From: Jan Beulich <jbeulich@suse.com>
To: Binutils <binutils@sourceware.org>
Subject: [PATCH 02/12] x86: allow use of broadcast with X/Y/Z-suffixed AVX512-FP16 insns
Date: Fri, 5 Aug 2022 14:20:04 +0200 [thread overview]
Message-ID: <39936ed4-08ae-87cf-a168-09a2c3dc393c@suse.com> (raw)
In-Reply-To: <b45b6c58-e06a-2cef-ad97-0cb7956d3fd5@suse.com>
While the x/y/z suffix isn't necessary to use in this case, it is still
odd that these forms don't support broadcast (unlike their AVX512F /
AVX512DQ counterparts). The lack thereof can e.g. make macro-ized
programming more difficult.
--- a/gas/testsuite/gas/i386/avx512_fp16.d
+++ b/gas/testsuite/gas/i386/avx512_fp16.d
@@ -546,6 +546,7 @@ Disassembly of section \.text:
[ ]*[a-f0-9]+:[ ]*62 f3 7c 58 66 29 7b[ ]*vfpclassph \$0x7b,\(%ecx\)\{1to32\},%k5
[ ]*[a-f0-9]+:[ ]*62 f3 7c 48 66 69 7f 7b[ ]*vfpclassphz \$0x7b,0x1fc0\(%ecx\),%k5
[ ]*[a-f0-9]+:[ ]*62 f3 7c 5f 66 6a 80 7b[ ]*vfpclassph \$0x7b,-0x100\(%edx\)\{1to32\},%k5\{%k7\}
+[ ]*[a-f0-9]+:[ ]*62 f3 7c 58 66 69 01 7b[ ]*vfpclassph \$0x7b,0x2\(%ecx\)\{1to32\},%k5
[ ]*[a-f0-9]+:[ ]*62 f3 7c 08 67 ee 7b[ ]*vfpclasssh \$0x7b,%xmm6,%k5
[ ]*[a-f0-9]+:[ ]*62 f3 7c 0f 67 ee 7b[ ]*vfpclasssh \$0x7b,%xmm6,%k5\{%k7\}
[ ]*[a-f0-9]+:[ ]*62 f3 7c 0f 67 ac f4 00 00 00 10 7b[ ]*vfpclasssh \$0x7b,0x10000000\(%esp,%esi,8\),%k5\{%k7\}
--- a/gas/testsuite/gas/i386/avx512_fp16.s
+++ b/gas/testsuite/gas/i386/avx512_fp16.s
@@ -541,6 +541,7 @@ _start:
vfpclassph $123, (%ecx){1to32}, %k5 #AVX512-FP16 BROADCAST_EN
vfpclassphz $123, 8128(%ecx), %k5 #AVX512-FP16 Disp8(7f)
vfpclassph $123, -256(%edx){1to32}, %k5{%k7} #AVX512-FP16 BROADCAST_EN Disp8(80) MASK_ENABLING
+ vfpclassphz $123, 2(%ecx){1to32}, %k5 #AVX512-FP16 BROADCAST_EN
vfpclasssh $123, %xmm6, %k5 #AVX512-FP16
vfpclasssh $123, %xmm6, %k5{%k7} #AVX512-FP16 MASK_ENABLING
vfpclasssh $123, 0x10000000(%esp, %esi, 8), %k5{%k7} #AVX512-FP16 MASK_ENABLING
--- a/gas/testsuite/gas/i386/avx512_fp16-intel.d
+++ b/gas/testsuite/gas/i386/avx512_fp16-intel.d
@@ -546,6 +546,7 @@ Disassembly of section \.text:
[ ]*[a-f0-9]+:[ ]*62 f3 7c 58 66 29 7b[ ]*vfpclassph k5,WORD BCST \[ecx\]\{1to32\},0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 48 66 69 7f 7b[ ]*vfpclassph k5,ZMMWORD PTR \[ecx\+0x1fc0\],0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 5f 66 6a 80 7b[ ]*vfpclassph k5\{k7\},WORD BCST \[edx-0x100\]\{1to32\},0x7b
+[ ]*[a-f0-9]+:[ ]*62 f3 7c 58 66 69 01 7b[ ]*vfpclassph k5,WORD BCST \[ecx\+0x2\]\{1to32\},0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 08 67 ee 7b[ ]*vfpclasssh k5,xmm6,0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 0f 67 ee 7b[ ]*vfpclasssh k5\{k7\},xmm6,0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 0f 67 ac f4 00 00 00 10 7b[ ]*vfpclasssh k5\{k7\},WORD PTR \[esp\+esi\*8\+0x10000000\],0x7b
--- a/gas/testsuite/gas/i386/avx512_fp16_vl.d
+++ b/gas/testsuite/gas/i386/avx512_fp16_vl.d
@@ -574,9 +574,11 @@ Disassembly of section \.text:
[ ]*[a-f0-9]+:[ ]*62 f3 7c 18 66 29 7b[ ]*vfpclassph \$0x7b,\(%ecx\)\{1to8\},%k5
[ ]*[a-f0-9]+:[ ]*62 f3 7c 08 66 69 7f 7b[ ]*vfpclassphx \$0x7b,0x7f0\(%ecx\),%k5
