2016-09-03 12:37:50 +08:00
|
|
|
; RUN: llc -O3 -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+avx512bw < %s | FileCheck %s
|
|
|
|
|
|
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
|
target triple = "x86_64-unknown-unknown"
|
|
|
|
|
|
|
|
|
|
; Stack reload folding tests.
|
|
|
|
|
;
|
|
|
|
|
; By including a nop call with sideeffects we can force a partial register spill of the
|
|
|
|
|
; relevant registers and check that the reload is correctly folded into the instruction.
|
|
|
|
|
|
2016-09-04 01:20:07 +08:00
|
|
|
define <16 x i8> @stack_fold_paddb(<16 x i8> %a0, <16 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddb
|
|
|
|
|
;CHECK: vpaddb {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = add <16 x i8> %a0, %a1
|
|
|
|
|
ret <16 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <32 x i8> @stack_fold_paddb_ymm(<32 x i8> %a0, <32 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddb_ymm
|
|
|
|
|
;CHECK: vpaddb {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = add <32 x i8> %a0, %a1
|
|
|
|
|
ret <32 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <4 x i32> @stack_fold_paddd(<4 x i32> %a0, <4 x i32> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddd
|
|
|
|
|
;CHECK: vpaddd {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = add <4 x i32> %a0, %a1
|
|
|
|
|
ret <4 x i32> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <8 x i32> @stack_fold_paddd_ymm(<8 x i32> %a0, <8 x i32> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddd_ymm
|
|
|
|
|
;CHECK: vpaddd {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = add <8 x i32> %a0, %a1
|
|
|
|
|
ret <8 x i32> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <2 x i64> @stack_fold_paddq(<2 x i64> %a0, <2 x i64> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddq
|
|
|
|
|
;CHECK: vpaddq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = add <2 x i64> %a0, %a1
|
|
|
|
|
ret <2 x i64> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <4 x i64> @stack_fold_paddq_ymm(<4 x i64> %a0, <4 x i64> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddq_ymm
|
|
|
|
|
;CHECK: vpaddq {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = add <4 x i64> %a0, %a1
|
|
|
|
|
ret <4 x i64> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <16 x i8> @stack_fold_paddsb(<16 x i8> %a0, <16 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddsb
|
|
|
|
|
;CHECK: vpaddsb {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a0, <16 x i8> %a1)
|
|
|
|
|
ret <16 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8>, <16 x i8>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <32 x i8> @stack_fold_paddsb_ymm(<32 x i8> %a0, <32 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddsb_ymm
|
|
|
|
|
;CHECK: vpaddsb {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %a0, <32 x i8> %a1)
|
|
|
|
|
ret <32 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
declare <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8>, <32 x i8>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <8 x i16> @stack_fold_paddsw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddsw
|
|
|
|
|
;CHECK: vpaddsw {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16> %a0, <8 x i16> %a1)
|
|
|
|
|
ret <8 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
declare <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16>, <8 x i16>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <16 x i16> @stack_fold_paddsw_ymm(<16 x i16> %a0, <16 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddsw_ymm
|
|
|
|
|
;CHECK: vpaddsw {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %a0, <16 x i16> %a1)
|
|
|
|
|
ret <16 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16>, <16 x i16>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <16 x i8> @stack_fold_paddusb(<16 x i8> %a0, <16 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddusb
|
|
|
|
|
;CHECK: vpaddusb {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8> %a0, <16 x i8> %a1)
|
|
|
|
|
ret <16 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i8> @llvm.x86.sse2.paddus.b(<16 x i8>, <16 x i8>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <32 x i8> @stack_fold_paddusb_ymm(<32 x i8> %a0, <32 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddusb_ymm
|
|
|
|
|
;CHECK: vpaddusb {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <32 x i8> @llvm.x86.avx2.paddus.b(<32 x i8> %a0, <32 x i8> %a1)
