Data processing unit

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

A data processing unit (DPU) is a programmable specialized electronic circuit with hardware acceleration of data processing for data-centric computing.[1][2] The data is transmitted to and from the component as multiplexed packets of information. A DPU generally contains a CPU, NIC and programmable data acceleration engines.[3][4][5] This allows DPUs to have the generality and the programmability of central processing units while being specialized to operate efficiently on networking packets, storage requests or analytics requests.[6][7][8]

The data acceleration engines differentiates itself from a CPU by a larger degree of parallelism (required to process many requests) and from a GPU by a MIMD architecture rather than an SIMD architecture (required as each request needs to make different decisions and follow a different path through the chip).[9][10] DPUs can be either ASIC-based, FPGA-based or SoC-based.[11] DPUs have been increasingly used in data centers and supercomputers since their introduction in the 2010s due to the rise in use of data-centric computing, big data, security, and artificial intelligence/machine learning/deep learning.[12] DPUs are designed to be independent infrastructure endpoints.[13]

DPU vendors & product lines include:

Software vendors utilizing DPUs include:


  1. ^ "A Peek Inside Fungible, A Data Center Startup From Juniper Cofounder Pradeep Sindhu - Packet Pushers". Retrieved 2019-08-06.
  2. ^ "SmartNICs, IPUs, DPUs de-hyped: Why and how cloud giants are offloading work from server CPUs". Retrieved 2022-01-03.
  3. ^ Deierling, Kevin (2020-05-21). "What Is a DPU? | NVIDIA Blog". The Official NVIDIA Blog. Retrieved 2021-05-29.
  4. ^ a b servethehome (2020-09-29). "What is a DPU A Data Processing Unit Quick Primer". ServeTheHome. Retrieved 2021-06-06.
  5. ^ ServeTheHome (2021-05-30). "DPU vs SmarNICs vs Exotic FPGAs". ServeTheHome. Retrieved 2022-01-03.
  6. ^ "To handle the data tsunami, Juniper's founder turns to custom silicon". SiliconANGLE. 2018-11-30. Retrieved 2019-08-06.
  7. ^ 20190012350, Sindhu, Pradeep; Frailong, Jean-marc & Noureddine, Wael et al., "Data Processing Unit for Stream Processing", issued 2019-01-10 
  8. ^ Hennessy, John. “The End of Moore's Law, CPUs (as We Know Them), and the Rise of Domain Specific Architectures.” AI Hardware Summit. Stanford University. September 29, 2019.
  9. ^ Deierling, Kevin (2020-05-21). "What's a DPU?". The Official NVIDIA Blog. Retrieved 2020-10-03.
  10. ^ "The renaissance of silicon will create industry giants". TechCrunch. Retrieved 2019-08-16.
  11. ^ Deierling, Kevin (2018-08-30). "Defining SmartNIC: What is a SmartNIC and How to Choose the Best One". Mellanox Technologies Blog. Retrieved 2021-05-29.
  12. ^ Bhageshpur, Kiran (2016-10-06). "The Emergence Of Data-Centric Computing". The Next Platform. Retrieved 2021-05-29.
  13. ^ servethehome (2021-05-29). "DPU vs SmartNIC and the STH NIC Continuum Framework". ServeTheHome. Retrieved 2021-06-06.
  14. ^ "NVIDIA BlueField Data Processing Units". NVIDIA. Retrieved 2021-05-29.
  15. ^ "Data Processing Units (DPUs) | Empowering Carrier, Enterprise and Cloud Data Services - Marvell". Retrieved 2021-05-29.
  16. ^ "DPU Platform – Fungible". Retrieved 2021-05-29.
  17. ^ "The Pensando Distributed Services Platform". Pensando. Retrieved 2021-05-29.
  18. ^ "At a Glance: The Broadcom Stingray PS1100R delivers breakthrough performance and efficiency". Retrieved 2021-06-06.
  19. ^ "Intel Unveils Infrastructure Processing Unit". Intel. Retrieved 2021-06-16.
  21. ^ "NetLOX loxilight". Retrieved 2022-01-03.