forked from OSchip/llvm-project
459 lines
31 KiB
LLVM
459 lines
31 KiB
LLVM
; RUN: llc -O3 -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+avx512dq < %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.
|
|
|
|
define <2 x double> @stack_fold_addpd(<2 x double> %a0, <2 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_addpd
|
|
;CHECK: vaddpd {{-?[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 = fadd <2 x double> %a0, %a1
|
|
ret <2 x double> %2
|
|
}
|
|
|
|
define <4 x double> @stack_fold_addpd_ymm(<4 x double> %a0, <4 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_addpd_ymm
|
|
;CHECK: vaddpd {{-?[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 = fadd <4 x double> %a0, %a1
|
|
ret <4 x double> %2
|
|
}
|
|
|
|
define <4 x float> @stack_fold_addps(<4 x float> %a0, <4 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_addps
|
|
;CHECK: vaddps {{-?[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 = fadd <4 x float> %a0, %a1
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
define <8 x float> @stack_fold_addps_ymm(<8 x float> %a0, <8 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_addps_ymm
|
|
;CHECK: vaddps {{-?[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 = fadd <8 x float> %a0, %a1
|
|
ret <8 x float> %2
|
|
}
|
|
|
|
define <2 x double> @stack_fold_andnpd(<2 x double> %a0, <2 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_andnpd
|
|
;CHECK: vandnpd {{-?[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},~{flags}"()
|
|
%2 = bitcast <2 x double> %a0 to <2 x i64>
|
|
%3 = bitcast <2 x double> %a1 to <2 x i64>
|
|
%4 = xor <2 x i64> %2, <i64 -1, i64 -1>
|
|
%5 = and <2 x i64> %4, %3
|
|
%6 = bitcast <2 x i64> %5 to <2 x double>
|
|
; fadd forces execution domain
|
|
%7 = fadd <2 x double> %6, <double 0x0, double 0x0>
|
|
ret <2 x double> %7
|
|
}
|
|
|
|
define <4 x double> @stack_fold_andnpd_ymm(<4 x double> %a0, <4 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_andnpd_ymm
|
|
;CHECK: vandnpd {{-?[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},~{flags}"()
|
|
%2 = bitcast <4 x double> %a0 to <4 x i64>
|
|
%3 = bitcast <4 x double> %a1 to <4 x i64>
|
|
%4 = xor <4 x i64> %2, <i64 -1, i64 -1, i64 -1, i64 -1>
|
|
%5 = and <4 x i64> %4, %3
|
|
%6 = bitcast <4 x i64> %5 to <4 x double>
|
|
; fadd forces execution domain
|
|
%7 = fadd <4 x double> %6, <double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <4 x double> %7
|
|
}
|
|
|
|
define <4 x float> @stack_fold_andnps(<4 x float> %a0, <4 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_andnps
|
|
;CHECK: vandnps {{-?[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},~{flags}"()
|
|
%2 = bitcast <4 x float> %a0 to <2 x i64>
|
|
%3 = bitcast <4 x float> %a1 to <2 x i64>
|
|
%4 = xor <2 x i64> %2, <i64 -1, i64 -1>
|
|
%5 = and <2 x i64> %4, %3
|
|
%6 = bitcast <2 x i64> %5 to <4 x float>
|
|
; fadd forces execution domain
|
|
%7 = fadd <4 x float> %6, <float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <4 x float> %7
|
|
}
|
|
|
|
define <8 x float> @stack_fold_andnps_ymm(<8 x float> %a0, <8 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_andnps_ymm
|
|
;CHECK: vandnps {{-?[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},~{flags}"()
|
|
%2 = bitcast <8 x float> %a0 to <4 x i64>
|
|
%3 = bitcast <8 x float> %a1 to <4 x i64>
|
|
%4 = xor <4 x i64> %2, <i64 -1, i64 -1, i64 -1, i64 -1>
|
|
%5 = and <4 x i64> %4, %3
|
|
%6 = bitcast <4 x i64> %5 to <8 x float>
|
|
; fadd forces execution domain
|
|
%7 = fadd <8 x float> %6, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <8 x float> %7
|
|
}
|
|
|
|
define <2 x double> @stack_fold_andpd(<2 x double> %a0, <2 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_andpd
|
|
;CHECK: vandpd {{-?[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 = bitcast <2 x double> %a0 to <2 x i64>
