Evgeny Mankov

Results 82 comments of Evgeny Mankov

Additionally, be aware of `Configuration` (`Debug` and `Release` by default). You may change the `Platform Toolset` only for a single `Configuration`, or for `All configurations`, or for `Multiple Configurations...`.

Right, for now (I'm not sure that's got to be fixed soon due to backward compatibility), `reinterpret_cast` is the only solution already supported by `hipify-clang` ([#801](https://github.com/ROCm-Developer-Tools/HIPIFY/issues/801)), but not by hipify-perl.

Update for `ROCm HIP 5.3.0`: The following HIP-specific elements of the `enum hipGraphNodeType` don't have a correspondence in CUDA: ```cpp #define hipGraphNodeTypeMemcpyFromSymbol cudaGraphNodeTypeMemcpyFromSymbol #define hipGraphNodeTypeMemcpyToSymbol cudaGraphNodeTypeMemcpyToSymbol ``` https://github.com/ROCm-Developer-Tools/hipamd/blob/develop/include/hip/nvidia_detail/nvidia_hip_runtime_api.h#L1145-L1146 `cudaGraphNodeTypeMemcpyFromSymbol` and...

I do not see here something HIP RT-related: ```cpp case hipDeviceAttributeVirtualMemoryManagementSupported: *pi = static_cast(g_devices[device]->devices()[0]->info().virtualMemoryManagement_); break; ``` Looks like HW or HSA RT specifics. @gargrahul, could you please have a look...

@gargrahul, @mangupta could you please let us know to whom we should address this ticket? We suspect HSA RT/HW. Thank you in advance!

Neither hipcc, nor hip-clang is intended to compile CUDA. You may translate CUDA to HIP by hipify-clang and then compile the generated HIP code. Source CUDA code may contain (guarded)...

@Kaveh01 Did you try hip-clang? Compiling hip files with *.cu extension is possible under `-x hip` option. It is the same clang's trick as compiling *.cpp under `-x cuda`.

> My collaborators wish to have both CUDA and HIP codes in the same .cu source file ... That is exactly what I wrote above: "Source CUDA code may contain...

Hi @Kaveh01 1. Ensure that `AMDGPU `is presented in `LLVM_TARGETS_TO_BUILD` in your LLVM's cmake command line. 2. Here is a guide for building missing `AMDGCN` bytecodes: https://github.com/RadeonOpenCompute/ROCm-Device-Libs

`--hip-device-lib-path=$(path_to_bitcode_libs)`