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/unaligned-load.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/unaligned-load.ll')
-rw-r--r-- | test/CodeGen/X86/unaligned-load.ll | 25 |
1 files changed, 9 insertions, 16 deletions
diff --git a/test/CodeGen/X86/unaligned-load.ll b/test/CodeGen/X86/unaligned-load.ll index 6a493c0..0408577 100644 --- a/test/CodeGen/X86/unaligned-load.ll +++ b/test/CodeGen/X86/unaligned-load.ll @@ -1,6 +1,4 @@ -; RUN: llc < %s -mtriple=i386-apple-darwin10.0 -mcpu=core2 -relocation-model=dynamic-no-pic --asm-verbose=0 | FileCheck -check-prefix=I386 %s -; RUN: llc < %s -mtriple=x86_64-apple-darwin10.0 -mcpu=core2 -relocation-model=dynamic-no-pic --asm-verbose=0 | FileCheck -check-prefix=CORE2 %s -; RUN: llc < %s -mtriple=x86_64-apple-darwin10.0 -mcpu=corei7 -relocation-model=dynamic-no-pic --asm-verbose=0 | FileCheck -check-prefix=COREI7 %s +; RUN: llc < %s -mtriple=x86_64-apple-darwin10.0 -mcpu=core2 -relocation-model=dynamic-no-pic --asm-verbose=0 | FileCheck %s @.str1 = internal constant [31 x i8] c"DHRYSTONE PROGRAM, SOME STRING\00", align 8 @.str3 = internal constant [31 x i8] c"DHRYSTONE PROGRAM, 2'ND STRING\00", align 8 @@ -13,13 +11,8 @@ entry: bb: %String2Loc9 = getelementptr inbounds [31 x i8]* %String2Loc, i64 0, i64 0 call void @llvm.memcpy.i64(i8* %String2Loc9, i8* getelementptr inbounds ([31 x i8]* @.str3, i64 0, i64 0), i64 31, i32 1) -; I386: calll {{_?}}memcpy - -; CORE2: movabsq -; CORE2: movabsq -; CORE2: movabsq - -; COREI7: movups _.str3 +; CHECK: movabsq $2325069237881678925, %rax +; CHECK: movups _.str3(%rip), %xmm0 br label %bb return: @@ -28,9 +21,9 @@ return: declare void @llvm.memcpy.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind -; CORE2: .section -; CORE2: .align 4 -; CORE2-NEXT: _.str1: -; CORE2-NEXT: .asciz "DHRYSTONE PROGRAM, SOME STRING" -; CORE2: .align 4 -; CORE2-NEXT: _.str3: +; CHECK: .section +; CHECK: .align 4 +; CHECK-NEXT: _.str1: +; CHECK-NEXT: .asciz "DHRYSTONE PROGRAM, SOME STRING" +; CHECK: .align 4 +; CHECK-NEXT: _.str3: |