================
@@ -1024,6 +1024,15 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC,
IntrinsicInst &II) const {
}
break;
}
+ case Intrinsic::amdgcn_wavefrontsize: {
+ // TODO: this is a workaround for the pseudo-generic target one gets with
no
+ // specified mcpu, which spoofs its wave size to 64; it should be removed.
+ if ((ST->getCPU().empty() || ST->getCPU() == "generic") &&
+ !ST->getFeatureString().contains("+wavefrontsize"))
----------------
jhuber6 wrote:
I'd be fine with multiple builds, but right now the AMDGCN infra doesn't
support it very well since we'd need to port the ROCm Device Libs to use my
build system. Beyond that it'd be pretty easy to just default the triple
depending on mcpu and `-mwavefrontsize`.
https://github.com/llvm/llvm-project/pull/114481
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
