diff options
Diffstat (limited to 'gas')
-rw-r--r-- | gas/ChangeLog | 19 | ||||
-rw-r--r-- | gas/config/tc-i386.c | 3 | ||||
-rw-r--r-- | gas/doc/c-i386.texi | 6 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/avx512_4vnniw-intel.d | 45 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/avx512_4vnniw.d | 45 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/avx512_4vnniw.s | 41 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/avx512_4vnniw_vl-intel.d | 79 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/avx512_4vnniw_vl.d | 79 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/avx512_4vnniw_vl.s | 75 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/i386.exp | 8 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-avx512_4vnniw-intel.d | 45 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-avx512_4vnniw.d | 45 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-avx512_4vnniw.s | 41 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl-intel.d | 79 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl.d | 79 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl.s | 75 |
16 files changed, 762 insertions, 2 deletions
diff --git a/gas/ChangeLog b/gas/ChangeLog index a40647d..98aa7499 100644 --- a/gas/ChangeLog +++ b/gas/ChangeLog @@ -1,5 +1,24 @@ 2016-11-02 Igor Tsimbalist <igor.v.tsimbalist@intel.com> + * config/tc-i386.c: (cpu_arch) Add .avx512_4vnniw. + (cpu_noarch): Add noavx512_4vnniw. + * doc/c-i386.texi: Document avx512_4vnniw, noavx512_4vnniw. + * testsuite/gas/i386/i386.exp: Run AVX512_4VNNIW tests. + * testsuite/gas/i386/avx512_4vnniwd_vl-intel.d: New test. + * testsuite/gas/i386/avx512_4vnniwd_vl.d: Ditto. + * testsuite/gas/i386/avx512_4vnniwd_vl.s: Ditto. + * testsuite/gas/i386/avx512_4vnniwd-intel.d: Ditto. + * testsuite/gas/i386/avx512_4vnniwd.d: Ditto. + * testsuite/gas/i386/avx512_4vnniwd.s: Ditto. + * testsuite/gas/i386/x86-64-avx512_4vnniwd_vl-intel.d: Ditto. + * testsuite/gas/i386/x86-64-avx512_4vnniwd_vl.d: Ditto. + * testsuite/gas/i386/x86-64-avx512_4vnniwd_vl.s: Ditto. + * testsuite/gas/i386/x86-64-avx512_4vnniwd-intel.d: Ditto. + * testsuite/gas/i386/x86-64-avx512_4vnniwd.d: Ditto. + * testsuite/gas/i386/x86-64-avx512_4vnniwd.s: Ditto. + +2016-11-02 Igor Tsimbalist <igor.v.tsimbalist@intel.com> + * config/tc-i386.c (cpu_arch): Add .avx512_4fmaps. (cpu_noarch): Add noavx512_4fmaps. (process_operands): Handle implicit quad group. diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c index d2ec480..ca26127 100644 --- a/gas/config/tc-i386.c +++ b/gas/config/tc-i386.c @@ -964,6 +964,8 @@ static const arch_entry cpu_arch[] = CPU_AVX512VBMI_FLAGS, 0 }, { STRING_COMMA_LEN (".avx512_4fmaps"), PROCESSOR_UNKNOWN, CPU_AVX512_4FMAPS_FLAGS, 0 }, + { STRING_COMMA_LEN (".avx512_4vnniw"), PROCESSOR_UNKNOWN, + CPU_AVX512_4VNNIW_FLAGS, 0 }, { STRING_COMMA_LEN (".clzero"), PROCESSOR_UNKNOWN, CPU_CLZERO_FLAGS, 0 }, { STRING_COMMA_LEN (".mwaitx"), PROCESSOR_UNKNOWN, @@ -1002,6 +1004,7 @@ static const noarch_entry cpu_noarch[] = { STRING_COMMA_LEN ("noavx512ifma"), CPU_ANY_AVX512IFMA_FLAGS }, { STRING_COMMA_LEN ("noavx512vbmi"), CPU_ANY_AVX512VBMI_FLAGS }, { STRING_COMMA_LEN ("noavx512_4fmaps"), CPU_ANY_AVX512_4FMAPS_FLAGS }, + { STRING_COMMA_LEN ("noavx512_4vnniw"), CPU_ANY_AVX512_4VNNIW_FLAGS }, }; #ifdef I386COFF diff --git a/gas/doc/c-i386.texi b/gas/doc/c-i386.texi index 7aa043e..c3c632d 100644 --- a/gas/doc/c-i386.texi +++ b/gas/doc/c-i386.texi @@ -181,6 +181,7 @@ accept various extension mnemonics. For example, @code{avx512ifma}, @code{avx512vbmi}, @code{avx512_4fmaps}, +@code{avx512_4vnniw}, @code{noavx512f}, @code{noavx512cd}, @code{noavx512er}, @@ -191,6 +192,7 @@ accept various extension mnemonics. For example, @code{noavx512ifma}, @code{noavx512vbmi}, @code{noavx512_4fmaps}, +@code{noavx512_4vnniw}, @code{vmx}, @code{vmfunc}, @code{smx}, @@ -1192,8 +1194,8 @@ supported on the CPU specified. The choices for @var{cpu_type} are: @item @samp{.clflushopt} @tab @samp{.xsavec} @tab @samp{.xsaves} @tab @samp{.se1} @item @samp{.avx512f} @tab @samp{.avx512cd} @tab @samp{.avx512er} @tab @samp{.avx512pf} @item @samp{.avx512vl} @tab @samp{.avx512bw} @tab @samp{.avx512dq} @tab @samp{.avx512ifma} -@item @samp{.avx512vbmi} @tab @samp{.avx512_4fmaps} @tab @samp{.clwb} -@item @samp{.rdpid} @tab @samp{.ptwrite} +@item @samp{.avx512vbmi} @tab @samp{.avx512_4fmaps} @tab @samp{.avx512_4vnniw} +@item @samp{.clwb} @tab @samp{.rdpid} @tab @samp{.ptwrite} @item @samp{.3dnow} @tab @samp{.3dnowa} @tab @samp{.sse4a} @tab @samp{.sse5} @item @samp{.syscall} @tab @samp{.rdtscp} @tab @samp{.svme} @tab @samp{.abm} @item @samp{.lwp} @tab @samp{.fma4} @tab @samp{.xop} @tab @samp{.cx16} diff --git a/gas/testsuite/gas/i386/avx512_4vnniw-intel.d b/gas/testsuite/gas/i386/avx512_4vnniw-intel.d new file mode 100644 index 0000000..ba4299a --- /dev/null +++ b/gas/testsuite/gas/i386/avx512_4vnniw-intel.d @@ -0,0 +1,45 @@ +#objdump: -dw -Mintel +#name: i386 AVX512/4VNNIW insns (Intel disassembly) +#source: avx512_4vnniw.s + +.*: +file format .* + + +Disassembly of section \.text: + +0+ <_start>: +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 09[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 4f 52 09[ ]*vp4dpwssd zmm1\{k7\},zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f cf 52 09[ ]*vp4dpwssd zmm1\{k7\}\{z\},zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a e0 0f 00 00[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a 00 10 00 00[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a 00 f0 ff ff[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a e0 ef ff ff[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 09[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 4f 53 09[ ]*vp4dpwssds zmm1\{k7\},zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f cf 53 09[ ]*vp4dpwssds zmm1\{k7\}\{z\},zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a e0 0f 00 00[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a 00 10 00 00[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a 00 f0 ff ff[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a e0 ef ff ff[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 09[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 