maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][SSE] Force blend domains on stack folding tests 

llvm-svn: 322385
This commit is contained in:
Simon Pilgrim 2018-01-12 18:05:29 +00:00
parent b8bc537923
commit edff13b9de
2 changed files with 18 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
llvm/test/CodeGen/X86/stack-folding-fp-avx1.ll
View File

@ -223,7 +223,9 @@ define <2 x double> @stack_fold_blendpd(<2 x double> %a0, <2 x double> %a1) {
;CHECK: vblendpd $2, {{-?[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 = select <2 x i1> <i1 1, i1 0>, <2 x double> %a0, <2 x double> %a1
ret <2 x double> %2
; fadd forces execution domain
%3 = fadd <2 x double> %2, <double 0x0, double 0x0>
ret <2 x double> %3
}
define <4 x double> @stack_fold_blendpd_ymm(<4 x double> %a0, <4 x double> %a1) {
@ -231,15 +233,18 @@ define <4 x double> @stack_fold_blendpd_ymm(<4 x double> %a0, <4 x double> %a1)
;CHECK: vblendpd $6, {{-?[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 = select <4 x i1> <i1 1, i1 0, i1 0, i1 1>, <4 x double> %a0, <4 x double> %a1
ret <4 x double> %2
}
; fadd forces execution domain
%3 = fadd <4 x double> %2, <double 0x0, double 0x0, double 0x0, double 0x0>
ret <4 x double> %3}
define <4 x float> @stack_fold_blendps(<4 x float> %a0, <4 x float> %a1) {
;CHECK-LABEL: stack_fold_blendps
;CHECK: vblendps $6, {{-?[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 = select <4 x i1> <i1 1, i1 0, i1 0, i1 1>, <4 x float> %a0, <4 x float> %a1
ret <4 x float> %2
; fadd forces execution domain
%3 = fadd <4 x float> %2, <float 0x0, float 0x0, float 0x0, float 0x0>
ret <4 x float> %3
}
define <8 x float> @stack_fold_blendps_ymm(<8 x float> %a0, <8 x float> %a1) {
@ -247,7 +252,9 @@ define <8 x float> @stack_fold_blendps_ymm(<8 x float> %a0, <8 x float> %a1) {
;CHECK: vblendps $102, {{-?[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 = select <8 x i1> <i1 1, i1 0, i1 0, i1 1, i1 1, i1 0, i1 0, i1 1>, <8 x float> %a0, <8 x float> %a1
ret <8 x float> %2
; fadd forces execution domain
%3 = fadd <8 x float> %2, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
ret <8 x float> %3
}
define <2 x double> @stack_fold_blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %c) {

8
llvm/test/CodeGen/X86/stack-folding-fp-sse42.ll
View File

@ -135,7 +135,9 @@ define <2 x double> @stack_fold_blendpd(<2 x double> %a0, <2 x double> %a1) {
;CHECK: blendpd $2, {{-?[0-9]*}}(%rsp), {{%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 = select <2 x i1> <i1 1, i1 0>, <2 x double> %a0, <2 x double> %a1
ret <2 x double> %2
; fadd forces execution domain
%3 = fadd <2 x double> %2, <double 0x0, double 0x0>
ret <2 x double> %3
}
define <4 x float> @stack_fold_blendps(<4 x float> %a0, <4 x float> %a1) {
@ -143,7 +145,9 @@ define <4 x float> @stack_fold_blendps(<4 x float> %a0, <4 x float> %a1) {
;CHECK: blendps $6, {{-?[0-9]*}}(%rsp), {{%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 = select <4 x i1> <i1 1, i1 0, i1 0, i1 1>, <4 x float> %a0, <4 x float> %a1
ret <4 x float> %2
; fadd forces execution domain
%3 = fadd <4 x float> %2, <float 0x0, float 0x0, float 0x0, float 0x0>
ret <4 x float> %3
}
define <2 x double> @stack_fold_blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %c) {