Add support for 256-bit versions of VSHUFPD and VSHUFPS.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@138546 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 31 insertions, 4 deletions

diff --git a/test/CodeGen/X86/avx-basic.ll b/test/CodeGen/X86/avx-basic.ll
index 1c10814..d085f5d 100644
--- a/test/CodeGen/X86/avx-basic.ll
+++ b/test/CodeGen/X86/avx-basic.ll
@@ -64,10 +64,8 @@ entry:
   ret <4 x i64> %shuffle
 }
 
-; CHECK: vpunpckhqdq
-; CHECK-NEXT: vextractf128  $1
-; CHECK-NEXT: movlhps
-; CHECK-NEXT: vinsertf128 $1
+; CHECK: _B
+; CHECK: vshufpd $1, %ymm
 define <4 x i64> @B(<4 x i64> %a, <4 x i64> %b) nounwind uwtable readnone ssp {
 entry:
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 undef, i32 undef, i32 6>
diff --git a/test/CodeGen/X86/avx-vshufp.ll b/test/CodeGen/X86/avx-vshufp.ll
new file mode 100644
index 0000000..f06548d
--- /dev/null
+++ b/test/CodeGen/X86/avx-vshufp.ll
@@ -0,0 +1,29 @@
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
+
+; CHECK: vshufps  $-53, %ymm
+define <8 x float> @A(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 8, i32 11, i32 7, i32 6, i32 12, i32 15>
+  ret <8 x float> %shuffle
+}
+
+; CHECK: vshufpd  $10, %ymm
+define <4 x double> @B(<4 x double> %a, <4 x double> %b) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+  ret <4 x double> %shuffle
+}
+
+; CHECK: vshufps  $-53, %ymm
+define <8 x float> @C(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 undef, i32 undef, i32 11, i32 undef, i32 6, i32 12, i32 undef>
+  ret <8 x float> %shuffle
+}
+
+; CHECK: vshufpd  $2, %ymm
+define <4 x double> @D(<4 x double> %a, <4 x double> %b) nounwind uwtable readnone ssp {
+entry:
+  %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 5, i32 2, i32 undef>
+  ret <4 x double> %shuffle
+}