void MetadataStreamerMsgPackV3::emitKernel(const MachineFunction &MF,
const SIProgramInfo &ProgramInfo) {
auto &Func = MF.getFunction();
+ if (Func.getCallingConv() != CallingConv::AMDGPU_KERNEL &&
+ Func.getCallingConv() != CallingConv::SPIR_KERNEL)
+ return;
+
auto CodeObjectVersion = AMDGPU::getCodeObjectVersion(*Func.getParent());
auto Kern = getHSAKernelProps(MF, ProgramInfo, CodeObjectVersion);
- assert(Func.getCallingConv() == CallingConv::AMDGPU_KERNEL ||
- Func.getCallingConv() == CallingConv::SPIR_KERNEL);
-
auto Kernels =
getRootMetadata("amdhsa.kernels").getArray(/*Convert=*/true);
unsigned AMDGPUSubtarget::getKernArgSegmentSize(const Function &F,
Align &MaxAlign) const {
+ if (F.getCallingConv() != CallingConv::AMDGPU_KERNEL &&
+ F.getCallingConv() != CallingConv::SPIR_KERNEL)
+ return 0;
+
uint64_t ExplicitArgBytes = getExplicitKernArgSize(F, MaxAlign);
unsigned ExplicitOffset = getExplicitKernelArgOffset();