NVIDIA DGX™ A100 is the universal system for all AI workloads, offering unprecedented compute density, performance, and flexibility in the world’s first 5 petaFLOPS AI system.
NVIDIA DGX A100 features the world’s most advanced accelerator, the NVIDIA A100 Tensor Core GPU, enabling enterprises to consolidate training, inference, and analytics into a unified, easy-to-deploy AI infrastructure that includes direct access to NVIDIA AI experts.
PERFORMANCE
Game Changing Performance
TRAINING
DLRM Training
Up to 3X Higher Throughput for AI Training on Largest Models
DLRM on HugeCTR framework, precision = FP16 | 1x DGX A100 640GB batch size = 48 | 2x DGX A100 320GB batch size = 32 | 1x DGX-2 (16x V100 32GB) batch size = 32. Speedups Normalized to Number of GPUs.
INFERENCE
RNN-T Inference: Single Stream
Up to 1.25X Higher Throughput
for AI Inference
MLPerf 0.7 RNN-T measured with (1/7) MIG slices. Framework: TensorRT 7.2, dataset = LibriSpeech, precision = FP16.
DATA ANALYTICS
Big Data Analytics Benchmark
Up to 83X Higher Throughput than CPU, 2X Higher Throughput than DGX A100 320GB
Big data analytics benchmark | 30 analytical retail queries, ETL, ML, NLP on 10TB dataset | CPU: 19x Intel Xeon Gold 6252 2.10 GHz, Hadoop | 16x DGX-1 (8x V100 32GB each), RAPIDS/Dask | 12x DGX A100 320GB and 6x DGX A100 640GB, RAPIDS/Dask/BlazingSQL. Speedups Normalized to Number of GPUs
实例
Top Use Cases Deployed on DGX Systems
Building Leading Edge AI Across Industries
主要特点
Essential Building Block of the AI Data Center
NVIDIA DGX A100 is the universal system for all AI infrastructure, from analytics to training to inference. It sets a new bar for compute density, packing 5 petaFLOPS of AI performance into a 6U form factor, replacing legacy infrastructure silos with one platform for every AI workload.
NVIDIA DGXperts are a global team of 16,000+ AI-fluent professionals who have built a wealth of experience over the last decade to help you maximize the value of your DGX investment.
NVIDIA DGX A100 is the world’s first AI system built on the NVIDIA A100 Tensor Core GPU. Integrating eight A100 GPUs with up to 640GB of GPU memory, the system provides unprecedented acceleration and is fully optimized for NVIDIA CUDA-X™ software and the end-to-end NVIDIA data center solution stack.
NVIDIA DGX A100 features Mellanox ConnectX-6 VPI HDR InfiniBand/Ethernet network adapters with 500 gigabytes per second (GB/s) of peak bi-directional bandwidth. This is one of the many features that make DGX A100 the foundational building block for large AI clusters such as NVIDIA DGX SuperPOD™, the enterprise blueprint for scalable AI infrastructure.
Resources
DGX A100 System Architecture
