A deep learning acceleration solution based on Altera’s Arria® 10 FPGAs and DNN algorithm from iFLYTEK, an intelligent speech technology provider in China, results in Inspur with HPC heterogeneous computing application capabilities in GPU, MIC and FPGA. The deep learning speech recognition acceleration solution leverages an Altera Arria 10 FPGA, iFLYTEK’s deep neural network (DNN) Read more…
When it comes to mainstream adoption of the use of GPUs and other accelerators, one of the primary barriers lies in programmability. While the vendor communities around accelerators have pushed to flatten the learning curve, the fact remains that it takes special effort on the part of ordinary developers to undertake the educational process. In this in-depth audio feature, we talk to Rice University researcher, Max Grossman about how Java…
HPC programmers who are tired of managing low-level details when using OpenCL or CUDA to write general purpose applications for GPUs (GPGPU) may be interested in Harlan, a new declarative programming language designed to mask the complexity and eliminate errors common in GPGPU application development.
This week we talked with AMD’s GM of the Server Business Unit, Andrew Feldman about his company’s role in the future of HPC. We asked how invested they are in the future of this market, what technologies will push their drive forward, and where they see the biggest opportunities in high performance computing. Interestingly, we found that….
In this article, we will consider how OpenCL can address some of the coming challenges, and what the OpenCL community is doing to insure that there is a vibrant ecosystem of support, as more and more users turn to OpenCL from vendor-locked solutions.
<img src=”http://media2.hpcwire.com/hpcwire/world_connectivity_200x.jpg” alt=”” width=”95″ height=”70″ />The top research stories of the week include lessons learned from system failures; a cross-platform OpenCL implementation; the best memory to extract GPU’s potential; innovative ideas for next-generation interconnects; and the benefits of cloud storage to HPC applications.
<img style=”float: left;” src=”http://media2.hpcwire.com/hpcwire/GPU_cluster_for_password_cracking_2012_200x.jpg” alt=”” width=”101″ height=”77″ />Today’s notion of safe passwords may soon be a thing of the past. Thanks to cheaper hardware, cloud software, and free password cracking programs, it’s easier than ever to hack these digital keys. Just how easy? Earlier this week, a custom-built GPU cluster tore through 348 billion password hashes per second during the Passwords^12 Conference in Oslo, Norway.
<img style=”float: left;” src=”http://media2.hpcwire.com/hpcwire/OpenCL_logo.png” alt=”” width=”80″ height=”76″ />As the two major programming frameworks for GPU computing, OpenCL and CUDA have been competing for mindshare in the developer community for the past few years. Until recently, CUDA has attracted most of the attention from developers, especially in the high performance computing realm. But OpenCL software has now matured to the point where HPC practitioners are taking a second look.
<img style=”float: left;” src=”http://media2.hpcwire.com/hpcwire/AMD_APU_small.jpg” alt=”” width=”97″ height=”68″ />Last week, AMD used its Financial Analyst Day to talk up heterogeneous computing, the technology that the company is betting on to be the next “big thing” in the microprocessor business. To that end, company execs explained how their newly hatched Heterogeneous System Architecture (HSA) will evolve over the next three years to drive their product roadmap forward.
Software maker offers heterogeneous computing in a C++ wrapper.