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

[x86] add common FileCheck prefix to reduce assert duplication; NFC 

llvm-svn: 350356
This commit is contained in:
Sanjay Patel 2019-01-03 22:11:14 +00:00
parent 8de916d1a4
commit 8db27b31ac
1 changed files with 86 additions and 182 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

268
llvm/test/CodeGen/X86/haddsub-undef.ll
View File

@ -1,10 +1,10 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSE-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+ssse3,fast-hops | FileCheck %s --check-prefixes=SSE,SSE-FAST
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1,AVX1-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx,fast-hops | FileCheck %s --check-prefixes=AVX,AVX1,AVX1-FAST
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2,fast-hops | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSE-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+ssse3,fast-hops | FileCheck %s --check-prefixes=SSE,SSE-FAST
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX-SLOW,AVX1,AVX1-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx,fast-hops | FileCheck %s --check-prefixes=AVX,AVX-FAST,AVX1,AVX1-FAST
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX-SLOW,AVX2,AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+avx2,fast-hops | FileCheck %s --check-prefixes=AVX,AVX-FAST,AVX2,AVX2-FAST
; Verify that we correctly fold horizontal binop even in the presence of UNDEFs.
@ -463,27 +463,16 @@ define <2 x double> @add_pd_003(<2 x double> %x) {
; SSE-FAST-NEXT: haddpd %xmm0, %xmm0
; SSE-FAST-NEXT: retq
;
; AVX1-SLOW-LABEL: add_pd_003:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX1-SLOW-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: retq
; AVX-SLOW-LABEL: add_pd_003:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX-SLOW-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: retq
;
; AVX1-FAST-LABEL: add_pd_003:
; AVX1-FAST: # %bb.0:
; AVX1-FAST-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; AVX1-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: add_pd_003:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX2-SLOW-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: add_pd_003:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; AVX2-FAST-NEXT: retq
; AVX-FAST-LABEL: add_pd_003:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; AVX-FAST-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
ret <2 x double> %add
@ -505,27 +494,16 @@ define <2 x double> @add_pd_003_2(<2 x double> %x) {
; SSE-FAST-NEXT: haddpd %xmm0, %xmm0
; SSE-FAST-NEXT: retq
;
; AVX1-SLOW-LABEL: add_pd_003_2:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; AVX1-SLOW-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: retq
; AVX-SLOW-LABEL: add_pd_003_2:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; AVX-SLOW-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: retq
;
; AVX1-FAST-LABEL: add_pd_003_2:
; AVX1-FAST: # %bb.0:
; AVX1-FAST-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; AVX1-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: add_pd_003_2:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
; AVX2-SLOW-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: add_pd_003_2:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; AVX2-FAST-NEXT: retq
; AVX-FAST-LABEL: add_pd_003_2:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: retq
%l = shufflevector <2 x double> %x, <2 x double> undef, <2 x i32> <i32 1, i32 0>
%add = fadd <2 x double> %l, %x
ret <2 x double> %add
@ -545,31 +523,18 @@ define <2 x double> @add_pd_010(<2 x double> %x) {
; SSE-FAST-NEXT: haddpd %xmm0, %xmm0
; SSE-FAST-NEXT: retq
;
; AVX1-SLOW-LABEL: add_pd_010:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX1-SLOW-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX1-SLOW-NEXT: retq
; AVX-SLOW-LABEL: add_pd_010:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX-SLOW-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX-SLOW-NEXT: retq
;
; AVX1-FAST-LABEL: add_pd_010:
; AVX1-FAST: # %bb.0:
; AVX1-FAST-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; AVX1-FAST-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX1-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: add_pd_010:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0]
; AVX2-SLOW-NEXT: vaddpd %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: add_pd_010:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX2-FAST-NEXT: retq
; AVX-FAST-LABEL: add_pd_010:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX-FAST-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
%shuffle2 = shufflevector <2 x double> %add, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
@ -590,29 +555,17 @@ define <4 x float> @add_ps_007(<4 x float> %x) {
; SSE-FAST-NEXT: haddps %xmm0, %xmm0
; SSE-FAST-NEXT: retq
;
; AVX1-SLOW-LABEL: add_ps_007:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,1,0,2]
; AVX1-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX1-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: retq
; AVX-SLOW-LABEL: add_ps_007:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,1,0,2]
; AVX-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: retq
;
; AVX1-FAST-LABEL: add_ps_007:
; AVX1-FAST: # %bb.0:
; AVX1-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX1-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: add_ps_007:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,1,0,2]
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX2-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: add_ps_007:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX2-FAST-NEXT: retq
