projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 0d26eea) | patch
Improved cost model for FDIV and FSQRT, by Andrew Tischenko
authorAlexey Bataev <a.bataev@hotmail.com>
Mon, 31 Oct 2016 12:10:53 +0000 (12:10 +0000)
committerAlexey Bataev <a.bataev@hotmail.com>
Mon, 31 Oct 2016 12:10:53 +0000 (12:10 +0000)
commitd07c731d86d15d52bc3b8be028393cb11a76374a
treea936a1236238864eb539320e27ae5c2fc5381d7atree | snapshot
parent0d26eea60965d5c061f386567d2af26c5b386210commit | diff
Improved cost model for FDIV and FSQRT, by Andrew Tischenko

There is a bug describing poor cost model for floating point operations:
Bug 29083 - [X86][SSE] Improve costs for floating point operations. This
patch is the second one in series of patches dealing with cost model.

Differential Revision: https://reviews.llvm.org/D25722

llvm-svn: 285564
llvm/lib/Target/X86/X86TargetTransformInfo.cpp diff | blob | history
llvm/test/Analysis/CostModel/X86/arith-fp.ll diff | blob | history
Domain: System / Toolchain;