm volatile("vcvtps2qq %ymm5,%zmm6{%k7}"); + asm volatile("vcvtpd2qq %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 7f */ + + asm volatile("movq.s %mm0,%mm4"); + asm volatile("vmovdqa.s %ymm5,%ymm6"); + asm volatile("vmovdqa32.s %zmm5,%zmm6"); + asm volatile("vmovdqa64.s %zmm5,%zmm6"); + asm volatile("vmovdqu.s %ymm5,%ymm6"); + asm volatile("vmovdqu32.s %zmm5,%zmm6"); + asm volatile("vmovdqu64.s %zmm5,%zmm6"); + asm volatile("vmovdqu8.s %zmm5,%zmm6"); + asm volatile("vmovdqu16.s %zmm5,%zmm6"); + + /* AVX-512: Op code 0f db */ + + asm volatile("pand %mm1,%mm2"); + asm volatile("pand %xmm1,%xmm2"); + asm volatile("vpand %ymm4,%ymm6,%ymm2"); + asm volatile("vpandd %zmm4,%zmm5,%zmm6"); + asm volatile("vpandq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f df */ + + asm volatile("pandn %mm1,%mm2"); + asm volatile("pandn %xmm1,%xmm2"); + asm volatile("vpandn %ymm4,%ymm6,%ymm2"); + asm volatile("vpandnd %zmm4,%zmm5,%zmm6"); + asm volatile("vpandnq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f e6 */ + + asm volatile("vcvttpd2dq %xmm1,%xmm2"); + asm volatile("vcvtdq2pd %xmm5,%xmm6"); + asm volatile("vcvtdq2pd %ymm5,%zmm6{%k7}"); + asm volatile("vcvtqq2pd %zmm5,%zmm6"); + asm volatile("vcvtpd2dq %xmm1,%xmm2"); + + /* AVX-512: Op code 0f eb */ + + asm volatile("por %mm4,%mm6"); + asm volatile("vpor %ymm4,%ymm6,%ymm2"); + asm volatile("vpord %zmm4,%zmm5,%zmm6"); + asm volatile("vporq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f ef */ + + asm volatile("pxor %mm4,%mm6"); + asm volatile("vpxor %ymm4,%ymm6,%ymm2"); + asm volatile("vpxord %zmm4,%zmm5,%zmm6"); + asm volatile("vpxorq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 10 */ + + asm volatile("pblendvb %xmm1,%xmm0"); + asm volatile("vpsrlvw %zmm4,%zmm5,%zmm6"); + asm volatile("vpmovuswb %zmm5,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 11 */ + + asm volatile("vpmovusdb %zmm5,%xmm6{%k7}"); + asm volatile("vpsravw %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 12 */ + + asm volatile("vpmovusqb %zmm5,%xmm6{%k7}"); + asm volatile("vpsllvw %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 13 */ + + asm volatile("vcvtph2ps %xmm3,%ymm5"); + asm volatile("vcvtph2ps %ymm5,%zmm6{%k7}"); + asm volatile("vpmovusdw %zmm5,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 14 */ + + asm volatile("blendvps %xmm1,%xmm0"); + asm volatile("vpmovusqw %zmm5,%xmm6{%k7}"); + asm volatile("vprorvd %zmm4,%zmm5,%zmm6"); + asm volatile("vprorvq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 15 */ + + asm volatile("blendvpd %xmm1,%xmm0"); + asm volatile("vpmovusqd %zmm5,%ymm6{%k7}"); + asm volatile("vprolvd %zmm4,%zmm5,%zmm6"); + asm volatile("vprolvq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 16 */ + + asm volatile("vpermps %ymm4,%ymm6,%ymm2"); + asm volatile("vpermps %ymm4,%ymm6,%ymm2{%k7}"); + asm volatile("vpermpd %ymm4,%ymm6,%ymm2{%k7}"); + + /* AVX-512: Op code 0f 38 19 */ + + asm volatile("vbroadcastsd %xmm4,%ymm6"); + asm volatile("vbroadcastf32x2 %xmm7,%zmm6"); + + /* AVX-512: Op code 0f 38 1a */ + + asm volatile("vbroadcastf128 (%ecx),%ymm4"); + asm volatile("vbroadcastf32x4 (%ecx),%zmm6"); + asm volatile("vbroadcastf64x2 (%ecx),%zmm6"); + + /* AVX-512: Op code 0f 38 1b */ + + asm volatile("vbroadcastf32x8 (%ecx),%zmm6"); + asm volatile("vbroadcastf64x4 (%ecx),%zmm6"); + + /* AVX-512: Op code 0f 38 1f */ + + asm volatile("vpabsq %zmm4,%zmm6"); + + /* AVX-512: Op code 0f 38 20 */ + + asm volatile("vpmovsxbw %xmm4,%xmm5"); + asm volatile("vpmovswb %zmm5,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 21 */ + + asm volatile("vpmovsxbd %xmm4,%ymm6"); + asm volatile("vpmovsdb %zmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 22 */ + + asm volatile("vpmovsxbq %xmm4,%ymm4"); + asm volatile("vpmovsqb %zmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 23 */ + + asm volatile("vpmovsxwd %xmm4,%ymm4"); + asm volatile("vpmovsdw %zmm5,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 24 */ + + asm volatile("vpmovsxwq %xmm4,%ymm6"); + asm volatile("vpmovsqw %zmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 25 */ + + asm volatile("vpmovsxdq %xmm4,%ymm4"); + asm volatile("vpmovsqd %zmm5,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 26 */ + + asm volatile("vptestmb %zmm5,%zmm6,%k5"); + asm volatile("vptestmw %zmm5,%zmm6,%k5"); + asm volatile("vptestnmb %zmm4,%zmm5,%k5"); + asm volatile("vptestnmw %zmm4,%zmm5,%k5"); + + /* AVX-512: Op code 0f 38 27 */ + + asm volatile("vptestmd %zmm5,%zmm6,%k5"); + asm volatile("vptestmq %zmm5,%zmm6,%k5"); + asm volatile("vptestnmd %zmm4,%zmm5,%k5"); + asm volatile("vptestnmq %zmm4,%zmm5,%k5"); + + /* AVX-512: Op code 0f 38 28 */ + + asm volatile("vpmuldq %ymm4,%ymm6,%ymm2"); + asm volatile("vpmovm2b %k5,%zmm6"); + asm volatile("vpmovm2w %k5,%zmm6"); + + /* AVX-512: Op code 0f 38 29 */ + + asm volatile("vpcmpeqq %ymm4,%ymm6,%ymm2"); + asm volatile("vpmovb2m %zmm6,%k5"); + asm volatile("vpmovw2m %zmm6,%k5"); + + /* AVX-512: Op code 0f 38 2a */ + + asm volatile("vmovntdqa (%ecx),%ymm4"); + asm volatile("vpbroadcastmb2q %k6,%zmm1"); + + /* AVX-512: Op code 0f 38 2c */ + + asm volatile("vmaskmovps (%ecx),%ymm4,%ymm6"); + asm volatile("vscalefps %zmm4,%zmm5,%zmm6"); + asm volatile("vscalefpd %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 2d */ + + asm volatile("vmaskmovpd (%ecx),%ymm4,%ymm6"); + asm volatile("vscalefss %xmm4,%xmm5,%xmm6{%k7}"); + asm volatile("vscalefsd %xmm4,%xmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 30 */ + + asm volatile("vpmovzxbw %xmm4,%ymm4"); + asm volatile("vpmovwb %zmm5,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 31 */ + + asm volatile("vpmovzxbd %xmm4,%ymm6"); + asm volatile("vpmovdb %zmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 32 */ + + asm volatile("vpmovzxbq %xmm4,%ymm4"); + asm volatile("vpmovqb %zmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 33 */ + + asm volatile("vpmovzxwd %xmm4,%ymm4"); + asm volatile("vpmovdw %zmm5,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 34 */ + + asm volatile("vpmovzxwq %xmm4,%ymm6"); + asm volatile("vpmovqw %zmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 35 */ + + asm volatile("vpmovzxdq %xmm4,%ymm4"); + asm volatile("vpmovqd %zmm5,%ymm6{%k7}"); + + /* AVX-512: Op code 0f 38 36 */ + + asm volatile("vpermd %ymm4,%ymm6,%ymm2"); + asm volatile("vpermd %ymm4,%ymm6,%ymm2{%k7}"); + asm volatile("vpermq %ymm4,%ymm6,%ymm2{%k7}"); + + /* AVX-512: Op code 0f 38 38 */ + + asm volatile("vpminsb %ymm4,%ymm6,%ymm2"); + asm volatile("vpmovm2d %k5,%zmm6"); + asm volatile("vpmovm2q %k5,%zmm6"); + + /* AVX-512: Op code 0f 38 39 */ + + asm volatile("vpminsd %xmm1,%xmm2,%xmm3"); + asm volatile("vpminsd %zmm4,%zmm5,%zmm6"); + asm volatile("vpminsq %zmm4,%zmm5,%zmm6"); + asm volatile("vpmovd2m %zmm6,%k5"); + asm volatile("vpmovq2m %zmm6,%k5"); + + /* AVX-512: Op code 0f 38 3a */ + + asm volatile("vpminuw %ymm4,%ymm6,%ymm2"); + asm volatile("vpbroadcastmw2d %k6,%zmm6"); + + /* AVX-512: Op code 0f 38 3b */ + + asm volatile("vpminud %ymm4,%ymm6,%ymm2"); + asm volatile("vpminud %zmm4,%zmm5,%zmm6"); + asm volatile("vpminuq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 3d */ + + asm volatile("vpmaxsd %ymm4,%ymm6,%ymm2"); + asm