Sorry, I was just missing "git pull" in the llvm repo.
Cheers,
Rafael
Artem Belevich writes:
> Thanks for the heads up.
>
> Which buildbot shows the failure? I don't see the failure on the cuda
> buildbot, nor do I see it on my machine locally.
>
> It may be due to llvm/clang being out of sync.
Thanks for the heads up.
Which buildbot shows the failure? I don't see the failure on the cuda
buildbot, nor do I see it on my machine locally.
It may be due to llvm/clang being out of sync. The commit had changes for
both sides and if clang and llvm are out of sync, you may see this kind of
erro
With this clang/test/CodeGen/builtins-nvptx-sm_70.cu is crashing:
lib/IR/Instructions.cpp:299: void
llvm::CallInst::init(llvm::FunctionType *, llvm::Value *,
ArrayRef, ArrayRef, const
llvm::Twine &): Assertion `(i >= FTy->getNumParams()||
FTy->getParamType(i) == Args[i]->getType()) && "Calling a f
Author: tra
Date: Tue Mar 20 10:18:59 2018
New Revision: 328006
URL: http://llvm.org/viewvc/llvm-project?rev=328006&view=rev
Log:
[NVPTX] Make tensor load/store intrinsics overloaded.
This way we can support address-space specific variants without explicitly
encoding the space in the name of the