|
|
%3 = bitcast <2 x double> %a1 to <2 x i64>
|
|
%4 = and <2 x i64> %2, %3
|
|
%5 = bitcast <2 x i64> %4 to <2 x double>
|
|
; fadd forces execution domain
|
|
%6 = fadd <2 x double> %5, <double 0x0, double 0x0>
|
|
ret <2 x double> %6
|
|
}
|
|
|
|
define <4 x double> @stack_fold_andpd_ymm(<4 x double> %a0, <4 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_andpd_ymm
|
|
;CHECK: vandpd {{-?[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 = bitcast <4 x double> %a0 to <4 x i64>
|
|
%3 = bitcast <4 x double> %a1 to <4 x i64>
|
|
%4 = and <4 x i64> %2, %3
|
|
%5 = bitcast <4 x i64> %4 to <4 x double>
|
|
; fadd forces execution domain
|
|
%6 = fadd <4 x double> %5, <double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <4 x double> %6
|
|
}
|
|
|
|
define <4 x float> @stack_fold_andps(<4 x float> %a0, <4 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_andps
|
|
;CHECK: vandps {{-?[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 = bitcast <4 x float> %a0 to <4 x i32>
|
|
%3 = bitcast <4 x float> %a1 to <4 x i32>
|
|
%4 = and <4 x i32> %2, %3
|
|
%5 = bitcast <4 x i32> %4 to <4 x float>
|
|
; fadd forces execution domain
|
|
%6 = fadd <4 x float> %5, <float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <4 x float> %6
|
|
}
|
|
|
|
define <8 x float> @stack_fold_andps_ymm(<8 x float> %a0, <8 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_andps_ymm
|
|
;CHECK: vandps {{-?[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 = bitcast <8 x float> %a0 to <8 x i32>
|
|
%3 = bitcast <8 x float> %a1 to <8 x i32>
|
|
%4 = and <8 x i32> %2, %3
|
|
%5 = bitcast <8 x i32> %4 to <8 x float>
|
|
; fadd forces execution domain
|
|
%6 = fadd <8 x float> %5, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <8 x float> %6
|
|
}
|
|
|
|
define i8 @stack_fold_cmppd(<2 x double> %a0, <2 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_cmppd
|
|
;CHECK: vcmpeqpd {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%k[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}"()
|
|
%res = call i8 @llvm.x86.avx512.mask.cmp.pd.128(<2 x double> %a0, <2 x double> %a1, i32 0, i8 -1)
|
|
ret i8 %res
|
|
}
|
|
declare i8 @llvm.x86.avx512.mask.cmp.pd.128(<2 x double> , <2 x double> , i32, i8)
|
|
|
|
define i8 @stack_fold_cmppd_ymm(<4 x double> %a0, <4 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_cmppd_ymm
|
|
;CHECK: vcmpeqpd {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%k[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}"()
|
|
%res = call i8 @llvm.x86.avx512.mask.cmp.pd.256(<4 x double> %a0, <4 x double> %a1, i32 0, i8 -1)
|
|
ret i8 %res
|
|
}
|
|
declare i8 @llvm.x86.avx512.mask.cmp.pd.256(<4 x double> , <4 x double> , i32, i8)
|
|
|
|
define i8 @stack_fold_cmpps(<4 x float> %a0, <4 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_cmpps
|
|
;CHECK: vcmpeqps {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}}, {{%k[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}"()
|
|
%res = call i8 @llvm.x86.avx512.mask.cmp.ps.128(<4 x float> %a0, <4 x float> %a1, i32 0, i8 -1)
|
|
ret i8 %res
|
|
}
|
|
declare i8 @llvm.x86.avx512.mask.cmp.ps.128(<4 x float> , <4 x float> , i32, i8)
|
|
|
|
define i8 @stack_fold_cmpps_ymm(<8 x float> %a0, <8 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_cmpps_ymm
|
|
;CHECK: vcmpeqps {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%k[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}"()
|
|
%res = call i8 @llvm.x86.avx512.mask.cmp.ps.256(<8 x float> %a0, <8 x float> %a1, i32 0, i8 -1)
|
|
ret i8 %res
|
|
}
|
|
declare i8 @llvm.x86.avx512.mask.cmp.ps.256(<8 x float> , <8 x float> , i32, i8)
|
|
|
|
define <2 x double> @stack_fold_maxpd(<2 x double> %a0, <2 x double> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_maxpd
