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

[x86] add hadd test with no undefs, remove duplicate tests; NFC 

llvm-svn: 343975
This commit is contained in:
Sanjay Patel 2018-10-08 16:24:43 +00:00
parent d48789c0c4
commit 8459465a44
1 changed files with 11 additions and 154 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

165
llvm/test/CodeGen/X86/haddsub-undef.ll
View File

@ -467,19 +467,23 @@ define <2 x double> @add_pd_003(<2 x double> %x) {
ret <2 x double> %add ret <2 x double> %add
} }
define <2 x double> @add_pd_005(<2 x double> %x) { ; Change shuffle mask - no undefs.
; SSE-LABEL: add_pd_005:
define <2 x double> @add_pd_003_2(<2 x double> %x) {
; SSE-LABEL: add_pd_003_2:
; SSE: # %bb.0: ; SSE: # %bb.0:
; SSE-NEXT: movddup {{.*#+}} xmm1 = xmm0[0,0] ; SSE-NEXT: movapd %xmm0, %xmm1
; SSE-NEXT: addpd %xmm1, %xmm0 ; SSE-NEXT: shufpd {{.*#+}} xmm1 = xmm1[1],xmm0[0]
; SSE-NEXT: addpd %xmm0, %xmm1
; SSE-NEXT: movapd %xmm1, %xmm0
; SSE-NEXT: retq ; SSE-NEXT: retq
; ;
; AVX-LABEL: add_pd_005: ; AVX-LABEL: add_pd_003_2:
; AVX: # %bb.0: ; AVX: # %bb.0:
; AVX-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0] ; AVX-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; AVX-NEXT: vaddpd %xmm0, %xmm1, %xmm0 ; AVX-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq ; AVX-NEXT: retq
%l = shufflevector <2 x double> %x, <2 x double> undef, <2 x i32> <i32 undef, i32 0> %l = shufflevector <2 x double> %x, <2 x double> undef, <2 x i32> <i32 1, i32 0>
%add = fadd <2 x double> %l, %x %add = fadd <2 x double> %l, %x
ret <2 x double> %add ret <2 x double> %add
} }
@ -505,27 +509,6 @@ define <2 x double> @add_pd_010(<2 x double> %x) {
ret <2 x double> %shuffle2 ret <2 x double> %shuffle2
} }
define <2 x double> @add_pd_012(<2 x double> %x) {
; SSE-LABEL: add_pd_012:
; SSE: # %bb.0:
; SSE-NEXT: movddup {{.*#+}} xmm1 = xmm0[0,0]
; SSE-NEXT: addpd %xmm0, %xmm1
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1,1]
; SSE-NEXT: movapd %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: add_pd_012:
; AVX: # %bb.0:
; AVX-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX-NEXT: retq
%l = shufflevector <2 x double> %x, <2 x double> undef, <2 x i32> <i32 undef, i32 0>
%add = fadd <2 x double> %l, %x
%shuffle = shufflevector <2 x double> %add, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
ret <2 x double> %shuffle
}
define <4 x float> @add_ps_007(<4 x float> %x) { define <4 x float> @add_ps_007(<4 x float> %x) {
; SSE-LABEL: add_ps_007: ; SSE-LABEL: add_ps_007:
; SSE: # %bb.0: ; SSE: # %bb.0:
@ -547,27 +530,6 @@ define <4 x float> @add_ps_007(<4 x float> %x) {
ret <4 x float> %add ret <4 x float> %add
} }
define <4 x float> @add_ps_013(<4 x float> %x) {
; SSE-LABEL: add_ps_013:
; SSE: # %bb.0:
; SSE-NEXT: movaps %xmm0, %xmm1
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm0[0,2]
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; SSE-NEXT: addps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: add_ps_013:
; AVX: # %bb.0:
; AVX-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,1,0,2]
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%l = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 2>
%r = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 1, i32 3>
%add = fadd <4 x float> %l, %r
ret <4 x float> %add
}
define <4 x float> @add_ps_030(<4 x float> %x) { define <4 x float> @add_ps_030(<4 x float> %x) {
; SSE-LABEL: add_ps_030: ; SSE-LABEL: add_ps_030:
; SSE: # %bb.0: ; SSE: # %bb.0:
@ -592,30 +554,6 @@ define <4 x float> @add_ps_030(<4 x float> %x) {
ret <4 x float> %shuffle2 ret <4 x float> %shuffle2
} }
define <4 x float> @add_ps_036(<4 x float> %x) {
; SSE-LABEL: add_ps_036:
; SSE: # %bb.0:
; SSE-NEXT: movaps %xmm0, %xmm1
