diff options
| author | Evan Cheng <evan.cheng@apple.com> | 2008-03-05 01:30:59 +0000 |
|---|---|---|
| committer | Evan Cheng <evan.cheng@apple.com> | 2008-03-05 01:30:59 +0000 |
| commit | 6fd599fa6916bd9438dbea7994cf2437bdf4ab8c (patch) | |
| tree | 3c6d40842c57c1ed5309750a1c82a8dd107f107f /test/CodeGen/X86/shrink-fp-const1.ll | |
| parent | d19189e9905e14a4001a8ca6fc4effb6a3f88e45 (diff) | |
| download | llvm-6fd599fa6916bd9438dbea7994cf2437bdf4ab8c.tar.gz llvm-6fd599fa6916bd9438dbea7994cf2437bdf4ab8c.tar.bz2 llvm-6fd599fa6916bd9438dbea7994cf2437bdf4ab8c.tar.xz | |
Add a target lowering hook to control whether it's worthwhile to compress fp constant.
For x86, if sse2 is available, it's not a good idea since cvtss2sd is slower than a movsd load and it prevents load folding. On x87, it's important to shrink fp constant since fldt is very expensive.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@47931 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/shrink-fp-const1.ll')
| -rw-r--r-- | test/CodeGen/X86/shrink-fp-const1.ll | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/test/CodeGen/X86/shrink-fp-const1.ll b/test/CodeGen/X86/shrink-fp-const1.ll new file mode 100644 index 0000000000..966e69ec77 --- /dev/null +++ b/test/CodeGen/X86/shrink-fp-const1.ll @@ -0,0 +1,7 @@ +; RUN: llvm-as < %s | llc -march=x86-64 -mattr=+sse2 | not grep cvtss2sd +; PR1264 + +define double @foo(double %x) { + %y = mul double %x, 5.000000e-01 + ret double %y +} |