StreamComputing launched an educational initiative this week that aims to get more developers to study and use OpenCL in their projects. Within this project, up to 20 collaborators will port as many GEGL operations to OpenCL as possible. There is tons of work to be done, but the benefit is that your code will be running in GIMP. Vincent Hindriksen and Adel Johar … [Read more...]
SC15 – Accelerator Use in World’s Top Supercomputers
NVIDIA notes more than 100 accelerated systems now on TOP500 list TOP500 Highlights: One-third of FLOPS now powered by accelerators NVIDIA Tesla GPUs sweep 23 of 24 new accelerated supercomputers Tesla supercomputers growing at 48% CAGR over past five years AUSTIN, Texas—SC15—Nov. 16, 2015—Today’s list of the world’s TOP500 supercomputers shows the extent to which … [Read more...]
Pre-order Your $599 Tegra X1 Powered TX1 Developer Kit
NVIDIA is now taking pre-orders for the Tegra X1 powered TX1 development kit at the NVIDIA online store. You can develop OpenACC, CUDA, and OpenCL codes for this 64-bit ARM based system! No word yet on pricing of the actual credit card sized TX1 computer. JETSON TX1 MODULE NVIDIA Maxwell™ GPU with 256 NVIDIA® CUDA® Cores Quad-core ARM® Cortex®-A57 MPCore … [Read more...]
No longer a preview – Intel updates the INDE OpenCL Code Analyzer
Intel has updated the new OpenCL™ Code Analyzer, a feature of Intel® INDE OpenCL™ Code Builder, which adds performance analysis capabilities integrated into a Microsoft Visual Studio OpenCL development environment. No longer a preview, the OpenCL Code Builder now supports OpenCL code development, which enables developers to carry on performance optimizations in each step of … [Read more...]
ACM Paper Observes FPGA, GPU, CPU Energy Efficiency Hierarchy
Sparsh Mittal and Jeff Vetter provide a survey of the comparative energy efficiency of GPUs relative to FPGAs and CPUs in their Jan. 2015 ACM Computing Surveys (CSUR) paper, "A Survey of Methods for Analyzing and Improving GPU Energy Efficiency" in which they observe a general energy efficiency hierarchy where, "it is clear that although for majority of works, FPGAs are … [Read more...]
Provisional OpenCL 2.1 Enables Kernels Written Using a Subset of C++14 and Uses SPIR-V
The Khronos™ Group today announced the ratification and public release of the OpenCL™ 2.1 provisional specification viewable at www.khronos.org/opencl/ so developers and implementers can provide feedback before finalization at the OpenCL forums. Comments can be made via https://www.khronos.org/opencl/opencl_feedback_forum. The OpenCL 2.1 C++ kernel language is a static … [Read more...]
OpenCL Programmed FPGAs Claim a 3X Performance-to-Power Advantage at Microsoft
The Microsoft white paper, "Accelerating Deep Convolutional Neural Networks Using Specialized Hardware" describes an OpenCL programmed implementation of Convolutional Neural Networks (CNNs) that touts a conservative estimate of 3x the performance-to-power advantage over NVIDIA GPUs when running on new FPGA hardware. Doug Berger posted on the Inside Microsoft Research … [Read more...]
Tutorial on the OpenCL 2.0 Generic Address Space
Adam Lake and Robert Ioffe posted a nice tutorial on the Intel website about the new OpenCL 2.0 generic address space. The OpenCL 2.0 generic address space makes writing OpenCL programs easier by removing the requirement of decorating all pointers with a points to address space. Instead, OpenCL programmers just use pointers as they would in standard C. Utilizing this new … [Read more...]
Intel Posts OpenCL 2.0 QuickSort Tutorial (Compare to TE CUDA Version)
Intel Engineer Robert Ioffe has posted an OpenCL QuickSort tutorial that utilizes nested parallelism and Workgroup-scan functions. In particular, the tutorial shows how to use the OpenCL™ 2.0 enqueue_kernel functions that queue kernels from the device without host intervention (Much like dynamic parallelism) plus work_group_scan_exclusive_add and … [Read more...]
Attend or Submit to the 3rd IWOCL May 12-13, 2015 at Stanford University
The 3rd IWOCL (International Workshop on OpenCL) takes place at Stanford University, California from Tuesday 12 to Wednesday 13 May 2015. Workshops are held on the Tuesday, followed by the one-day conference on Wednesday. The conference is accompanied by a poster session and table-top displays by sponsors. OpenCL Papers, Workshops and Posters The IWOCL 2015 call for … [Read more...]