[PATCH] x86: VCVTNEPS2BF16{X,Y} should permit broadcasting
Jan Beulich
jbeulich@suse.com
Mon Jan 20 12:00:00 GMT 2020
Just like other VCVT*{X,Y} templates do, and to allow the programmer
flexibility (might be relevant in particular when heavily macro-izing
code), the two templates should also have Broadcast set, just like their
X/Y-suffix-less counterparts. This in turn requires them to also have
* Dword set on their memory operands, to cover the logic added to i386gen
by 4a1b91eabbe7 ("x86: Expand Broadcast to 3 bits"),
* Xmmword/Ymmword set on their memory operands, to satisfy broadcast
sizing logic in gas itself.
Otherwise ATTSyntax templates wouldn't need such operand size attributes.
While extending the test cases, also add Intel syntax broadcast forms
without explicit size specifiers.
gas/
2020-01-XX Jan Beulich <jbeulich@suse.com>
* testsuite/gas/i386/avx512_bf16_vl.s,
testsuite/gas/i386/x86-64-avx512_bf16_vl.s: Add broadcast forms
of VCVTNEPS2BF16{X,Y}. Add operand-size less Intel syntax
broadcast forms of VCVTNEPS2BF16.
* testsuite/gas/i386/avx512_bf16_vl.d,
testsuite/gas/i386/x86-64-avx512_bf16_vl.d: Adjust expectations.
opcodes/
2020-01-XX Jan Beulich <jbeulich@suse.com>
* i386-opc.tbl (vcvtneps2bf16x): Add Broadcast, Xmmword, and
Dword.
(vcvtneps2bf16y): Add Broadcast, Ymmword, and Dword.
* i386-tbl.h: Re-generate.
---
Arguably, just like other VCVT*{X,Y}, the ones here could then also be
made permit RegXMM/RegYMM as source operand. Personally I'd prefer this,
but there was resistance to such in similar earlier cases.
--- a/gas/testsuite/gas/i386/avx512_bf16_vl.d
+++ b/gas/testsuite/gas/i386/avx512_bf16_vl.d
@@ -23,9 +23,11 @@ Disassembly of section .text:
[ ]*[a-f0-9]+: 62 f2 7e 28 72 f5 vcvtneps2bf16 %ymm5,%xmm6
[ ]*[a-f0-9]+: 62 f2 7e 0f 72 b4 f4 00 00 00 10 vcvtneps2bf16x 0x10000000\(%esp,%esi,8\),%xmm6\{%k7\}
[ ]*[a-f0-9]+: 62 f2 7e 18 72 31 vcvtneps2bf16 \(%ecx\)\{1to4\},%xmm6
+[ ]*[a-f0-9]+: 62 f2 7e 18 72 31 vcvtneps2bf16 \(%ecx\)\{1to4\},%xmm6
[ ]*[a-f0-9]+: 62 f2 7e 08 72 71 7f vcvtneps2bf16x 0x7f0\(%ecx\),%xmm6
[ ]*[a-f0-9]+: 62 f2 7e 9f 72 b2 00 f8 ff ff vcvtneps2bf16 -0x800\(%edx\)\{1to4\},%xmm6\{%k7\}\{z\}
[ ]*[a-f0-9]+: 62 f2 7e 38 72 31 vcvtneps2bf16 \(%ecx\)\{1to8\},%xmm6
+[ ]*[a-f0-9]+: 62 f2 7e 38 72 31 vcvtneps2bf16 \(%ecx\)\{1to8\},%xmm6
[ ]*[a-f0-9]+: 62 f2 7e 28 72 71 7f vcvtneps2bf16y 0xfe0\(%ecx\),%xmm6
[ ]*[a-f0-9]+: 62 f2 7e bf 72 b2 00 f0 ff ff vcvtneps2bf16 -0x1000\(%edx\)\{1to8\},%xmm6\{%k7\}\{z\}
