================
@@ -303,6 +303,21 @@ HIPAMDToolChain::TranslateArgs(const
llvm::opt::DerivedArgList &Args,
const OptTable &Opts = getDriver().getOpts();
for (Arg *A : Args) {
+ // Handle device-side profile data file for PGO
+ if (A->getOption().matches(options::OPT_fprofile_use_EQ)) {
+ StringRef ProfileFile = A->getValue();
+ auto [Base, Ext] = ProfileFile.rsplit('.');
+ std::string DeviceProfileFile;
+ if (!Ext.empty()) {
+ DeviceProfileFile = (Base + "." + getTriple().str() + "." + Ext).str();
+ } else {
+ DeviceProfileFile = (ProfileFile + "." + getTriple().str()).str();
+ }
+ DAL->AddJoinedArg(A, Opts.getOption(options::OPT_fprofile_instr_use_EQ),
+ DeviceProfileFile);
+ A->claim();
+ continue;
+ }
----------------
EthanLuisMcDonough wrote:
The current PGO offloading infrastructure uses `-Xarch_device` and
`-Xarch_host` to supply target specific profiling flags:
```
clang ... -Xarch_device -fprofile-use=device.profdata -Xarch_host
-fprofile-use=host.profdata
```
This is certainly more verbose than automatically assuming the device's profile
filename, but it allows the end user a greater degree of flexibility while also
being more explicit. @jhuber6 originally suggested using these flags instead of
introducing new flags for GPU PGO (see #94268), perhaps he could weigh in here
as well?
https://github.com/llvm/llvm-project/pull/177665
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
