diff options
| author | Justin Holewinski <jholewinski@nvidia.com> | 2012-05-04 20:18:50 +0000 |
|---|---|---|
| committer | Justin Holewinski <jholewinski@nvidia.com> | 2012-05-04 20:18:50 +0000 |
| commit | 49683f3c961379fbc088871a5d6304950f1f1cbc (patch) | |
| tree | 830fa1ee9c992ef4645863d128be912ce2bfc987 /test/CodeGen/NVPTX/fma.ll | |
| parent | 2c7e5c714c8675f757c4936a3a2132c2466a626c (diff) | |
| download | llvm-49683f3c961379fbc088871a5d6304950f1f1cbc.tar.gz llvm-49683f3c961379fbc088871a5d6304950f1f1cbc.tar.bz2 llvm-49683f3c961379fbc088871a5d6304950f1f1cbc.tar.xz | |
This patch adds a new NVPTX back-end to LLVM which supports code generation for NVIDIA PTX 3.0. This back-end will (eventually) replace the current PTX back-end, while maintaining compatibility with it.
The new target machines are:
nvptx (old ptx32) => 32-bit PTX
nvptx64 (old ptx64) => 64-bit PTX
The sources are based on the internal NVIDIA NVPTX back-end, and
contain more functionality than the current PTX back-end currently
provides.
NV_CONTRIB
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156196 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/NVPTX/fma.ll')
| -rw-r--r-- | test/CodeGen/NVPTX/fma.ll | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/test/CodeGen/NVPTX/fma.ll b/test/CodeGen/NVPTX/fma.ll new file mode 100644 index 0000000000..4ef1a9a4ce --- /dev/null +++ b/test/CodeGen/NVPTX/fma.ll @@ -0,0 +1,17 @@ +; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s + +define ptx_device float @t1_f32(float %x, float %y, float %z) { +; CHECK: fma.rn.f32 %f{{[0-9]+}}, %f{{[0-9]+}}, %f{{[0-9]+}}, %f{{[0-9]+}}; +; CHECK: ret; + %a = fmul float %x, %y + %b = fadd float %a, %z + ret float %b +} + +define ptx_device double @t1_f64(double %x, double %y, double %z) { +; CHECK: fma.rn.f64 %fl{{[0-9]+}}, %fl{{[0-9]+}}, %fl{{[0-9]+}}, %fl{{[0-9]+}}; +; CHECK: ret; + %a = fmul double %x, %y + %b = fadd double %a, %z + ret double %b +} |