diff options
author | Jan Beulich <jbeulich@suse.com> | 2023-07-04 17:07:26 +0200 |
---|---|---|
committer | Jan Beulich <jbeulich@suse.com> | 2023-07-04 17:07:26 +0200 |
commit | eb4031cb20aa710834be891f8638e04dbba81edc (patch) | |
tree | 718e79578a21b150e826d3b0a618364857aeca04 /gas | |
parent | 33889538969edd801bdaf5422c863fe2a0b7cf45 (diff) | |
download | fsf-binutils-gdb-eb4031cb20aa710834be891f8638e04dbba81edc.zip fsf-binutils-gdb-eb4031cb20aa710834be891f8638e04dbba81edc.tar.gz fsf-binutils-gdb-eb4031cb20aa710834be891f8638e04dbba81edc.tar.bz2 |
x86: optimize 128-bit VPBROADCASTQ to VPUNPCKLQDQ
The alternative is 1 byte shorter when the source is %xmm0-7, as a
2-byte VEX prefix can then be used.
Diffstat (limited to 'gas')
-rw-r--r-- | gas/config/tc-i386.c | 27 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/optimize-2.d | 1 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/optimize-2.s | 2 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/optimize-2b.d | 1 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-optimize-3.d | 2 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-optimize-3.s | 3 | ||||
-rw-r--r-- | gas/testsuite/gas/i386/x86-64-optimize-3b.d | 2 |
7 files changed, 38 insertions, 0 deletions
diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c index 8ebeaf1..bc02f8e0 100644 --- a/gas/config/tc-i386.c +++ b/gas/config/tc-i386.c @@ -4620,6 +4620,33 @@ optimize_encoding (void) i.op[1].regs = i.op[0].regs; } } + else if (optimize_for_space + && i.tm.base_opcode == 0x59 + && i.tm.opcode_space == SPACE_0F38 + && i.operands == i.reg_operands + && i.tm.opcode_modifier.vex + && !(i.op[0].regs->reg_flags & RegRex) + && i.op[0].regs->reg_type.bitfield.xmmword + && i.vec_encoding != vex_encoding_vex3) + { + /* Optimize: -Os: + vpbroadcastq %xmmN, %xmmM -> vpunpcklqdq %xmmN, %xmmN, %xmmM (N < 8) + */ + i.tm.opcode_space = SPACE_0F; + i.tm.base_opcode = 0x6c; + i.tm.opcode_modifier.vexvvvv = 1; + + ++i.operands; + ++i.reg_operands; + ++i.tm.operands; + + i.op[2].regs = i.op[0].regs; + i.types[2] = i.types[0]; + i.flags[2] = i.flags[0]; + i.tm.operand_types[2] = i.tm.operand_types[0]; + + swap_2_operands (1, 2); + } } /* Return non-zero for load instruction. */ diff --git a/gas/testsuite/gas/i386/optimize-2.d b/gas/testsuite/gas/i386/optimize-2.d index 60a9069..41056fb 100644 --- a/gas/testsuite/gas/i386/optimize-2.d +++ b/gas/testsuite/gas/i386/optimize-2.d @@ -164,4 +164,5 @@ Disassembly of section .text: +[a-f0-9]+: 66 .* pcmpeqd %xmm2,%xmm2 +[a-f0-9]+: c5 .* vpcmpeqd %xmm2,%xmm2,%xmm0 +[a-f0-9]+: c5 .* vpcmpeqd %ymm2,%ymm2,%ymm0 + +[a-f0-9]+: c5 .* vpunpcklqdq %xmm2,%xmm2,%xmm0 #pass diff --git a/gas/testsuite/gas/i386/optimize-2.s b/gas/testsuite/gas/i386/optimize-2.s index 3cf41b1..29399ae 100644 --- a/gas/testsuite/gas/i386/optimize-2.s +++ b/gas/testsuite/gas/i386/optimize-2.s @@ -184,3 +184,5 @@ _start: pcmpeqq %xmm2, %xmm2 vpcmpeqq %xmm2, %xmm2, %xmm0 vpcmpeqq %ymm2, %ymm2, %ymm0 + + vpbroadcastq %xmm2, %xmm0 diff --git a/gas/testsuite/gas/i386/optimize-2b.d b/gas/testsuite/gas/i386/optimize-2b.d index 0624cb4..d9e8319 100644 --- a/gas/testsuite/gas/i386/optimize-2b.d +++ b/gas/testsuite/gas/i386/optimize-2b.d @@ -165,4 +165,5 @@ Disassembly of section .text: +[a-f0-9]+: 66 .* pcmpeqq %xmm2,%xmm2 +[a-f0-9]+: c4 .* vpcmpeqq %xmm2,%xmm2,%xmm0 +[a-f0-9]+: c4 .* vpcmpeqq %ymm2,%ymm2,%ymm0 + +[a-f0-9]+: c4 .* vpbroadcastq %xmm2,%xmm0 #pass diff --git a/gas/testsuite/gas/i386/x86-64-optimize-3.d b/gas/testsuite/gas/i386/x86-64-optimize-3.d index fc5ec5e..23b9305 100644 --- a/gas/testsuite/gas/i386/x86-64-optimize-3.d +++ b/gas/testsuite/gas/i386/x86-64-optimize-3.d @@ -205,4 +205,6 @@ Disassembly of section .text: +[a-f0-9]+: 66 .* pcmpeqd %xmm12,%xmm12 +[a-f0-9]+: c4 .* vpcmpeqq %xmm12,%xmm12,%xmm0 +[a-f0-9]+: c4 .* vpcmpeqq %ymm12,%ymm12,%ymm0 + +[a-f0-9]+: c5 .* vpunpcklqdq %xmm2,%xmm2,%xmm0 + +[a-f0-9]+: c4 .* vpbroadcastq %xmm12,%xmm0 #pass diff --git a/gas/testsuite/gas/i386/x86-64-optimize-3.s b/gas/testsuite/gas/i386/x86-64-optimize-3.s index d2bcbce..bab99cf 100644 --- a/gas/testsuite/gas/i386/x86-64-optimize-3.s +++ b/gas/testsuite/gas/i386/x86-64-optimize-3.s @@ -229,3 +229,6 @@ _start: pcmpeqq %xmm12, %xmm12 vpcmpeqq %xmm12, %xmm12, %xmm0 vpcmpeqq %ymm12, %ymm12, %ymm0 + + vpbroadcastq %xmm2, %xmm0 + vpbroadcastq %xmm12, %xmm0 diff --git a/gas/testsuite/gas/i386/x86-64-optimize-3b.d b/gas/testsuite/gas/i386/x86-64-optimize-3b.d index abd48dc..929c6f7 100644 --- a/gas/testsuite/gas/i386/x86-64-optimize-3b.d +++ b/gas/testsuite/gas/i386/x86-64-optimize-3b.d @@ -206,4 +206,6 @@ Disassembly of section .text: +[a-f0-9]+: 66 .* pcmpeqq %xmm12,%xmm12 +[a-f0-9]+: c4 .* vpcmpeqq %xmm12,%xmm12,%xmm0 +[a-f0-9]+: c4 .* vpcmpeqq %ymm12,%ymm12,%ymm0 + +[a-f0-9]+: c4 .* vpbroadcastq %xmm2,%xmm0 + +[a-f0-9]+: c4 .* vpbroadcastq %xmm12,%xmm0 #pass |