|
|
;CHECK: vmaxpd {{-?[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 <2 x double> @llvm.x86.sse2.max.pd(<2 x double> %a0, <2 x double> %a1)
|
|
ret <2 x double> %2
|
|
}
|
|
declare <2 x double> @llvm.x86.sse2.max.pd(<2 x double>, <2 x double>) nounwind readnone
|
|
|
|
define <2 x double> @stack_fold_maxpd_commutable(<2 x double> %a0, <2 x double> %a1) #1 {
|
|
;CHECK-LABEL: stack_fold_maxpd_commutable
|
|
;CHECK: vmaxpd {{-?[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 <2 x double> @llvm.x86.sse2.max.pd(<2 x double> %a0, <2 x double> %a1)
|
|
ret <2 x double> %2
|
|
}
|
|
|
|
define <4 x double> @stack_fold_maxpd_ymm(<4 x double> %a0, <4 x double> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_maxpd_ymm
|
|
;CHECK: vmaxpd {{-?[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 <4 x double> @llvm.x86.avx.max.pd.256(<4 x double> %a0, <4 x double> %a1)
|
|
ret <4 x double> %2
|
|
}
|
|
declare <4 x double> @llvm.x86.avx.max.pd.256(<4 x double>, <4 x double>) nounwind readnone
|
|
|
|
define <4 x double> @stack_fold_maxpd_ymm_commutable(<4 x double> %a0, <4 x double> %a1) #1 {
|
|
;CHECK-LABEL: stack_fold_maxpd_ymm_commutable
|
|
;CHECK: vmaxpd {{-?[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 <4 x double> @llvm.x86.avx.max.pd.256(<4 x double> %a0, <4 x double> %a1)
|
|
ret <4 x double> %2
|
|
}
|
|
|
|
define <4 x float> @stack_fold_maxps(<4 x float> %a0, <4 x float> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_maxps
|
|
;CHECK: vmaxps {{-?[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 <4 x float> @llvm.x86.sse.max.ps(<4 x float> %a0, <4 x float> %a1)
|
|
ret <4 x float> %2
|
|
}
|
|
declare <4 x float> @llvm.x86.sse.max.ps(<4 x float>, <4 x float>) nounwind readnone
|
|
|
|
define <4 x float> @stack_fold_maxps_commutable(<4 x float> %a0, <4 x float> %a1) #1 {
|
|
;CHECK-LABEL: stack_fold_maxps_commutable
|
|
;CHECK: vmaxps {{-?[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 <4 x float> @llvm.x86.sse.max.ps(<4 x float> %a0, <4 x float> %a1)
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
define <8 x float> @stack_fold_maxps_ymm(<8 x float> %a0, <8 x float> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_maxps_ymm
|
|
;CHECK: vmaxps {{-?[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 <8 x float> @llvm.x86.avx.max.ps.256(<8 x float> %a0, <8 x float> %a1)
|
|
ret <8 x float> %2
|
|
}
|
|
declare <8 x float> @llvm.x86.avx.max.ps.256(<8 x float>, <8 x float>) nounwind readnone
|
|
|
|
define <8 x float> @stack_fold_maxps_ymm_commutable(<8 x float> %a0, <8 x float> %a1) #1 {
|
|
;CHECK-LABEL: stack_fold_maxps_ymm_commutable
|
|
;CHECK: vmaxps {{-?[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 <8 x float> @llvm.x86.avx.max.ps.256(<8 x float> %a0, <8 x float> %a1)
|
|
ret <8 x float> %2
|
|
}
|
|
|
|
define <4 x float> @stack_fold_minps(<4 x float> %a0, <4 x float> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_minps
|
|
;CHECK: vminps {{-?[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},~{flags}"()
|
|
%2 = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %a0, <4 x float> %a1)
|
|
ret <4 x float> %2
|
|
}
|
|
declare <4 x float> @llvm.x86.sse.min.ps(<4 x float>, <4 x float>) nounwind readnone
|
|
|
|
define <4 x float> @stack_fold_minps_commutable(<4 x float> %a0, <4 x float> %a1) #1 {
|
|
;CHECK-LABEL: stack_fold_minps_commutable
|
|
;CHECK: vminps {{-?[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},~{flags}"()
|
|
%2 = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %a0, <4 x float> %a1)
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
define <8 x float> @stack_fold_minps_ymm(<8 x float> %a0, <8 x float> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_minps_ymm
|
|
;CHECK: vminps {{-?[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},~{flags}"()
