Displaying 3 results from an estimated 3 matches for "load_constant".
2011 Aug 24
1
[LLVMdev] proposal: add macro expansion of for-loop to TableGen
...: PatFrag<(ops node:$ptr), (load node:$ptr), [{
const Value *Src;
const PointerType *PT;
if ((Src = cast<LoadSDNode>(N)->getSrcValue()) &&
(PT = dyn_cast<PointerType>(Src->getType())))
return PT->getAddressSpace() == PTX::GLOBAL;
return false;
}]>;
def load_constant : PatFrag<(ops node:$ptr), (load node:$ptr), [{
const Value *Src;
const PointerType *PT;
if ((Src = cast<LoadSDNode>(N)->getSrcValue()) &&
(PT = dyn_cast<PointerType>(Src->getType())))
return PT->getAddressSpace() == PTX::CONSTANT;
return false;
}]>;
d...
2016 Mar 28
0
RFC: atomic operations on SI+
...t a/lib/Target/AMDGPU/AMDGPUISelLowering.h b/lib/Target/AMDGPU/AMDGPUISelLowering.h
> index 4627f34..fce8e76 100644
> --- a/lib/Target/AMDGPU/AMDGPUISelLowering.h
> +++ b/lib/Target/AMDGPU/AMDGPUISelLowering.h
> @@ -313,6 +313,7 @@ enum NodeType : unsigned {
> STORE_MSKOR,
> LOAD_CONSTANT,
> TBUFFER_STORE_FORMAT,
> + CMP_SWAP,
> LAST_AMDGPU_ISD_NUMBER
> };
>
> diff --git a/lib/Target/AMDGPU/CIInstructions.td b/lib/Target/AMDGPU/CIInstructions.td
> index 593300f..d99b013 100644
> --- a/lib/Target/AMDGPU/CIInstructions.td
> +++ b/lib/Target/AMDGPU/...
2016 Mar 25
2
RFC: atomic operations on SI+
Hi Tom, Matt,
I'm working on a project that needs few coherent atomic operations (HSA
mode: load, store, compare-and-swap) for std::atomic_uint in HCC.
the attached patch implements atomic compare and swap for SI+
(untested). I tried to stay within what was available, but there are
few issues that I was unsure how to address:
1.) it currently uses v2i32 for both input and output. This