NVIDIA A100 TENSOR CORE GPU 80GB PCIe

NVIDIA A100 TENSOR CORE GPU 80GB PCIe

From
Special Price $26,499.00 Regular Price $35,000.00
compare favorite favorite
  • Home
  • NVIDIA A100 TENSOR CORE GPU 80GB PCIe
NVIDIA A100 TENSOR CORE GPU 80GB PCIe
NVIDIA A100 TENSOR CORE GPU 80GB PCIe
Sale
See all specs
Have questions about this purchase?
Chat with Uvation Assistant
Rewards Banner

NVIDIA A100 TENSOR CORE GPU 80GB PCIe

MFG.PART: 900-21001-0020-100
Item Condition : Brand New

Earn 26,499 points when you buy me!

Hurry! Other 3 people are watching this product
SKU
NVIDIA-A100-1
Add a Review
Be the first to review this product
Special Price $26,499.00 Regular Price $35,000.00
In stock
Free shipping
could be yours in 1 - 5 days
favorite
days hrs mins secs
Hurry! Other 3 people are watching this product

The NVIDIA A100 Tensor Core GPU delivers unprecedented acceleration at every scale for AI, data analytics, and HPC to tackle the world’s toughest computing challenges. As the engine of the NVIDIA data center platform, A100 can efficiently scale up to thousands of GPUs or, using new Multi-Instance GPU (MIG) technology, can be partitioned into seven isolated GPU instances to accelerate workloads of all sizes. A100’s thirdgeneration Tensor Core technology now accelerates more levels of precision for diverse workloads, speeding time to insight as well as time to market.

Form FactorPCIe Dual-slot air-cooled or single-slot liquid-cooled
Details

An Order-of-Magnitude Leap for Accelerated Computing

The Most Powerful End-to-End AI and HPC Data Center Platform

A100 is part of the complete NVIDIA data center solution that incorporates building blocks across hardware, networking, software, libraries, and optimized AI models and applications from NGC™. Representing the most powerful end-to-end AI and HPC platform for data centers, it allows researchers to deliver real-world results and deploy solutions into production at scale.

 
 

Deep Learning Training

 
 

Up to 3X Higher AI Training on Largest Models

DLRM Training

 
Up to 3X Higher AI Training on Largest Models
 
 

DLRM on HugeCTR framework, precision = FP16 | ​NVIDIA A100 80GB batch size = 48 | NVIDIA A100 40GB batch size = 32 | NVIDIA V100 32GB batch size = 32.

 
 
 

​AI models are exploding in complexity as they take on next-level challenges such as conversational AI. Training them requires massive compute power and scalability.

NVIDIA A100 Tensor Cores with Tensor Float (TF32) provide up to 20X higher performance over the NVIDIA Volta with zero code changes and an additional 2X boost with automatic mixed precision and FP16. When combined with NVIDIA® NVLink®, NVIDIA NVSwitch™, PCI Gen4, NVIDIA® InfiniBand®, and the NVIDIA Magnum IO™ SDK, it’s possible to scale to thousands of A100 GPUs.

A training workload like BERT can be solved at scale in under a minute by 2,048 A100 GPUs, a world record for time to solution.

For the largest models with massive data tables like deep learning recommendation models (DLRM), A100 80GB reaches up to 1.3 TB of unified memory per node and delivers up to a 3X throughput increase over A100 40GB.

NVIDIA’s leadership in MLPerf, setting multiple performance records in the industry-wide benchmark for AI training.

Learn More About A100 for Training
 

Deep Learning Inference

A100 introduces groundbreaking features to optimize inference workloads. It accelerates a full range of precision, from FP32 to INT4. Multi-Instance GPU (MIG) technology lets multiple networks operate simultaneously on a single A100 for optimal utilization of compute resources. And structural sparsity support delivers up to 2X more performance on top of A100’s other inference performance gains.

On state-of-the-art conversational AI models like BERT, A100 accelerates inference throughput up to 249X over CPUs.

On the most complex models that are batch-size constrained like RNN-T for automatic speech recognition, A100 80GB’s increased memory capacity doubles the size of each MIG and delivers up to 1.25X higher throughput over A100 40GB.

NVIDIA’s market-leading performance was demonstrated in MLPerf Inference. A100 brings 20X more performance to further extend that leadership.

Learn More About A100 for Inference
 

Up to 249X Higher AI Inference Performance
Over CPUs

BERT-LARGE Inference

 
Up to 249X Higher AI Inference Performance Over CPUs
 

BERT-Large Inference | CPU only: Xeon Gold 6240 @ 2.60 GHz, precision = FP32, batch size = 128 | V100: NVIDIA TensorRT™ (TRT) 7.2, precision = INT8, batch size = 256 | A100 40GB and 80GB, batch size = 256, precision = INT8 with sparsity.​

 
 
 

Up to 1.25X Higher AI Inference Performance
Over A100 40GB

RNN-T Inference: Single Stream

 
Up to 1.25X Higher AI Inference Performance Over A100 40GB
 
 

MLPerf 0.7 RNN-T measured with (1/7) MIG slices. Framework: TensorRT 7.2, dataset = LibriSpeech, precision = FP16.

 
 
 

High-Performance Computing

To unlock next-generation discoveries, scientists look to simulations to better understand the world around us.

NVIDIA A100 introduces double precision Tensor Cores  to deliver the biggest leap in HPC performance since the introduction of GPUs. Combined with 80GB of the fastest GPU memory, researchers can reduce a 10-hour, double-precision simulation to under four hours on A100. HPC applications can also leverage TF32 to achieve up to 11X higher throughput for single-precision, dense matrix-multiply operations.

For the HPC applications with the largest datasets, A100 80GB’s additional memory delivers up to a 2X throughput increase with Quantum Espresso, a materials simulation. This massive memory and unprecedented memory bandwidth makes the A100 80GB the ideal platform for next-generation workloads.

Learn More About A100 for Hpc
 

11X More HPC Performance in Four Years

Top HPC Apps​

 
11X More HPC Performance in Four Years
 
 

Geometric mean of application speedups vs. P100: Benchmark application: Amber [PME-Cellulose_NVE], Chroma [szscl21_24_128], GROMACS  [ADH Dodec], MILC [Apex Medium], NAMD [stmv_nve_cuda], PyTorch (BERT-Large Fine Tuner], Quantum Espresso [AUSURF112-jR]; Random Forest FP32 [make_blobs (160000 x 64 : 10)], TensorFlow [ResNet-50], VASP 6 [Si Huge] | GPU node with dual-socket CPUs with 4x NVIDIA P100, V100, or A100 GPUs.

 
 
 

Up to 1.8X Higher Performance for HPC Applications

Quantum Espresso​

 
Up to 1.8X Higher Performance for HPC Applications
 

Quantum Espresso measured using CNT10POR8 dataset, precision = FP64.

 
 

High-Performance Data Analytics

 
 

2X Faster than A100 40GB on Big Data Analytics Benchmark

 
2X Faster than A100 40GB on Big Data Analytics Benchmark
 

Big data analytics benchmark |  30 analytical retail queries, ETL, ML, NLP on 10TB dataset | V100 32GB, RAPIDS/Dask | A100 40GB and A100 80GB, RAPIDS/Dask/BlazingSQL​

 
 
 

Data scientists need to be able to analyze, visualize, and turn massive datasets into insights. But scale-out solutions are often bogged down by datasets scattered across multiple servers.

Accelerated servers with A100 provide the needed compute power—along with massive memory, over 2 TB/sec of memory bandwidth, and scalability with NVIDIA® NVLink® and NVSwitch™, —to tackle these workloads. Combined with InfiniBand, NVIDIA Magnum IO™ and the RAPIDS™ suite of open-source libraries, including the RAPIDS Accelerator for Apache Spark for GPU-accelerated data analytics, the NVIDIA data center platform accelerates these huge workloads at unprecedented levels of performance and efficiency.

On a big data analytics benchmark, A100 80GB delivered insights with a 2X increase over A100 40GB, making it ideally suited for emerging workloads with exploding dataset sizes.

Learn More About Data Analytics
 
 

Enterprise-Ready Utilization

 
 

7X Higher Inference Throughput with Multi-Instance GPU (MIG)

BERT Large Inference

 
7X Higher Inference Throughput with Multi-Instance GPU (MIG)
 
 

BERT Large Inference | NVIDIA TensorRT™ (TRT) 7.1 | NVIDIA T4 Tensor Core GPU: TRT 7.1, precision = INT8, batch size = 256 | V100: TRT 7.1, precision = FP16, batch size = 256 | A100 with 1 or 7 MIG instances of 1g.5gb: batch size = 94, precision = INT8 with sparsity.​

 
 
 

Enterprise-Ready Utilization

A100 with MIG maximizes the utilization of GPU-accelerated infrastructure. With MIG, an A100 GPU can be partitioned into as many as seven independent instances, giving multiple users access to GPU acceleration. With A100 40GB, each MIG instance can be allocated up to 5GB, and with A100 80GB’s increased memory capacity, that size is doubled to 10GB.

MIG works with Kubernetes, containers, and hypervisor-based server virtualization. MIG lets infrastructure managers offer a right-sized GPU with guaranteed quality of service (QoS) for every job, extending the reach of accelerated computing resources to every user.

 
 
Tech Specs

Product Specifications

 

Form Factor A100 PCIe 
FP64 9.7 teraFLOPS 
FP64 Tensor Core 19.5 teraFLOPS 
FP32 19.5 teraFLOPS 
TF32 Tensor Core 156 TFLOPS | 312 TFLOPS* 
BFLOAT16 Tensor Core 312 TFLOPS | 624 TFLOPS* 
FP16 Tensor Core 312 TFLOPS | 624 TFLOPS* 
FP8 Tensor Core 3,026 teraFLOPS2 
INT8 Tensor Core 624 TOPS | 1248 TOPS* 
GPU memory 80GB HBM2e 
GPU memory bandwidth 1,935 GB/s 
Decoders 7 NVDEC 7 JPEG 
Max thermal design power (TDP) 300W 
Multi-Instance GPUs Up to 7 MIGs @ 10GB 
Form factor PCIe dual-slot air-cooled or single-slot liquid-cooled 
Interconnect NVIDIA® NVLink® Bridge for 2 GPUs: 600 GB/s ** PCIe Gen4: 64 GB/s 
Server options Partner and NVIDIA-Certified Systems with 1–8 GPUs 
NVIDIA AI Enterprise Included 
Models
Reviews

Write Your Own Review

You're reviewing: NVIDIA A100 TENSOR CORE GPU 80GB PCIe


Works Best Together With

^Top