volatile("vpmaxsd %zmm4,%zmm5,%zmm6"); + asm volatile("vpmaxsq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 3f */ + + asm volatile("vpmaxud %ymm4,%ymm6,%ymm2"); + asm volatile("vpmaxud %zmm4,%zmm5,%zmm6"); + asm volatile("vpmaxuq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 40 */ + + asm volatile("vpmulld %ymm4,%ymm6,%ymm2"); + asm volatile("vpmulld %zmm4,%zmm5,%zmm6"); + asm volatile("vpmullq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 42 */ + + asm volatile("vgetexpps %zmm5,%zmm6"); + asm volatile("vgetexppd %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 43 */ + + asm volatile("vgetexpss %xmm4,%xmm5,%xmm6{%k7}"); + asm volatile("vgetexpsd %xmm2,%xmm3,%xmm4{%k7}"); + + /* AVX-512: Op code 0f 38 44 */ + + asm volatile("vplzcntd %zmm5,%zmm6"); + asm volatile("vplzcntq %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 46 */ + + asm volatile("vpsravd %ymm4,%ymm6,%ymm2"); + asm volatile("vpsravd %zmm4,%zmm5,%zmm6"); + asm volatile("vpsravq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 4c */ + + asm volatile("vrcp14ps %zmm5,%zmm6"); + asm volatile("vrcp14pd %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 4d */ + + asm volatile("vrcp14ss %xmm4,%xmm5,%xmm6{%k7}"); + asm volatile("vrcp14sd %xmm4,%xmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 4e */ + + asm volatile("vrsqrt14ps %zmm5,%zmm6"); + asm volatile("vrsqrt14pd %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 4f */ + + asm volatile("vrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}"); + asm volatile("vrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 38 59 */ + + asm volatile("vpbroadcastq %xmm4,%xmm6"); + asm volatile("vbroadcasti32x2 %xmm7,%zmm6"); + + /* AVX-512: Op code 0f 38 5a */ + + asm volatile("vbroadcasti128 (%ecx),%ymm4"); + asm volatile("vbroadcasti32x4 (%ecx),%zmm6"); + asm volatile("vbroadcasti64x2 (%ecx),%zmm6"); + + /* AVX-512: Op code 0f 38 5b */ + + asm volatile("vbroadcasti32x8 (%ecx),%zmm6"); + asm volatile("vbroadcasti64x4 (%ecx),%zmm6"); + + /* AVX-512: Op code 0f 38 64 */ + + asm volatile("vpblendmd %zmm4,%zmm5,%zmm6"); + asm volatile("vpblendmq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 65 */ + + asm volatile("vblendmps %zmm4,%zmm5,%zmm6"); + asm volatile("vblendmpd %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 66 */ + + asm volatile("vpblendmb %zmm4,%zmm5,%zmm6"); + asm volatile("vpblendmw %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 75 */ + + asm volatile("vpermi2b %zmm4,%zmm5,%zmm6"); + asm volatile("vpermi2w %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 76 */ + + asm volatile("vpermi2d %zmm4,%zmm5,%zmm6"); + asm volatile("vpermi2q %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 77 */ + + asm volatile("vpermi2ps %zmm4,%zmm5,%zmm6"); + asm volatile("vpermi2pd %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 7a */ + + asm volatile("vpbroadcastb %eax,%xmm3"); + + /* AVX-512: Op code 0f 38 7b */ + + asm volatile("vpbroadcastw %eax,%xmm3"); + + /* AVX-512: Op code 0f 38 7c */ + + asm volatile("vpbroadcastd %eax,%xmm3"); + + /* AVX-512: Op code 0f 38 7d */ + + asm volatile("vpermt2b %zmm4,%zmm5,%zmm6"); + asm volatile("vpermt2w %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 7e */ + + asm volatile("vpermt2d %zmm4,%zmm5,%zmm6"); + asm volatile("vpermt2q %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 7f */ + + asm volatile("vpermt2ps %zmm4,%zmm5,%zmm6"); + asm volatile("vpermt2pd %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 83 */ + + asm volatile("vpmultishiftqb %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 88 */ + + asm