================
@@ -193,49 +204,238 @@ ABIArgInfo
SPIRVABIInfo::classifyKernelArgumentType(QualType Ty) const {
return classifyArgumentType(Ty);
}
-ABIArgInfo SPIRVABIInfo::classifyArgumentType(QualType Ty) const {
- if (getTarget().getTriple().getVendor() != llvm::Triple::AMD)
- return DefaultABIInfo::classifyArgumentType(Ty);
- if (!isAggregateTypeForABI(Ty))
- return DefaultABIInfo::classifyArgumentType(Ty);
+void SPIRVABIInfo::computeInfo(CGFunctionInfo &FI) const {
+ // The logic is same as in DefaultABIInfo with an exception on the kernel
+ // arguments handling.
+ llvm::CallingConv::ID CC = FI.getCallingConvention();
+
+ if (!getCXXABI().classifyReturnType(FI))
+ FI.getReturnInfo() = classifyReturnType(FI.getReturnType());
+
+ for (auto &I : FI.arguments()) {
+ if (CC == llvm::CallingConv::SPIR_KERNEL) {
+ I.info = classifyKernelArgumentType(I.type);
+ } else {
+ I.info = classifyArgumentType(I.type);
+ }
+ }
+}
+
+unsigned AMDGCNSPIRVABIInfo::numRegsForType(QualType Ty) const {
+ // This duplicates the AMDGPUABI computation.
+ unsigned NumRegs = 0;
+
+ if (const VectorType *VT = Ty->getAs<VectorType>()) {
+ // Compute from the number of elements. The reported size is based on the
+ // in-memory size, which includes the padding 4th element for 3-vectors.
+ QualType EltTy = VT->getElementType();
+ unsigned EltSize = getContext().getTypeSize(EltTy);
+
+ // 16-bit element vectors should be passed as packed.
+ if (EltSize == 16)
+ return (VT->getNumElements() + 1) / 2;
+
+ unsigned EltNumRegs = (EltSize + 31) / 32;
+ return EltNumRegs * VT->getNumElements();
+ }
+
+ if (const auto *RD = Ty->getAsRecordDecl()) {
+ assert(!RD->hasFlexibleArrayMember());
+
+ for (const FieldDecl *Field : RD->fields()) {
+ QualType FieldTy = Field->getType();
+ NumRegs += numRegsForType(FieldTy);
+ }
+
+ return NumRegs;
+ }
+
+ return (getContext().getTypeSize(Ty) + 31) / 32;
+}
+
+llvm::Type *AMDGCNSPIRVABIInfo::coerceKernelArgumentType(llvm::Type *Ty,
+ unsigned FromAS,
+ unsigned ToAS) const {
+ // Single value types.
+ auto *PtrTy = llvm::dyn_cast<llvm::PointerType>(Ty);
+ if (PtrTy && PtrTy->getAddressSpace() == FromAS)
+ return llvm::PointerType::get(Ty->getContext(), ToAS);
+ return Ty;
+}
+
+ABIArgInfo AMDGCNSPIRVABIInfo::classifyReturnType(QualType RetTy) const {
----------------
arsenm wrote:
Can we do something better than duplicate all of this AMDGPU stuff?
https://github.com/llvm/llvm-project/pull/169865
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
