Advanced Computing in the Age of AI | Wednesday, April 24, 2024

Intel Expands Workload Acceleration with HPE in new Programmable Acceleration Card 

August 5, 2019 --  Intel announced today it is working with Hewlett Packard Enterprise* (HPE) to provide increased workload acceleration capacity for the HPE ProLiant DL380 Gen10 server. This will address computing intensive markets, like streaming analytics, media transcoding, financial technology, and network security within the new high-performance Intel FPGA Programmable Acceleration Card (Intel FPGA PAC) D5005. The Intel FPGA PAC D5005 is the second card in the Intel PAC Portfolio and is shipping now in HPE ProLiant DL3809 Gen10 server.

“The HPE ProLiant Gen10 server family is the world’s most secure, manageable and agile server platform available on the market today. By integrating the Intel FPGA PAC D5005 accelerator into the HPE ProLiant DL380 Gen10 server, we are now delivering optimized 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,” said Bill Mannel, vice president and general manager, HPC and AI, HPE

Why It’s Important: Applications like streaming analytics, artificial intelligence (including speech to text), and media transcoding require large amounts of computational capability to meet today’s increasing demands. Data center customers use hardware accelerators for specific workloads that can most benefit from FPGA-based hardware acceleration. Diverting such tasks to tailored hardware accelerators offloads suitable workloads and frees a server’s CPU cycles for higher-value workloads. Offloading appropriate workloads lowers the data center operator’s total cost of ownership.

The new Intel FPGA PAC D5005, offers more logic, memory and networking capability than previous PACs. The Intel FPGA PAC D5005 is now qualified in the HPE ProLiant DL380 Gen10 server, offering customers a higher performance PAC option in addition to the already shipping Intel PAC with Intel Arria 10 GX FPGA.

The Intel FPGA PAC D5005 acceleration card, which is based on an Intel Stratix 10 SX FPGA, provides high-performance inline and lookaside workload acceleration to servers based on Intel Xeon Scalable processors using the Intel Acceleration Stack, which includes acceleration libraries and development tools.

HPE is the first server OEM to announce pre-qualification of the Intel FPGA PAC D5005 accelerator card for use with its servers, specifically the HPE ProLiant DL380 Gen10 server. Other server vendors are also qualifying the Intel FPGA PAC D5005 accelerator card. Initial workloads specifically developed for the Intel FPGA PAC D5005 accelerator card include:

  • AI (speech-to-text translation) from Myrtle*
  • Network security from Algo-Logic*
  • Image transcoding from CTAccel*
  • Video transcoding from IBEX*

The Intel FPGA PAC D5005 accelerator card is the latest in a growing line of FPGA-based server-accelerator cards from Intel. Compared with the Intel programmable acceleration card with Intel Arria 10 GX FPGA, the Intel FPGA PAC D5005 accelerator card offers significantly more resources including three times the amount of programmable logic, as much as 32 GB of DDR4 memory (a 4x increase) and faster Ethernet ports (two 100GE ports versus one 40GE port). With a smaller physical and power footprint, the Intel PAC with Intel Arria 10 GX FPGA fits a broader range of servers, while the Intel PAC D5005 is focused on providing a higher level of acceleration.

The Small Print:

Results have been estimated or simulated using internal Intel analysis, architecture simulation, and modeling, and provided to you for informational purposes. Any differences in your system hardware, software or configuration may affect your actual performance.

Tests document performance of components on a particular test, in specific systems. Differences in hardware, software, or configuration will affect actual performance. Consult other sources of information to evaluate performance as you consider your purchase.  For more complete information about performance and benchmark results, visit www.intel.com/benchmarks.


Source: Intel 

EnterpriseAI