Questions tagged [sycl]

SYCL (pronounced ‘sickle’) is a royalty-free, cross-platform abstraction layer that builds on the underlying concepts, portability and efficiency of OpenCL that enables code for heterogeneous processors to be written in a “single-source” style using completely standard C++.

SYCL (pronounced ‘sickle’) is a royalty-free, cross-platform abstraction layer that builds on the underlying concepts, portability and efficiency of OpenCL that enables code for heterogeneous processors to be written in a “single-source” style using completely standard C++. SYCL is developed by the Khronos group.

SYCL single-source programming enables the host and kernel code for an application to be contained in the same source file, in a type-safe way and with the simplicity of a cross-platform asynchronous task graph. SYCL includes templates and generic lambda functions to enable higher-level application software to be cleanly coded with optimized acceleration of kernel code across the extensive range of shipping OpenCL 1.2 implementations.

Developers program at a higher level than OpenCL C or C++, but always have access to lower-level code through seamless integration with OpenCL, C/C++ libraries, and frameworks such as OpenCV™ or OpenMP™.

Implementations of SYCL include ComputeCpp and triSYCL.

151 questions
0
votes
1 answer

Error:: SYCL objects are still alive while the runtime is shutting down

I am trying to implement a simple vector addition example on SYCL with visual studio. It builds successfully but on execution it gives me SYCL objects are still alive while the runtime is shutting down.. What does it mean and how can i solve it,…
ZSA
  • 85
  • 1
  • 13
0
votes
1 answer

Why every SYCL device by default comes in separate context?

When I use a cpu_selector and a gpu_selector, these two devices fall into 2 different context by default? Why is that the default when having devices within same context helps with performant memory access of buffers (no overhead of copying over the…
Anoop - Intel
  • 354
  • 2
  • 11
0
votes
2 answers

CL/cl.h not found in SYCL

I have just started working on SYCL and ran ComputeCpp_info on my system and following data on 3 devices is showed ComputeCpp Info (CE 1.1.0) SYCL 1.2.1 revision 3 Device 1 ( GeForce GTX 1050 = NO - Device does not support SPIR) Device 2 (Intel(R)…
ZSA
  • 85
  • 1
  • 13
0
votes
1 answer

Multiple AMD GPUs with Tensorflow and OpenCL on Ubuntu 16.04

After a lot of struggles: Built successfully Tensorflow with OpenCL on fresh Ubuntu 16.04 with amdgpu 17.50. Have 5 identical GPUs (rx580) installed and all of them are reported by clinfo and computecpp_info as expected. Running the MNIST convnet…
Gianks
  • 63
  • 1
  • 15
0
votes
0 answers

/usr/local/cuda-8.0/lib64/libOpenCL.so.1: no version information available

When I am running computecpp_info $ /usr/local/computecpp/bin/computecpp_info /usr/local/computecpp/bin/computecpp_info: /usr/local/cuda-8.0/lib64/libOpenCL.so.1: no version information available (required by…
Akhilesh
  • 1,024
  • 1
  • 9
  • 26
-1
votes
1 answer

How to measure the execution time of GPU with using Profiling+openCL+Sycl+DPCPP

I read this link https://github.com/intel/pti-gpu and I tried to use Device Activity Tracing for OpenCL(TM), but I am confused and I do not know how should I measure the time on the accelerators with using Device Activity documentation. for…
Sahar Sa
  • 25
  • 9
-1
votes
1 answer

Are SYCL and OpenACC competing frameworks? or complementary?

I'm gathering information about heterogeneous computing. I've come across SYCL and OpenACC. I gather that OpenACC has many pragma directives (similar to OpenMP) to abstract GPU calculations (either OpenCL or CUDA or both??). However, it seems to me…
Aaron B.
  • 1,605
  • 13
  • 12
-1
votes
1 answer

Pass a function body from C to C++

Not sure if this is even possible. I need to pass a function from C to C++. It cannot be a function pointer. C++ Function that I need to call: template void parfor(int N, Lam lam) { lam(i); } C Function that I want to give to parfor…
-2
votes
1 answer

error: no viable conversion from 'std::array' to 'const void *' using SYCL/DPC++

I am a beginner in SYCL/DPC++. I have written a code using USM(Unified Shared Memory) and have taken two array host and device array in which I want to copy the host array values to device array and performing basic operations and printing the…
sv6
  • 11
  • 4
1 2 3
9
10