|
|
%2 = call <8 x float> @llvm.x86.avx.min.ps.256(<8 x float> %a0, <8 x float> %a1)
|
|
ret <8 x float> %2
|
|
}
|
|
declare <8 x float> @llvm.x86.avx.min.ps.256(<8 x float>, <8 x float>) nounwind readnone
|
|
|
|
define <8 x float> @stack_fold_minps_ymm_commutable(<8 x float> %a0, <8 x float> %a1) #1 {
|
|
;CHECK-LABEL: stack_fold_minps_ymm_commutable
|
|
;CHECK: vminps {{-?[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},~{flags}"()
|
|
%2 = call <8 x float> @llvm.x86.avx.min.ps.256(<8 x float> %a0, <8 x float> %a1)
|
|
ret <8 x float> %2
|
|
}
|
|
|
|
define <2 x double> @stack_fold_orpd(<2 x double> %a0, <2 x double> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_orpd
|
|
;CHECK: vorpd {{-?[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 = bitcast <2 x double> %a0 to <2 x i64>
|
|
%3 = bitcast <2 x double> %a1 to <2 x i64>
|
|
%4 = or <2 x i64> %2, %3
|
|
%5 = bitcast <2 x i64> %4 to <2 x double>
|
|
; fadd forces execution domain
|
|
%6 = fadd <2 x double> %5, <double 0x0, double 0x0>
|
|
ret <2 x double> %6
|
|
}
|
|
|
|
define <4 x double> @stack_fold_orpd_ymm(<4 x double> %a0, <4 x double> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_orpd_ymm
|
|
;CHECK: vorpd {{-?[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 = bitcast <4 x double> %a0 to <4 x i64>
|
|
%3 = bitcast <4 x double> %a1 to <4 x i64>
|
|
%4 = or <4 x i64> %2, %3
|
|
%5 = bitcast <4 x i64> %4 to <4 x double>
|
|
; fadd forces execution domain
|
|
%6 = fadd <4 x double> %5, <double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <4 x double> %6
|
|
}
|
|
|
|
define <4 x float> @stack_fold_orps(<4 x float> %a0, <4 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_orps
|
|
;CHECK: vorps {{-?[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 = bitcast <4 x float> %a0 to <4 x i32>
|
|
%3 = bitcast <4 x float> %a1 to <4 x i32>
|
|
%4 = or <4 x i32> %2, %3
|
|
%5 = bitcast <4 x i32> %4 to <4 x float>
|
|
; fadd forces execution domain
|
|
%6 = fadd <4 x float> %5, <float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <4 x float> %6
|
|
}
|
|
|
|
define <8 x float> @stack_fold_orps_ymm(<8 x float> %a0, <8 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_orps_ymm
|
|
;CHECK: vorps {{-?[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 = bitcast <8 x float> %a0 to <8 x i32>
|
|
%3 = bitcast <8 x float> %a1 to <8 x i32>
|
|
%4 = or <8 x i32> %2, %3
|
|
%5 = bitcast <8 x i32> %4 to <8 x float>
|
|
; fadd forces execution domain
|
|
%6 = fadd <8 x float> %5, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <8 x float> %6
|
|
}
|
|
|
|
define <2 x double> @stack_fold_subpd(<2 x double> %a0, <2 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_subpd
|
|
;CHECK: vsubpd {{-?[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 = fsub <2 x double> %a0, %a1
|
|
ret <2 x double> %2
|
|
}
|
|
|
|
define <4 x double> @stack_fold_subpd_ymm(<4 x double> %a0, <4 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_subpd_ymm
|
|
;CHECK: vsubpd {{-?[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 = fsub <4 x double> %a0, %a1
|
|
ret <4 x double> %2
|
|
}
|
|
|
|
define <4 x float> @stack_fold_subps(<4 x float> %a0, <4 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_subps
|
|
;CHECK: vsubps {{-?[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 = fsub <4 x float> %a0, %a1
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
define <8 x float> @stack_fold_subps_ymm(<8 x float> %a0, <8 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_subps_ymm
|
|
;CHECK: vsubps {{-?[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 = fsub <8 x float> %a0, %a1
|
|
ret <8 x float> %2
|
|
}
|
|
|
|
define <2 x double> @stack_fold_xorpd(<2 x double> %a0, <2 x double> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_xorpd