[ ]*[a-f0-9]+: 62 f2 56 28 52 f4 vdpbf16ps %ymm4,%ymm5,%ymm6
@@ -52,9 +54,11 @@ Disassembly of section .text:
[ ]*[a-f0-9]+: 62 f2 7e 28 72 f5 vcvtneps2bf16 %ymm5,%xmm6
[ ]*[a-f0-9]+: 62 f2 7e 0f 72 b4 f4 00 00 00 10 vcvtneps2bf16x 0x10000000\(%esp,%esi,8\),%xmm6\{%k7\}
[ ]*[a-f0-9]+: 62 f2 7e 18 72 31 vcvtneps2bf16 \(%ecx\)\{1to4\},%xmm6
+[ ]*[a-f0-9]+: 62 f2 7e 18 72 31 vcvtneps2bf16 \(%ecx\)\{1to4\},%xmm6
[ ]*[a-f0-9]+: 62 f2 7e 08 72 71 7f vcvtneps2bf16x 0x7f0\(%ecx\),%xmm6
[ ]*[a-f0-9]+: 62 f2 7e 9f 72 b2 00 f8 ff ff vcvtneps2bf16 -0x800\(%edx\)\{1to4\},%xmm6\{%k7\}\{z\}
[ ]*[a-f0-9]+: 62 f2 7e 38 72 31 vcvtneps2bf16 \(%ecx\)\{1to8\},%xmm6
+[ ]*[a-f0-9]+: 62 f2 7e 38 72 31 vcvtneps2bf16 \(%ecx\)\{1to8\},%xmm6
[ ]*[a-f0-9]+: 62 f2 7e 28 72 71 7f vcvtneps2bf16y 0xfe0\(%ecx\),%xmm6
[ ]*[a-f0-9]+: 62 f2 7e bf 72 b2 00 f0 ff ff vcvtneps2bf16 -0x1000\(%edx\)\{1to8\},%xmm6\{%k7\}\{z\}
[ ]*[a-f0-9]+: 62 f2 56 28 52 f4 vdpbf16ps %ymm4,%ymm5,%ymm6
--- a/gas/testsuite/gas/i386/avx512_bf16_vl.s
+++ b/gas/testsuite/gas/i386/avx512_bf16_vl.s
@@ -17,9 +17,11 @@ _start:
vcvtneps2bf16 %ymm5, %xmm6 #AVX512{BF16,VL}
vcvtneps2bf16x 0x10000000(%esp, %esi, 8), %xmm6{%k7} #AVX512{BF16,VL} MASK_ENABLING
vcvtneps2bf16 (%ecx){1to4}, %xmm6 #AVX512{BF16,VL} BROADCAST_EN
+ vcvtneps2bf16x (%ecx){1to4}, %xmm6 #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16x 2032(%ecx), %xmm6 #AVX512{BF16,VL} Disp8
vcvtneps2bf16 -2048(%edx){1to4}, %xmm6{%k7}{z} #AVX512{BF16,VL} Disp8 BROADCAST_EN MASK_ENABLING ZEROCTL
vcvtneps2bf16 (%ecx){1to8}, %xmm6 #AVX512{BF16,VL} BROADCAST_EN
+ vcvtneps2bf16y (%ecx){1to8}, %xmm6 #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16y 4064(%ecx), %xmm6 #AVX512{BF16,VL} Disp8
vcvtneps2bf16 -4096(%edx){1to8}, %xmm6{%k7}{z} #AVX512{BF16,VL} Disp8 BROADCAST_EN MASK_ENABLING ZEROCTL
vdpbf16ps %ymm4, %ymm5, %ymm6 #AVX512{BF16,VL}
@@ -47,9 +49,11 @@ _start:
vcvtneps2bf16 xmm6, xmm5 #AVX512{BF16,VL}
vcvtneps2bf16 xmm6, ymm5 #AVX512{BF16,VL}
vcvtneps2bf16 xmm6{k7}, XMMWORD PTR [esp+esi*8+0x10000000] #AVX512{BF16,VL} MASK_ENABLING
+ vcvtneps2bf16 xmm6, [ecx]{1to4} #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16 xmm6, DWORD PTR [ecx]{1to4} #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16 xmm6, XMMWORD PTR [ecx+2032] #AVX512{BF16,VL} Disp8
vcvtneps2bf16 xmm6{k7}{z}, DWORD PTR [edx-2048]{1to4} #AVX512{BF16,VL} Disp8 BROADCAST_EN MASK_ENABLING ZEROCTL
