AN ACCELERATOR FOR MEMORY INTENSIVE WORKLOADS

HALF THE COST; HALF THE POWER

High Performance

SEAL is proven to deliver a 5x throughput improvement on industry-standard recommendation model benchmarks under real-world traffic

Optimizes Your Infrastructure

SEAL unlocks the compute power of your infrastructure by offloading memory-bound operations such as embedding table lookups

Hardware Acceleration; Software Programmability

SEAL is the only OCP M.2 accelerator which can be programmed to hardware-accelerate multiple memory-intensive workloads

High Level of System Flexibility

SEAL supports recommendation model co-location and sharding with zero performance degradation, and is complementary to next-gen AI inference accelerators

Low Latency

Hard latency constraints are a necessary feature of data center deployments. SEAL delivers highly deterministic latency-bounded throughput

Widely Compatible

SEAL accelerates all number formats, bit depths and quantization schemes. Compatible with all major deep learning frameworks

OCP M.2 Form Factor

  • Available today in the Open Compute Project M.2 Accelerator Module form factor
  • Compatible with Glacier Point V2 carriers for Yosemite V2 and V2.5 chassis
  • Additional form factors under development

Learn more about SEAL, and what it can do for your business