[ ]*[a-f0-9]+:[ ]*62 f3 7c 1f 66 6a 80 7b[ ]*vfpclassph \$0x7b,-0x100\(%edx\)\{1to8\},%k5\{%k7\}
+[ ]*[a-f0-9]+:[ ]*62 f3 7c 18 66 69 01 7b[ ]*vfpclassph \$0x7b,0x2\(%ecx\)\{1to8\},%k5
[ ]*[a-f0-9]+:[ ]*62 f3 7c 38 66 29 7b[ ]*vfpclassph \$0x7b,\(%ecx\)\{1to16\},%k5
[ ]*[a-f0-9]+:[ ]*62 f3 7c 28 66 69 7f 7b[ ]*vfpclassphy \$0x7b,0xfe0\(%ecx\),%k5
[ ]*[a-f0-9]+:[ ]*62 f3 7c 3f 66 6a 80 7b[ ]*vfpclassph \$0x7b,-0x100\(%edx\)\{1to16\},%k5\{%k7\}
+[ ]*[a-f0-9]+:[ ]*62 f3 7c 38 66 69 01 7b[ ]*vfpclassph \$0x7b,0x2\(%ecx\)\{1to16\},%k5
[ ]*[a-f0-9]+:[ ]*62 f6 7d 08 42 f5[ ]*vgetexpph %xmm5,%xmm6
[ ]*[a-f0-9]+:[ ]*62 f6 7d 8f 42 f5[ ]*vgetexpph %xmm5,%xmm6\{%k7\}\{z\}
[ ]*[a-f0-9]+:[ ]*62 f6 7d 28 42 f5[ ]*vgetexpph %ymm5,%ymm6
--- a/gas/testsuite/gas/i386/avx512_fp16_vl.s
+++ b/gas/testsuite/gas/i386/avx512_fp16_vl.s
@@ -569,9 +569,11 @@ _start:
vfpclassph $123, (%ecx){1to8}, %k5 #AVX512-FP16,AVX512VL BROADCAST_EN
vfpclassphx $123, 2032(%ecx), %k5 #AVX512-FP16,AVX512VL Disp8(7f)
vfpclassph $123, -256(%edx){1to8}, %k5{%k7} #AVX512-FP16,AVX512VL BROADCAST_EN Disp8(80) MASK_ENABLING
+ vfpclassphx $123, 2(%ecx){1to8}, %k5 #AVX512-FP16,AVX512VL BROADCAST_EN
vfpclassph $123, (%ecx){1to16}, %k5 #AVX512-FP16,AVX512VL BROADCAST_EN
vfpclassphy $123, 4064(%ecx), %k5 #AVX512-FP16,AVX512VL Disp8(7f)
vfpclassph $123, -256(%edx){1to16}, %k5{%k7} #AVX512-FP16,AVX512VL BROADCAST_EN Disp8(80) MASK_ENABLING
+ vfpclassphy $123, 2(%ecx){1to16}, %k5 #AVX512-FP16,AVX512VL BROADCAST_EN
vgetexpph %xmm5, %xmm6 #AVX512-FP16,AVX512VL
vgetexpph %xmm5, %xmm6{%k7}{z} #AVX512-FP16,AVX512VL MASK_ENABLING ZEROCTL
vgetexpph %ymm5, %ymm6 #AVX512-FP16,AVX512VL
--- a/gas/testsuite/gas/i386/avx512_fp16_vl-intel.d
+++ b/gas/testsuite/gas/i386/avx512_fp16_vl-intel.d
@@ -574,9 +574,11 @@ Disassembly of section \.text:
[ ]*[a-f0-9]+:[ ]*62 f3 7c 18 66 29 7b[ ]*vfpclassph k5,WORD BCST \[ecx\]\{1to8\},0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 08 66 69 7f 7b[ ]*vfpclassph k5,XMMWORD PTR \[ecx\+0x7f0\],0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 1f 66 6a 80 7b[ ]*vfpclassph k5\{k7\},WORD BCST \[edx-0x100\]\{1to8\},0x7b
+[ ]*[a-f0-9]+:[ ]*62 f3 7c 18 66 69 01 7b[ ]*vfpclassph k5,WORD BCST \[ecx\+0x2\]\{1to8\},0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 38 66 29 7b[ ]*vfpclassph k5,WORD BCST \[ecx\]\{1to16\},0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 28 66 69 7f 7b[ ]*vfpclassph k5,YMMWORD PTR \[ecx\+0xfe0\],0x7b
[ ]*[a-f0-9]+:[ ]*62 f3 7c 3f 66 6a 80 7b[ ]*vfpclassph k5\{k7\},WORD BCST \[edx-0x100\]\{1to16\},0x7b
+[ ]*[a-f0-9]+:[ ]*62 f3 7c 38 66 69 01 7b[ ]*vfpclassph k5,WORD BCST \[ecx\+0x2\]\{1to16\},0x7b
[ ]*[a-f0-9]+:[ ]*62 f6 7d 08 42 f5[ ]*vgetexpph xmm6,xmm5
[ ]*[a-f0-9]+:[ ]*62 f6 7d 8f 42 f5[ ]*vgetexpph xmm6\{k7\}\{z\},xmm5
[ ]*[a-f0-9]+:[ ]*62 f6 7d 28 42 f5[ ]*vgetexpph ymm6,ymm5
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -3560,38 +3560,38 @@ vucomish, 0x2e, None, CpuAVX512_FP16, Mo
vcvtdq2ph, 0x5b, None, CpuAVX512_FP16, Modrm|EVex512|Masking=3|EVexMap5|VexW0|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE, { RegZMM|Dword|Unspecified|BaseIndex, RegYMM }
