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

[X86][SSE] Force execution domain on float/double unpack shuffle tests. 

llvm-svn: 235259
This commit is contained in:
Simon Pilgrim 2015-04-18 18:50:55 +00:00
parent 7216ccc3f3
commit e68c8606ed
2 changed files with 36 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
llvm/test/CodeGen/X86/stack-folding-fp-avx1.ll
View File

@ -1699,7 +1699,9 @@ define <2 x double> @stack_fold_unpckhpd(<2 x double> %a0, <2 x double> %a1) {
;CHECK: vunpckhpd {{-?[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 = shufflevector <2 x double> %a0, <2 x double> %a1, <2 x i32> <i32 1, i32 3>
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_unpckhpd_ymm(<4 x double> %a0, <4 x double> %a1) {
@ -1707,7 +1709,9 @@ define <4 x double> @stack_fold_unpckhpd_ymm(<4 x double> %a0, <4 x double> %a1)
;CHECK: vunpckhpd {{-?[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 = shufflevector <4 x double> %a0, <4 x double> %a1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
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_unpckhps(<4 x float> %a0, <4 x float> %a1) {
@ -1715,7 +1719,9 @@ define <4 x float> @stack_fold_unpckhps(<4 x float> %a0, <4 x float> %a1) {
;CHECK: vunpckhps {{-?[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 = shufflevector <4 x float> %a0, <4 x float> %a1, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
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_unpckhps_ymm(<8 x float> %a0, <8 x float> %a1) {
@ -1723,7 +1729,9 @@ define <8 x float> @stack_fold_unpckhps_ymm(<8 x float> %a0, <8 x float> %a1) {
;CHECK: vunpckhps {{-?[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 = shufflevector <8 x float> %a0, <8 x float> %a1, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
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_unpcklpd(<2 x double> %a0, <2 x double> %a1) {
@ -1731,7 +1739,9 @@ define <2 x double> @stack_fold_unpcklpd(<2 x double> %a0, <2 x double> %a1) {
;CHECK: vunpcklpd {{-?[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 = shufflevector <2 x double> %a0, <2 x double> %a1, <2 x i32> <i32 0, i32 2>
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_unpcklpd_ymm(<4 x double> %a0, <4 x double> %a1) {
@ -1739,7 +1749,9 @@ define <4 x double> @stack_fold_unpcklpd_ymm(<4 x double> %a0, <4 x double> %a1)
;CHECK: vunpcklpd {{-?[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 = shufflevector <4 x double> %a0, <4 x double> %a1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
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_unpcklps(<4 x float> %a0, <4 x float> %a1) {
@ -1747,7 +1759,9 @@ define <4 x float> @stack_fold_unpcklps(<4 x float> %a0, <4 x float> %a1) {
;CHECK: vunpcklps {{-?[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 = shufflevector <4 x float> %a0, <4 x float> %a1, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
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_unpcklps_ymm(<8 x float> %a0, <8 x float> %a1) {
@ -1755,7 +1769,9 @@ define <8 x float> @stack_fold_unpcklps_ymm(<8 x float> %a0, <8 x float> %a1) {
;CHECK: vunpcklps {{-?[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 = shufflevector <8 x float> %a0, <8 x float> %a1, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
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_xorpd(<2 x double> %a0, <2 x double> %a1) {

16
llvm/test/CodeGen/X86/stack-folding-fp-sse42.ll
View File

@ -1035,7 +1035,9 @@ define <2 x double> @stack_fold_unpckhpd(<2 x double> %a0, <2 x double> %a1) {
;CHECK: unpckhpd {{-?[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 = shufflevector <2 x double> %a0, <2 x double> %a1, <2 x i32> <i32 1, i32 3>
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_unpckhps(<4 x float> %a0, <4 x float> %a1) {
@ -1043,7 +1045,9 @@ define <4 x float> @stack_fold_unpckhps(<4 x float> %a0, <4 x float> %a1) {
;CHECK: unpckhps {{-?[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 = shufflevector <4 x float> %a0, <4 x float> %a1, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
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_unpcklpd(<2 x double> %a0, <2 x double> %a1) {
@ -1051,7 +1055,9 @@ define <2 x double> @stack_fold_unpcklpd(<2 x double> %a0, <2 x double> %a1) {
;CHECK: unpcklpd {{-?[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 = shufflevector <2 x double> %a0, <2 x double> %a1, <2 x i32> <i32 0, i32 2>
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_unpcklps(<4 x float> %a0, <4 x float> %a1) {
@ -1059,7 +1065,9 @@ define <4 x float> @stack_fold_unpcklps(<4 x float> %a0, <4 x float> %a1) {
;CHECK: unpcklps {{-?[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 = shufflevector <4 x float> %a0, <4 x float> %a1, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
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_xorpd(<2 x double> %a0, <2 x double> %a1) {