NVIDIA pioneered accelerated computing to tackle challenges ordinary computers cannot. NVIDIA reinvented modern computer graphics in 1999, and made real-time programmable shading possible, giving artists an infinite palette for expression.

NVIDIA is powering the next era of high-performance computing, the universe of supercomputing has expanded rapidly to include AI, advanced data analytics, and cloud computing.

 

 

 

 

 

NVIDIA DGX A800

The Universal System for AI Infrastructure

NVIDIA DGX™ A800 is the universal system for all AI workloads—from analytics to training to inference. DGX A800 offers the ability to deliver a fine-grained allocation of computing power using the Multi-Instance GPU (MIG) capability in the NVIDIA A800 Tensor Core GPU. This enables administrators to assign resources that are right-sized for specific workloads.

NVIDIA H100

Unprecedented performance, scalability, and security for every data center

The NVIDIA® H100 Tensor Core GPU delivers unprecedented acceleration to power the world’s highest-performing elastic data centers for AI, data analytics, and high-performance computing (HPC) applications. NVIDIA H100 Tensor Core technology supports a broad range of math precisions, providing a single accelerator for every compute workload. The NVIDIA H100 PCIe supports double-precision (FP64), single-precision (FP32), half-precision (FP16), and integer (INT8) compute tasks. NVIDIA H100 PCIe cards use three NVIDIA® NVLink® bridges. They are the same as the bridges used with NVIDIA A100 PCIe cards. This allows two NVIDIA H100 PCIe cards to be connected to deliver 900 GB/s bidirectional bandwidth or 5x the bandwidth of PCIe Gen5, to maximize application performance for large workloads.

NVIDIA DGX H100

The World’s Proven Choice for Enterprise AI

NVIDIA DGX H100 is the fourth generation of the world’s premier purpose-built AI infrastructure, a fully optimized platform powered by the operating system of the accelerated data center, NVIDIA Base Command, a rich ecosystem of third-party support, and access to expert advice from NVIDIA professional services. NVIDIA DGX H100 features up to 9X more performance, 2X faster networking, and high-speed scalability for NVIDIA DGX SuperPOD. The next-generation architecture is supercharged for the largest workloads such as natural language processing and deep learning recommendation models. DGX H100 can be installed on-premises for direct management, colocated in NVIDIA DGX-Ready data centers, and accessed through NVIDIA-certified managed service providers. And with DGX-Ready Lifecycle Management, organizations get a predictable financial model to keep their deployment at the leading edge.

NVIDIA Key Products

NVIDIA DGX A800
NVIDIA DGX A800

The Universal System for Every AI Workload

 

 

 

 

 

NVIDIA H100
NVIDIA H100

NVIDIA H100 – Unprecedented performance, scalability, and security for every data center

 

 

 

 

 

NVIDIA DGX H100
NVIDIA DGX H100

NVIDIA DGX H100 – The World’s Proven Choice for Enterprise AI

 

 

 

 

 

GTC Sept 2022 Keynote with NVIDIA CEO Jensen Huang
GTC Sept 2022 Keynote with NVIDIA CEO Jensen Huang

 

 

 

 

 

 

System Specifications

 

 

 

 

 

 