+ vcvtneps2bf16 xmm6, [ecx]{1to8} #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16 xmm6, DWORD PTR [ecx]{1to8} #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16 xmm6, YMMWORD PTR [ecx+4064] #AVX512{BF16,VL} Disp8
vcvtneps2bf16 xmm6{k7}{z}, DWORD PTR [edx-4096]{1to8} #AVX512{BF16,VL} Disp8 BROADCAST_EN MASK_ENABLING ZEROCTL
--- a/gas/testsuite/gas/i386/x86-64-avx512_bf16_vl.d
+++ b/gas/testsuite/gas/i386/x86-64-avx512_bf16_vl.d
@@ -23,9 +23,11 @@ Disassembly of section .text:
[ ]*[a-f0-9]+: 62 02 7e 28 72 f5 vcvtneps2bf16 %ymm29,%xmm30
[ ]*[a-f0-9]+: 62 22 7e 0f 72 b4 f5 00 00 00 10 vcvtneps2bf16x 0x10000000\(%rbp,%r14,8\),%xmm30\{%k7\}
[ ]*[a-f0-9]+: 62 c2 7e 18 72 29 vcvtneps2bf16 \(%r9\)\{1to4\},%xmm21
+[ ]*[a-f0-9]+: 62 f2 7e 18 72 09 vcvtneps2bf16 \(%rcx\)\{1to4\},%xmm1
[ ]*[a-f0-9]+: 62 62 7e 08 72 71 7f vcvtneps2bf16x 0x7f0\(%rcx\),%xmm30
[ ]*[a-f0-9]+: 62 62 7e 9f 72 aa 00 f8 ff ff vcvtneps2bf16 -0x800\(%rdx\)\{1to4\},%xmm29\{%k7\}\{z\}
[ ]*[a-f0-9]+: 62 c2 7e 38 72 31 vcvtneps2bf16 \(%r9\)\{1to8\},%xmm22
+[ ]*[a-f0-9]+: 62 f2 7e 38 72 11 vcvtneps2bf16 \(%rcx\)\{1to8\},%xmm2
[ ]*[a-f0-9]+: 62 e2 7e 28 72 79 7f vcvtneps2bf16y 0xfe0\(%rcx\),%xmm23
[ ]*[a-f0-9]+: 62 62 7e bf 72 9a 00 f0 ff ff vcvtneps2bf16 -0x1000\(%rdx\)\{1to8\},%xmm27\{%k7\}\{z\}
[ ]*[a-f0-9]+: 62 02 16 20 52 f4 vdpbf16ps %ymm28,%ymm29,%ymm30
@@ -51,9 +53,11 @@ Disassembly of section .text:
[ ]*[a-f0-9]+: 62 02 7e 08 72 f5 vcvtneps2bf16 %xmm29,%xmm30
[ ]*[a-f0-9]+: 62 02 7e 28 72 f5 vcvtneps2bf16 %ymm29,%xmm30
[ ]*[a-f0-9]+: 62 22 7e 0f 72 b4 f5 00 00 00 10 vcvtneps2bf16x 0x10000000\(%rbp,%r14,8\),%xmm30\{%k7\}
+[ ]*[a-f0-9]+: 62 f2 7e 18 72 29 vcvtneps2bf16 \(%rcx\)\{1to4\},%xmm5
[ ]*[a-f0-9]+: 62 42 7e 18 72 09 vcvtneps2bf16 \(%r9\)\{1to4\},%xmm25
[ ]*[a-f0-9]+: 62 62 7e 08 72 71 7f vcvtneps2bf16x 0x7f0\(%rcx\),%xmm30
[ ]*[a-f0-9]+: 62 62 7e 9f 72 b2 00 f8 ff ff vcvtneps2bf16 -0x800\(%rdx\)\{1to4\},%xmm30\{%k7\}\{z\}
+[ ]*[a-f0-9]+: 62 f2 7e 38 72 21 vcvtneps2bf16 \(%rcx\)\{1to8\},%xmm4
[ ]*[a-f0-9]+: 62 42 7e 38 72 01 vcvtneps2bf16 \(%r9\)\{1to8\},%xmm24
[ ]*[a-f0-9]+: 62 62 7e 28 72 71 7f vcvtneps2bf16y 0xfe0\(%rcx\),%xmm30
[ ]*[a-f0-9]+: 62 62 7e bf 72 b2 00 f0 ff ff vcvtneps2bf16 -0x1000\(%rdx\)\{1to8\},%xmm30\{%k7\}\{z\}
--- a/gas/testsuite/gas/i386/x86-64-avx512_bf16_vl.s
+++ b/gas/testsuite/gas/i386/x86-64-avx512_bf16_vl.s
@@ -17,9 +17,11 @@ _start:
vcvtneps2bf16 %ymm29, %xmm30 #AVX512{BF16,VL}
