topic Fat binary with PTX backend in Intel® oneAPI DPC++/C++ Compiler

Fat binary with PTX backend

Viet-Duc — Fri, 04 Jun 2021 08:16:39 GMT

Hi,

To compiler SYCL code for a specific NVIDIA device, I've used to following:

clang++ \ -fsycl \ -fsycl-targets=nvptx64-nvidia-cuda-sycldevice \ -fsycl-unnamed-lambda \ -Xsycl-target-backend "--cuda-gpu-arch=sm_35" \ test.cpp

Is there a way to generate a fat binary containing several sm_* computes ?

I have gone through the manual with no avail.

Thanks

Re: Fat binary with PTX backend

RahulV_intel — Mon, 07 Jun 2021 10:39:20 GMT

Hi,

Could you try the following command and let us know?

clang++ -fsycl -fsycl-targets=nvptx64-nvidia-cuda-sycldevice sample.cpp -o sample

IMO, the above command should work on any SM architecture.

Thanks,

Rahul

Re: Fat binary with PTX backend

Viet-Duc — Mon, 07 Jun 2021 14:46:15 GMT

Thanks for suggestions.

But if you remove '-Xsycl-target-backend', the program will fail at runtime, for instance on Tesla K40

PI CUDA ERROR: Value: 209 Name: CUDA_ERROR_NO_BINARY_FOR_GPU Description: no kernel image is available for execution on the device Function: build_program Source Location: .../apps/src/llvm/unstable/sycl/plugins/cuda/pi_cuda.cpp:516 PI CUDA ERROR: Value: 400 Name: CUDA_ERROR_INVALID_HANDLE Description: invalid resource handle Function: cuda_piProgramRelease Source Location: .../apps/src/llvm/unstable/sycl/plugins/cuda/pi_cuda.cpp:2938 The program was built for 1 devices Build program log for 'Tesla K40m': -999 (Unknown OpenCL error code)

If I force sm35, it will not work on other gpus such as V100.

Since the manual is quite terse, I have asked the question in case I overlooked something.

Re:Fat binary with PTX backend

RahulV_intel — Wed, 09 Jun 2021 06:31:04 GMT

Hi,

As per the documentation, SM-50 and above architectures are supported.

https://github.com/intel/llvm/blob/sycl/sycl/doc/GetStartedGuide.md

Please note that only the Github version of DPC++ supports the CUDA backend. If you have further queries, please raise a new issue in the below link:

https://github.com/intel/llvm/issues

Thanks,

Rahul

Re: Fat binary with PTX backend

Viet-Duc — Wed, 09 Jun 2021 12:18:56 GMT

Hi,

You are right.

For CUDA-related question, I should have asked the intel-llvm developers instead.

I will raise the issue through github page. Nevertheless, thanks for your time.

Regards.

Re:Fat binary with PTX backend

RahulV_intel — Mon, 14 Jun 2021 10:03:36 GMT

Intel will no longer monitor this thread. Further discussions on this thread will be considered community only.