diff options
author | H.J. Lu <hjl.tools@gmail.com> | 2018-03-08 19:57:35 -0800 |
---|---|---|
committer | H.J. Lu <hjl.tools@gmail.com> | 2018-03-08 19:57:48 -0800 |
commit | 0089daceaba4338046932e65a1b5882065416633 (patch) | |
tree | 779e5859464843e858b513e0eedbec3c07c949a6 /gas | |
parent | 567a3e54d211ab8d09119f99fed10b57db895450 (diff) | |
download | gdb-0089daceaba4338046932e65a1b5882065416633.zip gdb-0089daceaba4338046932e65a1b5882065416633.tar.gz gdb-0089daceaba4338046932e65a1b5882065416633.tar.bz2 |
x86: Optimize with EVEX128 encoding for AVX512VL
We can optimize AVX512 instructions with EVEX128 only if AVX512VL is
enabled:
1. Instruction is an AVX512VL instruction. Or
2. AVX512VL is enabled explicitly by -march=+avx512vl/".arch .avx512vl".
We should optimize EVEX instructions with EVEX128 encoding when pseudo
{evex} prefix is used.
* config/tc-i386.c (set_cpu_arch): Set cpu_arch_isa_flags.
(md_parse_option): Likewise.
(optimize_encoding): Check i.tm.cpu_flags and cpu_arch_isa_flags
for cpuavx512vl instead of cpu_arch_flags. Optimize EVEX with
EVEX128 when EVEX encoding is required.
* testsuite/gas/i386/i386.exp: Run optimize-4, optimize-5,
x86-64-optimize-5 and x86-64-optimize-6.
* testsuite/gas/i386/optimize-1.d: Updated.
* testsuite/gas/i386/x86-64-optimize-2.d: Likewise.
* testsuite/gas/i386/optimize-4.d: New file.
* testsuite/gas/i386/optimize-4.s: Likewise.
* testsuite/gas/i386/optimize-5.d: Likewise.
* testsuite/gas/i386/optimize-5.s: Likewise.
* testsuite/gas/i386/x86-64-optimize-5.d: Likewise.
* testsuite/gas/i386/x86-64-optimize-5.s: Likewise.
* testsuite/gas/i386/x86-64-optimize-6.d: Likewise.
* testsuite/gas/i386/x86-64-optimize-6.s: Likewise.
Diffstat (limited to 'gas')
-rw-r--r-- | gas/ChangeLog | 20 | ||||
-rw-r--r-- | gas/config/tc-i386.c | 19 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/i386.exp | 4 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/optimize-1.d | 24 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/optimize-4.d | 63 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/optimize-4.s | 6 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/optimize-5.d | 63 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/optimize-5.s | 8 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-optimize-2.d | 72 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-optimize-5.d | 111 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-optimize-5.s | 6 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-optimize-6.d | 111 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-optimize-6.s | 8 |
13 files changed, 459 insertions, 56 deletions
diff --git a/gas/ChangeLog b/gas/ChangeLog index 7c37f13..0cf0108 100644 --- a/gas/ChangeLog +++ b/gas/ChangeLog @@ -1,5 +1,25 @@ 2018-03-08 H.J. Lu <hongjiu.lu@intel.com> + * config/tc-i386.c (set_cpu_arch): Set cpu_arch_isa_flags. + (md_parse_option): Likewise. + (optimize_encoding): Check i.tm.cpu_flags and cpu_arch_isa_flags + for cpuavx512vl instead of cpu_arch_flags. Optimize EVEX with + EVEX128 when EVEX encoding is required. + * testsuite/gas/i386/i386.exp: Run optimize-4, optimize-5, + x86-64-optimize-5 and x86-64-optimize-6. + * testsuite/gas/i386/optimize-1.d: Updated. + * testsuite/gas/i386/x86-64-optimize-2.d: Likewise. + * testsuite/gas/i386/optimize-4.d: New file. + * testsuite/gas/i386/optimize-4.s: Likewise. + * testsuite/gas/i386/optimize-5.d: Likewise. + * testsuite/gas/i386/optimize-5.s: Likewise. + * testsuite/gas/i386/x86-64-optimize-5.d: Likewise. + * testsuite/gas/i386/x86-64-optimize-5.s: Likewise. + * testsuite/gas/i386/x86-64-optimize-6.d: Likewise. + * testsuite/gas/i386/x86-64-optimize-6.s: Likewise. + +2018-03-08 H.J. Lu <hongjiu.lu@intel.com> + * config/tc-i386.c (optimize_encoding): Also encode "clr reg64" as "xor reg32, reg32". * testsuite/gas/i386/x86-64-optimize-1.s: Add "clr reg64" tests. diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c index 1c64d08..ef7b64b 100644 --- a/gas/config/tc-i386.c +++ b/gas/config/tc-i386.c @@ -2622,6 +2622,10 @@ set_cpu_arch (int dummy ATTRIBUTE_UNUSED) cpu_arch_flags = flags; cpu_arch_isa_flags = flags; } + else + cpu_arch_isa_flags + = cpu_flags_or (cpu_arch_isa_flags, + cpu_arch[j].flags); (void) restore_line_pointer (e); demand_empty_rest_of_line (); return; @@ -3871,7 +3875,8 @@ optimize_encoding (void) || (!i.mask && !i.rounding && is_evex_encoding (&i.tm) - && cpu_arch_flags.bitfield.cpuavx512vl)) + && (i.tm.cpu_flags.bitfield.cpuavx512vl + || cpu_arch_isa_flags.bitfield.cpuavx512vl))) && ((i.tm.base_opcode == 0x55 || i.tm.base_opcode == 0x6655 || i.tm.base_opcode == 0x66df @@ -3915,13 +3920,7 @@ optimize_encoding (void) */ if (is_evex_encoding (&i.tm)) { - /* If only lower 16 vector registers are used, we can use - VEX encoding. */ - for (j = 0; j < 3; j++) - if (register_number (i.op[j].regs) > 15) - break; - - if (j < 3) + if (i.vec_encoding == vex_encoding_evex) i.tm.opcode_modifier.evex = EVEX128; else { @@ -10524,6 +10523,10 @@ md_parse_option (int c, const char *arg) cpu_arch_flags = flags; cpu_arch_isa_flags = flags; } + else + cpu_arch_isa_flags + = cpu_flags_or (cpu_arch_isa_flags, + cpu_arch[j].flags); break; } } diff --git a/gas/testsuite/gas/i386/i386.exp b/gas/testsuite/gas/i386/i386.exp index f28e6a9..fd87562 100644 --- a/gas/testsuite/gas/i386/i386.exp +++ b/gas/testsuite/gas/i386/i386.exp @@ -442,6 +442,8 @@ if [expr ([istarget "i*86-*-*"] || [istarget "x86_64-*-*"]) && [gas_32_check]] run_dump_test "optimize-1" run_dump_test "optimize-2" run_dump_test "optimize-3" + run_dump_test "optimize-4" + run_dump_test "optimize-5" # These tests require support for 8 and 16 bit relocs, # so we only run them for ELF and COFF targets. @@ -928,6 +930,8 @@ if [expr ([istarget "i*86-*-*"] || [istarget "x86_64-*-*"]) && [gas_64_check]] t run_dump_test "x86-64-optimize-2" run_dump_test "x86-64-optimize-3" run_dump_test "x86-64-optimize-4" + run_dump_test "x86-64-optimize-5" + run_dump_test "x86-64-optimize-6" if { ![istarget "*-*-aix*"] && ![istarget "*-*-beos*"] diff --git a/gas/testsuite/gas/i386/optimize-1.d b/gas/testsuite/gas/i386/optimize-1.d index 3ea6e75..f7da296 100644 --- a/gas/testsuite/gas/i386/optimize-1.d +++ b/gas/testsuite/gas/i386/optimize-1.d @@ -10,52 +10,52 @@ Disassembly of section .text: 0+ <_start>: +[a-f0-9]+: 62 f1 f5 4f 55 e9 vandnpd %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 f5 af 55 e9 vandnpd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 55 e9 vandnpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 48 55 e9 vandnpd %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 55 e9 vandnpd %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 74 4f 55 e9 vandnps %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 74 af 55 e9 vandnps %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f0 55 e9 vandnps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 74 48 55 e9 vandnps %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f0 55 e9 vandnps %xmm1,%xmm1,%xmm5 +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 75 4f df e9 vpandnd %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 75 af df e9 vpandnd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 48 df e9 vpandnd %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 f5 4f df e9 vpandnq %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 f5 af df e9 vpandnq %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 48 df e9 vpandnq %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 f5 4f 57 e9 vxorpd %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 f5 af 57 e9 vxorpd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 57 e9 vxorpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 48 57 e9 vxorpd %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 57 e9 vxorpd %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 74 4f 57 e9 vxorps %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 74 af 57 e9 vxorps %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f0 57 e9 vxorps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 74 48 57 e9 vxorps %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f0 57 e9 vxorps %xmm1,%xmm1,%xmm5 +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 75 4f ef e9 vpxord %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 75 af ef e9 vpxord %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 48 ef e9 vpxord %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 f5 4f ef e9 vpxorq %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 f5 af ef e9 vpxorq %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 48 ef e9 vpxorq %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 75 4f f8 e9 vpsubb %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 75 af f8 e9 vpsubb %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 f8 e9 vpsubb %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 48 f8 e9 vpsubb %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 f8 e9 vpsubb %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 75 4f f9 e9 vpsubw %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 75 af f9 e9 vpsubw %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 f9 e9 vpsubw %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 48 f9 e9 vpsubw %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 f9 e9 vpsubw %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 75 4f fa e9 vpsubd %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 75 af fa e9 vpsubd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 fa e9 vpsubd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 48 fa e9 vpsubd %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 fa e9 vpsubd %xmm1,%xmm1,%xmm5 +[a-f0-9]+: 62 f1 f5 4f fb e9 vpsubq %zmm1,%zmm1,%zmm5\{%k7\} +[a-f0-9]+: 62 f1 f5 af fb e9 vpsubq %ymm1,%ymm1,%ymm5\{%k7\}\{z\} - +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 48 fb e9 vpsubq %zmm1,%zmm1,%zmm5 +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5 #pass diff --git a/gas/testsuite/gas/i386/optimize-4.d b/gas/testsuite/gas/i386/optimize-4.d new file mode 100644 index 0000000..8c1cea5 --- /dev/null +++ b/gas/testsuite/gas/i386/optimize-4.d @@ -0,0 +1,63 @@ +#as: -O2 -march=+avx512vl -I${srcdir}/$subdir +#objdump: -drw +#name: optimized encoding 4 with -O2 + +.