NVIDIA DGX A800
NVIDIA DGX A800
GPUs
8x NVIDIA A800 80GB SXM Tensor Core GPUs
GPU Memory
640GB total
Performance
5 petaFLOPS AI 10 petaOPS INT8
NVIDIA NVSwitches
6
System Power Usage
6.5 kW max
CPU
Dual AMD Rome 7742
System Memory
2TB
Networking
Up to 8x Single- Port NVIDIA ConnectX-6 VPI; 200 Gb/s InfiniBand; Up to 2x Dual-Port NVIDIA ConnectX-6 VPI; 10/25/50/100/200 Gb/s Ethernet
Storage
OS: 2x 1.92TB M.2 NVME drives; Internal Storage: 30TB (8x 3.84 TB) U.2 NVMe drives
Software
Ubuntu / Red Hat Enterprise Linux / CentOS – Operating system; NVIDIA Base Command – Management; NVIDIA AI Enterprise – AI software
Support
Comes with 3-year business-standard hardware and software support
System Weight
271.5 lbs (123.16 kgs) max
Packaged System Weight
359.7 lbs (163.16 kgs) max
System Dimensions
Height: 10.4 in (264.0 mm); Width: 19.0 in (482.3 mm) max; Length: 35.3 in (897.1 mm) max
Operating Temperature Range
5ºC to 30ºC (41ºF to 86ºF)
NVIDIA H100
NVIDIA H100
H100 - SXM
H100 - PCle
FP64
34 TFLOPS
26 TFLOPS
FP64 Tensor Core
67 TFLOPS
51 TFLOPS
FP32
67 TFLOPS
51 TFLOPS
TF32 Tensor Core
989 TFLOPS*
756 TFLOPS*
BFLOAT16 Tensor Core
1,979 TFLOPS*
1,513 TFLOPS*
FP16 Tensor Core
1,979 TFLOPS*
1,513 TFLOPS*
FP8 Tensor Core
3,958 TFLOPS*
3,026 TFLOPS*
INT8 Tensor Core
3,958 TOPS*
3,026 TOPS*
GPU memory
80GB
80GB
GPU memory bandwidth
3.35TB/s
2TB/s
Decoders
7 NVDEC; 7 JPEG
Max thermal design power (TDP)
Up to 700W (configurable)
300-350W (configurable)
Multi-Instance GPUs
Up to 7 MIGS @ 10GB each
Form factor
SXM
PCIe dual-slot air-cooled
Interconnect
NVLink: 900GB/s PCIe Gen5: 128GB/s
NVLink: 600GB/s PCIe Gen5: 128GB/s
Server options
NVIDIA HGX™ H100 partner and NVIDIA- Certified Systems™ with 4 or 8 GPUs NVIDIA DGX™ H100 with 8 GPUs
Partner and NVIDIA- Certified Systems with 1–8 GPUs
NVIDIA AI Enterprise
Add-on
Included
* Shown with sparsity. Specifications 1/2 lower without sparsity. DATASHEET
NVIDIA DGX H100
NVIDIA DGX H100
GPUs
8x NVIDIA H100 Tensor Core GPUs
GPU Memory
640GB total
Performance
32 petaFLOPS FP8
NVIDIA® NVSwitch™
4x
System power usage
~10.2kW max
CPU
Dual x86
System memory
2TB
Networking
4x OSFP ports serving 8x single-port NVIDIA ConnectX-7 VPI 400 Gb/s InfiniBand or 200 Gb/s Ethernet 2x dual-port NVIDIA ConnectX-7 VPI 1x 400 Gb/s InfiniBand 1x 200 Gb/s Ethernet
Management network
10 Gb/s onboard NIC with RJ45 50 Gb/s Ethernet optional NIC Host baseboard management controller (BMC) with RJ45
Storage
OS: 2x 1.9TB NVMe M.2 Internal storage: 8x 3.84TB NVMe U.2
Software
NVIDIA AI Enterprise – Optimized AI software NVIDIA Base Command – Orchestration, scheduling, and cluster management Ubuntu / Red Hat Enterprise Linux / CentOS – Operating system
Support
Comes with 3-year business-standard hardware and software support
Operating temperature range
5–30°C (41–86°F)

NVIDIA Key Benefits

Scalable - Up to 7X higher performance of high-performance computing (HPC) applications

H100 triples the floating-point operations per second (FLOPS) of double-precision Tensor Cores, delivering 60 teraFLOPS of FP64 computing for HPC. AI-fused HPC applications can leverage H100’s TF32 precision to achieve one petaFLOP of throughput for single-precision, matrix-multiply operations, with zero code changes. Deploying H100 GPUs at data center scale delivers outstanding performance and brings the next generation of exascale high-performance computing (HPC) and trillion-parameter AI within the reach of all researchers. In addition, NVIDIA Magnum IO™ software delivers efficient scalability from small enterprises to massive, unified GPU clusters.

Unprecedented Performance – Up to 30X higher AI inference performance on the largest models

H100 further extends NVIDIA’s market-leading inference leadership with several advancements that accelerate inference by up to 30X and deliver the lowest latency. Fourth-generation Tensor Cores speed up all precisions, including FP64, TF32, FP32, FP16, and INT8, and the Transformer Engine utilizes FP8 and FP16 together to reduce memory usage and increase performance while still maintaining accuracy for large language models.

Secure – Built-in confidential computing

Today’s confidential computing solutions are CPU-based, which is too limited for compute-intensive workloads like AI and HPC. NVIDIA Confidential Computing is a built-in security feature of the NVIDIA Hopper™ architecture that makes H100 the world’s first accelerator with confidential computing capabilities. Users can protect the confidentiality and integrity of their data and applications in use while accessing the unsurpassed acceleration of H100 GPUs. It creates a hardware-based trusted execution environment (TEE) that secures and isolates the entire workload running on a single H100 GPU, multiple H100 GPUs within a node, or individual MIG instances.

Accelerated data analytics

Accelerated servers with H100 deliver the compute power—along with 3 terabytes per second (TB/s) of memory bandwidth per GPU and scalability with NVLink and NVSwitch—to tackle data analytics with high performance and scale to support massive datasets. Combined with NVIDIA Quantum-2 Infiniband, the Magnum IO software, GPU-accelerated Spark 3.0, and NVIDIA RAPIDS™, the NVIDIA data center platform is uniquely able to accelerate these huge workloads with unparalleled levels of performance and efficiency.

The most powerful and complete AI platform

NVIDIA DGX™ systems is designed to maximize AI throughput, providing enterprises with a highly refined, systemized, and scalable platform to help them achieve breakthroughs in natural language processing, recommender systems, data analytics, and much more.

AI Center of Excellence

DGX H100 is designed to be the centerpiece of an enterprise AI center of excellence. It’s a fully optimized hardware and software platform that includes full support for the new range of NVIDIA AI software solutions, a rich ecosystem of third-party support, and access to expert advice from NVIDIA professional services. DGX H100 offers proven reliability, with DGX systems being used by thousands of customers around the world spanning nearly every industry.

To learn more about NVIDIA, please CLICK HERE.

 

 

 

 

 

Please leave your message here, we will contact you shortly.