vcvtdq2ph, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|Masking=3|EVexMap5|VexW0|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IntelSyntax, { RegXMM|RegYMM|Dword|Unspecified|BaseIndex, RegXMM }
vcvtdq2ph, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|Masking=3|EVexMap5|VexW0|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|RegYMM|Dword|BaseIndex, RegXMM }
-vcvtdq2phx, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW0|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vcvtdq2phy, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW0|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Unspecified|BaseIndex, RegXMM }
+vcvtdq2phx, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW0|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
+vcvtdq2phy, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW0|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Dword|Unspecified|BaseIndex, RegXMM }
vcvtudq2ph, 0xf27a, None, CpuAVX512_FP16, Modrm|EVex512|Masking=3|EVexMap5|VexW0|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE, { RegZMM|Dword|Unspecified|BaseIndex, RegYMM }
vcvtudq2ph, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|Masking=3|EVexMap5|VexW0|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IntelSyntax, { RegXMM|RegYMM|Dword|Unspecified|BaseIndex, RegXMM }
vcvtudq2ph, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|Masking=3|EVexMap5|VexW0|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|RegYMM|Dword|BaseIndex, RegXMM }
-vcvtudq2phx, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW0|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vcvtudq2phy, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW0|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Unspecified|BaseIndex, RegXMM }
+vcvtudq2phx, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW0|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
+vcvtudq2phy, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW0|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Dword|Unspecified|BaseIndex, RegXMM }
vcvtqq2ph, 0x5b, None, CpuAVX512_FP16, Modrm|Masking=3|EVexMap5|VexW1|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|IntelSyntax, { RegXMM|RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegXMM }
vcvtqq2ph, 0x5b, None, CpuAVX512_FP16, Modrm|Masking=3|EVexMap5|VexW1|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|ATTSyntax, { RegXMM|RegYMM|RegZMM|Qword|BaseIndex, RegXMM }
-vcvtqq2phz, 0x5b, None, CpuAVX512_FP16, Modrm|EVex512|Masking=3|EVexMap5|VexW1|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|ATTSyntax, { RegZMM|Unspecified|BaseIndex, RegXMM }
-vcvtqq2phx, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW1|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vcvtqq2phy, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW1|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Unspecified|BaseIndex, RegXMM }
+vcvtqq2phz, 0x5b, None, CpuAVX512_FP16, Modrm|EVex512|Masking=3|EVexMap5|VexW1|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|ATTSyntax, { RegZMM|Qword|Unspecified|BaseIndex, RegXMM }
