commit	b3dc73634c492085c861127953ed2f4ccade2fcc	[log] [tgz]
author	Matt Arsenault <Matthew.Arsenault@amd.com>	Fri May 17 12:02:27 2019 +0000
committer	Matt Arsenault <Matthew.Arsenault@amd.com>	Fri May 17 12:02:27 2019 +0000
tree	a572708d20b6eb1c5608eb2a9ff24c74ab8b6c02
parent	1400a35f71675e4d06c673e656270e0dcdd6a344 [diff]

AMDGPU/GlobalISel: Use waterfall loop for buffer_load

This adds support for more complex waterfall loops that need to handle
operands > 32-bits, and multiple operands.

llvm-svn: 361021

llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp[diff]
llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.h[diff]
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn-buffer-load.mir[Added - diff]
llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-extract-vector-elt.mir[diff]

4 files changed

tree: a572708d20b6eb1c5608eb2a9ff24c74ab8b6c02

clang/
clang-tools-extra/
compiler-rt/
debuginfo-tests/
libclc/
libcxx/
libcxxabi/
libunwind/
lld/
lldb/
llgo/
llvm/
openmp/
parallel-libs/
polly/
pstl/
.arcconfig
.clang-format
.clang-tidy
.gitignore
README.md

README.md

The LLVM Compiler Infrastructure

This directory and its subdirectories contain source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and runtime environments.