diff options
| author | Evan Cheng <evan.cheng@apple.com> | 2011-01-07 19:35:30 +0000 |
|---|---|---|
| committer | Evan Cheng <evan.cheng@apple.com> | 2011-01-07 19:35:30 +0000 |
| commit | a5e1362f968568d66d76ddcdcff4ab98e203a48c (patch) | |
| tree | 53e266c315432b49be8ad6f3a2d2a5873265ab53 /test/CodeGen/X86/2010-06-25-CoalescerSubRegDefDead.ll | |
| parent | 1434f66b2e132a707e2c8ccb3350ea13fb5aa051 (diff) | |
| download | llvm-a5e1362f968568d66d76ddcdcff4ab98e203a48c.tar.gz llvm-a5e1362f968568d66d76ddcdcff4ab98e203a48c.tar.bz2 llvm-a5e1362f968568d66d76ddcdcff4ab98e203a48c.tar.xz | |
Revert r122955. It seems using movups to lower memcpy can cause massive regression (even on Nehalem) in edge cases. I also didn't see any real performance benefit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123015 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/2010-06-25-CoalescerSubRegDefDead.ll')
| -rw-r--r-- | test/CodeGen/X86/2010-06-25-CoalescerSubRegDefDead.ll | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/test/CodeGen/X86/2010-06-25-CoalescerSubRegDefDead.ll b/test/CodeGen/X86/2010-06-25-CoalescerSubRegDefDead.ll index f31cdad861..6db3ce1f42 100644 --- a/test/CodeGen/X86/2010-06-25-CoalescerSubRegDefDead.ll +++ b/test/CodeGen/X86/2010-06-25-CoalescerSubRegDefDead.ll @@ -26,7 +26,7 @@ bb: ; CHECK: rep;stosl %tmp5 = bitcast i32* %tmp4 to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp5, i8 0, i64 124, i32 4, i1 false) + call void @llvm.memset.p0i8.i64(i8* %tmp5, i8 0, i64 84, i32 4, i1 false) %tmp6 = getelementptr inbounds %struct.type* %s, i32 0, i32 62 store i32* null, i32** %tmp6, align 8 br label %bb1 |