|
|
;CHECK: vxorpd {{-?[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 = bitcast <2 x double> %a0 to <2 x i64>
|
|
%3 = bitcast <2 x double> %a1 to <2 x i64>
|
|
%4 = xor <2 x i64> %2, %3
|
|
%5 = bitcast <2 x i64> %4 to <2 x double>
|
|
; fadd forces execution domain
|
|
%6 = fadd <2 x double> %5, <double 0x0, double 0x0>
|
|
ret <2 x double> %6
|
|
}
|
|
|
|
define <4 x double> @stack_fold_xorpd_ymm(<4 x double> %a0, <4 x double> %a1) #0 {
|
|
;CHECK-LABEL: stack_fold_xorpd_ymm
|
|
;CHECK: vxorpd {{-?[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 = bitcast <4 x double> %a0 to <4 x i64>
|
|
%3 = bitcast <4 x double> %a1 to <4 x i64>
|
|
%4 = xor <4 x i64> %2, %3
|
|
%5 = bitcast <4 x i64> %4 to <4 x double>
|
|
; fadd forces execution domain
|
|
%6 = fadd <4 x double> %5, <double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <4 x double> %6
|
|
}
|
|
|
|
define <4 x float> @stack_fold_xorps(<4 x float> %a0, <4 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_xorps
|
|
;CHECK: vxorps {{-?[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 = bitcast <4 x float> %a0 to <4 x i32>
|
|
%3 = bitcast <4 x float> %a1 to <4 x i32>
|
|
%4 = xor <4 x i32> %2, %3
|
|
%5 = bitcast <4 x i32> %4 to <4 x float>
|
|
; fadd forces execution domain
|
|
%6 = fadd <4 x float> %5, <float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <4 x float> %6
|
|
}
|
|
|
|
define <8 x float> @stack_fold_xorps_ymm(<8 x float> %a0, <8 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_xorps_ymm
|
|
;CHECK: vxorps {{-?[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 = bitcast <8 x float> %a0 to <8 x i32>
|
|
%3 = bitcast <8 x float> %a1 to <8 x i32>
|
|
%4 = xor <8 x i32> %2, %3
|
|
%5 = bitcast <8 x i32> %4 to <8 x float>
|
|
; fadd forces execution domain
|
|
%6 = fadd <8 x float> %5, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <8 x float> %6
|
|
}
|
|
|
|
define <4 x float> @stack_fold_extractf32x4(<8 x float> %a0, <8 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_extractf32x4
|
|
;CHECK: vextractf32x4 $1, {{%ymm[0-9][0-9]*}}, {{-?[0-9]*}}(%rsp) {{.*#+}} 16-byte Folded Spill
|
|
%1 = shufflevector <8 x float> %a0, <8 x float> %a1, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
|
%2 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{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}"()
|
|
ret <4 x float> %1
|
|
}
|
|
|
|
define <2 x double> @stack_fold_extractf64x2(<4 x double> %a0, <4 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_extractf64x2
|
|
;CHECK: vextractf64x2 $1, {{%ymm[0-9][0-9]*}}, {{-?[0-9]*}}(%rsp) {{.*#+}} 16-byte Folded Spill
|
|
%1 = shufflevector <4 x double> %a0, <4 x double> %a1, <2 x i32> <i32 2, i32 3>
|
|
%2 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{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}"()
|
|
ret <2 x double> %1
|
|
}
|
|
|
|
define <8 x float> @stack_fold_insertf32x4(<4 x float> %a0, <4 x float> %a1) {
|
|
;CHECK-LABEL: stack_fold_insertf32x4
|
|
;CHECK: vinsertf32x4 $1, {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[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},~{flags}"()
|
|
%2 = shufflevector <4 x float> %a0, <4 x float> %a1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
ret <8 x float> %2
|
|
}
|
|
|
|
define <4 x double> @stack_fold_insertf64x2(<2 x double> %a0, <2 x double> %a1) {
|
|
;CHECK-LABEL: stack_fold_insertf64x2
|
|
;CHECK: vinsertf64x2 $1, {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[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},~{flags}"()
|
|
%2 = shufflevector <2 x double> %a0, <2 x double> %a1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
ret <4 x double> %2
|
|
}
|
|
|
|
attributes #0 = { "unsafe-fp-math"="false" }
|
|
attributes #1 = { "unsafe-fp-math"="true" }
|