diff --git a/llvm/test/CodeGen/X86/avx-insert.ll b/llvm/test/CodeGen/X86/avx-insert.ll deleted file mode 100644 index d9eae03eee75..000000000000 --- a/llvm/test/CodeGen/X86/avx-insert.ll +++ /dev/null @@ -1,17 +0,0 @@ -; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s - -; It is faster to make two saves, if the data is already in XMM registers. For -; example, after making an integer operation. -define void @double_save(<4 x i32>* %Ap, <4 x i32>* %Bp, <8 x i32>* %P) nounwind ssp { -entry: - ; CHECK: movaps - ; CHECK: movaps - ; CHECK: movaps - ; CHECK: movaps - %A = load <4 x i32>* %Ap - %B = load <4 x i32>* %Bp - %Z = shufflevector <4 x i32>%A, <4 x i32>%B, <8 x i32> - store <8 x i32> %Z, <8 x i32>* %P, align 16 - ret void -} - diff --git a/llvm/test/CodeGen/X86/avx-load-store.ll b/llvm/test/CodeGen/X86/avx-load-store.ll index d191af88638b..f70291b96e16 100644 --- a/llvm/test/CodeGen/X86/avx-load-store.ll +++ b/llvm/test/CodeGen/X86/avx-load-store.ll @@ -64,3 +64,17 @@ define void @storev32i8_01(<32 x i8> %a) nounwind { unreachable } +; It is faster to make two saves, if the data is already in XMM registers. For +; example, after making an integer operation. +; CHECK: _double_save +; CHECK-NOT: vinsertf128 $1 +; CHECK-NOT: vinsertf128 $0 +; CHECK: vmovaps %xmm +; CHECK: vmovaps %xmm +define void @double_save(<4 x i32> %A, <4 x i32> %B, <8 x i32>* %P) nounwind ssp { +entry: + %Z = shufflevector <4 x i32>%A, <4 x i32>%B, <8 x i32> + store <8 x i32> %Z, <8 x i32>* %P, align 16 + ret void +} +