The countdown is on — IWOCL 2026 is just two weeks away.

Join the global OpenCL and SYCL community in Heilbronn, Germany (May 6–8) for the premier forum dedicated to open compute languages and heterogeneous platform programming. Expect the latest technical talks, Khronos Working Group updates, and ample opportunity to connect with peers across industry and academia.

Registration is open: www.iwocl.org
#IWOCL #OpenCL #SYCL #HPC #Khronos #HeterogeneousComputing

Khronos Group's OpenVX Working Group have released two new extensions, Target Kernel and Node Command, to tackle efficiently distributing computation across dedicated hardware, and adapting processing pipelines dynamically at runtime without touching the data path.

https://www.khronos.org/blog/openvx-extensions-unlock-computer-vision-and-ai-capabilities?utm_medium=social&utm_source=mastodon&utm_campaign=OpenVX_Extensions_for_SOC&utm_content=blog
#OpenVX #ComputerVision #EmbeddedSystems #ADAS #HeterogeneousComputing #MachineLearning

Join us at IWOCL 2026 to hear from Professor Hu He of Tsinghua University. Professor Hu will present on utilizing OpenCL to build the foundation for computing in China.

IWOCL 2026 takes place May 6–8 in Heilbronn, Germany.

Learn more and register: https://www.iwocl.org/
#IWOCL2026 #OpenCL #OpenSource #HPC #HeterogeneousComputing

Join us at IWOCL 2026 to hear from Professor Pekka Jääskeläinen of Tampere University. Pekka will look back — and forward — in a talk titled "15 Years of PoCL: Past Lessons, Present Reality, Future Directions."

IWOCL 2026 takes place May 6–8 in Heilbronn, Germany.

Learn more and register: https://www.iwocl.org/
#IWOCL2026 #PoCL #OpenCL #OpenSource #HPC #HeterogeneousComputing

Keynote at IWOCL 2026: Paulius Velesko presents chipStar — compiling unmodified CUDA/HIP code into OpenCL & SPIR-V fat binaries that run on Intel, AMD, NVIDIA, ARM, and RISC-V hardware. No recompilation needed.

Join us at IWOCL 2026, May 6–8 in Heilbronn, Germany to hear more.

View the full program at: https://www.iwocl.org/iwocl-2026/conference-program/
#IWOCL2026 #OpenCL #SYCL #CUDA #HPC #HeterogeneousComputing #RISCV #CUDA

Apple's M1 chip blends high-performance P-cores with energy-efficient E-cores, dynamically scheduling tasks to maximize efficiency and performance. Embrace structured concurrency, profiling real workloads, and avoid affinity assumptions for faster, greener apps. #HeterogeneousComputing #AppleSilicon #Concurrency #PerformanceOptimization #SoftwareEngineering #Portability

https://saysomething.hashnode.dev/apple-silicons-heterogeneous-design-unlocking-performance-efficiency-for-developers

Assessing Intel OneAPI capabilities and cloud-performance for heterogeneous computing

#oneAPI #HeterogeneousComputing #FPGA

https://hgpu.org/?p=29214

Assessing Intel OneAPI capabilities and cloud-performance for heterogeneous computing

This work presents a performance-oriented study of a heterogeneous application developed with Intel OneAPI to solve two well-known diffusion problems: heat diffusion and image denoising. We have ex…

hgpu.org
PoCL 4.0 released! Various new features to support more CUDA, HIP and SYCL app inputs via chipStar and DPC++. Also MacOS/CPU support is back and has now a maintainer, and a lot more: https://github.com/pocl/pocl/releases/tag/v4.0
#opencl #HeterogeneousComputing #opensource
Release PoCL 4.0 · pocl/pocl

PoCL 4.0 Highlights Support for Clang/LLVM 16.0 Support for Clang/LLVM 6-9 (inclusive) dropped More improvements to SPIR-V support for CPU and CUDA drivers CPU drivers gained support for program-s...

GitHub

What is a good book to begin learning C++? My focus is to learn C++17/C++20. I will apply it to general-purpose programming GPU (OpenCL, SYCL end HPC).

#c++ #hpc #opencl #sycl #heterogeneouscomputing

PoCL 3.1 is now out! It has LLVM 15 support, much improved SPIR-V input for CPUs and CUDA, better custom/HW accelerator device interfacing, first version of command buffer support, and other goodies! http://portablecl.org/pocl-3.1.html #opencl #HeterogeneousComputing
PoCL home page

PoCL: a performance portable open source OpenCL implementation

PoCL