Based on reader feedback, this weeks OpenCL News roundup now sees the news grouped into sections for easer reading. Thanks to everyone for their feedback. If we missed any news please contact us.
News
- Intel TBB 4.4 (Threading Building Blocks) Update 2 introduces opencl_node which enables OpenCL powered devices to be utilized and coordinated by a flow graph.
- Video: Variance Clamping with OpenCL in upcoming LuxRender v1.6
- Intel Hooks OpenCL Beignet in with their C Media Runtime (CMRT)
- Altera updates OpenCL training courses
- Video: Real-time medical GPU-based marching cubes surface extraction with FAST
IWOCL News
- Neil Trevett to present IWOCL 2016 keynote. We are delighted to announce that Neil, president of the Khronos Group and chair of the OpenCL working group and vice president at NVIDIA, will be presenting a keynote at IWOCL 2016.
- Call for ‘Vulkan Compute‘ submissions to IWOCL 2016. If you would like to present a technical session around this topic please submit a paper or contact us.
- A reminder that the IWOCL 2015 Proceedings are online in the ACM digital Library
- 47 days left to submit your abstract for IWOCL 2016 paper or presentation.
Articles and Blogs
- Using Intel Media Server Studio with OpenCL Framework
- Article: Measuring GPU Compute performance for #OpenCL kernels by Imagination
- Check out Memory Fences instead of Synchronization Barriers by GPGPNotes
Research Papers
- Accelerating Exact Similarity Search on CPU-GPU Systems
- Large-Scale Compute-Intensive Analysis via In-Situ and Co-Scheduling
- Behavioral Non-portability in Scientific Numeric Computing
- A Scalable Lane Detection Algorithm on COTSs with OpenCL
- GRATER: Exploiting Data-Level Parallelism in FPGA Acceleration
- High Performance Histograms on SIMT and SIMD Architectures
- Scaling Deep Learning on Multiple In-Memory Processors