The goal of the Xilinx-IBM partnership is to give developers acceleration tools, software and middleware to better handle machine learning, network functions virtualization, big data and high-performance computing.
Advertisement
IBM is partnering with Xilinx to expand the use of programmable chips to its Power systems as the tech vendor looks to gain more share of the server chip market from Intel. The new offerings center on the integration of IBM’s open and licensable POWER processors with accelerators, dedicated high performance processors that can be optimized for computationally intensive software code. Accelerators such as GPUs and FPGAs have been used in the HPC space for nearly a decade as a way of increasing the performance of the systems while holding down power consumption.
IBM and Xilinx have announced their teaming up, which brings IBM’s Power processor to a wider array of servers. Since OpenPOWER allows creating both Power servers and Power processors, it will be attractive for the Chinese companies and so deals between IBM and the local firms are expected in future. “IBM’s vast resources and expertise in data center and cloud software will contribute greatly to the FPGA-based accelerator movement now underway”. The company aims to grab a bigger slice of the data center market by taking on Intel, which is now a major player. NEC announced availability of its ExpEther Technology that is also suited for POWER architecture-based systems, along with plans to leverage IBM’s innovative Coherent Accelerator Processor Interface (CAPI) technology to deliver additional accelerated computing value to its clients in 2016. (NASDAQ:XLNX) chips in Power systems. The Big Blue wants to jump-start its Power programme by licencing the design for use by other companies. Intel earlier this year bought Altera largely for its programmable processors and accelerators.
Advertisement
New Cluster at University of Texas at Austin: IBM and new OpenPOWER Foundation member, the Texas Advanced Computing Center (TACC) at The University of Texas at Austin, announced a POWER8-based accelerated computing cluster to be made available to academic researchers and developers. NVIDIA Tesla GPU-based supercomputers comprise 70 of these systems – including 23 of the 24 new systems on the list. However, the use of accelerators-and the kinds of accelerators-is expanding, with FPGAs in the spotlight. The company believes it is a key competitor to x86.