+vcvtqq2phx, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW1|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
+vcvtqq2phy, 0x5b, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW1|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Qword|Unspecified|BaseIndex, RegXMM }
vcvtuqq2ph, 0xf27a, None, CpuAVX512_FP16, Modrm|Masking=3|EVexMap5|VexW1|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|IntelSyntax, { RegXMM|RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegXMM }
vcvtuqq2ph, 0xf27a, None, CpuAVX512_FP16, Modrm|Masking=3|EVexMap5|VexW1|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|ATTSyntax, { RegXMM|RegYMM|RegZMM|Qword|BaseIndex, RegXMM }
-vcvtuqq2phz, 0xf27a, None, CpuAVX512_FP16, Modrm|EVex512|Masking=3|EVexMap5|VexW1|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|ATTSyntax, { RegZMM|Unspecified|BaseIndex, RegXMM }
-vcvtuqq2phx, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW1|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vcvtuqq2phy, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW1|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Unspecified|BaseIndex, RegXMM }
+vcvtuqq2phz, 0xf27a, None, CpuAVX512_FP16, Modrm|EVex512|Masking=3|EVexMap5|VexW1|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|ATTSyntax, { RegZMM|Qword|Unspecified|BaseIndex, RegXMM }
+vcvtuqq2phx, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW1|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
+vcvtuqq2phy, 0xf27a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW1|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Qword|Unspecified|BaseIndex, RegXMM }
vcvtpd2ph, 0x665a, None, CpuAVX512_FP16, Modrm|Masking=3|EVexMap5|VexW1|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|IntelSyntax, { RegXMM|RegYMM|RegZMM|Qword|Unspecified|BaseIndex, RegXMM }
vcvtpd2ph, 0x665a, None, CpuAVX512_FP16, Modrm|Masking=3|EVexMap5|VexW1|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|ATTSyntax, { RegXMM|RegYMM|RegZMM|Qword|BaseIndex, RegXMM }
-vcvtpd2phx, 0x665a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW1|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vcvtpd2phy, 0x665a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW1|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Unspecified|BaseIndex, RegXMM }
-vcvtpd2phz, 0x665a, None, CpuAVX512_FP16, Modrm|EVex512|Masking=3|EVexMap5|VexW1|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|ATTSyntax, { RegZMM|Unspecified|BaseIndex, RegXMM }
+vcvtpd2phx, 0x665a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW1|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Qword|Unspecified|BaseIndex, RegXMM }
+vcvtpd2phy, 0x665a, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW1|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Qword|Unspecified|BaseIndex, RegXMM }
+vcvtpd2phz, 0x665a, None, CpuAVX512_FP16, Modrm|EVex512|Masking=3|EVexMap5|VexW1|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE|ATTSyntax, { RegZMM|Qword|Unspecified|BaseIndex, RegXMM }
