Commit Graph

5 Commits

Author SHA1 Message Date
Aaron En Ye Shi 77df5a8283 [HIP] Move HIP Linking Logic into HIP ToolChain
This patch is a follow up on https://reviews.llvm.org/D78759.

Extract the HIP Linker script from generic GNU linker,
and move it into HIP ToolChain. Update OffloadActionBuilder
Link actions feature to apply device linking and host linking
actions separately. Using MC Directives, embed the device images
and define symbols.

Reviewers: JonChesterfield, yaxunl

Subscribers: tra, echristo, jdoerfert, msearles, scchan

Differential Revision: https://reviews.llvm.org/D81963
2020-06-22 19:48:48 +00:00
Yaxun (Sam) Liu e8090d83fd [HIP] Do not call opt/llc for -fno-gpu-rdc
Currently HIP toolchain calls clang to emit bitcode then calls opt/llc for device compilation for the default -fno-gpu-rdc
case, which is unnecessary since clang is able to compile a single source file to ISA.

This patch fixes the HIP action builder and toolchain so that the default -fno-gpu-rdc can be done like a canonical
toolchain, i.e. one clang -cc1 invocation to compile source code to ISA.

This can avoid unnecessary processes to speed up the compilation, and avoid redundant LLVM passes which are
performed in clang -cc1 and opt.

Differential Revision: https://reviews.llvm.org/D81627
2020-06-15 18:55:01 -04:00
Yaxun Liu ab851939fc [HIP] Do not unbundle object files for -fno-gpu-rdc
When -fno-gpu-rdc is set, device code is compiled, linked, and assembled into fat binary
and embedded as string in object files. The object files are normal object files which
can be linked by host linker. In the linking stage, the object files should not be unbundled
when -fno-gpu-rdc is set since they are normal object files, not bundles. The object files
only need to be unbundled when -fgpu-rdc is set.

Currently clang always unbundles object files, disregarding -fgpu-rdc option.

This patch fixes that.

Differential Revision: https://reviews.llvm.org/D58917

llvm-svn: 355410
2019-03-05 16:07:56 +00:00
Petr Hosek 7b27454477 [ADT] Normalize empty triple components
LLVM triple normalization is handling "unknown" and empty components
differently; for example given "x86_64-unknown-linux-gnu" and
"x86_64-linux-gnu" which should be equivalent, triple normalization
returns "x86_64-unknown-linux-gnu" and "x86_64--linux-gnu". autoconf's
config.sub returns "x86_64-unknown-linux-gnu" for both
"x86_64-linux-gnu" and "x86_64-unknown-linux-gnu". This changes the
triple normalization to behave the same way, replacing empty triple
components with "unknown".

This addresses PR37129.

Differential Revision: https://reviews.llvm.org/D50219

llvm-svn: 339294
2018-08-08 22:23:57 +00:00
Yaxun Liu 470b833bed [HIP] Fix unbundling
HIP uses clang-offload-bundler to bundle intermediate files for host
and different gpu archs together. When a file is unbundled,
clang-offload-bundler should be called only once, and the objects
for host and different gpu archs should be passed to the next
jobs. This is because Driver maintains CachedResults which maps
triple-arch string to output files for each job.

This patch fixes a bug in Driver::BuildJobsForActionNoCache which
uses incorrect key for CachedResults for HIP which causes
clang-offload-bundler being called mutiple times and incorrect
output files being used.

It only affects HIP.

Differential Revision: https://reviews.llvm.org/D47555

llvm-svn: 334128
2018-06-06 19:44:10 +00:00