================
@@ -1444,15 +1444,16 @@ void clang::emitBackendOutput(CompilerInstance &CI,
CodeGenOptions &CGOpts,
// Verify clang's TargetInfo DataLayout against the LLVM TargetMachine's
// DataLayout.
- if (AsmHelper.TM) {
- std::string DLDesc = M->getDataLayout().getStringRepresentation();
- if (DLDesc != TDesc) {
+ if (AsmHelper.TM)
+ if (!AsmHelper.TM->isCompatibleDataLayout(M->getDataLayout()) ||
+ !AsmHelper.TM->isCompatibleDataLayout(DataLayout(TDesc))) {
+ std::string DLDesc = M->getDataLayout().getStringRepresentation();
----------------
thetheodor wrote:
A lot (most?) of these address space casts in the tests stem from front-end
lowering patterns like this:
```
define hidden noundef i32 @_Z3fooRi(ptr noundef nonnull align 4
dereferenceable(4) %a) #3 {
entry:
%retval = alloca i32, align 4, addrspace(5)
%a.addr = alloca ptr, align 8, addrspace(5)
%retval.ascast = addrspacecast ptr addrspace(5) %retval to ptr
%a.addr.ascast = addrspacecast ptr addrspace(5) %a.addr to ptr
store ptr %a, ptr %a.addr.ascast, align 8, !tbaa !12
%0 = load ptr, ptr %a.addr.ascast, align 8, !tbaa !12, !nonnull !14, !align
!15
%1 = load i32, ptr %0, align 4, !tbaa !10
ret i32 %1
}
```
and because no optimizations are enabled in these OpenMP tests, these
alloca-cast-store-load chains are not simplified. Running SROA eliminates the
noise:
```
; *** IR Dump After SROAPass on _Z3fooRi ***
; Function Attrs: convergent mustprogress nounwind
define hidden noundef i32 @_Z3fooRi(ptr noundef nonnull align 4
dereferenceable(4) %a) #3 {
entry:
%0 = load i32, ptr %a, align 4, !tbaa !10
ret i32 %0
}
```
The only casts not removed by SROA are for the OpenMP API calls that need
generic addresses.
(The amdgpu OpenMP tests also include this pattern)
https://github.com/llvm/llvm-project/pull/154814
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
