================
@@ -1701,17 +1732,33 @@ unsigned SILoadStoreOptimizer::getNewOpcode(const
CombineInfo &CI,
return AMDGPU::S_BUFFER_LOAD_DWORDX8_SGPR_IMM;
}
case S_LOAD_IMM:
- switch (Width) {
- default:
- return 0;
- case 2:
- return AMDGPU::S_LOAD_DWORDX2_IMM;
- case 3:
- return AMDGPU::S_LOAD_DWORDX3_IMM;
- case 4:
- return AMDGPU::S_LOAD_DWORDX4_IMM;
- case 8:
- return AMDGPU::S_LOAD_DWORDX8_IMM;
+ // For targets that support XNACK replay, use the constrained load opcode.
+ if (STI && STI->hasXnackReplay()) {
+ switch (Width) {
----------------
rampitec wrote:
> > currently the alignment is picked from the first MMO and that'd definitely
> > be smaller than the natural align requirement for the new load
>
> You don't know that - the alignment in the first MMO will be whatever
> alignment the compiler could deduce, which could be large, e.g. if the
> pointer used for the first load was known to have a large alignment.
Moreover, it can easily be as large as a page. In a case of scalar load and
kernarg.
https://github.com/llvm/llvm-project/pull/96162
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