09[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 4f 52 09[ ]*vp4dpwssd zmm1\{k7\},zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f cf 52 09[ ]*vp4dpwssd zmm1\{k7\}\{z\},zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a e0 0f 00 00[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a 00 10 00 00[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a 00 f0 ff ff[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a e0 ef ff ff[ ]*vp4dpwssd zmm1,zmm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 09[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 09[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 4f 53 09[ ]*vp4dpwssds zmm1\{k7\},zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f cf 53 09[ ]*vp4dpwssds zmm1\{k7\}\{z\},zmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a e0 0f 00 00[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a 00 10 00 00[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a 00 f0 ff ff[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a e0 ef ff ff[ ]*vp4dpwssds zmm1,zmm4,XMMWORD PTR \[edx-0x1020\] +#pass diff --git a/gas/testsuite/gas/i386/avx512_4vnniw.d b/gas/testsuite/gas/i386/avx512_4vnniw.d new file mode 100644 index 0000000..919f31e --- /dev/null +++ b/gas/testsuite/gas/i386/avx512_4vnniw.d @@ -0,0 +1,45 @@ +#objdump: -dw +#name: i386 AVX512/4VNNIW insns +#source: avx512_4vnniw.s + +.*: +file format .* + + +Disassembly of section \.text: + +0+ <_start>: +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 09[ ]*vp4dpwssd \(%ecx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 4f 52 09[ ]*vp4dpwssd \(%ecx\),%zmm4,%zmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f cf 52 09[ ]*vp4dpwssd \(%ecx\),%zmm4,%zmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%esp,%esi,8\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 09[ ]*vp4dpwssds \(%ecx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 4f 53 09[ ]*vp4dpwssds \(%ecx\),%zmm4,%zmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f cf 53 09[ ]*vp4dpwssds \(%ecx\),%zmm4,%zmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%esp,%esi,8\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 09[ ]*vp4dpwssd \(%ecx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 09[ ]*vp4dpwssd \(%ecx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 4f 52 09[ ]*vp4dpwssd \(%ecx\),%zmm4,%zmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f cf 52 09[ ]*vp4dpwssd \(%ecx\),%zmm4,%zmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%esp,%esi,8\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 09[ ]*vp4dpwssds \(%ecx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 09[ ]*vp4dpwssds \(%ecx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 4f 53 09[ ]*vp4dpwssds \(%ecx\),%zmm4,%zmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f cf 53 09[ ]*vp4dpwssds \(%ecx\),%zmm4,%zmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%esp,%esi,8\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%edx\),%zmm4,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 48 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%edx\),%zmm4,%zmm1 +#pass diff --git a/gas/testsuite/gas/i386/avx512_4vnniw.s b/gas/testsuite/gas/i386/avx512_4vnniw.s new file mode 100644 index 0000000..a67d854 --- /dev/null +++ b/gas/testsuite/gas/i386/avx512_4vnniw.s @@ -0,0 +1,41 @@ +# Check 32bit AVX512_4VNNIW instructions + + .allow_index_reg + .text +_start: + vp4dpwssd (%ecx), %zmm4, %zmm1 # AVX512_4VNNIW + vp4dpwssd (%ecx), %zmm4, %zmm1{%k7} # AVX512_4VNNIW + vp4dpwssd (%ecx), %zmm4, %zmm1{%k7}{z} # AVX512_4VNNIW + vp4dpwssd -123456(%esp,%esi,8), %zmm4, %zmm1 # AVX512_4VNNIW + vp4dpwssd 4064(%edx), %zmm4, %zmm1 # AVX512_4VNNIW Disp8 + vp4dpwssd 4096(%edx), %zmm4, %zmm1 # AVX512_4VNNIW + vp4dpwssd -4096(%edx), %zmm4, %zmm1 # AVX512_4VNNIW Disp8 + vp4dpwssd -4128(%edx), %zmm4, %zmm1 # AVX512_4VNNIW + vp4dpwssds (%ecx), %zmm4, %zmm1 # AVX512_4VNNIW + vp4dpwssds (%ecx), %zmm4, %zmm1{%k7} # AVX512_4VNNIW + vp4dpwssds (%ecx), %zmm4, %zmm1{%k7}{z} # AVX512_4VNNIW + vp4dpwssds -123456(%esp,%esi,8), %zmm4, %zmm1 # AVX512_4VNNIW + vp4dpwssds 4064(%edx), %zmm4, %zmm1 # AVX512_4VNNIW Disp8 + vp4dpwssds 4096(%edx), %zmm4, %zmm1 # AVX512_4VNNIW + vp4dpwssds -4096(%edx), %zmm4, %zmm1 # AVX512_4VNNIW Disp8 + vp4dpwssds -4128(%edx), %zmm4, %zmm1 # AVX512_4VNNIW + + .intel_syntax noprefix + vp4dpwssd zmm1, zmm4, [ecx] # AVX512_4VNNIW + vp4dpwssd zmm1, zmm4, XMMWORD PTR [ecx] # AVX512_4VNNIW + vp4dpwssd zmm1{k7}, zmm4, XMMWORD PTR [ecx] # AVX512_4VNNIW + vp4dpwssd zmm1{k7}{z}, zmm4, XMMWORD PTR [ecx] # AVX512_4VNNIW + vp4dpwssd zmm1, zmm4, XMMWORD PTR [esp+esi*8-123456] # AVX512_4VNNIW + vp4dpwssd zmm1, zmm4, XMMWORD PTR [edx+4064] # AVX512_4VNNIW Disp8 + vp4dpwssd zmm1, zmm4, XMMWORD PTR [edx+4096] # AVX512_4VNNIW + vp4dpwssd zmm1, zmm4, XMMWORD PTR [edx-4096] # AVX512_4VNNIW Disp8 + vp4dpwssd zmm1, zmm4, XMMWORD PTR [edx-4128] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm4, [ecx] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm4, XMMWORD PTR [ecx] # AVX512_4VNNIW + vp4dpwssds zmm1{k7}, zmm4, XMMWORD PTR [ecx] # AVX512_4VNNIW + vp4dpwssds zmm1{k7}{z}, zmm4, XMMWORD PTR [ecx] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm4, XMMWORD PTR [esp+esi*8-123456] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm4, XMMWORD PTR [edx+4064] # AVX512_4VNNIW Disp8 + vp4dpwssds zmm1, zmm4, XMMWORD PTR [edx+4096] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm4, XMMWORD PTR [edx-4096] # AVX512_4VNNIW Disp8 + vp4dpwssds zmm1, zmm4, XMMWORD PTR [edx-4128] # AVX512_4VNNIW diff --git a/gas/testsuite/gas/i386/avx512_4vnniw_vl-intel.d b/gas/testsuite/gas/i386/avx512_4vnniw_vl-intel.d new file mode 100644 index 0000000..a7d3ed9 --- /dev/null +++ b/gas/testsuite/gas/i386/avx512_4vnniw_vl-intel.d @@ -0,0 +1,79 @@ +#objdump: -dw -Mintel +#name: i386 AVX512/4VNNIW_VL insns (Intel disassembly) +#source: avx512_4vnniw_vl.s + +.*: +file format .