NVIDIA H100 PCIe — Spécifications

Spécifications Benchmarks Synonymes

Spécifications

Données techniques

GPU

Architecture
Hopper
Execution Units
7296
Puce GPU
GH100
Unités de sortie de rendu
24
Unités de texture
456

Mémoire

Memory Bandwidth
1,280 GB/s
Memory Bus
5120 bit
Memory Clock
1000 MHz
Memory Data Rate
2 Gbps
Taille de la mémoire
80 GB
Type de mémoire
HBM2e

Fréquence d'horloge

Fréquence de base
1065 MHz
Fréquence maximale
1650 MHz

Consommation d'énergie

System Power Supply
750 W (PSU recommendation)
TDP
350 W

Connectivité

Max. Affichages
1
PCIe Interface
PCIe 5.0 x16
Power Connectors
8-pin EPS

Jeu de fonctions

CUDA
9.0
DirectX
Non
OpenCL
3.0
OpenGL
Non
Shader Model
Non
Vulkan
Non

Données supplémentaires

Process Technology
4 nm
Date de sortie
Q2/2022

Theoretical Performance

FP16 (theoretical)
96.31 TFLOPS
FP32 (theoretical)
24.08 TFLOPS
FP64 (theoretical)
12.04 TFLOPS
Pixel Rate
39.60 GPixel/s
Texture Rate
752.4 GTexel/s

Positions dans tous les classements

Positions communes NVIDIA H100 PCIe GPU dans des benchmarks populaires, pour comparaison avec d'autres modèles.

No data

Benchmarks

Tests de performance GPU

No benchmark results are available yet. This model is listed with specifications only.

These are saved results from the earlier catalog. Measurement dates and test configurations were not recorded. Models with no comparable results are omitted.

Recent models: test results with identified primary sources — Game frame rates

Comparable benchmark results are required to suggest performance alternatives.

Base Clock is the base GPU frequency stated by the manufacturer for this model.

Boost Clock describes automatic frequency increases. Actual clock speed varies with workload, temperature and power limits; it is not a guarantee of manual overclocking.

Évaluez la carte vidéo
NVIDIA H100 PCIe