0

I have a server equipped with 24 Intel(R) Xeon(R) CPUs and Tesla K80 GPU devices. Each CPU has 6 cores. I want to develop a parallel program that runs on all the CPUs and their cores. I started with OpenCL framework. When I list the platforms available on the server, I only get one platform with the following information:

number of platforms: 1

Name : NVIDIA CUDA

Vendor : NVIDIA Corporation

Version : OpenCL 1.2 CUDA 8.0.0

Profile : FULL_PROFILE

Extensions : cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_copy_opts

Shouldn't their be another platform for the CPUs?

If this is not possible in OpenCL, is there another framework that helps in leveraging all the CPUs (and their cores) for parallel programs?

5
  • You have to install the Intel OpenCL runtime Commented Nov 14, 2016 at 11:05
  • Or you can install Intel's integrated gppu driver but if you don't have that igpu then you have to install runtimes for opencl as @Jovasa said here: software.intel.com/en-us/articles/opencl-drivers. If you are using mpi, you could do purey with host code. MPI+opencl should enable gpu and cpu. Commented Nov 14, 2016 at 11:16
  • I'm pretty sure Xeons don't have igpus Commented Nov 14, 2016 at 11:23
  • @Jovasa I installed OpenCL runtime and it worked. Thanks much. How can I accept your comment as answer? Commented Nov 14, 2016 at 11:45
  • I'll have to post an actual answer for that just gimme a moment Commented Nov 14, 2016 at 12:00

1 Answer 1

1

To use OpenCL on Intel devices for processors you need to install the OpenCL runtime and for possible integrated GPUs you'll need to install GPUs drivers.

Sign up to request clarification or add additional context in comments.

Comments

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.