vcvtps2phx, 0x661d, None, CpuAVX512_FP16, Modrm|EVex512|Masking=3|EVexMap5|VexW0|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE, { RegZMM|Dword|Unspecified|BaseIndex, RegYMM }
vcvtps2phx, 0x661d, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|Masking=3|EVexMap5|VexW0|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|IntelSyntax, { RegXMM|RegYMM|Dword|Unspecified|BaseIndex, RegXMM }
vcvtps2phx, 0x661d, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|Masking=3|EVexMap5|VexW0|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|RegYMM|Dword|BaseIndex, RegXMM }
-vcvtps2phxx, 0x661d, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW0|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Unspecified|BaseIndex, RegXMM }
-vcvtps2phxy, 0x661d, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW0|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Unspecified|BaseIndex, RegXMM }
+vcvtps2phxx, 0x661d, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=3|EVexMap5|VexW0|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegXMM|Dword|Unspecified|BaseIndex, RegXMM }
+vcvtps2phxy, 0x661d, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=3|EVexMap5|VexW0|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { RegYMM|Dword|Unspecified|BaseIndex, RegXMM }
vcvtw2ph, 0xf37d, None, CpuAVX512_FP16, Modrm|Masking=3|EVexMap5|VexW0|Broadcast|Disp8ShiftVL|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|Word|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
vcvtuw2ph, 0xf27d, None, CpuAVX512_FP16, Modrm|Masking=3|EVexMap5|VexW0|Broadcast|Disp8ShiftVL|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE, { RegXMM|RegYMM|RegZMM|Word|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
@@ -3675,9 +3675,9 @@ vfnmsub<fma>ph, 0x668e | 0x<fma:opc>, No
vfnmsub<fma>sh, 0x668f | 0x<fma:opc>, None, CpuAVX512_FP16, Modrm|EVexLIG|VexVVVV|Masking=3|EVexMap6|VexW0|Disp8MemShift=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|StaticRounding|SAE, { RegXMM|Word|Unspecified|BaseIndex, RegXMM, RegXMM }
vfpclassph, 0x66, None, CpuAVX512_FP16, Modrm|Masking=2|Space0F3A|VexW0|Broadcast|Disp8ShiftVL|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|RegYMM|RegZMM|Word|BaseIndex, RegMask }
-vfpclassphz, 0x66, None, CpuAVX512_FP16, Modrm|EVex512|Masking=2|Space0F3A|VexW0|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Imm8, RegZMM|Unspecified|BaseIndex, RegMask }
-vfpclassphx, 0x66, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=2|Space0F3A|VexW0|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Imm8, RegXMM|Unspecified|BaseIndex, RegMask }
-vfpclassphy, 0x66, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=2|Space0F3A|VexW0|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Imm8, RegYMM|Unspecified|BaseIndex, RegMask }
+vfpclassphz, 0x66, None, CpuAVX512_FP16, Modrm|EVex512|Masking=2|Space0F3A|VexW0|Broadcast|Disp8MemShift=6|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Imm8, RegZMM|Word|Unspecified|BaseIndex, RegMask }
+vfpclassphx, 0x66, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex128|Masking=2|Space0F3A|VexW0|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Imm8, RegXMM|Word|Unspecified|BaseIndex, RegMask }
