DPUs to Innovate and Accelerate Your HPL Benchmarks

X-ScaleHPL-DPU

Our version of the High-Performance Linpack Code v2.3 is DPU-optimized and enhanced to offload communication to the NVIDIA BlueField DPU.

Request A Demo
Flexible Operations

Enabled to run in two optimized modes: Host and DPU with the MVAPICH2-DPU library.

Rigorous Testing

Our team evaluated HPL performance on the HPC-Al cluster on 16 and 31 Xeon nodes with the MVAPICH2-DPU MPI library.

Optimal Performance

Our DPU-offloaded mode accelerates HPL benchmark up to 18% faster while used in conjunction with the latest MVAPICH2-DPU 2023.05 version. See illustration below.

Performance Case Studies

Utilizing DPUs to Improve HPL Benchmarks

Questions on X-ScaleHPL-DPU?

Our team of experts are available to answer your questions and show you an X-ScaleHPL-DPU demo to help you accelerate HPL benchmarks.

Connect With An Expert