* + + +Disassembly of section \.text: + +0+ <_start>: +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 09[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 0f 52 09[ ]*vp4dpwssd xmm1\{k7\},xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 8f 52 09[ ]*vp4dpwssd xmm1\{k7\}\{z\},xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a e0 0f 00 00[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a 00 10 00 00[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a 00 f0 ff ff[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a e0 ef ff ff[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 09[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 2f 52 09[ ]*vp4dpwssd ymm1\{k7\},ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f af 52 09[ ]*vp4dpwssd ymm1\{k7\}\{z\},ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a e0 0f 00 00[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a 00 10 00 00[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a 00 f0 ff ff[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a e0 ef ff ff[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 09[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 0f 53 09[ ]*vp4dpwssds xmm1\{k7\},xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 8f 53 09[ ]*vp4dpwssds xmm1\{k7\}\{z\},xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a e0 0f 00 00[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a 00 10 00 00[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a 00 f0 ff ff[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a e0 ef ff ff[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 09[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 2f 53 09[ ]*vp4dpwssds ymm1\{k7\},ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f af 53 09[ ]*vp4dpwssds ymm1\{k7\}\{z\},ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a e0 0f 00 00[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a 00 10 00 00[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a 00 f0 ff ff[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a e0 ef ff ff[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 09[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 09[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 0f 52 09[ ]*vp4dpwssd xmm1\{k7\},xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 8f 52 09[ ]*vp4dpwssd xmm1\{k7\}\{z\},xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a e0 0f 00 00[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a 00 10 00 00[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a 00 f0 ff ff[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a e0 ef ff ff[ ]*vp4dpwssd xmm1,xmm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 09[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 09[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 2f 52 09[ ]*vp4dpwssd ymm1\{k7\},ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f af 52 09[ ]*vp4dpwssd ymm1\{k7\}\{z\},ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a e0 0f 00 00[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a 00 10 00 00[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a 00 f0 ff ff[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a e0 ef ff ff[ ]*vp4dpwssd ymm1,ymm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 09[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 09[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 0f 53 09[ ]*vp4dpwssds xmm1\{k7\},xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 8f 53 09[ ]*vp4dpwssds xmm1\{k7\}\{z\},xmm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a e0 0f 00 00[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a 00 10 00 00[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a 00 f0 ff ff[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a e0 ef ff ff[ ]*vp4dpwssds xmm1,xmm4,XMMWORD PTR \[edx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 09[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 09[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 2f 53 09[ ]*vp4dpwssds ymm1\{k7\},ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f af 53 09[ ]*vp4dpwssds ymm1\{k7\}\{z\},ymm4,XMMWORD PTR \[ecx\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[esp\+esi\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a e0 0f 00 00[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[edx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a 00 10 00 00[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[edx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a 00 f0 ff ff[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[edx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a e0 ef ff ff[ ]*vp4dpwssds ymm1,ymm4,XMMWORD PTR \[edx-0x1020\] +#pass diff --git a/gas/testsuite/gas/i386/avx512_4vnniw_vl.d b/gas/testsuite/gas/i386/avx512_4vnniw_vl.d new file mode 100644 index 0000000..e796321 --- /dev/null +++ b/gas/testsuite/gas/i386/avx512_4vnniw_vl.d @@ -0,0 +1,79 @@ +#objdump: -dw +#name: i386 AVX512/4VNNIW_VL insns +#source: avx512_4vnniw_vl.s + +.*: +file format .* + + +Disassembly of section \.text: + +0+ <_start>: +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 09[ ]*vp4dpwssd \(%ecx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 0f 52 09[ ]*vp4dpwssd \(%ecx\),%xmm4,%xmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 8f 52 09[ ]*vp4dpwssd \(%ecx\),%xmm4,%xmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%esp,%esi,8\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 09[ ]*vp4dpwssd \(%ecx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 2f 52 09[ ]*vp4dpwssd \(%ecx\),%ymm4,%ymm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f af 52 09[ ]*vp4dpwssd \(%ecx\),%ymm4,%ymm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%esp,%esi,8\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 09[ ]*vp4dpwssds \(%ecx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 0f 53 09[ ]*vp4dpwssds \(%ecx\),%xmm4,%xmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 8f 53 09[ ]*vp4dpwssds \(%ecx\),%xmm4,%xmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%esp,%esi,8\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 09[ ]*vp4dpwssds \(%ecx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 2f 53 09[ ]*vp4dpwssds \(%ecx\),%ymm4,%ymm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f af 53 09[ ]*vp4dpwssds \(%ecx\),%ymm4,%ymm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%esp,%esi,8\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 