[PATCH] D78900: [HIP][AMDGPU] Enable structurizer workarounds
Sameer Sahasrabuddhe via Phabricator via cfe-commits
cfe-commits at lists.llvm.org
Mon Apr 27 20:29:05 PDT 2020
sameerds added inline comments.
================
Comment at: clang/lib/Driver/ToolChains/HIP.cpp:158
Args.MakeArgString(Twine("-filetype=") + (OutputIsAsm ? "asm" : "obj")));
+ LlcArgs.push_back("--amdgpu-enable-structurizer-workarounds");
----------------
arsenm wrote:
> We should just flip this in the backend. llc flags are not intended for frontends to set options
Admittedly, this is a broken workflow. I am not even sure if Clang should be invoking llc at all. Ideally, we would want to eliminate this flag entirely. But flipping it is okay too if graphics workloads are sensitive to it. The priority right now is to enable the workarounds officially only for HIP and this seems to be most concise way to do it. We can flip the flag once other users of the AMDGPU are on board.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D78900/new/
https://reviews.llvm.org/D78900
More information about the cfe-commits
mailing list