projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: efb6bb6) | patch
R600: Enable vector fpow.
authorTom Stellard <thomas.stellard@amd.com>
Tue, 4 Feb 2014 17:18:37 +0000 (17:18 +0000)
committerTom Stellard <thomas.stellard@amd.com>
Tue, 4 Feb 2014 17:18:37 +0000 (17:18 +0000)
commit4ee42eaec9031a5be474ca82224807be1f5dd925
tree9a9ed2b7c5c3f45c32772a623e4ea5487f982172tree | snapshot
parentefb6bb68637230b666b88c915be6ffa1426afab6commit | diff
R600: Enable vector fpow.

The OpenCL specs say: "The vector versions of the math functions operate
component-wise. The description is per-component."

Patch by: Jan Vesely

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200773 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/R600/AMDGPUISelLowering.cpp diff | blob | history
test/CodeGen/R600/llvm.pow.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors