summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorSimon Pilgrim <llvm-dev@redking.me.uk>2024-04-23 16:29:15 +0100
committerSimon Pilgrim <llvm-dev@redking.me.uk>2024-04-23 16:39:37 +0100
commit03c8a29d1061c9dd47953c21aae70f46075f1b0c (patch)
treed308c3c38454f3b72f30defb0e65d546bb476231
parented255ed20b730160f8aec54e0acdbb40e3bc7fcf (diff)
[X86] pr34592.ll - add O3 codegen run for comparison
-rw-r--r--llvm/test/CodeGen/X86/pr34592.ll111
1 files changed, 70 insertions, 41 deletions
diff --git a/llvm/test/CodeGen/X86/pr34592.ll b/llvm/test/CodeGen/X86/pr34592.ll
index d86ca637cfeb..23de746ecb35 100644
--- a/llvm/test/CodeGen/X86/pr34592.ll
+++ b/llvm/test/CodeGen/X86/pr34592.ll
@@ -1,47 +1,76 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 -O0 | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 -O0 | FileCheck %s --check-prefixes=CHECK-O0
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 -O3 | FileCheck %s --check-prefixes=CHECK-O3
define <16 x i64> @pluto(<16 x i64> %arg, <16 x i64> %arg1, <16 x i64> %arg2, <16 x i64> %arg3, <16 x i64> %arg4) nounwind {
-; CHECK-LABEL: pluto:
-; CHECK: # %bb.0: # %bb
-; CHECK-NEXT: pushq %rbp
-; CHECK-NEXT: movq %rsp, %rbp
-; CHECK-NEXT: andq $-32, %rsp
-; CHECK-NEXT: subq $32, %rsp
-; CHECK-NEXT: vmovaps %ymm4, %ymm10
-; CHECK-NEXT: vmovaps %ymm3, %ymm9
-; CHECK-NEXT: vmovaps %ymm1, %ymm8
-; CHECK-NEXT: vmovaps 240(%rbp), %ymm4
-; CHECK-NEXT: vmovaps 208(%rbp), %ymm3
-; CHECK-NEXT: vmovaps 176(%rbp), %ymm1
-; CHECK-NEXT: vmovaps 144(%rbp), %ymm1
-; CHECK-NEXT: vmovaps 112(%rbp), %ymm11
-; CHECK-NEXT: vmovaps 80(%rbp), %ymm11
-; CHECK-NEXT: vmovaps 48(%rbp), %ymm11
-; CHECK-NEXT: vmovaps 16(%rbp), %ymm11
-; CHECK-NEXT: vpblendd {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm2[6,7]
-; CHECK-NEXT: vpunpcklqdq {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[2],ymm3[2]
-; CHECK-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,1,3]
-; CHECK-NEXT: vpermq {{.*#+}} ymm0 = ymm0[3,1,2,1]
-; CHECK-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5],ymm0[6,7]
-; CHECK-NEXT: vperm2i128 {{.*#+}} ymm1 = ymm7[2,3],ymm6[0,1]
-; CHECK-NEXT: vxorps %xmm2, %xmm2, %xmm2
-; CHECK-NEXT: vpblendd {{.*#+}} ymm2 = ymm1[0,1],ymm2[2,3],ymm1[4,5,6,7]
-; CHECK-NEXT: vpunpcklqdq {{.*#+}} ymm1 = ymm7[0],ymm5[0],ymm7[2],ymm5[2]
-; CHECK-NEXT: vpermq {{.*#+}} ymm1 = ymm1[2,1,2,3]
