NVIDIA H100 SXM5 — Specifiche

Specifiche Benchmark (test) Sinonimi

Specifiche

Dati tecnici

GPU

Architettura
Hopper
Execution Units
8448
Chip GPU
GH100
L1 Cache
192 KB
L2 Cache
50 MB
Unità di uscita del rendering
24
Unità di texture
528

Memoria

Memory Bandwidth
1,920 GB/s
Memory Bus
5120 bit
Memory Clock
1500 MHz
Memory Data Rate
3 Gbps
Dimensione della memoria
80 GB
Tipo di memoria
HBM3

Frequenza di clock

Frequenza di base
1065 MHz
Frequenza massima
1780 MHz

Consumo di energia

Board Number
PG520
System Power Supply
1100 W (PSU recommendation)
TDP
700 W

Connettività

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

Featureset

CUDA
9.0
DirectX
No
Risoluzione massima
3840x2160@60Hz
OpenCL
3.0
OpenGL
No
Shader Model
No
Vulkan
No

Dati aggiuntivi

Process Technology
4 nm
Data di rilascio
Q2/2022

Theoretical Performance

FP16 (theoretical)
120.3 TFLOPS
FP32 (theoretical)
30.07 TFLOPS
FP64 (theoretical)
15.04 TFLOPS
Pixel Rate
42.72 GPixel/s
Texture Rate
939.8 GTexel/s

Posizioni in tutte le classifiche

Posizioni comuni NVIDIA H100 SXM5 GPU in benchmark popolari, per un confronto con altri modelli.

No data

Benchmark (test)

Test di 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.

Valuta la scheda video
NVIDIA H100 SXM5