Unprecedented Performance, Scalability, and Security for Every Data Center
The NVIDIA® H100 Tensor Core GPU enables an order-of-magnitude leap for large-scale AI and HPC with unprecedented performance, scalability, and security for every data center and includes the NVIDIA AI Enterprise software suite to streamline AI development and deployment. H100 accelerates exascale scale workloads with a dedicated Transformer Engine for trillion parameter language models. For small jobs, H100 can be partitioned down to right-sized Multi-Instance GPU (MIG) partitions. With Hopper Confidential Computing, this scalable compute power can secure sensitive applications on shared data center infrastructure. The inclusion of NVIDIA AI Enterprise with H100 PCIe purchases reduces time to development and simplifies deployment of AI workloads, and makes H100 the most powerful end-to-end AI and HPC data center platform.
The NVIDIA Hopper architecture delivers unprecedented performance, scalability and security to every data center. Hopper builds upon prior generations from new compute core capabilities, such as the Transformer Engine, to faster networking to power the data center with an order of magnitude speedup over the prior generation. NVIDIA NVLink supports ultra-high bandwidth and extremely low latency between two H100 boards, and supports memory pooling and performance scaling (application support required). Second-generation MIG securely partitions the GPU into isolated right-size instances to maximize QoS (quality of service) for 7x more secured tenants. The inclusion of NVIDIA AI Enterprise (exclusive to the H100 PCIe), a software suite that optimizes the development and deployment of accelerated AI workflows, maximizes performance through these new H100 architectural innovations. These technology breakthroughs fuel the H100 Tensor Core GPU - the world’s most
advanced GPU ever built.
vGPU SOFTWARE SUPPORT
NVIDIA Virtual Compute Server (vCS)
| Product | NVIDIA H100 Tensor Core GPU Accelerator |
| FP64 | 26 TFLOPS |
| FP64 Tensor Core | 51 TFLOPS | Sparsity |
| FP32 | 51 TFLOPS |
| TF32 Tensor Core | 51 TFLOPS | Sparsity |
| BFLOAT16 Tensor Core | 1513 TFLOPS | Sparsity |
| FP16 Tensor Core | 1513 TFLOPS | Sparsity |
| FP8 Tensor Core | 3026 TFLOPS | Sparsity |
| GPU Memory | 80GB HBM3 |
| Memory Bandwidth | 2.0 TB/sec |
Data Center Class ReliabilityDesigned for 24 x 7 data center operations and driven by power-efficient hardware and components selected for optimum performance, durability, and longevity. Every NVIDIA H100 board is designed, built and tested by NVIDIA to the most rigorous quality and performance standards, ensuring that leading OEMs and systems integrators can meet or exceed the most demanding real-world conditions. |
NVIDIA Hopper ArchitectureThe H100 PCIe Gen5 configuration provides all the capabilities of H100 SXM5 GPUs in just 350 Watts of Thermal Design Power (TDP). This configuration can optionally use the NVLink bridge for connecting up to two GPUs at 600 GB/s of bandwidth, nearly five times PCIe Gen5. |
H100 Compute Performance SummaryOverall, H100 provides approximately 6x compute performance improvement over A100 when factoring in all the new compute technology advances in H100. To summarize the improvements in H100, let's start with its 132 SMs providing a 22% SM count increase over A100’s 108 SMs. Each of the H100 SMs is 2x faster thanks to its new 4th Generation Tensor Core. |
| CUDA® Cores | 18176 |
|---|---|
| Architecture | NVIDIA Hopper |
| GPU rozwiązania i zastosowanie | NVIDIA Virtual Applications (vApps), Application Performance, Visualization and AI, NVIDIA AI Enterprise for VMWare |
| wsparcie VR | brak |
| chłodzenie grafiki | pasywne serwerowe |
| rodzaj pamięci | HBM3 |
| pamieć karty | 80GB |
| Mocowanie i profil kart | PCIe FHHL/ HHHL |
| Gwarancja | 3 lata |
Konfiguracja