09[ ]*vp4dpwssd \(%ecx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 09[ ]*vp4dpwssd \(%ecx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 0f 52 09[ ]*vp4dpwssd \(%ecx\),%xmm4,%xmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 8f 52 09[ ]*vp4dpwssd \(%ecx\),%xmm4,%xmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%esp,%esi,8\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 09[ ]*vp4dpwssd \(%ecx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 09[ ]*vp4dpwssd \(%ecx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 2f 52 09[ ]*vp4dpwssd \(%ecx\),%ymm4,%ymm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f af 52 09[ ]*vp4dpwssd \(%ecx\),%ymm4,%ymm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8c f4 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%esp,%esi,8\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 09[ ]*vp4dpwssds \(%ecx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 09[ ]*vp4dpwssds \(%ecx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 0f 53 09[ ]*vp4dpwssds \(%ecx\),%xmm4,%xmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 8f 53 09[ ]*vp4dpwssds \(%ecx\),%xmm4,%xmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%esp,%esi,8\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 08 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%edx\),%xmm4,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 09[ ]*vp4dpwssds \(%ecx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 09[ ]*vp4dpwssds \(%ecx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 2f 53 09[ ]*vp4dpwssds \(%ecx\),%ymm4,%ymm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f af 53 09[ ]*vp4dpwssds \(%ecx\),%ymm4,%ymm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8c f4 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%esp,%esi,8\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%edx\),%ymm4,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 5f 28 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%edx\),%ymm4,%ymm1 +#pass diff --git a/gas/testsuite/gas/i386/avx512_4vnniw_vl.s b/gas/testsuite/gas/i386/avx512_4vnniw_vl.s new file mode 100644 index 0000000..dfdd485 --- /dev/null +++ b/gas/testsuite/gas/i386/avx512_4vnniw_vl.s @@ -0,0 +1,75 @@ +# Check 32bit AVX512{_4VNNIW,VL} instructions + + .allow_index_reg + .text +_start: + vp4dpwssd (%ecx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssd (%ecx), %xmm4, %xmm1{%k7} # AVX512{_4VNNIW,VL} + vp4dpwssd (%ecx), %xmm4, %xmm1{%k7}{z} # AVX512{_4VNNIW,VL} + vp4dpwssd -123456(%esp,%esi,8), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssd 4064(%edx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd 4096(%edx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssd -4096(%edx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd -4128(%edx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssd (%ecx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssd (%ecx), %ymm4, %ymm1{%k7} # AVX512{_4VNNIW,VL} + vp4dpwssd (%ecx), %ymm4, %ymm1{%k7}{z} # AVX512{_4VNNIW,VL} + vp4dpwssd -123456(%esp,%esi,8), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssd 4064(%edx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd 4096(%edx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssd -4096(%edx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd -4128(%edx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssds (%ecx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssds (%ecx), %xmm4, %xmm1{%k7} # AVX512{_4VNNIW,VL} + vp4dpwssds (%ecx), %xmm4, %xmm1{%k7}{z} # AVX512{_4VNNIW,VL} + vp4dpwssds -123456(%esp,%esi,8), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssds 4064(%edx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds 4096(%edx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssds -4096(%edx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds -4128(%edx), %xmm4, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssds (%ecx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssds (%ecx), %ymm4, %ymm1{%k7} # AVX512{_4VNNIW,VL} + vp4dpwssds (%ecx), %ymm4, %ymm1{%k7}{z} # AVX512{_4VNNIW,VL} + vp4dpwssds -123456(%esp,%esi,8), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssds 4064(%edx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds 4096(%edx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssds -4096(%edx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds -4128(%edx), %ymm4, %ymm1 # AVX512{_4VNNIW,VL} + + .intel_syntax noprefix + vp4dpwssd xmm1, xmm4, [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1, xmm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1{k7}, xmm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1{k7}{z}, xmm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1, xmm4, XMMWORD PTR [esp+esi*8-123456] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1, xmm4, XMMWORD PTR [edx+4064] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd xmm1, xmm4, XMMWORD PTR [edx+4096] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1, xmm4, XMMWORD PTR [edx-4096] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd xmm1, xmm4, XMMWORD PTR [edx-4128] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm4, [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1{k7}, ymm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1{k7}{z}, ymm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm4, XMMWORD PTR [esp+esi*8-123456] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm4, XMMWORD PTR [edx+4064] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd ymm1, ymm4, XMMWORD PTR [edx+4096] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm4, XMMWORD PTR [edx-4096] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd ymm1, ymm4, XMMWORD PTR [edx-4128] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm4, [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1{k7}, xmm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1{k7}{z}, xmm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm4, XMMWORD PTR [esp+esi*8-123456] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm4, XMMWORD PTR [edx+4064] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds xmm1, xmm4, XMMWORD