IBM and Xilinx Join Forces to Drive the Data Center Efficiency Multifold through App Acceleration
FREMONT,CA: IBM collaborates with Xilinx to offer higher performance and energy-efficient data center applications through Xilinx FPGA-enabled workload acceleration on IBM POWER-based systems. The companies are working together to develop open acceleration infrastructures, software and middleware to tackle emerging applications like genomics, high performance computing, Big Data analytics, machine learning, and network functions virtualization.
Xilinx All Programmable FPGAs (field programmable gate arrays) deliver the power efficiency that makes accelerators practical to deploy throughout the data center. IBM’s POWER architecture together with Xilinx FPGAs delivers coercive performance/watt while lowering total ownership cost for data centers workloads.
As part of the IBM and Xilinx strategic collaboration, IBM Systems Group developers will create solution stacks for POWER-based servers, storage and middleware systems with Xilinx FPGA accelerators for data center architectures such as OpenStack, Docker, and Spark.
Xilinx is developing POWER-based versions of its leading software defined SDAccel Development Environment and libraries for the OpenPOWER developer community.
The companies further utilize IBM’s Coherent Accelerator Processor Interface (CAPI) to build tightly integrated, coherent solutions on the POWER architecture. This helps the independent software vendors in leveraging IBM Flash Storage attached to CAPI to create very large memory spaces for in-memory processing of analytics, enabling the same query workloads to run with 1/24 the number of servers compared to commodity x86 solutions.
"Xilinx is collaborating with IBM, data center customers and the industry ecosystem to enable world class solutions for the next generation of cloud computing and NFV applications," said Hemant Dhulla, Vice President of Wired Communications and Data Center Business, Xilinx. "IBM's vast resources and expertise in data center and cloud software will contribute greatly to the FPGA-based accelerator movement currently underway."