vcvtneps2bf16x 0x10000000(%rbp, %r14, 8), %xmm30{%k7} #AVX512{BF16,VL} MASK_ENABLING
vcvtneps2bf16 (%r9){1to4}, %xmm21 #AVX512{BF16,VL} BROADCAST_EN
+ vcvtneps2bf16x (%rcx){1to4}, %xmm1 #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16x 2032(%rcx), %xmm30 #AVX512{BF16,VL} Disp8
vcvtneps2bf16 -2048(%rdx){1to4}, %xmm29{%k7}{z} #AVX512{BF16,VL} Disp8 BROADCAST_EN MASK_ENABLING ZEROCTL
vcvtneps2bf16 (%r9){1to8}, %xmm22 #AVX512{BF16,VL} BROADCAST_EN
+ vcvtneps2bf16y (%rcx){1to8}, %xmm2 #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16y 4064(%rcx), %xmm23 #AVX512{BF16,VL} Disp8
vcvtneps2bf16 -4096(%rdx){1to8}, %xmm27{%k7}{z} #AVX512{BF16,VL} Disp8 BROADCAST_EN MASK_ENABLING ZEROCTL
vdpbf16ps %ymm28, %ymm29, %ymm30 #AVX512{BF16,VL}
@@ -47,9 +49,11 @@ _start:
vcvtneps2bf16 xmm30, xmm29 #AVX512{BF16,VL}
vcvtneps2bf16 xmm30, ymm29 #AVX512{BF16,VL}
vcvtneps2bf16 xmm30{k7}, XMMWORD PTR [rbp+r14*8+0x10000000] #AVX512{BF16,VL} MASK_ENABLING
+ vcvtneps2bf16 xmm5, [rcx]{1to4} #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16 xmm25, DWORD PTR [r9]{1to4} #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16 xmm30, XMMWORD PTR [rcx+2032] #AVX512{BF16,VL} Disp8
vcvtneps2bf16 xmm30{k7}{z}, DWORD PTR [rdx-2048]{1to4} #AVX512{BF16,VL} Disp8 BROADCAST_EN MASK_ENABLING ZEROCTL
+ vcvtneps2bf16 xmm4, [rcx]{1to8} #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16 xmm24, DWORD PTR [r9]{1to8} #AVX512{BF16,VL} BROADCAST_EN
vcvtneps2bf16 xmm30, YMMWORD PTR [rcx+4064] #AVX512{BF16,VL} Disp8
vcvtneps2bf16 xmm30{k7}{z}, DWORD PTR [rdx-4096]{1to8} #AVX512{BF16,VL} Disp8 BROADCAST_EN MASK_ENABLING ZEROCTL
--- a/opcodes/i386-opc.tbl
+++ b/opcodes/i386-opc.tbl
@@ -4771,8 +4771,8 @@ vcvtneps2bf16, 2, 0xf372, None, 1, CpuAV
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 }
-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|EVex128|Masking=3|VexW0|Broadcast|Disp8MemShift=4|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf|ATTSyntax, { Xmmword|Dword|Unspecified|BaseIndex, RegXMM }
+vcvtneps2bf16y, 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|ATTSyntax, { Ymmword|Dword|Unspecified|BaseIndex, RegXMM }
vdpbf16ps, 3, 0xf352, None, 1, CpuAVX512_BF16, Modrm|VexOpcode|VexVVVV|Masking=3|VexW0|Broadcast|Disp8ShiftVL|CheckRegSize|No_bSuf|No_wSuf|No_lSuf|No_sSuf|No_qSuf|No_ldSuf, { RegXMM|RegYMM|RegZMM|Dword|Unspecified|BaseIndex, RegXMM|RegYMM|RegZMM, RegXMM|RegYMM|RegZMM }
More information about the Binutils
mailing list