; AVX-FAST-LABEL: add_ps_007:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX-FAST-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
@ -635,33 +588,19 @@ define <4 x float> @add_ps_030(<4 x float> %x) {
; SSE-FAST-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,2,2,3]
; SSE-FAST-NEXT: retq
;
; AVX1-SLOW-LABEL: add_ps_030:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,1,0,2]
; AVX1-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX1-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,2,3]
; AVX1-SLOW-NEXT: retq
; AVX-SLOW-LABEL: add_ps_030:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,1,0,2]
; AVX-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,2,3]
; AVX-SLOW-NEXT: retq
;
; AVX1-FAST-LABEL: add_ps_030:
; AVX1-FAST: # %bb.0:
; AVX1-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX1-FAST-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,2,3]
; AVX1-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: add_ps_030:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,1,0,2]
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX2-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,2,3]
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: add_ps_030:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,2,3]
; AVX2-FAST-NEXT: retq
; AVX-FAST-LABEL: add_ps_030:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,2,3]
; AVX-FAST-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
@ -689,10 +628,10 @@ define <4 x float> @add_ps_007_2(<4 x float> %x) {
; AVX1-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: retq
;
; AVX1-FAST-LABEL: add_ps_007_2:
; AVX1-FAST: # %bb.0:
; AVX1-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX1-FAST-NEXT: retq
; AVX-FAST-LABEL: add_ps_007_2:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: add_ps_007_2:
; AVX2-SLOW: # %bb.0:
@ -700,11 +639,6 @@ define <4 x float> @add_ps_007_2(<4 x float> %x) {
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
; AVX2-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: add_ps_007_2:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX2-FAST-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
@ -723,27 +657,16 @@ define <4 x float> @add_ps_008(<4 x float> %x) {
; SSE-FAST-NEXT: haddps %xmm0, %xmm0
; SSE-FAST-NEXT: retq
;
; AVX1-SLOW-LABEL: add_ps_008:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vmovsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; AVX1-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: retq
; AVX-SLOW-LABEL: add_ps_008:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vmovsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; AVX-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: retq
;
; AVX1-FAST-LABEL: add_ps_008:
; AVX1-FAST: # %bb.0:
; AVX1-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX1-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: add_ps_008:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vmovsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; AVX2-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: add_ps_008:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX2-FAST-NEXT: retq
; AVX-FAST-LABEL: add_ps_008:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX-FAST-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
@ -764,31 +687,18 @@ define <4 x float> @add_ps_017(<4 x float> %x) {
; SSE-FAST-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE-FAST-NEXT: retq
;
; AVX1-SLOW-LABEL: add_ps_017:
; AVX1-SLOW: # %bb.0:
; AVX1-SLOW-NEXT: vmovsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; AVX1-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX1-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX1-SLOW-NEXT: retq
; AVX-SLOW-LABEL: add_ps_017:
; AVX-SLOW: # %bb.0:
; AVX-SLOW-NEXT: vmovsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; AVX-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX-SLOW-NEXT: retq
;
; AVX1-FAST-LABEL: add_ps_017:
; AVX1-FAST: # %bb.0:
; AVX1-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX1-FAST-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX1-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: add_ps_017:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vmovsldup {{.*#+}} xmm1 = xmm0[0,0,2,2]
; AVX2-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: add_ps_017:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX2-FAST-NEXT: retq
; AVX-FAST-LABEL: add_ps_017:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX-FAST-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
%shuffle2 = shufflevector <4 x float> %add, <4 x float> undef, <4 x i32> <i32 3, i32 undef, i32 undef, i32 undef>
@ -818,11 +728,11 @@ define <4 x float> @add_ps_018(<4 x float> %x) {
; AVX1-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-SLOW-NEXT: retq
;
; AVX1-FAST-LABEL: add_ps_018:
; AVX1-FAST: # %bb.0:
; AVX1-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX1-FAST-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-FAST-NEXT: retq
; AVX-FAST-LABEL: add_ps_018:
; AVX-FAST: # %bb.0:
; AVX-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX-FAST-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX-FAST-NEXT: retq
;
; AVX2-SLOW-LABEL: add_ps_018:
; AVX2-SLOW: # %bb.0:
@ -831,12 +741,6 @@ define <4 x float> @add_ps_018(<4 x float> %x) {
; AVX2-SLOW-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: add_ps_018:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vhaddps %xmm0, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX2-FAST-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