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 v2.1 with NVIDIA GPU-Based Benchmarks on Dell PowerEdge Servers
Introduction What is new in MLPerf Inference v2.1? Growth of MLPerf Inference as a benchmark Dell results Notable results Highlighting performance scores
Summary
System performance details PowerEdge server, GPU, and Software specifications Performance improvements Conclusion and Key Takeaways Acknowledgment References

Summary

Home > AI Solutions > Artificial Intelligence > White Papers > MLPerf™ Inference v2.1 with NVIDIA GPU-Based Benchmarks on Dell PowerEdge Servers > Summary

Summary

  • The PowerEdge R750xa server can claim the following positions, compared against per GPU performance with the same PCIe form factor accelerator: 

    • #1 position with ResNet Server 
    • #1 position with ResNet Offline
    • #1 position with RetinaNet Server 
    • #1 position with RNN-T Server 
    • #1 position with RNN-T Offline 
    • #2 position with BERT 99 Server 
    • #2 position with BERT 99 Server 
    • #2 position with DLRM 99, 99.9 Server 
    • #2 position with DLRM 99, 99.9 Server