volatile("vexpandps (%ecx),%zmm6"); + asm volatile("vexpandpd (%ecx),%zmm6"); + + /* AVX-512: Op code 0f 38 89 */ + + asm volatile("vpexpandd (%ecx),%zmm6"); + asm volatile("vpexpandq (%ecx),%zmm6"); + + /* AVX-512: Op code 0f 38 8a */ + + asm volatile("vcompressps %zmm6,(%ecx)"); + asm volatile("vcompresspd %zmm6,(%ecx)"); + + /* AVX-512: Op code 0f 38 8b */ + + asm volatile("vpcompressd %zmm6,(%ecx)"); + asm volatile("vpcompressq %zmm6,(%ecx)"); + + /* AVX-512: Op code 0f 38 8d */ + + asm volatile("vpermb %zmm4,%zmm5,%zmm6"); + asm volatile("vpermw %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 90 */ + + asm volatile("vpgatherdd %xmm2,0x02(%ebp,%xmm7,2),%xmm1"); + asm volatile("vpgatherdq %xmm2,0x04(%ebp,%xmm7,2),%xmm1"); + asm volatile("vpgatherdd 0x7b(%ebp,%zmm7,8),%zmm6{%k1}"); + asm volatile("vpgatherdq 0x7b(%ebp,%ymm7,8),%zmm6{%k1}"); + + /* AVX-512: Op code 0f 38 91 */ + + asm volatile("vpgatherqd %xmm2,0x02(%ebp,%xmm7,2),%xmm1"); + asm volatile("vpgatherqq %xmm2,0x02(%ebp,%xmm7,2),%xmm1"); + asm volatile("vpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}"); + asm volatile("vpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}"); + + /* AVX-512: Op code 0f 38 a0 */ + + asm volatile("vpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vpscatterdq %zmm6,0x7b(%ebp,%ymm7,8){%k1}"); + + /* AVX-512: Op code 0f 38 a1 */ + + asm volatile("vpscatterqd %ymm6,0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vpscatterqq %ymm6,0x7b(%ebp,%ymm7,8){%k1}"); + + /* AVX-512: Op code 0f 38 a2 */ + + asm volatile("vscatterdps %zmm6,0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vscatterdpd %zmm6,0x7b(%ebp,%ymm7,8){%k1}"); + + /* AVX-512: Op code 0f 38 a3 */ + + asm volatile("vscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}"); + + /* AVX-512: Op code 0f 38 b4 */ + + asm volatile("vpmadd52luq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 b5 */ + + asm volatile("vpmadd52huq %zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 c4 */ + + asm volatile("vpconflictd %zmm5,%zmm6"); + asm volatile("vpconflictq %zmm5,%zmm6"); + + /* AVX-512: Op code 0f 38 c8 */ + + asm volatile("vexp2ps %zmm6,%zmm7"); + asm volatile("vexp2pd %zmm6,%zmm7"); + + /* AVX-512: Op code 0f 38 ca */ + + asm volatile("vrcp28ps %zmm6,%zmm7"); + asm volatile("vrcp28pd %zmm6,%zmm7"); + + /* AVX-512: Op code 0f 38 cb */ + + asm volatile("vrcp28ss %xmm5,%xmm6,%xmm7{%k7}"); + asm volatile("vrcp28sd %xmm5,%xmm6,%xmm7{%k7}"); + + /* AVX-512: Op code 0f 38 cc */ + + asm volatile("vrsqrt28ps %zmm6,%zmm7"); + asm volatile("vrsqrt28pd %zmm6,%zmm7"); + + /* AVX-512: Op code 0f 38 cd */ + + asm volatile("vrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}"); + asm volatile("vrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}"); + + /* AVX-512: Op code 0f 3a 03 */ + + asm volatile("valignd $0x12,%zmm5,%zmm6,%zmm7"); + asm volatile("valignq $0x12,%zmm5,%zmm6,%zmm7"); + + /* AVX-512: Op code 0f 3a 08 */ + + asm volatile("vroundps $0x5,%ymm6,%ymm2"); + asm volatile("vrndscaleps $0x12,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 3a 09 */ + + asm volatile("vroundpd $0x5,%ymm6,%ymm2"); + asm volatile("vrndscalepd $0x12,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 3a 0a */ + + asm volatile("vroundss $0x5,%xmm4,%xmm6,%xmm2"); + asm volatile("vrndscaless $0x12,%xmm4,%xmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 3a 0b */ + + asm volatile("vroundsd $0x5,%xmm4,%xmm6,%xmm2"); + asm volatile("vrndscalesd $0x12,%xmm4,%xmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 3a 18 */ + + asm volatile("vinsertf128 $0x5,%xmm4,%ymm4,%ymm6"); + asm