[InstCombine][AVX2] Tests showing missed opportunities to pass demanded elts through a vpermd/vpermps shuffle

llvm-svn: 292368

1 files changed, 27 insertions, 0 deletions

diff --git a/llvm/test/Transforms/InstCombine/x86-avx2.ll b/llvm/test/Transforms/InstCombine/x86-avx2.ll
index 4c13b4c6ae7..aafe473d544 100644
--- a/llvm/test/Transforms/InstCombine/x86-avx2.ll
+++ b/llvm/test/Transforms/InstCombine/x86-avx2.ll
@@ -81,5 +81,32 @@ define <8 x float> @undef_test_vpermps(<8 x float> %a0) {
   ret <8 x float> %a
 }
 
+; Verify simplify demanded elts.
+
+define <8 x i32> @elts_test_vpermd(<8 x i32> %a0, i32 %a1) {
+; CHECK-LABEL: @elts_test_vpermd(
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>, i32 %a1, i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> [[TMP1]])
+; CHECK-NEXT:    ret <8 x i32> [[TMP2]]
+;
+  %1 = insertelement <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>, i32 %a1, i32 0
+  %2 = tail call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> %1)
+  %3 = shufflevector <8 x i32> %2, <8 x i32> undef, <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  ret <8 x i32> %3
+}
+
+define <8 x float> @elts_test_vpermps(<8 x float> %a0, <8 x i32> %a1) {
+; CHECK-LABEL: @elts_test_vpermps(
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x i32> %a1, i32 0, i32 7
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> [[TMP1]])
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <8 x float> [[TMP2]], <8 x float> undef, <8 x i32> zeroinitializer
+; CHECK-NEXT:    ret <8 x float> [[TMP3]]
+;
+  %1 = insertelement <8 x i32> %a1, i32 0, i32 7
+  %2 = tail call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> %1)
+  %3 = shufflevector <8 x float> %2, <8 x float> undef, <8 x i32> zeroinitializer
+  ret <8 x float> %3
+}
+
 declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>)
 declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x i32>)