Bow IPU Processors

1 min read Original article ↗

A Major Leap Forward

The IPU is the first processor in the world to use Wafer-on-Wafer (WoW) 3D stacking technology, taking the proven benefits of the IPU to the next level.

Featuring groundbreaking advances in compute architecture and silicon implementation, communication and memory, each Bow IPU delivers up to 350 teraFLOPS of AI compute, an impressive 40% leap forward in performance and up to 16% more power efficiency compared to the previous generation IPU.

PCIe

  • PCIe Gen4 x16
  • 64GB/s bidrectional bandwidth to host

Wafer-On-Wafer

  • Advanced silicon 3D stacking technology
  • Closely coupled power delivery die
  • Higher operating frequency and enhanced overall performance

Deep Trench Capacitors

  • Efficient power delivery
  • Enables increase in operational performance

IPU-Exchange™

  • 11TB/s all to all IPU-Exchange
  • Non-blocking, any communication pattern

IPU-Tiles™

  • 1472 independent IPU-Tiles each with IPU-Core™ and In-Processor-Memory™

In-Processor-Memory™

  • 900MB In-Processor-Memory per IPU
  • 65.4TB/s memory bandwidth per IPU

IPU-Core™

  • 1472 independent IPU-Cores
  • 8832 independent program threads executing in parallel

IPU-Links™

  • 10x IPU-Links
  • 320GB/s chip to chip bandwidth

marker

Click the markers on the diagram for more details about the chip

Swipe to see more