diff options
| author | Benjamin Kramer <benny.kra@googlemail.com> | 2013-03-31 12:49:15 +0000 |
|---|---|---|
| committer | Benjamin Kramer <benny.kra@googlemail.com> | 2013-03-31 12:49:15 +0000 |
| commit | b8f0d89d0584e37e205c04ed5753f57a23365403 (patch) | |
| tree | 7113d755dcc54b6be1cb18650341f0fa8a5116ec /test/CodeGen | |
| parent | 8049ab15e4b638a07d6f230329945c2310eca27b (diff) | |
X86: Promote sitofp <8 x i16> to <8 x i32> when AVX is available.
A vector sext + sitofp is a lot cheaper than 8 scalar conversions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178448 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen')
| -rw-r--r-- | test/CodeGen/X86/avx-cvt.ll | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/test/CodeGen/X86/avx-cvt.ll b/test/CodeGen/X86/avx-cvt.ll index 62bdea2b49..22fad7ce4b 100644 --- a/test/CodeGen/X86/avx-cvt.ll +++ b/test/CodeGen/X86/avx-cvt.ll @@ -18,6 +18,12 @@ define <4 x double> @sitofp01(<4 x i32> %a) { ret <4 x double> %b } +; CHECK: vcvtdq2ps %ymm +define <8 x float> @sitofp02(<8 x i16> %a) { + %b = sitofp <8 x i16> %a to <8 x float> + ret <8 x float> %b +} + ; CHECK: vcvttpd2dqy %ymm define <4 x i32> @fptosi01(<4 x double> %a) { %b = fptosi <4 x double> %a to <4 x i32> |