|
|
|
|
|
ret <32 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
declare <32 x i8> @llvm.x86.avx2.paddus.b(<32 x i8>, <32 x i8>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <8 x i16> @stack_fold_paddusw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddusw
|
|
|
|
|
;CHECK: vpaddusw {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16> %a0, <8 x i16> %a1)
|
|
|
|
|
ret <8 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
declare <8 x i16> @llvm.x86.sse2.paddus.w(<8 x i16>, <8 x i16>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <16 x i16> @stack_fold_paddusw_ymm(<16 x i16> %a0, <16 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddusw_ymm
|
|
|
|
|
;CHECK: vpaddusw {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <16 x i16> @llvm.x86.avx2.paddus.w(<16 x i16> %a0, <16 x i16> %a1)
|
|
|
|
|
ret <16 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i16> @llvm.x86.avx2.paddus.w(<16 x i16>, <16 x i16>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <8 x i16> @stack_fold_paddw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddw
|
|
|
|
|
;CHECK: vpaddw {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = add <8 x i16> %a0, %a1
|
|
|
|
|
ret <8 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <16 x i16> @stack_fold_paddw_ymm(<16 x i16> %a0, <16 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_paddw_ymm
|
|
|
|
|
;CHECK: vpaddw {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = add <16 x i16> %a0, %a1
|
|
|
|
|
ret <16 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-03 12:37:50 +08:00
|
|
|
define i16 @stack_fold_pcmpeqb(<16 x i8> %a0, <16 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_pcmpeqb
|
|
|
|
|
;CHECK: vpcmpeqb {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%k[0-7]}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = icmp eq <16 x i8> %a0, %a1
|
|
|
|
|
%3 = bitcast <16 x i1> %2 to i16
|
|
|
|
|
ret i16 %3
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define i8 @stack_fold_pcmpeqd(<4 x i32> %a0, <4 x i32> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_pcmpeqd
|
|
|
|
|
;CHECK: vpcmpeqd {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%k[0-7]}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = icmp eq <4 x i32> %a0, %a1
|
|
|
|
|
%3 = shufflevector <4 x i1> %2, <4 x i1> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
|
|
|
%4 = bitcast <8 x i1> %3 to i8
|
|
|
|
|
ret i8 %4
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define i8 @stack_fold_pcmpeqq(<2 x i64> %a0, <2 x i64> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_pcmpeqq
|
|
|
|
|
;CHECK: vpcmpeqq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%k[0-7]}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = icmp eq <2 x i64> %a0, %a1
|
|
|
|
|
%3 = shufflevector <2 x i1> %2, <2 x i1> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 2, i32 3>
|
|
|
|
|
%4 = bitcast <8 x i1> %3 to i8
|
|
|
|
|
ret i8 %4
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define i8 @stack_fold_pcmpeqw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_pcmpeqw
|
|
|
|
|
;CHECK: vpcmpeqw {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%k[0-7]}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = icmp eq <8 x i16> %a0, %a1
|
|
|
|
|
%3 = bitcast <8 x i1> %2 to i8
|
|
|
|
|
ret i8 %3
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-04 01:20:07 +08:00
|
|
|
define <16 x i8> @stack_fold_psubb(<16 x i8> %a0, <16 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubb
|
|
|
|
|
;CHECK: vpsubb {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = sub <16 x i8> %a0, %a1
|
|
|
|
|
ret <16 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <32 x i8> @stack_fold_psubb_ymm(<32 x i8> %a0, <32 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubb_ymm
|
|
|
|
|
;CHECK: vpsubb {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = sub <32 x i8> %a0, %a1
|
|
|
|
|
ret <32 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <4 x i32> @stack_fold_psubd(<4 x i32> %a0, <4 x i32> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubd
|
|
|
|
|
;CHECK: vpsubd {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = sub <4 x i32> %a0, %a1
|
|
|
|
|
ret <4 x i32> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <8 x i32> @stack_fold_psubd_ymm(<8 x i32> %a0, <8 x i32> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubd_ymm
|
|
|
|
|
