Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
MLPerf™ Inference v1.0 – NVIDIA GPU-Based Benchmarks on Dell EMC PowerEdge R750xa Servers
Executive summary MLPerf™ Inference v1.0 test bed configuration Measuring system performance using MLPerfTM Inference v1.0 MLPerf Inference v1.0 performance results for the PowerEdge R750xa server Comparing PowerEdge R740 and PowerEdge R750xa servers Conclusion
Conclusion
References

Conclusion

Conclusion

  • The PowerEdge R750xa server delivers optimal performance on different deep learning inference tasks such as image classification, object detection, medical image segmentation, speech to text, language processing, and recommendation. Intel CPUs and NVIDIA GPUs enable effective delivery of high throughputs on different deployment scenarios. Higher cores, higher bandwidth, and more PCIe lanes offered by Intel Xeon scalable processors enable expedited performance, even while running with an accelerator such as the NVIDIA A100 GPU, in which the GPU processes all the inference. The effective combination of the Ice Lake CPUs, NVIDIA A100 GPUs, and the PowerEdge R750xa server is an excellent choice for running inference workloads.