volatile("vinsertf32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}"); + asm volatile("vinsertf64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}"); + + /* AVX-512: Op code 0f 3a 19 */ + + asm volatile("vextractf128 $0x5,%ymm4,%xmm4"); + asm volatile("vextractf32x4 $0x12,%zmm5,%xmm6{%k7}"); + asm volatile("vextractf64x2 $0x12,%zmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 3a 1a */ + + asm volatile("vinsertf32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}"); + asm volatile("vinsertf64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}"); + + /* AVX-512: Op code 0f 3a 1b */ + + asm volatile("vextractf32x8 $0x12,%zmm6,%ymm7{%k7}"); + asm volatile("vextractf64x4 $0x12,%zmm6,%ymm7{%k7}"); + + /* AVX-512: Op code 0f 3a 1e */ + + asm volatile("vpcmpud $0x12,%zmm6,%zmm7,%k5"); + asm volatile("vpcmpuq $0x12,%zmm6,%zmm7,%k5"); + + /* AVX-512: Op code 0f 3a 1f */ + + asm volatile("vpcmpd $0x12,%zmm6,%zmm7,%k5"); + asm volatile("vpcmpq $0x12,%zmm6,%zmm7,%k5"); + + /* AVX-512: Op code 0f 3a 23 */ + + asm volatile("vshuff32x4 $0x12,%zmm5,%zmm6,%zmm7"); + asm volatile("vshuff64x2 $0x12,%zmm5,%zmm6,%zmm7"); + + /* AVX-512: Op code 0f 3a 25 */ + + asm volatile("vpternlogd $0x12,%zmm5,%zmm6,%zmm7"); + asm volatile("vpternlogq $0x12,%zmm5,%zmm6,%zmm7"); + + /* AVX-512: Op code 0f 3a 26 */ + + asm volatile("vgetmantps $0x12,%zmm6,%zmm7"); + asm volatile("vgetmantpd $0x12,%zmm6,%zmm7"); + + /* AVX-512: Op code 0f 3a 27 */ + + asm volatile("vgetmantss $0x12,%xmm5,%xmm6,%xmm7{%k7}"); + asm volatile("vgetmantsd $0x12,%xmm5,%xmm6,%xmm7{%k7}"); + + /* AVX-512: Op code 0f 3a 38 */ + + asm volatile("vinserti128 $0x5,%xmm4,%ymm4,%ymm6"); + asm volatile("vinserti32x4 $0x12,%xmm4,%zmm5,%zmm6{%k7}"); + asm volatile("vinserti64x2 $0x12,%xmm4,%zmm5,%zmm6{%k7}"); + + /* AVX-512: Op code 0f 3a 39 */ + + asm volatile("vextracti128 $0x5,%ymm4,%xmm6"); + asm volatile("vextracti32x4 $0x12,%zmm5,%xmm6{%k7}"); + asm volatile("vextracti64x2 $0x12,%zmm5,%xmm6{%k7}"); + + /* AVX-512: Op code 0f 3a 3a */ + + asm volatile("vinserti32x8 $0x12,%ymm5,%zmm6,%zmm7{%k7}"); + asm volatile("vinserti64x4 $0x12,%ymm5,%zmm6,%zmm7{%k7}"); + + /* AVX-512: Op code 0f 3a 3b */ + + asm volatile("vextracti32x8 $0x12,%zmm6,%ymm7{%k7}"); + asm volatile("vextracti64x4 $0x12,%zmm6,%ymm7{%k7}"); + + /* AVX-512: Op code 0f 3a 3e */ + + asm volatile("vpcmpub $0x12,%zmm6,%zmm7,%k5"); + asm volatile("vpcmpuw $0x12,%zmm6,%zmm7,%k5"); + + /* AVX-512: Op code 0f 3a 3f */ + + asm volatile("vpcmpb $0x12,%zmm6,%zmm7,%k5"); + asm volatile("vpcmpw $0x12,%zmm6,%zmm7,%k5"); + + /* AVX-512: Op code 0f 3a 42 */ + + asm volatile("vmpsadbw $0x5,%ymm4,%ymm6,%ymm2"); + asm volatile("vdbpsadbw $0x12,%zmm4,%zmm5,%zmm6"); + + /* AVX-512: Op code 0f 3a 43 */ + + asm volatile("vshufi32x4 $0x12,%zmm5,%zmm6,%zmm7"); + asm volatile("vshufi64x2 $0x12,%zmm5,%zmm6,%zmm7"); + + /* AVX-512: Op code 0f 3a 50 */ + + asm volatile("vrangeps $0x12,%zmm5,%zmm6,%zmm7"); + asm volatile("vrangepd $0x12,%zmm5,%zmm6,%zmm7"); + + /* AVX-512: Op code 0f 3a 51 */ + + asm volatile("vrangess $0x12,%xmm5,%xmm6,%xmm7"); + asm volatile("vrangesd $0x12,%xmm5,%xmm6,%xmm7"); + + /* AVX-512: Op code 0f 3a 54 */ + + asm volatile("vfixupimmps $0x12,%zmm5,%zmm6,%zmm7"); + asm volatile("vfixupimmpd $0x12,%zmm5,%zmm6,%zmm7"); + + /* AVX-512: Op code 0f 3a 55 */ + + asm volatile("vfixupimmss $0x12,%xmm5,%xmm6,%xmm7{%k7}"); + asm volatile("vfixupimmsd $0x12,%xmm5,%xmm6,%xmm7{%k7}"); + + /* AVX-512: Op code 0f 3a 56 */ + + asm volatile("vreduceps $0x12,%zmm6,%zmm7"); + asm volatile("vreducepd $0x12,%zmm6,%zmm7"); + + /* AVX-512: Op code 0f 