-; CHECK-NEXT: vpermq {{.*#+}} ymm4 = ymm4[1,1,1,1]
-; CHECK-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0,1],ymm4[2,3,4,5],ymm1[6,7]
-; CHECK-NEXT: vmovaps %xmm3, %xmm4
-; CHECK-NEXT: vmovaps %xmm7, %xmm3
-; CHECK-NEXT: vpblendd {{.*#+}} xmm4 = xmm3[0,1],xmm4[2,3]
-; CHECK-NEXT: # implicit-def: $ymm3
-; CHECK-NEXT: vmovaps %xmm4, %xmm3
-; CHECK-NEXT: vpermq {{.*#+}} ymm4 = ymm3[0,0,1,3]
-; CHECK-NEXT: vpslldq {{.*#+}} ymm3 = zero,zero,zero,zero,zero,zero,zero,zero,ymm5[0,1,2,3,4,5,6,7],zero,zero,zero,zero,zero,zero,zero,zero,ymm5[16,17,18,19,20,21,22,23]
-; CHECK-NEXT: vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm4[2,3,4,5],ymm3[6,7]
-; CHECK-NEXT: movq %rbp, %rsp
-; CHECK-NEXT: popq %rbp
-; CHECK-NEXT: retq
+; CHECK-O0-LABEL: pluto:
+; CHECK-O0: # %bb.0: # %bb
+; CHECK-O0-NEXT: pushq %rbp
+; CHECK-O0-NEXT: movq %rsp, %rbp
+; CHECK-O0-NEXT: andq $-32, %rsp
+; CHECK-O0-NEXT: subq $32, %rsp
+; CHECK-O0-NEXT: vmovaps %ymm4, %ymm10
+; CHECK-O0-NEXT: vmovaps %ymm3, %ymm9
+; CHECK-O0-NEXT: vmovaps %ymm1, %ymm8
+; CHECK-O0-NEXT: vmovaps 240(%rbp), %ymm4
+; CHECK-O0-NEXT: vmovaps 208(%rbp), %ymm3
+; CHECK-O0-NEXT: vmovaps 176(%rbp), %ymm1
+; CHECK-O0-NEXT: vmovaps 144(%rbp), %ymm1
+; CHECK-O0-NEXT: vmovaps 112(%rbp), %ymm11
+; CHECK-O0-NEXT: vmovaps 80(%rbp), %ymm11
+; CHECK-O0-NEXT: vmovaps 48(%rbp), %ymm11
+; CHECK-O0-NEXT: vmovaps 16(%rbp), %ymm11
+; CHECK-O0-NEXT: vpblendd {{.*#+}} ymm0 = ymm6[0,1,2,3,4,5],ymm2[6,7]
+; CHECK-O0-NEXT: vpunpcklqdq {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[2],ymm3[2]
+; CHECK-O0-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,1,3]
+; CHECK-O0-NEXT: vpermq {{.*#+}} ymm0 = ymm0[3,1,2,1]
+; CHECK-O0-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5],ymm0[6,7]
+; CHECK-O0-NEXT: vperm2i128 {{.*#+}} ymm1 = ymm7[2,3],ymm6[0,1]
+; CHECK-O0-NEXT: vxorps %xmm2, %xmm2, %xmm2
+; CHECK-O0-NEXT: vpblendd {{.*#+}} ymm2 = ymm1[0,1],ymm2[2,3],ymm1[4,5,6,7]
+; CHECK-O0-NEXT: vpunpcklqdq {{.*#+}} ymm1 = ymm7[0],ymm5[0],ymm7[2],ymm5[2]
+; CHECK-O0-NEXT: vpermq {{.*#+}} ymm1 = ymm1[2,1,2,3]
+; CHECK-O0-NEXT: vpermq {{.*#+}} ymm4 = ymm4[1,1,1,1]
+; CHECK-O0-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0,1],ymm4[2,3,4,5],ymm1[6,7]
+; CHECK-O0-NEXT: vmovaps %xmm3, %xmm4
+; CHECK-O0-NEXT: vmovaps %xmm7, %xmm3
+; CHECK-O0-NEXT: vpblendd {{.*#+}} xmm4 = xmm3[0,1],xmm4[2,3]
+; CHECK-O0-NEXT: # implicit-def: $ymm3
