Last year, Intel acquired FPGA-focused Khronos member Altera. Intel has now announced a new line of hybrid chips that combine FPGAs with their well-known CPUs. One of the more interesting aspects of the new Intel FPGA ecosystem is the Acceleration Stack, an OpenCL based programming environment that can be used by developers for hybrid cards or discrete cards, including FPGAs, CPUs, and GPUs. The stack abstracts the programming required for the FPGAs to streamline and speed up development for accelerators and applications being used. Additionally, it allows for code to be reusable — porting between FPGAs/GPU/CPU should be possible without major changes. OpenCL, a C based programming language, will. This is quite the opposite of what had been available when Intel released the E600C seven years ago.
Hybrid CPU-FPGA devices are expected to see widespread adoption. Intel is concentrating on the programming environment so the same tools will be used whether the CPUs and FPGAs are discrete or hybrid in the same socket. This is called the Acceleration Stack for Intel, and it is a complete programming environment that is based on OpenCL, the common higher level programming language that is converged to Verilog and VHDL for FPGAs. Learn more about the roadmap Intel has working on.
Announcing that the 6th International Workshop on OpenCL will take place on the 14-16 May, 2018 at St Catherine's College, Oxford, UK and that the Call for Submissions is now open. Submissions related to any aspect of using OpenCL (including SYCL, Vulkan Compute and OpenCL based libraries) are of interest, including (but not limited to): case-studies of their use in applications, software tools, programming methods, debugging, performance analysis, and integration.
The Xilinx software defined development environment, SDAccel, is now available on Amazon Web Services for use with Amazon Elastic Compute Cloud F1 instances. SDAccel automates the acceleration of software application written in C, C++ or OpenCL by building application-specific FPGA kernels for Amazon EC2 F1.
Non-profit organization The Blender Foundation has released Blender 2.79, an update to its cross-platform, open-source 3D graphics tool. The new build further improves its Cycles Rendering feature, bringing feature parity with NVIDIA CUDA and improved performance to AMD OpenCL hardware.
A pan-European project has started this month to bring together the technologies needed for exascale computing, tackling the key challenge of power usage. The project started this month, bringing together three existing exascale projects on FPGA accelerators, interconnect and 3D chip technologies to reach performance of 10^18 operations, 10 times that of today's fasest supercomputers. At the University of Manchester they are working on OpenCL as the programming model to configure modules that can be plugged into a system as an HPC accelerator.
Renesas Electronics announced their collaboration to deliver ComputeAorta™, Codeplay’s OpenCL open standard-based software framework for Renesas R-Car system-on-chips (SoCs). The new framework is designed to support software development for the R-Car’s latest image recognition IP, the IMP-X5, a multi-threading core optimized for computer vision and cognitive processing. Codeplay will also provide R-Car with ComputeCpp™, an implementation of the SYCL™ open standard, enabling single source C++ software for high level and object-oriented programming. The result of this collaboration provides developers with standard software development tools and support for a wide range of open source computer vision or open source deep learning software, such as TensorFlow™ library.
NVIDIA Nsight Visual Studio Edition for Microsoft Visual Studio allows you to build, debug, profile and trace heterogeneous compute, graphics, virtual reality, and UWP applications built with CUDA C/C++, OpenCL, DirectCompute, Direct3D, Vulkan, OpenGL, OpenVR, and the Oculus SDK. Check out the OpenGL frame debugging, the new Range Profiler for instant GPU bottleneck analysis, and all the new features.
Codeplay announces SPIR-V support for ComputeCpp in v0.3.0. This beta implementation of SPIR-V for OpenCL support means that developers can use SYCL and ComputeCpp to develop for any OpenCL hardware that includes a driver that consumes SPIR-V.