Category Archives: Benchmarking

DGX A100 review: Throughput and Hardware Summary

When NVIDIA launched the Ampere GPU architecture, they also launched their new flagship system for HPC and deep learning – the DGX 100. This system offers exceptional performance, but also new capabilities. We’ve seen immediate interest and have already shipped … Continue reading

What Can You Do with a $15k NVIDIA Data Science Workstation? – Change Healthcare Data Science

NVIDIA’s Data Science Workstation Platform is designed to bring the power of accelerated computing to a broad set of data science workflows. Recently, we found out what happens when you lend a talented data scientist (with a serious appetite for … Continue reading

Multi-GPU Scaling of MLPerf Benchmarks on NVIDIA DGX-1

In this post, we discuss how the training of deep neural networks scales on DGX-1. Considering 6 models across 4 out of 5 popular domains covered in the MLPerf v0.5 benchmarking suite, we discuss the time to state-of-the-art accuracy as … Continue reading

NVIDIA “Turing” Tesla T4 HPC Performance Benchmarks

Performance benchmarks are an insightful way to compare new products on the market. With so many GPUs available, it can be difficult to assess which are suitable to your needs. Various benchmarks provide information to compare performance on individual algorithms … Continue reading

NVIDIA Datacenter Manager (DCGM) for More Effective GPU Management

Managing an HPC server can be a tricky job, and managing multiple servers even more complex. Adding GPUs adds even more power yet new levels of granularity. Luckily, there’s a powerful, and effective tool available for managing multiple servers or … Continue reading

One-shot Learning Methods Applied to Drug Discovery with DeepChem

Experimental data sets for drug discovery are sometimes limited in size, due to the difficulty of gathering this type of data. Drug discovery data sets are expensive to obtain, and some are the result of clinical trials, which might not … Continue reading

NVIDIA Tesla P40 GPU Accelerator (Pascal GP102) Up Close

As NVIDIA’s GPUs become increasingly vital to the fields of AI and intelligent machines, NVIDIA has produced GPU models specifically targeted to these applications. The new Tesla P40 GPU is NVIDIA’s premiere product for deep learning deployments. It is specifically … Continue reading

Deep Learning Benchmarks of NVIDIA Tesla P100 PCIe, Tesla K80, and Tesla M40 GPUs

Sources of CPU benchmarks, used for estimating performance on similar workloads, have been available throughout the course of CPU development. For example, the Standard Performance Evaluation Corporation has compiled a large set of applications benchmarks, running on a variety of … Continue reading

Comparing NVLink vs PCI-E with NVIDIA Tesla P100 GPUs on OpenPOWER Servers

The new NVIDIA Tesla P100 GPUs are available with both PCI-Express and NVLink connectivity. How do these two types of connectivity compare? This post provides a rundown of NVLink vs PCI-E and explores the benefits of NVIDIA’s new NVLink technology.

NVIDIA Tesla P100 NVLink 16GB GPU Accelerator (Pascal GP100 SXM2) Up Close

The NVIDIA Tesla P100 NVLink GPUs are a big advancement. For the first time, the GPU is stepping outside the traditional “add in card” design. No longer tied to the fixed specifications of PCI-Express cards, NVIDIA’s engineers have designed a … Continue reading