PTR [edx+4096] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm4, XMMWORD PTR [edx-4096] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds xmm1, xmm4, XMMWORD PTR [edx-4128] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm4, [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1{k7}, ymm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1{k7}{z}, ymm4, XMMWORD PTR [ecx] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm4, XMMWORD PTR [esp+esi*8-123456] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm4, XMMWORD PTR [edx+4064] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds ymm1, ymm4, XMMWORD PTR [edx+4096] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm4, XMMWORD PTR [edx-4096] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds ymm1, ymm4, XMMWORD PTR [edx-4128] # AVX512{_4VNNIW,VL} diff --git a/gas/testsuite/gas/i386/i386.exp b/gas/testsuite/gas/i386/i386.exp index 89e132a..11c342a 100644 --- a/gas/testsuite/gas/i386/i386.exp +++ b/gas/testsuite/gas/i386/i386.exp @@ -363,6 +363,10 @@ if [expr ([istarget "i*86-*-*"] || [istarget "x86_64-*-*"]) && [gas_32_check]] run_dump_test "avx512_4fmaps_vl-intel" run_list_test "avx512_4fmaps-warn" run_list_test "avx512_4fmaps_vl-warn" + run_dump_test "avx512_4vnniw" + run_dump_test "avx512_4vnniw-intel" + run_dump_test "avx512_4vnniw_vl" + run_dump_test "avx512_4vnniw_vl-intel" run_dump_test "clzero" run_dump_test "disassem" run_dump_test "mwaitx-bdver4" @@ -771,6 +775,10 @@ if [expr ([istarget "i*86-*-*"] || [istarget "x86_64-*-*"]) && [gas_64_check]] t run_dump_test "x86-64-avx512_4fmaps_vl-intel" run_list_test "x86-64-avx512_4fmaps-warn" run_list_test "x86-64-avx512_4fmaps_vl-warn" + run_dump_test "x86-64-avx512_4vnniw" + run_dump_test "x86-64-avx512_4vnniw-intel" + run_dump_test "x86-64-avx512_4vnniw_vl" + run_dump_test "x86-64-avx512_4vnniw_vl-intel" run_dump_test "x86-64-clzero" run_dump_test "x86-64-mwaitx-bdver4" run_list_test "x86-64-mwaitx-reg" diff --git a/gas/testsuite/gas/i386/x86-64-avx512_4vnniw-intel.d b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw-intel.d new file mode 100644 index 0000000..2165353 --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw-intel.d @@ -0,0 +1,45 @@ +#objdump: -dw -Mintel +#name: x86_64 AVX512/4VNNIW insns (Intel disassembly) +#source: x86-64-avx512_4vnniw.s + +.*: +file format .* + + +Disassembly of section \.text: + +0+ <_start>: +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 09[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 4f 52 09[ ]*vp4dpwssd zmm1\{k7\},zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f cf 52 09[ ]*vp4dpwssd zmm1\{k7\}\{z\},zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 48 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a e0 0f 00 00[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a 00 10 00 00[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a 00 f0 ff ff[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a e0 ef ff ff[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 09[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 4f 53 09[ ]*vp4dpwssds zmm1\{k7\},zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f cf 53 09[ ]*vp4dpwssds zmm1\{k7\}\{z\},zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 48 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a e0 0f 00 00[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a 00 10 00 00[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a 00 f0 ff ff[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a e0 ef ff ff[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 09[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 09[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 4f 52 09[ ]*vp4dpwssd zmm1\{k7\},zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f cf 52 09[ ]*vp4dpwssd zmm1\{k7\}\{z\},zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 48 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a e0 0f 00 00[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a 00 10 00 00[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a 00 f0 ff ff[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a e0 ef ff ff[ ]*vp4dpwssd zmm1,zmm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 09[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 09[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 4f 53 09[ ]*vp4dpwssds zmm1\{k7\},zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f cf 53 09[ ]*vp4dpwssds zmm1\{k7\}\{z\},zmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 48 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a e0 0f 00 00[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a 00 10 00 00[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a 00 f0 ff ff[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a e0 ef ff ff[ ]*vp4dpwssds zmm1,zmm8,XMMWORD PTR \[rdx-0x1020\] +#pass diff --git a/gas/testsuite/gas/i386/x86-64-avx512_4vnniw.d b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw.d new file mode 100644 index 0000000..1938cfe --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw.d @@ -0,0 +1,45 @@ +#objdump: -dw +#name: x86_64 AVX512/4VNNIW insns +#source: x86-64-avx512_4vnniw.s + +.*: +file format .* + + +Disassembly of section \.text: + +0+ <_start>: +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 09[ ]*vp4dpwssd \(%rcx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 4f 52 09[ ]*vp4dpwssd \(%rcx\),%zmm8,%zmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f cf 52 09[ ]*vp4dpwssd \(%rcx\),%zmm8,%zmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 48 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%rax,%r14,8\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 09[ ]*vp4dpwssds \(%rcx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 4f 53 09[ ]*vp4dpwssds \(%rcx\),%zmm8,%zmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f cf 53 09[ ]*vp4dpwssds \(%rcx\),%zmm8,%zmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 48 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%rax,%r14,8\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 09[ ]*vp4dpwssd \(%rcx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 09[ ]*vp4dpwssd \(%rcx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 4f 52 09[ ]*vp4dpwssd \(%rcx\),%zmm8,%zmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f cf 52 09[ ]*vp4dpwssd \(%rcx\),%zmm8,%zmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 48 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%rax,%r14,8\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 09[ ]*vp4dpwssds \(%rcx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 09[ ]*vp4dpwssds \(%rcx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 4f 53 09[ ]*vp4dpwssds \(%rcx\),%zmm8,%zmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f cf 53 09[ ]*vp4dpwssds \(%rcx\),%zmm8,%zmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 48 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%rax,%r14,8\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%rdx\),%zmm8,%zmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 48 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%rdx\),%zmm8,%zmm1 +#pass diff --git a/gas/testsuite/gas/i386/x86-64-avx512_4vnniw.s b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw.s new file mode 100644 index 0000000..b4295f9 --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw.s @@ -0,0 +1,41 @@ +# Check 64bit AVX512_4VNNIW instructions + + .allow_index_reg + .text +_start: + vp4dpwssd (%rcx), %zmm8, %zmm1 # AVX512_4VNNIW + vp4dpwssd (%rcx), %zmm8, %zmm1{%k7} # AVX512_4VNNIW + vp4dpwssd (%rcx), %zmm8, %zmm1{%k7}{z} # AVX512_4VNNIW + vp4dpwssd -123456(%rax,%r14,8), %zmm8, %zmm1 # AVX512_4VNNIW + vp4dpwssd 4064(%rdx), %zmm8, %zmm1 # AVX512_4VNNIW Disp8 + vp4dpwssd 4096(%rdx), %zmm8, %zmm1 # AVX512_4VNNIW + vp4dpwssd -4096(%rdx), %zmm8, %zmm1 # AVX512_4VNNIW Disp8 + vp4dpwssd -4128(%rdx), %zmm8, %zmm1 # AVX512_4VNNIW + vp4dpwssds (%rcx), %zmm8, %zmm1 # AVX512_4VNNIW + vp4dpwssds (%rcx), %zmm8, %zmm1{%k7} # AVX512_4VNNIW + vp4dpwssds (%rcx), %zmm8, %zmm1{%k7}{z} # AVX512_4VNNIW + vp4dpwssds -123456(%rax,%r14,8), %zmm8, %zmm1 # AVX512_4VNNIW + vp4dpwssds 4064(%rdx), %zmm8, %zmm1 # AVX512_4VNNIW Disp8 + vp4dpwssds 4096(%rdx), %zmm8, %zmm1 # AVX512_4VNNIW + vp4dpwssds -4096(%rdx), %zmm8, %zmm1 # AVX512_4VNNIW Disp8 + vp4dpwssds -4128(%rdx), %zmm8, %zmm1 # AVX512_4VNNIW + + .intel_syntax noprefix + vp4dpwssd zmm1, zmm8, [rcx] # AVX512_4VNNIW + vp4dpwssd zmm1, zmm8, XMMWORD PTR [rcx] # AVX512_4VNNIW + vp4dpwssd zmm1{k7}, zmm8, XMMWORD PTR [rcx] # AVX512_4VNNIW + vp4dpwssd zmm1{k7}{z}, zmm8, XMMWORD PTR [rcx] # AVX512_4VNNIW + vp4dpwssd zmm1, zmm8, XMMWORD PTR [rax+r14*8-123456] # AVX512_4VNNIW + vp4dpwssd zmm1, zmm8, XMMWORD PTR [rdx+4064] # AVX512_4VNNIW Disp8 + vp4dpwssd zmm1, zmm8, XMMWORD PTR [rdx+4096] # AVX512_4VNNIW + vp4dpwssd zmm1, zmm8, XMMWORD PTR [rdx-4096] # AVX512_4VNNIW Disp8 + vp4dpwssd zmm1, zmm8, XMMWORD PTR [rdx-4128] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm8, [rcx] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm8, XMMWORD PTR [rcx] # AVX512_4VNNIW + vp4dpwssds zmm1{k7}, zmm8, XMMWORD PTR [rcx] # AVX512_4VNNIW + vp4dpwssds zmm1{k7}{z}, zmm8, XMMWORD PTR [rcx] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm8, XMMWORD PTR [rax+r14*8-123456] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm8, XMMWORD PTR [rdx+4064] # AVX512_4VNNIW Disp8 + vp4dpwssds zmm1, zmm8, XMMWORD PTR [rdx+4096] # AVX512_4VNNIW + vp4dpwssds zmm1, zmm8, XMMWORD PTR [rdx-4096] # AVX512_4VNNIW Disp8 + vp4dpwssds zmm1, zmm8, XMMWORD PTR [rdx-4128] # AVX512_4VNNIW diff --git a/gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl-intel.d b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl-intel.d new file mode 100644 index 0000000..d4a7a95 --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl-intel.d @@ -0,0 +1,79 @@ +#objdump: -dw -Mintel +#name: x86_64 AVX512/4VNNIW_VL insns (Intel disassembly) +#source: x86-64-avx512_4vnniw_vl.s + +.*: +file format .* + + +Disassembly of section \.text: + +0+ <_start>: +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 09[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 0f 52 09[ ]*vp4dpwssd xmm1\{k7\},xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 8f 52 09[ ]*vp4dpwssd xmm1\{k7\}\{z\},xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 08 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a e0 0f 00 00[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a 00 10 00 00[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a 00 f0 ff ff[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a e0 ef ff ff[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 09[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 2f 52 09[ ]*vp4dpwssd ymm1\{k7\},ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f af 52 09[ ]*vp4dpwssd ymm1\{k7\}\{z\},ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 28 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a e0 0f 00 00[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a 00 10 00 00[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a 00 f0 ff ff[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a e0 ef ff ff[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 09[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 0f 53 09[ ]*vp4dpwssds xmm1\{k7\},xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 8f 53 09[ ]*vp4dpwssds xmm1\{k7\}\{z\},xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 08 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a e0 0f 00 00[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a 00 10 00 00[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a 00 f0 ff ff[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a e0 ef ff ff[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 09[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 2f 53 09[ ]*vp4dpwssds ymm1\{k7\},ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f af 53 09[ ]*vp4dpwssds ymm1\{k7\}\{z\},ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 28 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a e0 0f 00 00[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a 00 10 00 00[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a 00 f0 ff ff[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a e0 ef ff ff[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 