+; CHECK-O0-NEXT: vmovaps %xmm4, %xmm3
+; CHECK-O0-NEXT: vpermq {{.*#+}} ymm4 = ymm3[0,0,1,3]
+; CHECK-O0-NEXT: vpslldq {{.*#+}} ymm3 = zero,zero,zero,zero,zero,zero,zero,zero,ymm5[0,1,2,3,4,5,6,7],zero,zero,zero,zero,zero,zero,zero,zero,ymm5[16,17,18,19,20,21,22,23]
+; CHECK-O0-NEXT: vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm4[2,3,4,5],ymm3[6,7]
+; CHECK-O0-NEXT: movq %rbp, %rsp
+; CHECK-O0-NEXT: popq %rbp
+; CHECK-O0-NEXT: retq
+;
+; CHECK-O3-LABEL: pluto:
+; CHECK-O3: # %bb.0: # %bb
+; CHECK-O3-NEXT: pushq %rbp
+; CHECK-O3-NEXT: movq %rsp, %rbp
+; CHECK-O3-NEXT: andq $-32, %rsp
+; CHECK-O3-NEXT: subq $32, %rsp
+; CHECK-O3-NEXT: vmovdqa 208(%rbp), %ymm3
+; CHECK-O3-NEXT: vmovdqa 144(%rbp), %ymm0
+; CHECK-O3-NEXT: vpblendd {{.*#+}} ymm1 = ymm6[0,1,2,3,4,5],ymm2[6,7]
+; CHECK-O3-NEXT: vpunpcklqdq {{.*#+}} ymm0 = ymm0[0],ymm3[0],ymm0[2],ymm3[2]
+; CHECK-O3-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
+; CHECK-O3-NEXT: vpermq {{.*#+}} ymm1 = ymm1[3,1,2,1]
+; CHECK-O3-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3,4,5],ymm1[6,7]
+; CHECK-O3-NEXT: vperm2i128 {{.*#+}} ymm1 = ymm7[2,3],ymm6[0,1]
+; CHECK-O3-NEXT: vpxor %xmm2, %xmm2, %xmm2
+; CHECK-O3-NEXT: vpblendd {{.*#+}} ymm2 = ymm1[0,1],ymm2[2,3],ymm1[4,5,6,7]
+; CHECK-O3-NEXT: vpunpcklqdq {{.*#+}} ymm1 = ymm7[0],ymm5[0],ymm7[2],ymm5[2]
+; CHECK-O3-NEXT: vpermq {{.*#+}} ymm1 = ymm1[2,1,2,3]
+; CHECK-O3-NEXT: vpbroadcastq 248(%rbp), %ymm4
+; CHECK-O3-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0,1],ymm4[2,3,4,5],ymm1[6,7]
+; CHECK-O3-NEXT: vpblendd {{.*#+}} xmm3 = xmm7[0,1],xmm3[2,3]
+; CHECK-O3-NEXT: vpermq {{.*#+}} ymm3 = ymm3[0,0,1,3]
+; CHECK-O3-NEXT: vpslldq {{.*#+}} ymm4 = zero,zero,zero,zero,zero,zero,zero,zero,ymm5[0,1,2,3,4,5,6,7],zero,zero,zero,zero,zero,zero,zero,zero,ymm5[16,17,18,19,20,21,22,23]
+; CHECK-O3-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0,1],ymm3[2,3,4,5],ymm4[6,7]
+; CHECK-O3-NEXT: movq %rbp, %rsp
+; CHECK-O3-NEXT: popq %rbp
+; CHECK-O3-NEXT: retq
bb:
%tmp = select <16 x i1> <i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 false, i1 false>, <16 x i64> %arg, <16 x i64> %arg1
%tmp5 = select <16 x i1> <i1 true, i1 false, i1 false, i1 true, i1 true, i1 false, i1 false, i1 true, i1 false, i1 true, i1 false, i1 false, i1 false, i1 false, i1 false, i1 false>, <16 x i64> %arg2, <16 x i64> zeroinitializer