Remove 256-bit specific node types for UNPCKHPS/D and instead use the 128-bit versions and let the operand type disinquish. Also fix the load form of the v8i32 patterns for these to realize that the load would be promoted to v4i64.

llvm-svn: 145126

1 files changed, 36 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/avx-unpack.ll b/llvm/test/CodeGen/X86/avx-unpack.ll
index d420101339f..fcd7bb6883a 100644
--- a/llvm/test/CodeGen/X86/avx-unpack.ll
+++ b/llvm/test/CodeGen/X86/avx-unpack.ll
@@ -67,6 +67,15 @@ entry:
   ret <8 x i32> %shuffle.i
 }
 
+; CHECK: vunpckhps (%
+define <8 x i32> @unpackhips2(<8 x i32>* %src1, <8 x i32>* %src2) nounwind uwtable readnone ssp {
+entry:
+  %a = load <8 x i32>* %src1
+  %b = load <8 x i32>* %src2
+  %shuffle.i = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
+  ret <8 x i32> %shuffle.i
+}
+
 ; CHECK: vunpckhpd
 define <4 x i64> @unpackhipd1(<4 x i64> %src1, <4 x i64> %src2) nounwind uwtable readnone ssp {
 entry:
@@ -74,6 +83,15 @@ entry:
   ret <4 x i64> %shuffle.i
 }
 
+; CHECK: vunpckhpd (%
+define <4 x i64> @unpackhipd2(<4 x i64>* %src1, <4 x i64>* %src2) nounwind uwtable readnone ssp {
+entry:
+  %a = load <4 x i64>* %src1
+  %b = load <4 x i64>* %src2
+  %shuffle.i = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
+  ret <4 x i64> %shuffle.i
+}
+
 ; CHECK: vunpcklps
 define <8 x i32> @unpacklops1(<8 x i32> %src1, <8 x i32> %src2) nounwind uwtable readnone ssp {
 entry:
@@ -81,9 +99,27 @@ entry:
   ret <8 x i32> %shuffle.i
 }
 
+; CHECK: vunpcklps (%
+define <8 x i32> @unpacklops2(<8 x i32>* %src1, <8 x i32>* %src2) nounwind uwtable readnone ssp {
+entry:
+  %a = load <8 x i32>* %src1
+  %b = load <8 x i32>* %src2
+  %shuffle.i = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
+  ret <8 x i32> %shuffle.i
+}
+
 ; CHECK: vunpcklpd
 define <4 x i64> @unpacklopd1(<4 x i64> %src1, <4 x i64> %src2) nounwind uwtable readnone ssp {
 entry:
   %shuffle.i = shufflevector <4 x i64> %src1, <4 x i64> %src2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
   ret <4 x i64> %shuffle.i
 }
+
+; CHECK: vunpcklpd (%
+define <4 x i64> @unpacklopd2(<4 x i64>* %src1, <4 x i64>* %src2) nounwind uwtable readnone ssp {
+entry:
+  %a = load <4 x i64>* %src1
+  %b = load <4 x i64>* %src2
+  %shuffle.i = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+  ret <4 x i64> %shuffle.i
+}