09[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 09[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 0f 52 09[ ]*vp4dpwssd xmm1\{k7\},xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 8f 52 09[ ]*vp4dpwssd xmm1\{k7\}\{z\},xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 08 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a e0 0f 00 00[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a 00 10 00 00[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a 00 f0 ff ff[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a e0 ef ff ff[ ]*vp4dpwssd xmm1,xmm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 09[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 09[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 2f 52 09[ ]*vp4dpwssd ymm1\{k7\},ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f af 52 09[ ]*vp4dpwssd ymm1\{k7\}\{z\},ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 28 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a e0 0f 00 00[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a 00 10 00 00[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a 00 f0 ff ff[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a e0 ef ff ff[ ]*vp4dpwssd ymm1,ymm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 09[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 09[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 0f 53 09[ ]*vp4dpwssds xmm1\{k7\},xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 8f 53 09[ ]*vp4dpwssds xmm1\{k7\}\{z\},xmm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 08 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a e0 0f 00 00[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a 00 10 00 00[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a 00 f0 ff ff[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a e0 ef ff ff[ ]*vp4dpwssds xmm1,xmm8,XMMWORD PTR \[rdx-0x1020\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 09[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 09[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 2f 53 09[ ]*vp4dpwssds ymm1\{k7\},ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f af 53 09[ ]*vp4dpwssds ymm1\{k7\}\{z\},ymm8,XMMWORD PTR \[rcx\] +[ ]*[a-f0-9]+:[ ]*62 b2 3f 28 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rax\+r14\*8-0x1e240\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a e0 0f 00 00[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rdx\+0xfe0\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a 00 10 00 00[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rdx\+0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a 00 f0 ff ff[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rdx-0x1000\] +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a e0 ef ff ff[ ]*vp4dpwssds ymm1,ymm8,XMMWORD PTR \[rdx-0x1020\] +#pass diff --git a/gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl.d b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl.d new file mode 100644 index 0000000..df0f522 --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl.d @@ -0,0 +1,79 @@ +#objdump: -dw +#name: x86_64 AVX512/4VNNIW_VL insns +#source: x86-64-avx512_4vnniw_vl.s + +.*: +file format .* + + +Disassembly of section \.text: + +0+ <_start>: +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 09[ ]*vp4dpwssd \(%rcx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 0f 52 09[ ]*vp4dpwssd \(%rcx\),%xmm8,%xmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f 8f 52 09[ ]*vp4dpwssd \(%rcx\),%xmm8,%xmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 08 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%rax,%r14,8\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 09[ ]*vp4dpwssd \(%rcx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 2f 52 09[ ]*vp4dpwssd \(%rcx\),%ymm8,%ymm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f af 52 09[ ]*vp4dpwssd \(%rcx\),%ymm8,%ymm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 28 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%rax,%r14,8\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 09[ ]*vp4dpwssds \(%rcx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 0f 53 09[ ]*vp4dpwssds \(%rcx\),%xmm8,%xmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f 8f 53 09[ ]*vp4dpwssds \(%rcx\),%xmm8,%xmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 08 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%rax,%r14,8\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 09[ ]*vp4dpwssds \(%rcx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 2f 53 09[ ]*vp4dpwssds \(%rcx\),%ymm8,%ymm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f af 53 09[ ]*vp4dpwssds \(%rcx\),%ymm8,%ymm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 28 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%rax,%r14,8\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 09[ ]*vp4dpwssd \(%rcx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 09[ ]*vp4dpwssd \(%rcx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 0f 52 09[ ]*vp4dpwssd \(%rcx\),%xmm8,%xmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f 8f 52 09[ ]*vp4dpwssd \(%rcx\),%xmm8,%xmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 08 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%rax,%r14,8\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 09[ ]*vp4dpwssd \(%rcx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 09[ ]*vp4dpwssd \(%rcx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 2f 52 09[ ]*vp4dpwssd \(%rcx\),%ymm8,%ymm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f af 52 09[ ]*vp4dpwssd \(%rcx\),%ymm8,%ymm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 28 52 8c f0 c0 1d fe ff[ ]*vp4dpwssd -0x1e240\(%rax,%r14,8\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a e0 0f 00 00[ ]*vp4dpwssd 0xfe0\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a 00 10 00 00[ ]*vp4dpwssd 0x1000\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a 00 f0 ff ff[ ]*vp4dpwssd -0x1000\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 52 8a e0 ef ff ff[ ]*vp4dpwssd -0x1020\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 09[ ]*vp4dpwssds \(%rcx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 09[ ]*vp4dpwssds \(%rcx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 0f 53 09[ ]*vp4dpwssds \(%rcx\),%xmm8,%xmm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f 8f 53 09[ ]*vp4dpwssds \(%rcx\),%xmm8,%xmm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 08 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%rax,%r14,8\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 08 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%rdx\),%xmm8,%xmm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 09[ ]*vp4dpwssds \(%rcx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 09[ ]*vp4dpwssds \(%rcx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 2f 53 09[ ]*vp4dpwssds \(%rcx\),%ymm8,%ymm1\{%k7\} +[ ]*[a-f0-9]+:[ ]*62 f2 3f af 53 09[ ]*vp4dpwssds \(%rcx\),%ymm8,%ymm1\{%k7\}\{z\} +[ ]*[a-f0-9]+:[ ]*62 b2 3f 28 53 8c f0 c0 1d fe ff[ ]*vp4dpwssds -0x1e240\(%rax,%r14,8\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a e0 0f 00 00[ ]*vp4dpwssds 0xfe0\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a 00 10 00 00[ ]*vp4dpwssds 0x1000\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a 00 f0 ff ff[ ]*vp4dpwssds -0x1000\(%rdx\),%ymm8,%ymm1 +[ ]*[a-f0-9]+:[ ]*62 f2 3f 28 53 8a e0 ef ff ff[ ]*vp4dpwssds -0x1020\(%rdx\),%ymm8,%ymm1 +#pass diff --git a/gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl.s b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl.s new file mode 100644 index 0000000..5f1a046 --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-avx512_4vnniw_vl.s @@ -0,0 +1,75 @@ +# Check 64bit AVX512{_4VNNIW,VL} instructions + + .allow_index_reg + .text +_start: + vp4dpwssd (%rcx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssd (%rcx), %xmm8, %xmm1{%k7} # AVX512{_4VNNIW,VL} + vp4dpwssd (%rcx), %xmm8, %xmm1{%k7}{z} # AVX512{_4VNNIW,VL} + vp4dpwssd -123456(%rax,%r14,8), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssd 4064(%rdx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd 4096(%rdx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssd -4096(%rdx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd -4128(%rdx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssd (%rcx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssd (%rcx), %ymm8, %ymm1{%k7} # AVX512{_4VNNIW,VL} + vp4dpwssd (%rcx), %ymm8, %ymm1{%k7}{z} # AVX512{_4VNNIW,VL} + vp4dpwssd -123456(%rax,%r14,8), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssd 4064(%rdx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd 4096(%rdx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssd -4096(%rdx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd -4128(%rdx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssds (%rcx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssds (%rcx), %xmm8, %xmm1{%k7} # AVX512{_4VNNIW,VL} + vp4dpwssds (%rcx), %xmm8, %xmm1{%k7}{z} # AVX512{_4VNNIW,VL} + vp4dpwssds -123456(%rax,%r14,8), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssds 4064(%rdx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds 4096(%rdx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssds -4096(%rdx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds -4128(%rdx), %xmm8, %xmm1 # AVX512{_4VNNIW,VL} + vp4dpwssds (%rcx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssds (%rcx), %ymm8, %ymm1{%k7} # AVX512{_4VNNIW,VL} + vp4dpwssds (%rcx), %ymm8, %ymm1{%k7}{z} # AVX512{_4VNNIW,VL} + vp4dpwssds -123456(%rax,%r14,8), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssds 4064(%rdx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds 4096(%rdx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} + vp4dpwssds -4096(%rdx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds -4128(%rdx), %ymm8, %ymm1 # AVX512{_4VNNIW,VL} + + .intel_syntax noprefix + vp4dpwssd xmm1, xmm8, [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1, xmm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1{k7}, xmm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1{k7}{z}, xmm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1, xmm8, XMMWORD PTR [rax+r14*8-123456] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1, xmm8, XMMWORD PTR [rdx+4064] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd xmm1, xmm8, XMMWORD PTR [rdx+4096] # AVX512{_4VNNIW,VL} + vp4dpwssd xmm1, xmm8, XMMWORD PTR [rdx-4096] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd xmm1, xmm8, XMMWORD PTR [rdx-4128] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm8, [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1{k7}, ymm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1{k7}{z}, ymm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm8, XMMWORD PTR [rax+r14*8-123456] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm8, XMMWORD PTR [rdx+4064] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd ymm1, ymm8, XMMWORD PTR [rdx+4096] # AVX512{_4VNNIW,VL} + vp4dpwssd ymm1, ymm8, XMMWORD PTR [rdx-4096] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssd ymm1, ymm8, XMMWORD PTR [rdx-4128] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm8, [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1{k7}, xmm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1{k7}{z}, xmm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm8, XMMWORD PTR [rax+r14*8-123456] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm8, XMMWORD PTR [rdx+4064] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds xmm1, xmm8, XMMWORD PTR [rdx+4096] # AVX512{_4VNNIW,VL} + vp4dpwssds xmm1, xmm8, XMMWORD PTR [rdx-4096] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds xmm1, xmm8, XMMWORD PTR [rdx-4128] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm8, [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1{k7}, ymm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1{k7}{z}, ymm8, XMMWORD PTR [rcx] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm8, XMMWORD PTR [rax+r14*8-123456] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm8, XMMWORD PTR [rdx+4064] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds ymm1, ymm8, XMMWORD PTR [rdx+4096] # AVX512{_4VNNIW,VL} + vp4dpwssds ymm1, ymm8, XMMWORD PTR [rdx-4096] # AVX512{_4VNNIW,VL} Disp8 + vp4dpwssds ymm1, ymm8, XMMWORD PTR [rdx-4128] # AVX512{_4VNNIW,VL} |