projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 186399b) | patch
R600: Implement getRsqrtEstimate
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Tue, 13 Jan 2015 20:53:18 +0000 (20:53 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Tue, 13 Jan 2015 20:53:18 +0000 (20:53 +0000)
commit8603a3d1c5738e3e3ac370de87a6052fec0c5326
treec5ebd6cc2a4d41ca8509c33ff4644f1a830c6a87tree | snapshot
parent186399b7db9a694010bcadd82d6a430651181d3ccommit | diff
R600: Implement getRsqrtEstimate

Only do for f32 since I'm unclear on both what this is expecting
for the refinement steps in terms of accuracy, and what
f64 instruction actually provides.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225827 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/R600/AMDGPUISelLowering.cpp diff | blob | history
lib/Target/R600/AMDGPUISelLowering.h diff | blob | history
test/CodeGen/R600/fsqrt.ll diff | blob | history
test/CodeGen/R600/rsq.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors