Intel has today announced its collaboration with Hewlett Packard Enterprise (HPE) to augment the workload acceleration capacity of the HPE ProLiant DL380 Gen10 server, in response to the increasing intensity of computing markets: it will address concerns surrounding recent trends like streaming analytics, media transcoding, financial technology and network security, through the integration of Intel’s FPGA Programmable Acceleration Card (PAC) D5005. All HPE ProLiant DL380 Gen10 servers will come equipped with this card in future. 

As stipulated, streaming analytics, AI and media transcoding, among other trends, demand a lot from their respective computational modules. In order to meet the combined demands of these respective applications, data centre customers utilise hardware accelerators like Intel’s FPGA PAC D5005 to balance workload and free a server’s CPU cycles for high-value workloads as a result: this reduces the total cost of ownership for the data centre operator, a benefit that can go on to improve services, technology and the business as a whole. Intel’s FPGA PAC D5005 offers the logic, memory and networking capability to withstand the demands mentioned here: based on an Intel Stratix 10 SX FPGA, it provides high-performance inline and look aside workload acceleration to servers based on Intel Xeon Scalable processors using the Intel Acceleration Stack, which includes acceleration libraries and development tools. 

“The HPE ProLiant Gen10 server family is a secure, manageable and agile server platform. By integrating the Intel FPGA PAC D5005 accelerator into the HPE ProLiant DL380 Gen10 server, we are now delivering optimised configurations for an increasing number of workloads, including AI inferencing, big data and streaming analytics, network security and image transcoding. Combined with our broad portfolio of services from HPE Pointnext, we enable our customers to accelerate time-to-value and increase ROI.”– Bill Mannel, VP and general manager, HPC and AI, HPE. 

For more information on Intel’s FPGA, click here.