[clang] [llvm] [AMDGPU] Add target intrinsic for s_buffer_prefetch_data (PR #107293)
Stanislav Mekhanoshin via cfe-commits
cfe-commits at lists.llvm.org
Fri Sep 6 00:39:06 PDT 2024
================
@@ -9934,6 +9934,12 @@ SDValue SITargetLowering::LowerINTRINSIC_VOID(SDValue Op,
auto NewMI = DAG.getMachineNode(Opc, DL, Op->getVTList(), Ops);
return SDValue(NewMI, 0);
}
+ case Intrinsic::amdgcn_s_prefetch_data: {
+ // For non-global address space preserve the chain and remove the call.
+ if (!AMDGPU::isFlatGlobalAddrSpace(cast<MemSDNode>(Op)->getAddressSpace()))
+ return Op.getOperand(0);
+ return Op;
----------------
rampitec wrote:
For the context of this change what do I have to do? This is the code the change does not touch.
https://github.com/llvm/llvm-project/pull/107293
More information about the cfe-commits
mailing list