AMDGPU: Split x8 and x16 vector loads instead of scalarize
[oota-llvm.git] / lib / Target / AMDGPU / TargetInfo /
drwxr-xr-x   ..
-rw-r--r-- 1091 AMDGPUTargetInfo.cpp
-rw-r--r-- 59 CMakeLists.txt
-rw-r--r-- 730 LLVMBuild.txt
-rw-r--r-- 548 Makefile