[PATCH] D103655: [AMDGPU] Handle constant LDS uses from different kernels

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/lower-module-lds-constantexpr.ll:43-45
+; CHECK: %4 = bitcast float addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.timestwo.lds.t, %llvm.amdgcn.kernel.timestwo.lds.t addrspace(3)* @llvm.amdgcn.kernel.timestwo.lds, i32 0, i32 0) to i32 addrspace(3)*
+; CHECK: %5 = addrspacecast i32 addrspace(3)* %4 to i32*
+; CHECK: %6 = ptrtoint i32* %5 to i64
----------------
rampitec wrote:
> foad wrote:
> > Why do %4, %5, %6 need to be Instructions? Couldn't they could be left as ConstantExprs?
> It converts the whole constant expr, this is how D103661 works (and you have already commented there). I am not sure that is important though. Do you see any benefits of having long constant expressions vs instructions? We have to admit the testcase is quite degenerate too, more a torture test than a real life use.
Actually these have to be instructions. Reading this huge expression... It uses two lds globals, both constexprs are the innermost. If we replace an innermost expression with an instruction we then have to replace all constantexpr uses with instructions too since a constantexpr cannot use an instruction.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D103655/new/

https://reviews.llvm.org/D103655