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm0[0,2]
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; SSE-NEXT: addps %xmm1, %xmm0
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,2,2,3]
; SSE-NEXT: retq
;
; AVX-LABEL: add_ps_036:
; AVX: # %bb.0:
; AVX-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,1,0,2]
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,2,3]
; AVX-NEXT: retq
%l = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 2>
%r = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 1, i32 3>
%add = fadd <4 x float> %l, %r
%shuffle = shufflevector <4 x float> %add, <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 undef, i32 undef>
ret <4 x float> %shuffle
}
define <4 x float> @add_ps_007_2(<4 x float> %x) { define <4 x float> @add_ps_007_2(<4 x float> %x) {
; SSE-LABEL: add_ps_007_2: ; SSE-LABEL: add_ps_007_2:
; SSE: # %bb.0: ; SSE: # %bb.0:
@ -653,43 +591,6 @@ define <4 x float> @add_ps_008(<4 x float> %x) {
ret <4 x float> %add ret <4 x float> %add
} }
define <4 x float> @add_ps_011(<4 x float> %x) {
; SSE-LABEL: add_ps_011:
; SSE: # %bb.0:
; SSE-NEXT: movddup {{.*#+}} xmm1 = xmm0[0,0]
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; SSE-NEXT: addps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: add_ps_011:
; AVX: # %bb.0:
; AVX-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%l = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 undef>
%r = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 1, i32 undef>
%add = fadd <4 x float> %l, %r
ret <4 x float> %add
}
define <4 x float> @add_ps_012(<4 x float> %x) {
; SSE-LABEL: add_ps_012:
; SSE: # %bb.0:
; SSE-NEXT: movsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; SSE-NEXT: addps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: add_ps_012:
; AVX: # %bb.0:
; AVX-NEXT: vmovsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%l = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 undef, i32 2>
%add = fadd <4 x float> %l, %x
ret <4 x float> %add
}
define <4 x float> @add_ps_017(<4 x float> %x) { define <4 x float> @add_ps_017(<4 x float> %x) {
; SSE-LABEL: add_ps_017: ; SSE-LABEL: add_ps_017:
; SSE: # %bb.0: ; SSE: # %bb.0:
@ -734,47 +635,3 @@ define <4 x float> @add_ps_018(<4 x float> %x) {
ret <4 x float> %shuffle2 ret <4 x float> %shuffle2
} }
define <4 x float> @add_ps_021(<4 x float> %x) {
; SSE-LABEL: add_ps_021:
; SSE: # %bb.0:
; SSE-NEXT: movsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; SSE-NEXT: addps %xmm0, %xmm1
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,1,2,3]
; SSE-NEXT: movaps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: add_ps_021:
; AVX: # %bb.0:
; AVX-NEXT: vmovsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX-NEXT: retq
%l = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 undef, i32 2>
%add = fadd <4 x float> %l, %x
%shuffle = shufflevector <4 x float> %add, <4 x float> undef, <4 x i32> <i32 3, i32 undef, i32 undef, i32 undef>
ret <4 x float> %shuffle
}
define <4 x float> @add_ps_022(<4 x float> %x) {
; SSE-LABEL: add_ps_022:
; SSE: # %bb.0:
; SSE-NEXT: movddup {{.*#+}} xmm1 = xmm0[0,0]
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; SSE-NEXT: addps %xmm1, %xmm0
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT: retq
;
; AVX-LABEL: add_ps_022:
; AVX: # %bb.0:
; AVX-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX-NEXT: retq
%l = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 undef>
%r = shufflevector <4 x float> %x, <4 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 1, i32 undef>
%add = fadd <4 x float> %l, %r
%shuffle = shufflevector <4 x float> %add, <4 x float> undef, <4 x i32> <i32 undef, i32 2, i32 undef, i32 undef>
ret <4 x float> %shuffle
}