June 12, 2013
HPC system makers are lining up to announce compatibility with the new fourth generation Intel Core processor, codenamed "Haswell." The new Iris GPUs based on the Haswell architecture are giving Intel new credibility in the graphics processing department. But according to Intel, just as important as the hardware is the full support for the OpenCL architecture that it's delivering with Haswell and its software development kit.
In 2011, Intel rolled out support for OpenCL with its SDK that helped developers parallelize code run on 2nd generation Intel Core processors by taking scalar input and vectorizing it to use the SIMD instruction set. In 2012, Intel introduced the Intel SDK for OpenCL Applications 2012, which unlocked OpenCL programmability of the Intel HD Graphics on 3rd generation Intel Core processors. That allowed ISVs to take advantage of both the CPU and the graphics components.
Now, with the launch of Intel SDK for OpenCL Applications 2013 in conjunction with the 4th gen Intel Core processors and Haswell GPUs, Intel is giving developers the most powerful set of tools yet for graphics processing, according to this graphic from Intel.
Fourth generation Intel X86 CPUs can provide up to a 20 percent performance boost at the same power levels as third generation CPUs. But the integrated Iris GPUs top that, with nearly double the performance over the previous generation.
That is giving developers, particularly those who work with the OpenCL framework, a chance to build HPC applications that really move. "As 4th generation Intel Core processors with Intel Iris graphics and Intel HD Graphics proliferate across all of the company's product lines, Intel's most concerted effort to improve graphics processing horsepower promises to amplify the benefit of OpenCL acceleration in the imaging and media processing applications optimized for it," the company says.
The new Intel SDK for OpenCL Applications 2013 brings GPU programmers a range of components, including Kernel Builder, which can be used to design and optimize kernels; integration with Windows Visual Studio development environment; and the VTune Amplifier XE feature (a beta feature for GPUs on Windows 7 and 8).
OpenCL coders will also appreciate the Intel Graphics Performance Analyzers (GPAs), a free download for the Intel SDK for OpenCL Applciations 2013 offering that optimizes the OpenCL code. They'll also appreciate the Intel GPA System Analyzer, which tracks utilization between the CPU and the Iris GPU, and the Intel GPA Platform Analyzer, which traces the profiles of OpenCL commands across the CPU and graphics engine.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?