diff options
| author | Evan Cheng <evan.cheng@apple.com> | 2011-01-06 07:58:36 +0000 |
|---|---|---|
| committer | Evan Cheng <evan.cheng@apple.com> | 2011-01-06 07:58:36 +0000 |
| commit | 461f1fc359dff438dad25e809499845b10a3d032 (patch) | |
| tree | 143a2a682ffdd84409d6bd1673e22630d42d565e /test/CodeGen/X86/memset-2.ll | |
| parent | cce240d26bbf1c2bec9cfff4838d8d807b215586 (diff) | |
| download | external_llvm-461f1fc359dff438dad25e809499845b10a3d032.zip external_llvm-461f1fc359dff438dad25e809499845b10a3d032.tar.gz external_llvm-461f1fc359dff438dad25e809499845b10a3d032.tar.bz2 | |
Use movups to lower memcpy and memset even if it's not fast (like corei7).
The theory is it's still faster than a pair of movq / a quad of movl. This
will probably hurt older chips like P4 but should run faster on current
and future Intel processors. rdar://8817010
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122955 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/memset-2.ll')
| -rw-r--r-- | test/CodeGen/X86/memset-2.ll | 16 |
1 files changed, 15 insertions, 1 deletions
diff --git a/test/CodeGen/X86/memset-2.ll b/test/CodeGen/X86/memset-2.ll index ae6b6e9..eb5597e 100644 --- a/test/CodeGen/X86/memset-2.ll +++ b/test/CodeGen/X86/memset-2.ll @@ -5,7 +5,21 @@ declare void @llvm.memset.i32(i8*, i8, i32, i32) nounwind define fastcc void @t1() nounwind { entry: ; CHECK: t1: -; CHECK: calll _memset +; CHECK: pxor %xmm0, %xmm0 +; CHECK: movups %xmm0, 160 +; CHECK: movups %xmm0, 144 +; CHECK: movups %xmm0, 128 +; CHECK: movups %xmm0, 112 +; CHECK: movups %xmm0, 96 +; CHECK: movups %xmm0, 80 +; CHECK: movups %xmm0, 64 +; CHECK: movups %xmm0, 48 +; CHECK: movups %xmm0, 32 +; CHECK: movups %xmm0, 16 +; CHECK: movups %xmm0, 0 +; CHECK: movl $0, 184 +; CHECK: movl $0, 180 +; CHECK: movl $0, 176 call void @llvm.memset.i32( i8* null, i8 0, i32 188, i32 1 ) nounwind unreachable } |