The deep learning speech recognition acceleration solution leverages an Altera Arria 10 FPGA, iFLYTEK’s deep neural network (DNN) recognition algorithms and Inspur’s FPGA-based DNN parallel design, migration and optimization with OpenCL. The solution has a hardware platform in CPU+Arria 10 FPGA heterogeneous architecture and software in a high-level programming model in OpenCL to enable migration from CPU to FPGAs.
The Embedded Vision Alliance has published a OpenCL-themed article along with help from several Khronos member companies, including AMD, ARM, Imagination Technologies and Intel. Free registration is required.
In this short tutorial Intel gives you a brief introduction to Khronos SPIR-V, touches on the differences between a SPIR-V binary and a SPIR binary, and demonstrates a couple of ways of creating SPIR-V binaries using tools shipped with the latest Intel SDK for OpenCL Applications and ways of consuming SPIR-V binaries in your OpenCL program.
Debugging with Intel SDK for OpenCL Applications: This video demonstrate how to use Intel SDK for OpenCL API debugger to debug your application’s host code and how to use Intel SDK for OpenCL CPU Kernel Debugger to debug your OpenCL kernels. Performance Analysis with Intel SDK for OpenCL Applications: This video demonstrate how to use Intel SDK for OpenCL analysis tools to identify performance bottlenecks in the host API calls and optimize the kernel code to get better utilization and reduce the latency on Intel® Processor Graphics.
The Lightweight Java Game Library released its final build of version 3, in development since 2012. Version 3 provides API bindings to Java for many libraries including Khronos APIs such as OpenGL, OpenGL ES, EGL, OpenCL and Vulkan. LWJGL powers many cross platform applications including the popular game Minecraft.
Synopsys, Inc. announced the DesignWare EV6x family, its newest generation of processor cores optimized for embedded vision applications requiring high definition resolutions. The EV6x processor family is supported by a comprehensive software programming environment based on common embedded vision standards including OpenVX and OpenCL C, as well as Synopsys’ MetaWare Development Toolkit. A complete software programming environment including OpenCV and OpenVX libraries, OpenVX runtime, and Synopsys’ MetaWare Development Toolkit with OpenCL C vectorizing compiler speeds the development of application software for the DesignWare EV6x processor family. The OpenVX framework simplifies the programming of the EV6x processors by automatically distributing tiled kernel execution over multiple scalar, vector DSP and CNN execution units. The OpenVX framework includes 43 standard computer vision kernels that have been optimized to run on the EV6x Processors. The MetaWare OpenCL C compiler offers automatic whole function vectorization for data-level parallelism and is used for creating kernels for the vector DSPs.
CodeXL now supports capturing a trace of Vulkan frames for games and apps running on Microsoft Windows. AMD also added UI enhancements to detail Microsoft DirectX® 12 command lists and Vulkan command buffers. As well, CodeXL now displays the details and content of OpenGL and OpenCL objects while debugging C++ host code on Linux.
YetiWare will be talking OpenCL at their booth at OCE Discovery in Toronto this week. OCE Discovery is Canada’s leading innovation-to-commercialization conference showcasing leading-edge technologies, best practices and research in Ontario Canada.