*: +file format .* + + +Disassembly of section .text: + +0+ <_start>: + +[a-f0-9]+: 62 f1 f5 4f 55 e9 vandnpd %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af 55 e9 vandnpd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 55 e9 vandnpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 55 e9 vandnpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 74 4f 55 e9 vandnps %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 74 af 55 e9 vandnps %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f0 55 e9 vandnps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f0 55 e9 vandnps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f df e9 vpandnd %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af df e9 vpandnd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 4f df e9 vpandnq %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af df e9 vpandnq %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 4f 57 e9 vxorpd %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af 57 e9 vxorpd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 57 e9 vxorpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 57 e9 vxorpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 74 4f 57 e9 vxorps %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 74 af 57 e9 vxorps %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f0 57 e9 vxorps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f0 57 e9 vxorps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f ef e9 vpxord %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af ef e9 vpxord %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 4f ef e9 vpxorq %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af ef e9 vpxorq %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f f8 e9 vpsubb %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af f8 e9 vpsubb %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 f8 e9 vpsubb %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 f8 e9 vpsubb %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f f9 e9 vpsubw %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af f9 e9 vpsubw %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 f9 e9 vpsubw %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 f9 e9 vpsubw %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f fa e9 vpsubd %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af fa e9 vpsubd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 fa e9 vpsubd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 fa e9 vpsubd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 4f fb e9 vpsubq %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af fb e9 vpsubq %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 08 55 e9 vandnpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 08 55 e9 vandnpd %xmm1,%xmm1,%xmm5 +#pass diff --git a/gas/testsuite/gas/i386/optimize-4.s b/gas/testsuite/gas/i386/optimize-4.s new file mode 100644 index 0000000..b44c44a --- /dev/null +++ b/gas/testsuite/gas/i386/optimize-4.s @@ -0,0 +1,6 @@ +# Check instructions with optimized encoding + +.include "optimize-1.s" + + {evex} vandnpd %zmm1, %zmm1, %zmm5 + {evex} vandnpd %ymm1, %ymm1, %ymm5 diff --git a/gas/testsuite/gas/i386/optimize-5.d b/gas/testsuite/gas/i386/optimize-5.d new file mode 100644 index 0000000..13cd578 --- /dev/null +++ b/gas/testsuite/gas/i386/optimize-5.d @@ -0,0 +1,63 @@ +#as: -O2 -I${srcdir}/$subdir +#objdump: -drw +#name: optimized encoding 5 with -O2 + +.*: +file format .* + + +Disassembly of section .text: + +0+ <_start>: + +[a-f0-9]+: 62 f1 f5 4f 55 e9 vandnpd %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af 55 e9 vandnpd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 55 e9 vandnpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 55 e9 vandnpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 74 4f 55 e9 vandnps %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 74 af 55 e9 vandnps %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f0 55 e9 vandnps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f0 55 e9 vandnps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f df e9 vpandnd %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af df e9 vpandnd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 4f df e9 vpandnq %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af df e9 vpandnq %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 4f 57 e9 vxorpd %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af 57 e9 vxorpd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 57 e9 vxorpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 57 e9 vxorpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 74 4f 57 e9 vxorps %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 74 af 57 e9 vxorps %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f0 57 