Intel® oneAPI Data Parallel C++
Support for Intel® oneAPI DPC++ Compiler, Intel® oneAPI DPC++ Library, Intel® DPC++ Compatibility Tool, and GDB*

SYCL target is invalid nvptx64-cuda

parody9
Beginner
1,039 Views

I am following this guide(https://intel.github.io/llvm-docs/GetStartedGuide.html) to learn DPC++ , I got an error like this

command : 

clang++ -fsycl -fsycl-targets=nvptx64-nvidia-cuda-sycldevice nvidia-test-app.cpp

error:

clang++: error: SYCL target is invalid: 'nvptx64-nvidia-cuda-sycldevice'

How can I solve this error?( I did configure.py option --cuda and compile.py executed well.)

My clinfo - l

Platform #0: Intel(R) FPGA Emulation Platform for OpenCL(TM)

`-- Device #0: Intel(R) FPGA Emulation Device

Platform #1: Intel(R) OpenCL

`-- Device #0: AMD Ryzen 7 3700X 8-Core Processor             

Platform #2: NVIDIA CUDA

`-- Device #0: GeForce RTX 2080 SUPER

0 Kudos
1 Solution
GouthamK_Intel
Moderator
977 Views

Hi,

Thanks for reaching out to us!

This forum is intended to support Intel oneAPI Products only. As we can see that you are using an open-source version of oneAPI for Nvidia devices support, we request you to raise an issue in GitHub for faster response: https://github.com/intel/llvm/issues

 

If you intended to use Intel oneAPI Products,  one place to download a free community version is the Intel oneAPI Base Toolkit and follow the installation guide to install the toolkit and required driver.

After installing the Intel oneAPI Base toolkit, you can refer to the below Get-Started guide for Linux.

https://software.intel.com/content/www/us/en/develop/documentation/get-started-with-intel-oneapi-bas...

Have a Good day!

 

Thanks & Regards

Goutham

 

View solution in original post

5 Replies
GouthamK_Intel
Moderator
978 Views

Hi,

Thanks for reaching out to us!

This forum is intended to support Intel oneAPI Products only. As we can see that you are using an open-source version of oneAPI for Nvidia devices support, we request you to raise an issue in GitHub for faster response: https://github.com/intel/llvm/issues

 

If you intended to use Intel oneAPI Products,  one place to download a free community version is the Intel oneAPI Base Toolkit and follow the installation guide to install the toolkit and required driver.

After installing the Intel oneAPI Base toolkit, you can refer to the below Get-Started guide for Linux.

https://software.intel.com/content/www/us/en/develop/documentation/get-started-with-intel-oneapi-bas...

Have a Good day!

 

Thanks & Regards

Goutham

 

parody9
Beginner
926 Views

Sorry i'm late to check your reply.

I appreciate for your answer.

GouthamK_Intel
Moderator
940 Views

Hi,

Could you please let us know if your issue is resolved or not?

If your issue is resolved, let us know if we can close this thread.


Thanks & Regards

Goutham


GouthamK_Intel
Moderator
912 Views

Hi, 

Thanks for the confirmation!

As this issue has been resolved, we will no longer respond to this thread. 

If you require any additional assistance from Intel, please start a new thread. 

Any further interaction in this thread will be considered community only. 

Have a Good day.


Thanks & Regards

Goutham


dpcpp_llvm
Beginner
361 Views

Sir, I am also facing same issue. And i have been trying this but no solution. Please help me.

 

1. My GPU is: NVIDIA GeFOrce GTX 1050 Ti

2. I have installed cuda and cuda Toolkit. 

3. I have gone through https://intel.github.io/llvm-docs/GetStartedGuide.html#prerequisites link and trying to build dpc++ program with support for NVIDIA CUDA.

4. I have done compile.py and configure.py successfully. And getting error when trying to compile dpc++ using 

-fsycl-targets=nvptx64-nvidia-cuda

5. command:  DPCPP_HOME/llvm/build/bin/clang++ -std=c++17 -O3 -fsycl -fsycl-targets=nvptx64-nvidia-cuda --cuda-path=/usr/local/cuda-11.7/targets/x86_64-linux/ add1DBuf.cpp -o a.out

after executing the command the error is:

clang-14: error: unkown argument: '-fsycl-targets=nvptx64-nvidia-cuda'

 

please help me to build 

Reply