NVIDIA and partners today announced a new way for interested users to partake in the AI-training capabilities of their Ampere graphics architecture in the form of the A100 PCIe. Diving a little deeper, and as the name implies, this solution differs from the SXM form-factor in that it can be deployed through systems' existing PCIe slots. The change in interface comes with a reduction in TDP from 400 W down to 250 W in the PCIe version - and equivalent reduced performance.

NVIDIA says peak throughput is the same across the SXM and PCIe version of their A100 accelerator. The difference comes in sustained workloads, where NVIDIA quotes the A100 as delivering 10% less performance compared to its SXM brethren. The A100 PCIe comes with the same 2.4 Gbps, 40 GB HBM2 memory footprint as the SXM version, and all other chip resources are the same. We're thus looking at the same 862 mm² silicon chip and 6,192 CUDA cores across both models. The difference is that the PCIe accelerator can more easily be integrated in existing server infrastructure.