e9 vxorps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f0 57 e9 vxorps %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f ef e9 vpxord %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af ef e9 vpxord %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 4f ef e9 vpxorq %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af ef e9 vpxorq %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f f8 e9 vpsubb %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af f8 e9 vpsubb %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 f8 e9 vpsubb %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 f8 e9 vpsubb %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f f9 e9 vpsubw %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af f9 e9 vpsubw %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 f9 e9 vpsubw %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 f9 e9 vpsubw %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 75 4f fa e9 vpsubd %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 75 af fa e9 vpsubd %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 fa e9 vpsubd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 fa e9 vpsubd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 4f fb e9 vpsubq %zmm1,%zmm1,%zmm5\{%k7\} + +[a-f0-9]+: 62 f1 f5 af fb e9 vpsubq %ymm1,%ymm1,%ymm5\{%k7\}\{z\} + +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 08 55 e9 vandnpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 08 55 e9 vandnpd %xmm1,%xmm1,%xmm5 +#pass diff --git a/gas/testsuite/gas/i386/optimize-5.s b/gas/testsuite/gas/i386/optimize-5.s new file mode 100644 index 0000000..66c762b --- /dev/null +++ b/gas/testsuite/gas/i386/optimize-5.s @@ -0,0 +1,8 @@ +# Check instructions with optimized encoding + + .arch .avx512vl + +.include "optimize-1.s" + + {evex} vandnpd %zmm1, %zmm1, %zmm5 + {evex} vandnpd %ymm1, %ymm1, %ymm5 diff --git a/gas/testsuite/gas/i386/x86-64-optimize-2.d b/gas/testsuite/gas/i386/x86-64-optimize-2.d index f59e9b6..9222efe 100644 --- a/gas/testsuite/gas/i386/x86-64-optimize-2.d +++ b/gas/testsuite/gas/i386/x86-64-optimize-2.d @@ -10,100 +10,100 @@ Disassembly of section .text: 0+ <_start>: +[a-f0-9]+: 62 71 f5 4f 55 f9 vandnpd %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 f5 af 55 f9 vandnpd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 f5 48 55 f9 vandnpd %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 55 f9 vandnpd %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 55 f9 vandnpd %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: 62 e1 f5 08 55 c1 vandnpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 48 55 c1 vandnpd %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 f5 08 55 c1 vandnpd %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 f5 00 55 c9 vandnpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 40 55 c9 vandnpd %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 f5 00 55 c9 vandnpd %xmm17,%xmm17,%xmm1 +[a-f0-9]+: 62 71 74 4f 55 f9 vandnps %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 74 af 55 f9 vandnps %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 74 48 55 f9 vandnps %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 70 55 f9 vandnps %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 70 55 f9 vandnps %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: 62 e1 74 08 55 c1 vandnps %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 74 48 55 c1 vandnps %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 74 08 55 c1 vandnps %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 74 00 55 c9 vandnps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 74 40 55 c9 vandnps %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 74 00 55 c9 vandnps %xmm17,%xmm17,%xmm1 +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 +[a-f0-9]+: 62 71 75 4f df f9 vpandnd %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 75 af df f9 vpandnd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 75 48 df f9 vpandnd %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 48 df c1 vpandnd %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 75 08 df c1 vpandnd %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 e1 75 08 df c1 vpandnd %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 75 00 df c9 vpandnd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 40 df c9 vpandnd %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 75 00 df c9 vpandnd %xmm17,%xmm17,%xmm1 +[a-f0-9]+: 62 71 f5 4f df f9 vpandnq %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 f5 af df f9 vpandnq %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 f5 48 df f9 vpandnq %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: 62 e1 f5 08 df c1 vpandnq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 48 df c1 vpandnq %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 f5 08 df c1 vpandnq %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 f5 00 df c9 vpandnq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 40 df c9 vpandnq %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 f5 00 df c9 vpandnq %xmm17,%xmm17,%xmm1 +[a-f0-9]+: 62 71 f5 4f 57 f9 vxorpd %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 f5 af 57 f9 vxorpd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 f5 48 57 f9 vxorpd %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 57 f9 vxorpd %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 57 f9 vxorpd %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: 62 e1 f5 08 57 c1 vxorpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 48 57 c1 vxorpd %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 f5 08 57 c1 vxorpd %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 f5 00 57 c9 vxorpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 40 57 c9 vxorpd %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 f5 00 57 c9 vxorpd %xmm17,%xmm17,%xmm1 +[a-f0-9]+: 62 71 74 4f 57 f9 vxorps %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 74 af 57 f9 vxorps %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 74 48 57 f9 vxorps %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 70 57 f9 vxorps %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 70 57 f9 vxorps %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 74 48 57 c1 vxorps %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 74 08 57 c1 vxorps %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 e1 74 08 57 c1 vxorps %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 74 00 57 c9 vxorps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 74 40 57 c9 vxorps %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 74 00 57 c9 vxorps %xmm17,%xmm17,%xmm1 +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 +[a-f0-9]+: 62 71 75 4f ef f9 vpxord %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 75 af ef f9 vpxord %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 75 48 ef f9 vpxord %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: 62 e1 75 08 ef c1 vpxord %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 48 ef c1 vpxord %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 75 08 ef c1 vpxord %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 75 00 ef c9 vpxord %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 40 ef c9 vpxord %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 75 00 ef c9 vpxord %xmm17,%xmm17,%xmm1 +[a-f0-9]+: 62 71 f5 4f ef f9 vpxorq %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 f5 af ef f9 vpxorq %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 f5 48 ef f9 vpxorq %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: 62 e1 f5 08 ef c1 vpxorq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 48 ef c1 vpxorq %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 f5 08 ef c1 vpxorq %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 f5 00 ef c9 vpxorq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 40 ef c9 vpxorq %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 f5 00 ef c9 vpxorq %xmm17,%xmm17,%xmm1 +[a-f0-9]+: 62 71 75 4f f8 f9 vpsubb %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 75 af f8 f9 vpsubb %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 75 48 f8 f9 vpsubb %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 f8 f9 vpsubb %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 f8 f9 vpsubb %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 48 f8 c1 vpsubb %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 75 08 f8 c1 vpsubb %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 e1 75 08 f8 c1 vpsubb %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 75 00 f8 c9 vpsubb %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 40 f8 c9 vpsubb %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 75 00 f8 c9 vpsubb %xmm17,%xmm17,%xmm1 +[a-f0-9]+: 62 71 75 4f f9 f9 vpsubw %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 75 af f9 f9 vpsubw %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 75 48 f9 f9 vpsubw %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 f9 f9 vpsubw %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 f9 f9 vpsubw %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: 62 e1 75 08 f9 c1 vpsubw %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 48 f9 c1 vpsubw %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 75 08 f9 c1 vpsubw %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 75 00 f9 c9 vpsubw %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 40 f9 c9 vpsubw %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 75 00 f9 c9 vpsubw %xmm17,%xmm17,%xmm1 +[a-f0-9]+: 62 71 75 4f fa f9 vpsubd %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 75 af fa f9 vpsubd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 75 48 fa f9 vpsubd %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 fa f9 vpsubd %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 fa f9 vpsubd %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: 62 e1 75 08 fa c1 vpsubd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 