+vfpclassphy, 0x66, None, CpuAVX512_FP16|CpuAVX512VL, Modrm|EVex256|Masking=2|Space0F3A|VexW0|Broadcast|Disp8MemShift=5|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Imm8, RegYMM|Word|Unspecified|BaseIndex, RegMask }
vfpclasssh, 0x67, None, CpuAVX512_FP16, Modrm|EVexLIG|Masking=2|Space0F3A|VexW0|Disp8MemShift=1|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { Imm8, RegXMM|Word|Unspecified|BaseIndex, RegMask }
vgetmantph, 0x26, None, CpuAVX512_FP16, Modrm|Masking=3|Space0F3A|VexW0|Broadcast|Disp8ShiftVL|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|SAE, { Imm8, RegXMM|RegYMM|RegZMM|Word|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM }
next prev parent reply other threads:[~2022-08-05 12:20 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-05 12:17 [PATCH 00/12] x86: more templatization of insn templates Jan Beulich
2022-08-05 12:19 ` [PATCH 01/12] x86/Intel: split certain AVX512-FP16 VCVT*2PH templates Jan Beulich
2022-08-05 22:28 ` H.J. Lu
2022-08-05 12:20 ` Jan Beulich [this message]
2022-08-05 22:31 ` [PATCH 02/12] x86: allow use of broadcast with X/Y/Z-suffixed AVX512-FP16 insns H.J. Lu
2022-08-05 12:20 ` [PATCH 03/12] x86: fold AVX VGATHERDPD / VPGATHERDQ Jan Beulich
2022-08-05 22:32 ` H.J. Lu
2022-08-05 12:21 ` [PATCH 04/12] x86: adjust MOVSD attributes Jan Beulich
2022-08-05 22:46 ` H.J. Lu
2022-08-05 12:22 ` [PATCH 05/12] x86-64: adjust MOVQ to/from SReg attributes Jan Beulich
2022-08-05 23:00 ` H.J. Lu
2022-08-05 12:23 ` [PATCH 06/12] revert "x86: Also pass -P to $(CPP) when processing i386-opc.tbl" Jan Beulich
2022-08-05 23:17 ` H.J. Lu
2022-08-09 7:22 ` Jan Beulich
2022-08-08 12:49 ` Michael Matz
2022-08-09 7:33 ` Jan Beulich
2022-08-11 16:40 ` H.J. Lu
2022-08-05 12:24 ` [PATCH 07/12] x86: template-ize packed/scalar vector floating point insns Jan Beulich
2022-08-05 23:07 ` H.J. Lu
2022-08-11 1:12 ` Jiang, Haochen
2022-08-11 6:03 ` Jan Beulich
2022-08-11 16:38 ` H.J. Lu
2022-08-05 12:25 ` [PATCH 08/12] x86: template-ize vector packed dword/qword integer insns Jan Beulich
2022-08-11 17:23 ` H.J. Lu
2022-08-16 7:37 ` Jan Beulich
2022-08-16 15:53 ` H.J. Lu
2022-08-16 16:20 ` Jan Beulich
2022-08-16 16:32 ` H.J. Lu
2022-08-05 12:26 ` [PATCH 09/12] x86: re-order AVX512 S/G templates Jan Beulich
2022-08-11 17:24 ` H.J. Lu
2022-08-05 12:27 ` [PATCH 10/12] x86: template-ize vector packed byte/word integer insns Jan Beulich
2022-08-11 17:38 ` H.J. Lu
2022-08-05 12:28 ` [PATCH 11/12] x86: template-ize certain vector conversion insns Jan Beulich
2022-08-11 17:48 ` H.J. Lu
2022-08-05 12:29 ` [PATCH 12/12] x86: shorten certain template names Jan Beulich
2022-08-11 17:49 ` H.J. Lu
2022-08-12 11:33 ` [PATCH v1.1 06/12] revert "x86: Also pass -P to $(CPP) when processing i386-opc.tbl" Jan Beulich
2022-08-15 18:11 ` H.J. Lu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=39936ed4-08ae-87cf-a168-09a2c3dc393c@suse.com \
--to=jbeulich@suse.com \
--cc=binutils@sourceware.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).