forked from OSchip/llvm-project
![]() I've extended the load/store optimizer to be able to produce dwordx3 loads and stores, This change allows many more load/stores to be combined, and results in much more optimal code for our hardware. Differential Revision: https://reviews.llvm.org/D54042 llvm-svn: 348937 |
||
---|---|---|
.. | ||
AMDGPUAsmUtils.cpp | ||
AMDGPUAsmUtils.h | ||
AMDGPUBaseInfo.cpp | ||
AMDGPUBaseInfo.h | ||
AMDKernelCodeTInfo.h | ||
AMDKernelCodeTUtils.cpp | ||
AMDKernelCodeTUtils.h | ||
CMakeLists.txt | ||
LLVMBuild.txt |