48 fa c1 vpsubd %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 75 08 fa c1 vpsubd %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 75 00 fa c9 vpsubd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 40 fa c9 vpsubd %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 75 00 fa c9 vpsubd %xmm17,%xmm17,%xmm1 +[a-f0-9]+: 62 71 f5 4f fb f9 vpsubq %zmm1,%zmm1,%zmm15\{%k7\} +[a-f0-9]+: 62 71 f5 af fb f9 vpsubq %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: 62 71 f5 48 fb f9 vpsubq %zmm1,%zmm1,%zmm15 +[a-f0-9]+: c5 71 fb f9 vpsubq %xmm1,%xmm1,%xmm15 - +[a-f0-9]+: c5 71 fb f9 vpsubq %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 48 fb c1 vpsubq %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 f5 08 fb c1 vpsubq %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 e1 f5 08 fb c1 vpsubq %xmm1,%xmm1,%xmm16 - +[a-f0-9]+: 62 b1 f5 00 fb c9 vpsubq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 40 fb c9 vpsubq %zmm17,%zmm17,%zmm1 +[a-f0-9]+: 62 b1 f5 00 fb c9 vpsubq %xmm17,%xmm17,%xmm1 #pass diff --git a/gas/testsuite/gas/i386/x86-64-optimize-5.d b/gas/testsuite/gas/i386/x86-64-optimize-5.d new file mode 100644 index 0000000..3ef5746 --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-optimize-5.d @@ -0,0 +1,111 @@ +#as: -O2 -march=+avx512vl -I${srcdir}/$subdir +#objdump: -drw +#name: x86-64 optimized encoding 5 with -O2 + +.*: +file format .* + + +Disassembly of section .text: + +0+ <_start>: + +[a-f0-9]+: 62 71 f5 4f 55 f9 vandnpd %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af 55 f9 vandnpd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 55 f9 vandnpd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 55 f9 vandnpd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 55 c1 vandnpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 55 c1 vandnpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 55 c9 vandnpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 55 c9 vandnpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 74 4f 55 f9 vandnps %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 74 af 55 f9 vandnps %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 70 55 f9 vandnps %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 70 55 f9 vandnps %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 74 08 55 c1 vandnps %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 74 08 55 c1 vandnps %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 74 00 55 c9 vandnps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 74 00 55 c9 vandnps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 71 75 4f df f9 vpandnd %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af df f9 vpandnd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 df c1 vpandnd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 df c1 vpandnd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 df c9 vpandnd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 df c9 vpandnd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 f5 4f df f9 vpandnq %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af df f9 vpandnq %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 df c1 vpandnq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 df c1 vpandnq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 df c9 vpandnq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 df c9 vpandnq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 f5 4f 57 f9 vxorpd %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af 57 f9 vxorpd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 57 f9 vxorpd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 57 f9 vxorpd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 57 c1 vxorpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 57 c1 vxorpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 57 c9 vxorpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 57 c9 vxorpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 74 4f 57 f9 vxorps %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 74 af 57 f9 vxorps %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 70 57 f9 vxorps %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 70 57 f9 vxorps %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 74 08 57 c1 vxorps %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 74 08 57 c1 vxorps %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 74 00 57 c9 vxorps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 74 00 57 c9 vxorps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 71 75 4f ef f9 vpxord %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af ef f9 vpxord %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 ef c1 vpxord %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 ef c1 vpxord %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 ef c9 vpxord %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 ef c9 vpxord %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 f5 4f ef f9 vpxorq %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af