SOLUTION
ACF-S: The Industry's First 3.2 Tbps Multi-GPU SuperNIC
- 8x elastic bandwidth for GPUs, congestion-free
- Multi-port 800GbE, PCIe Gen5 and CXL 2.0+ interfaces
- Enfabrica's patented Accelerated Compute Fabric (ACF) architecture
- PCIe Gen 6 and CXL 3.0 coming soon
Before
Before
AI server networking component sprawl
- NICs, PCIe and Rail Switches connected as stovepipes
- Limited bandwidth and fault-tolerance
Congestion-prone data movement across GPUs
- Multiple device hops
- Poor load distribution, incast-prone
Ballooning AI Cluster TCO
- Stranded resources with lower effective bandwidth
- GPU link failure stalls entire job
A New Architecture
A New Architecture
Collective 8X NIC for collective GPUs
- 8X scale-out RDMA bandwidth
- Efficient traffic distribution across GPUs
Cut down GPU data movement latencies
- Up to 66% fewer device hops in large GPU clusters
- Congestion-free network-to-GPU traffic
Boost AI cluster operational efficiency
- Eliminates job failures due to link flaps
- Lowers CapEx by up to 29%, OpEx by as much as 55%
