From 80c34c3812f8bae13fb902dbaaa287ca207857ac Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Fri, 9 Mar 2018 08:10:27 -0800 Subject: [PATCH] x86: Encode EVEX instructions with VEX128 if possible If EVEX encoding isn't required, we can encode EVEX instructions with VEX128. * config/tc-i386.c (optimize_encoding): Encode EVEX instructions with VEX128 if EVEX encoding isn't required. * testsuite/gas/i386/optimize-1.d: Updated. * testsuite/gas/i386/x86-64-optimize-2.d: Likewise. --- gas/ChangeLog | 7 +++++++ gas/config/tc-i386.c | 3 ++- gas/testsuite/gas/i386/optimize-1.d | 24 +++++++++++----------- gas/testsuite/gas/i386/x86-64-optimize-2.d | 24 +++++++++++----------- 4 files changed, 33 insertions(+), 25 deletions(-) diff --git a/gas/ChangeLog b/gas/ChangeLog index 2fe224c65fd..166e24e3b46 100644 --- a/gas/ChangeLog +++ b/gas/ChangeLog @@ -1,3 +1,10 @@ +2018-03-09 H.J. Lu + + * config/tc-i386.c (optimize_encoding): Encode EVEX instructions + with VEX128 if EVEX encoding isn't required. + * testsuite/gas/i386/optimize-1.d: Updated. + * testsuite/gas/i386/x86-64-optimize-2.d: Likewise. + 2018-03-09 H.J. Lu * config/tc-i386.c (check_VecOperations): Strip whitespace. diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c index 724376096f8..e94e01cf10d 100644 --- a/gas/config/tc-i386.c +++ b/gas/config/tc-i386.c @@ -3875,7 +3875,8 @@ optimize_encoding (void) || (!i.mask && !i.rounding && is_evex_encoding (&i.tm) - && (i.tm.cpu_flags.bitfield.cpuavx512vl + && (i.vec_encoding != vex_encoding_evex + || i.tm.cpu_flags.bitfield.cpuavx512vl || cpu_arch_isa_flags.bitfield.cpuavx512vl))) && ((i.tm.base_opcode == 0x55 || i.tm.base_opcode == 0x6655 diff --git a/gas/testsuite/gas/i386/optimize-1.d b/gas/testsuite/gas/i386/optimize-1.d index f7da296697d..3ea6e75b9a4 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]+: 62 f1 f5 48 55 e9 vandnpd %zmm1,%zmm1,%zmm5 + +[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]+: 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 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]+: 62 f1 75 48 df e9 vpandnd %zmm1,%zmm1,%zmm5 + +[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]+: 62 f1 f5 48 df e9 vpandnq %zmm1,%zmm1,%zmm5 + +[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]+: 62 f1 f5 48 57 e9 vxorpd %zmm1,%zmm1,%zmm5 + +[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]+: 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 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]+: 62 f1 75 48 ef e9 vpxord %zmm1,%zmm1,%zmm5 + +[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]+: 62 f1 f5 48 ef e9 vpxorq %zmm1,%zmm1,%zmm5 + +[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]+: 62 f1 75 48 f8 e9 vpsubb %zmm1,%zmm1,%zmm5 + +[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]+: 62 f1 75 48 f9 e9 vpsubw %zmm1,%zmm1,%zmm5 + +[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]+: 62 f1 75 48 fa e9 vpsubd %zmm1,%zmm1,%zmm5 + +[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]+: 62 f1 f5 48 fb e9 vpsubq %zmm1,%zmm1,%zmm5 + +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5 +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5 #pass diff --git a/gas/testsuite/gas/i386/x86-64-optimize-2.d b/gas/testsuite/gas/i386/x86-64-optimize-2.d index 9222efe8c14..ba3a2df887f 100644 --- a/gas/testsuite/gas/i386/x86-64-optimize-2.d +++ b/gas/testsuite/gas/i386/x86-64-optimize-2.d @@ -10,7 +10,7 @@ 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 48 55 c1 vandnpd %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 f5 08 55 c1 vandnpd %xmm1,%xmm1,%xmm16 @@ -18,7 +18,7 @@ Disassembly of section .text: +[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 48 55 c1 vandnps %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 74 08 55 c1 vandnps %xmm1,%xmm1,%xmm16 @@ -27,7 +27,7 @@ Disassembly of section .text: +[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 @@ -35,7 +35,7 @@ Disassembly of section .text: +[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 48 df c1 vpandnq %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 f5 08 df c1 vpandnq %xmm1,%xmm1,%xmm16 @@ -43,7 +43,7 @@ Disassembly of section .text: +[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 48 57 c1 vxorpd %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 f5 08 57 c1 vxorpd %xmm1,%xmm1,%xmm16 @@ -51,7 +51,7 @@ Disassembly of section .text: +[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 @@ -60,7 +60,7 @@ Disassembly of section .text: +[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 48 ef c1 vpxord %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 75 08 ef c1 vpxord %xmm1,%xmm1,%xmm16 @@ -68,7 +68,7 @@ Disassembly of section .text: +[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 48 ef c1 vpxorq %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 f5 08 ef c1 vpxorq %xmm1,%xmm1,%xmm16 @@ -76,7 +76,7 @@ Disassembly of section .text: +[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 @@ -84,7 +84,7 @@ Disassembly of section .text: +[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 48 f9 c1 vpsubw %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 75 08 f9 c1 vpsubw %xmm1,%xmm1,%xmm16 @@ -92,7 +92,7 @@ Disassembly of section .text: +[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 48 fa c1 vpsubd %zmm1,%zmm1,%zmm16 +[a-f0-9]+: 62 e1 75 08 fa c1 vpsubd %xmm1,%xmm1,%xmm16 @@ -100,7 +100,7 @@ Disassembly of section .text: +[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 -- 2.30.2