;CHECK: vpsubd {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = sub <8 x i32> %a0, %a1
|
|
|
|
|
ret <8 x i32> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <2 x i64> @stack_fold_psubq(<2 x i64> %a0, <2 x i64> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubq
|
|
|
|
|
;CHECK: vpsubq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = sub <2 x i64> %a0, %a1
|
|
|
|
|
ret <2 x i64> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <4 x i64> @stack_fold_psubq_ymm(<4 x i64> %a0, <4 x i64> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubq_ymm
|
|
|
|
|
;CHECK: vpsubq {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = sub <4 x i64> %a0, %a1
|
|
|
|
|
ret <4 x i64> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <16 x i8> @stack_fold_psubsb(<16 x i8> %a0, <16 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubsb
|
|
|
|
|
;CHECK: vpsubsb {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8> %a0, <16 x i8> %a1)
|
|
|
|
|
ret <16 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8>, <16 x i8>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <32 x i8> @stack_fold_psubsb_ymm(<32 x i8> %a0, <32 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubsb_ymm
|
|
|
|
|
;CHECK: vpsubsb {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %a0, <32 x i8> %a1)
|
|
|
|
|
ret <32 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
declare <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8>, <32 x i8>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <8 x i16> @stack_fold_psubsw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubsw
|
|
|
|
|
;CHECK: vpsubsw {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16> %a0, <8 x i16> %a1)
|
|
|
|
|
ret <8 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
declare <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16>, <8 x i16>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <16 x i16> @stack_fold_psubsw_ymm(<16 x i16> %a0, <16 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubsw_ymm
|
|
|
|
|
;CHECK: vpsubsw {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %a0, <16 x i16> %a1)
|
|
|
|
|
ret <16 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16>, <16 x i16>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <16 x i8> @stack_fold_psubusb(<16 x i8> %a0, <16 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubusb
|
|
|
|
|
;CHECK: vpsubusb {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8> %a0, <16 x i8> %a1)
|
|
|
|
|
ret <16 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i8> @llvm.x86.sse2.psubus.b(<16 x i8>, <16 x i8>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <32 x i8> @stack_fold_psubusb_ymm(<32 x i8> %a0, <32 x i8> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubusb_ymm
|
|
|
|
|
;CHECK: vpsubusb {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8> %a0, <32 x i8> %a1)
|
|
|
|
|
ret <32 x i8> %2
|
|
|
|
|
}
|
|
|
|
|
declare <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8>, <32 x i8>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <8 x i16> @stack_fold_psubusw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubusw
|
|
|
|
|
;CHECK: vpsubusw {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16> %a0, <8 x i16> %a1)
|
|
|
|
|
ret <8 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
declare <8 x i16> @llvm.x86.sse2.psubus.w(<8 x i16>, <8 x i16>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <16 x i16> @stack_fold_psubusw_ymm(<16 x i16> %a0, <16 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubusw_ymm
|
|
|
|
|
;CHECK: vpsubusw {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = call <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16> %a0, <16 x i16> %a1)
|
|
|
|
|
ret <16 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16>, <16 x i16>) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <8 x i16> @stack_fold_psubw(<8 x i16> %a0, <8 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubw
|
|
|
|
|
;CHECK: vpsubw {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = sub <8 x i16> %a0, %a1
|
|
|
|
|
ret <8 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
define <16 x i16> @stack_fold_psubw_ymm(<16 x i16> %a0, <16 x i16> %a1) {
|
|
|
|
|
;CHECK-LABEL: stack_fold_psubw_ymm
|
|
|
|
|
;CHECK: vpsubw {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
|
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
|
|
|
|
|
%2 = sub <16 x i16> %a0, %a1
|
|
|
|
|
ret <16 x i16> %2
|
|
|
|
|
}
|
|
|
|
|
|
