diff options
| author | Evan Cheng <evan.cheng@apple.com> | 2010-04-01 06:04:33 +0000 |
|---|---|---|
| committer | Evan Cheng <evan.cheng@apple.com> | 2010-04-01 06:04:33 +0000 |
| commit | 255f20f7f76e4ca1ac1c73294852cb6fcb18c77d (patch) | |
| tree | c3bd975c3254d60625b64fcff2c8b918060b6afa /test/CodeGen/X86/memset64-on-x86-32.ll | |
| parent | 48c58bb8610cd475d1acb073694e0d2b4dd7cc8c (diff) | |
| download | llvm-255f20f7f76e4ca1ac1c73294852cb6fcb18c77d.tar.gz llvm-255f20f7f76e4ca1ac1c73294852cb6fcb18c77d.tar.bz2 llvm-255f20f7f76e4ca1ac1c73294852cb6fcb18c77d.tar.xz | |
Fix sdisel memcpy, memset, memmove lowering:
1. Makes it possible to lower with floating point loads and stores.
2. Avoid unaligned loads / stores unless it's fast.
3. Fix some memcpy lowering logic bug related to when to optimize a
load from constant string into a constant.
4. Adjust x86 memcpy lowering threshold to make it more sane.
5. Fix x86 target hook so it uses vector and floating point memory
ops more effectively.
rdar://7774704
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@100090 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/memset64-on-x86-32.ll')
| -rw-r--r-- | test/CodeGen/X86/memset64-on-x86-32.ll | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/test/CodeGen/X86/memset64-on-x86-32.ll b/test/CodeGen/X86/memset64-on-x86-32.ll index da8fc51da8..8b817b49ee 100644 --- a/test/CodeGen/X86/memset64-on-x86-32.ll +++ b/test/CodeGen/X86/memset64-on-x86-32.ll @@ -1,4 +1,4 @@ -; RUN: llc < %s -mtriple=i386-apple-darwin | grep stosl +; RUN: llc < %s -mtriple=i386-apple-darwin | grep movl | count 20 ; RUN: llc < %s -mtriple=x86_64-apple-darwin | grep movq | count 10 define void @bork() nounwind { |