Arkville DMA for Intel® Agilex™ 7 FPGAs
Arkville DMA for Intel® Agilex™ 7 FPGAs
About this offer
Atomic Rules Arkville DMA for Intel® Agilex™ 7 FPGAs provide a high-throughput, low-latency path between host CPU memory and FPGA fabric logic, offloading CPU core usage, eliminating memory copies, and improving overall system efficiency. FPGA processing relies upon high throughput and low latency to maximize performance and efficiency. In conjunction with the new capabilities that Intel® Agilex™ 7 FPGAs provide, more than a doubling of useful throughput performance is possible. Sustained Gen 5 application data rates of 400 Gbps (50G Bytes/Second) are realized in both directions between the FPGA logic and host memory. With Arkville, a conduit is provided that seamlessly transports data in both directions between FPGA logic and host memory. Software engineers see industry-standard APIs for producing and consuming data in zero-copy user space buffers. Hardware engineers see industry-standard RTL interfaces which produce and consume data. Arkville supports data movement for a wide variety of applications. For packet-based applications, Arkville supports DPDK release 23.03, with a poll mode driver open-sourced and downloadable directly from dpdk.org. For bulk data movement between FPGA and the host user space memory, a zero-copy kernel mode driver is available. For use with 5G O-RAN offload, Arkville has a DPDK Baseband Device BBDEV PMD available. Whichever API is used, Arkville on Intel® Agilex™ 7 FPGAs provide 50G Bytes/Second (400 Gbps) data motion between user space host memory and FPGA logic.
Details
Regional Coverage
Americas:
Latin America Region
North America Region
Asia, Pacific, and Japan:
Southeast Asia
Australia and New Zealand
Japan
Taiwan
Rest of Asia
Korea
South Asia
Europe, Middle East, and Africa:
Middle East, Turkey, and Africa
Central Eastern Europe
Western European Union Region
Commonwealth of Independent States
Northern European Union Region
Southern European Union Region
Central European Region
People's Republic of China:
People's Republic of China
Use Case
Data Science
Storage
High Performance Computing
Cloud Computing
Industry
Communications
Government
Arts and Entertainment
Defense and Space
Software
Atomic Rules, LLC
Due to a technical difficulty, we were unable to submit the form. Please try again after a few minutes. We apologize for the inconvenience.
Atomic Rules, LLC
The recaptcha has identified the current interaction similar to a bot, please reload the page or try again after some time.
We provide our clients with effective solutions to problems involving interconnection networks and reconfigurable computing. Our practice employs scalable, rule-based methods to tackle complex concurrency among heterogeneous processors.
Arkville Dma For Intel® Agilex™ 7 Fpgas
Your request for information has been successfully sent to Atomic Rules, LLC