ef f9 vpxorq %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 ef c1 vpxorq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 ef c1 vpxorq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 ef c9 vpxorq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 ef c9 vpxorq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 75 4f f8 f9 vpsubb %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af f8 f9 vpsubb %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 f8 f9 vpsubb %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 f8 f9 vpsubb %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 f8 c1 vpsubb %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 f8 c1 vpsubb %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 f8 c9 vpsubb %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 f8 c9 vpsubb %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 75 4f f9 f9 vpsubw %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af f9 f9 vpsubw %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 f9 f9 vpsubw %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 f9 f9 vpsubw %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 f9 c1 vpsubw %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 f9 c1 vpsubw %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 f9 c9 vpsubw %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 f9 c9 vpsubw %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 75 4f fa f9 vpsubd %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af fa f9 vpsubd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 fa f9 vpsubd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 fa f9 vpsubd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 fa c1 vpsubd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 fa c1 vpsubd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 fa c9 vpsubd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 fa c9 vpsubd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 f5 4f fb f9 vpsubq %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af fb f9 vpsubq %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 fb f9 vpsubq %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 fb f9 vpsubq %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 fb c1 vpsubq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 fb c1 vpsubq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 fb c9 vpsubq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 fb c9 vpsubq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 f1 f5 08 55 e9 vandnpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 08 55 e9 vandnpd %xmm1,%xmm1,%xmm5 +#pass diff --git a/gas/testsuite/gas/i386/x86-64-optimize-5.s b/gas/testsuite/gas/i386/x86-64-optimize-5.s new file mode 100644 index 0000000..6b4ff10 --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-optimize-5.s @@ -0,0 +1,6 @@ +# Check 64bit instructions with optimized encoding + +.include "x86-64-optimize-2.s" + + {evex} vandnpd %zmm1, %zmm1, %zmm5 + {evex} vandnpd %ymm1, %ymm1, %ymm5 diff --git a/gas/testsuite/gas/i386/x86-64-optimize-6.d b/gas/testsuite/gas/i386/x86-64-optimize-6.d new file mode 100644 index 0000000..527f1a0 --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-optimize-6.d @@ -0,0 +1,111 @@ +#as: -O2 -I${srcdir}/$subdir +#objdump: -drw +#name: x86-64 optimized encoding 6 with -O2 + +.*: +file format .* + + +Disassembly of section .text: + +0+ <_start>: + +[a-f0-9]+: 62 71 f5 4f 55 f9 vandnpd %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af 55 f9 vandnpd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 55 f9 vandnpd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 55 f9 vandnpd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 55 c1 vandnpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 55 c1 vandnpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 55 c9 vandnpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 55 c9 vandnpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 74 4f 55 f9 vandnps %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 74 af 55 f9 vandnps %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 70 55 f9 vandnps %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 70 55 f9 vandnps %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 74 08 55 c1 vandnps %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 74 08 55 c1 vandnps %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 74 00 55 c9 vandnps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 74 00 55 c9 vandnps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 71 75 4f df f9 vpandnd %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af df f9 vpandnd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 df c1 vpandnd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 df c1 vpandnd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 df c9 vpandnd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 df c9 vpandnd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 f5 4f df f9 vpandnq %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af df f9 vpandnq %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 df c1 vpandnq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 df c1 vpandnq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 df c9 vpandnq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 df c9 vpandnq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 f5 4f 57 f9 vxorpd %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af 57 f9 vxorpd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 57 f9 vxorpd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 57 f9 vxorpd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 57 c1 vxorpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 57 c1 vxorpd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 57 c9 vxorpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 57 c9 vxorpd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 74 4f 57 f9 vxorps %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 74 af 57 f9 vxorps %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 70 57 f9 vxorps %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 70 57 f9 vxorps %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 74 08 57 c1 vxorps %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 74 08 57 c1 vxorps %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 74 00 57 c9 vxorps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 74 00 57 c9 vxorps %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 71 75 4f ef f9 vpxord %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af ef f9 vpxord %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 ef c1 vpxord %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 ef c1 vpxord %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 ef c9 vpxord %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 ef c9 vpxord %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 f5 4f ef f9 vpxorq %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af ef f9 vpxorq %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 ef c1 vpxorq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 ef c1 vpxorq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 ef c9 vpxorq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 ef c9 vpxorq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 75 4f f8 f9 vpsubb %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af f8 f9 vpsubb %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 f8 f9 vpsubb %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 f8 f9 vpsubb %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 f8 c1 vpsubb %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 f8 c1 vpsubb %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 f8 c9 vpsubb %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 f8 c9 vpsubb %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 75 4f f9 f9 vpsubw %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af f9 f9 vpsubw %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 f9 f9 vpsubw %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 f9 f9 vpsubw %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 f9 c1 vpsubw %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 f9 c1 vpsubw %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 f9 c9 vpsubw %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 f9 c9 vpsubw %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 75 4f fa f9 vpsubd %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 75 af fa f9 vpsubd %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 fa f9 vpsubd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 fa f9 vpsubd %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 75 08 fa c1 vpsubd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 75 08 fa c1 vpsubd %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 75 00 fa c9 vpsubd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 75 00 fa c9 vpsubd %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 71 f5 4f fb f9 vpsubq %zmm1,%zmm1,%zmm15\{%k7\} + +[a-f0-9]+: 62 71 f5 af fb f9 vpsubq %ymm1,%ymm1,%ymm15\{%k7\}\{z\} + +[a-f0-9]+: c5 71 fb f9 vpsubq %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: c5 71 fb f9 vpsubq %xmm1,%xmm1,%xmm15 + +[a-f0-9]+: 62 e1 f5 08 fb c1 vpsubq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 e1 f5 08 fb c1 vpsubq %xmm1,%xmm1,%xmm16 + +[a-f0-9]+: 62 b1 f5 00 fb c9 vpsubq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 b1 f5 00 fb c9 vpsubq %xmm17,%xmm17,%xmm1 + +[a-f0-9]+: 62 f1 f5 08 55 e9 vandnpd %xmm1,%xmm1,%xmm5 + +[a-f0-9]+: 62 f1 f5 08 55 e9 vandnpd %xmm1,%xmm1,%xmm5 +#pass diff --git a/gas/testsuite/gas/i386/x86-64-optimize-6.s b/gas/testsuite/gas/i386/x86-64-optimize-6.s new file mode 100644 index 0000000..70ccbc4 --- /dev/null +++ b/gas/testsuite/gas/i386/x86-64-optimize-6.s @@ -0,0 +1,8 @@ +# Check 64bit instructions with optimized encoding + + .arch .avx512vl + +.include "x86-64-optimize-2.s" + + {evex} vandnpd %zmm1, %zmm1, %zmm5 + {evex} vandnpd %ymm1, %ymm1, %ymm5 |