3a 57 */ + + asm volatile("vreducess $0x12,%xmm5,%xmm6,%xmm7"); + asm volatile("vreducesd $0x12,%xmm5,%xmm6,%xmm7"); + + /* AVX-512: Op code 0f 3a 66 */ + + asm volatile("vfpclassps $0x12,%zmm7,%k5"); + asm volatile("vfpclasspd $0x12,%zmm7,%k5"); + + /* AVX-512: Op code 0f 3a 67 */ + + asm volatile("vfpclassss $0x12,%xmm7,%k5"); + asm volatile("vfpclasssd $0x12,%xmm7,%k5"); + + /* AVX-512: Op code 0f 72 (Grp13) */ + + asm volatile("vprord $0x12,%zmm5,%zmm6"); + asm volatile("vprorq $0x12,%zmm5,%zmm6"); + asm volatile("vprold $0x12,%zmm5,%zmm6"); + asm volatile("vprolq $0x12,%zmm5,%zmm6"); + asm volatile("psrad $0x2,%mm6"); + asm volatile("vpsrad $0x5,%ymm6,%ymm2"); + asm volatile("vpsrad $0x5,%zmm6,%zmm2"); + asm volatile("vpsraq $0x5,%zmm6,%zmm2"); + + /* AVX-512: Op code 0f 38 c6 (Grp18) */ + + asm volatile("vgatherpf0dps 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vgatherpf0dpd 0x7b(%ebp,%ymm7,8){%k1}"); + asm volatile("vgatherpf1dps 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vgatherpf1dpd 0x7b(%ebp,%ymm7,8){%k1}"); + asm volatile("vscatterpf0dps 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vscatterpf0dpd 0x7b(%ebp,%ymm7,8){%k1}"); + asm volatile("vscatterpf1dps 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vscatterpf1dpd 0x7b(%ebp,%ymm7,8){%k1}"); + + /* AVX-512: Op code 0f 38 c7 (Grp19) */ + + asm volatile("vgatherpf0qps 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vgatherpf0qpd 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vgatherpf1qps 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vgatherpf1qpd 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vscatterpf0qps 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vscatterpf0qpd 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vscatterpf1qps 0x7b(%ebp,%zmm7,8){%k1}"); + asm volatile("vscatterpf1qpd 0x7b(%ebp,%zmm7,8){%k1}"); + + /* AVX-512: Examples */ + + asm volatile("vaddpd %zmm4,%zmm5,%zmm6"); + asm volatile("vaddpd %zmm4,%zmm5,%zmm6{%k7}"); + asm volatile("vaddpd %zmm4,%zmm5,%zmm6{%k7}{z}"); + asm volatile("vaddpd {rn-sae},%zmm4,%zmm5,%zmm6"); + asm volatile("vaddpd {ru-sae},%zmm4,%zmm5,%zmm6"); + asm volatile("vaddpd {rd-sae},%zmm4,%zmm5,%zmm6"); + asm volatile("vaddpd {rz-sae},%zmm4,%zmm5,%zmm6"); + asm volatile("vaddpd (%ecx),%zmm5,%zmm6"); + asm volatile("vaddpd 0x123(%eax,%ecx,8),%zmm5,%zmm6"); + asm volatile("vaddpd (%ecx){1to8},%zmm5,%zmm6"); + asm volatile("vaddpd 0x1fc0(%edx),%zmm5,%zmm6"); + asm volatile("vaddpd 0x3f8(%edx){1to8},%zmm5,%zmm6"); + asm volatile("vcmpeq_uqps 0x1fc(%edx){1to16},%zmm6,%k5"); + asm volatile("vcmpltsd 0x123(%eax,%ecx,8),%xmm3,%k5{%k7}"); + asm volatile("vcmplesd {sae},%xmm4,%xmm5,%k5{%k7}"); + asm volatile("vgetmantss $0x5b,0x123(%eax,%ecx,8),%xmm4,%xmm5{%k7}"); + /* bndmk m32, bnd */ asm volatile("bndmk (%eax), %bnd0"); -- cgit v0.10.2 From e5e6312b5bc74c6f119993f32257927a6b646bd7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 22 Jul 2016 12:12:49 -0300 Subject: perf tests kmod-path: Fix build on ubuntu:16.04-x-armhf Cross building it on Ubuntu 16.04 to ARM ends up showing we get the free() prototype by luck in other environments, fix it. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-0ktfgmmyhcfw8ondka2013f3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index d2af781..76f41f2 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -1,4 +1,5 @@ #include +#include #include "tests.h" #include "dso.h" #include "debug.h" -- cgit v0.10.2 From 0a943cb10ce783a1c55adf6f52f62bcbd5f49314 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 22 Jul 2016 09:55:53 -0300 Subject: tools build: Add HOSTARCH Makefile variable For tools that needs to be always compiled with the host headers. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Namhyung Kim Cc: Stephen Rothwell Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-907q32k2nep6q670dkxypmu6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch index e11fbd6..887321c 100644 --- a/tools/scripts/Makefile.arch +++ b/tools/scripts/Makefile.arch @@ -1,14 +1,13 @@ -ifndef ARCH -ARCH := $(shell uname -m 2>/dev/null || echo not) -endif - -ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ +HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ -e s/sun4u/sparc/ -e s/sparc64/sparc/ \ -e /arm64/!s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ -e s/tile.*/tile/ ) +ifndef ARCH +ARCH := $(HOSTARCH) +endif LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) -- cgit v0.10.2 From 630e7a2904a271a519093aff611f50e06d55085c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 22 Jul 2016 09:59:24 -0300 Subject: objtool: Use tools/scripts/Makefile.arch to get ARCH and HOSTARCH objtool's Makefile was setting up ARCH but fixing up just the x86_64 -> x86, using Makefile.arch will do the necessary fixups for all arches. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Namhyung Kim Cc: Stephen Rothwell Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-hbq0bbh03u2b722vozcyql31@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 1f75b0a..988129c 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -1,11 +1,9 @@ include ../scripts/Makefile.include +include ../scripts/Makefile.arch -ifndef ($(ARCH)) -ARCH ?= $(shell uname -m) ifeq ($(ARCH),x86_64) ARCH := x86 endif -endif # always use the host compiler CC = gcc -- cgit v0.10.2 From 0cf6eb603b83ea386f26363b5b12e64297822bb1 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 22 Jul 2016 16:28:46 -0300 Subject: objtool: Always use host headers From a conversation with Josh: From http://lkml.kernel.org/r/20160722034118.guckaniobf3f7czc@treble : It needs to be compiled with the host (powerpc) compiler, but then it needs to disassemble target (x86) files. ---- So use HOSTARCH instead of ARCH. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Namhyung Kim Cc: Stephen Rothwell Cc: Wang Nan Link: http://lkml.kernel.org/r/20160722034118.guckaniobf3f7czc@treble Link: http://lkml.kernel.org/n/tip-le1m1yzxnfpt3msbblu40nm8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 988129c..91b5f98 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -24,7 +24,7 @@ OBJTOOL_IN := $(OBJTOOL)-in.o all: $(OBJTOOL) -INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi +INCLUDES := -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi CFLAGS += -Wall -Werror $(EXTRA_WARNINGS) -fomit-frame-pointer -O2 -g $(INCLUDES) LDFLAGS += -lelf $(LIBSUBCMD) -- cgit v0.10.2 From 60cbdf5d051d4f4db23d267d511ca241d4be7c0d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 22 Jul 2016 14:19:20 -0500 Subject: tools build: Fix objtool build with ARCH=x86_64 The objtool build fails in a cross-compiled environment on a non-x86 host with "ARCH=x86_64": tools/objtool/objtool-in.o: In function `decode_instructions': tools/objtool/builtin-check.c:276: undefined reference to `arch_decode_instruction' We could override the ARCH environment variable and change it back to x86, similar to what the objtool Makefile was doing before; but it's tricky to override environment variables consistently. Instead, take a similar approach used by the Linux top-level Makefile and introduce a SRCARCH Makefile variable which evaluates to "x86" when ARCH is either "x86_64" or "x86". Reported-by: Stephen Rothwell Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160722191920.ej62fnspnqurbaa7@treble Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/objtool/Build b/tools/objtool/Build index 2457916..d6cdece 100644 --- a/tools/objtool/Build +++ b/tools/objtool/Build @@ -1,4 +1,4 @@ -objtool-y += arch/$(ARCH)/ +objtool-y += arch/$(SRCARCH)/ objtool-y += builtin-check.o objtool-y += elf.o objtool-y += special.o diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 91b5f98..0b43770 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -33,7 +33,7 @@ elfshdr := $(shell echo '\#include ' | $(CC) $(CFLAGS) -x c -E - | gre CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED) AWK = awk -export srctree OUTPUT CFLAGS ARCH AWK +export srctree OUTPUT CFLAGS SRCARCH AWK include $(srctree)/tools/build/Makefile.include $(OBJTOOL_IN): fixdep FORCE diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch index 887321c..ad85b92 100644 --- a/tools/scripts/Makefile.arch +++ b/tools/scripts/Makefile.arch @@ -5,10 +5,42 @@ HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ -e s/tile.*/tile/ ) + ifndef ARCH ARCH := $(HOSTARCH) endif +SRCARCH := $(ARCH) + +# Additional ARCH settings for x86 +ifeq ($(ARCH),i386) + SRCARCH := x86 +endif +ifeq ($(ARCH),x86_64) + SRCARCH := x86 +endif + +# Additional ARCH settings for sparc +ifeq ($(ARCH),sparc32) + SRCARCH := sparc +endif +ifeq ($(ARCH),sparc64) + SRCARCH := sparc +endif + +# Additional ARCH settings for sh +ifeq ($(ARCH),sh64) + SRCARCH := sh +endif + +# Additional ARCH settings for tile +ifeq ($(ARCH),tilepro) + SRCARCH := tile +endif +ifeq ($(ARCH),tilegx) + SRCARCH := tile +endif + LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) IS_64_BIT := 1 -- cgit v0.10.2 From d51306f1a3bc0e3a7b86d8f2b2dedf34b356d3dd Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Sat, 23 Jul 2016 14:35:40 +1000 Subject: x86: Make the vdso2c compiler use the host architecture headers To be clear: this is a ppc64le hosted, x86_64 target cross build. Signed-off-by: Stephen Rothwell Acked-by: Andy Lutomirski Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160723150845.3af8e452@canb.auug.org.au Signed-off-by: Arnaldo Carvalho de Melo diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 253b72e..25e88c0 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -55,7 +55,7 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) -HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi +HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi hostprogs-y += vdso2c quiet_cmd_vdso2c = VDSO2C $@ -- cgit v0.10.2 From 4e3ba8af21b00b91b451e7c4a9fa3a63b025dd56 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 25 Jul 2016 11:57:37 -0300 Subject: Revert "perf tools: event.h needs asm/perf_regs.h" This reverts commit e083a21fcac9311ca425e600a15332f4792c56cc. Not needed at all, tools/perf/util/perf_regs.h, included via: #include "perf_regs.h" Should have a definition for PERF_REGS_MAX, and since this is dependent on HAVE_PERF_REGS_SUPPORT, fixes the build on powerpc, noticed by trying to cross compile this from ubuntu16.04 with a locally build libz & elfutils pair, since those are not available in multilib packages. Cc: Jiri Olsa Cc: Naveen N. Rao Cc: Stephane Eranian Cc: Sukadev Bhattiprolu Link: http://lkml.kernel.org/n/tip-0bv204s71t4wuw1l53b6fz79@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index b32464b..8d363d5 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -8,7 +8,6 @@ #include "map.h" #include "build-id.h" #include "perf_regs.h" -#include struct mmap_event { struct perf_event_header header; -- cgit v0.10.2