From 6f2791d5de45a9490ba6844617feac038c8da8bd Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Mon, 8 Apr 2019 11:06:04 -0700 Subject: [PATCH] x86: Consolidate AVX512 BF16 entries in i386-opc.tbl 1. Use single entry for vcvtne2ps2bf16 and vdpbf16ps with Disp8ShiftVL. 2. Use 5 entries, instead of 8, for vcvtneps2bf16. * i386-opc.tbl: Consolidate AVX512 BF16 entries. * i386-init.h: Regenerated. --- opcodes/ChangeLog | 5 + opcodes/i386-opc.tbl | 29 ++--- opcodes/i386-tbl.h | 282 ++++--------------------------------------- 3 files changed, 34 insertions(+), 282 deletions(-) diff --git a/opcodes/ChangeLog b/opcodes/ChangeLog index bf775b5e3e..27557ebb08 100644 --- a/opcodes/ChangeLog +++ b/opcodes/ChangeLog @@ -1,3 +1,8 @@ +2019-04-08 H.J. Lu + + * i386-opc.tbl: Consolidate AVX512 BF16 entries. + * i386-init.h: Regenerated. + 2019-04-07 Alan Modra * ppc-dis.c (print_insn_powerpc): Use a tiny state machine diff --git a/opcodes/i386-opc.tbl b/opcodes/i386-opc.tbl index 56fe4ef356..11ee240708 100644 --- a/opcodes/i386-opc.tbl +++ b/opcodes/i386-opc.tbl @@ -4713,30 +4713,15 @@ movdir64b, 2, 0x660f38f8, None, 3, CpuMOVDIR64B|Cpu64, Modrm|No_bSuf|No_wSuf|No_ // AVX512_BF16 instructions. -vcvtne2ps2bf16, 3, 0xf272, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex128|VexVVVV=1|Masking=3|VexW0|Broadcast|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Xmmword|Unspecified|BaseIndex, RegXMM, RegXMM } -vcvtne2ps2bf16, 3, 0xf272, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex256|VexVVVV=1|Masking=3|VexW0|Broadcast|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Ymmword|Unspecified|BaseIndex, RegYMM, RegYMM } -vcvtne2ps2bf16, 3, 0xf272, None, 1, CpuAVX512_BF16, Modrm|VexOpcode=1|EVex=1|VexVVVV=1|Masking=3|VexW0|Broadcast|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Zmmword|Unspecified|BaseIndex, RegZMM, RegZMM } +vcvtne2ps2bf16, 3, 0xf272, None, 1, CpuAVX512_BF16, Modrm|VexOpcode|VexVVVV|Masking=3|VexW0|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM } -vcvtne2ps2bf16, 3, 0xf272, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex128|VexVVVV=1|Masking=3|VexW0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, RegXMM, RegXMM } -vcvtne2ps2bf16, 3, 0xf272, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex256|VexVVVV=1|Masking=3|VexW0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegYMM, RegYMM, RegYMM } -vcvtne2ps2bf16, 3, 0xf272, None, 1, CpuAVX512_BF16, Modrm|VexOpcode=1|EVex512|VexVVVV=1|Masking=3|VexW0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegZMM, RegZMM, RegZMM } +vcvtneps2bf16, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode|EVex128|Masking=3|VexW0|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|Dword|BaseIndex, RegXMM } +vcvtneps2bf16, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode|EVex256|Masking=3|VexW0|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegYMM|Dword|BaseIndex, RegXMM } +vcvtneps2bf16, 2, 0xf372, None, 1, CpuAVX512_BF16, Modrm|VexOpcode|EVex512|Masking=3|VexW0|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegZMM|Dword|Unspecified|BaseIndex, RegYMM } -vcvtneps2bf16, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex128|Masking=3|VexW0|Broadcast|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Xmmword|BaseIndex, RegXMM } -vcvtneps2bf16, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex256|Masking=3|VexW0|Broadcast|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Ymmword|BaseIndex, RegXMM } -vcvtneps2bf16, 2, 0xf372, None, 1, CpuAVX512_BF16, Modrm|VexOpcode=1|EVex512|Masking=3|VexW0|Broadcast|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Zmmword|Unspecified|BaseIndex, RegYMM } +vcvtneps2bf16x, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode|EVex128|Masking=3|VexW0|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Unspecified|BaseIndex, RegXMM } +vcvtneps2bf16y, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode|EVex256|Masking=3|VexW0|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Unspecified|BaseIndex, RegXMM } -vcvtneps2bf16x, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex128|Masking=3|VexW0|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Dword|Xmmword|Unspecified|BaseIndex, RegXMM } -vcvtneps2bf16y, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex256|Masking=3|VexW0|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Dword|Ymmword|Unspecified|BaseIndex, RegXMM } +vdpbf16ps, 3, 0xf352, None, 1, CpuAVX512_BF16, Modrm|VexOpcode|VexVVVV|Masking=3|VexW0|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM } -vcvtneps2bf16, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex128|Masking=3|VexW0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, RegXMM } -vcvtneps2bf16, 2, 0xf372, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex256|Masking=3|VexW0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegYMM, RegXMM } -vcvtneps2bf16, 2, 0xf372, None, 1, CpuAVX512_BF16, Modrm|VexOpcode=1|EVex512|Masking=3|VexW0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegZMM, RegYMM } - -vdpbf16ps, 3, 0xf352, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex128|VexVVVV=1|Masking=3|VexW0|Broadcast|Disp8MemShift=4|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Xmmword|Unspecified|BaseIndex, RegXMM, RegXMM } -vdpbf16ps, 3, 0xf352, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex256|VexVVVV=1|Masking=3|VexW0|Broadcast|Disp8MemShift=5|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Ymmword|Unspecified|BaseIndex, RegYMM, RegYMM } -vdpbf16ps, 3, 0xf352, None, 1, CpuAVX512_BF16, Modrm|VexOpcode=1|EVex512|VexVVVV=1|Masking=3|VexW0|Broadcast|Disp8MemShift=6|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Dword|Zmmword|Unspecified|BaseIndex, RegZMM, RegZMM } - -vdpbf16ps, 3, 0xf352, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex128|VexVVVV=1|Masking=3|VexW0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM, RegXMM, RegXMM } -vdpbf16ps, 3, 0xf352, None, 1, CpuAVX512_BF16|CpuAVX512VL, Modrm|VexOpcode=1|EVex256|VexVVVV=1|Masking=3|VexW0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegYMM, RegYMM, RegYMM } -vdpbf16ps, 3, 0xf352, None, 1, CpuAVX512_BF16, Modrm|VexOpcode=1|EVex512|VexVVVV=1|Masking=3|VexW0|IgnoreSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegZMM, RegZMM, RegZMM } // AVX512_BF16 instructions end.