projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: e4c6241) | patch
R600/SI: Implement less wrong f32 fdiv
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Tue, 15 Jul 2014 20:18:31 +0000 (20:18 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Tue, 15 Jul 2014 20:18:31 +0000 (20:18 +0000)
commit4b0a7f39463552ca2aec3d235f831264572f9916
tree2c2b019fb9db84ad5293802e9e1248cd6a8200c5tree | snapshot
parente4c62415054abd676ff8f89ba5d11dfcd7268d50commit | diff
R600/SI: Implement less wrong f32 fdiv

Assuming single precision denormals and accurate sqrt/div are not
reported, this passes the OpenCL conformance test.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213089 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/R600/SIISelLowering.cpp diff | blob | history
lib/Target/R600/SIISelLowering.h diff | blob | history
lib/Target/R600/SIInstructions.td diff | blob | history
test/CodeGen/R600/fdiv.ll diff | blob | history
test/CodeGen/R600/llvm.AMDGPU.rcp.ll diff | blob | history
test/CodeGen/R600/rsq.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors