NVIDIA H100 PCIe contre NVIDIA GeForce RTX 3090 Ti. Spécifications, performances, tests

Comparaison des données techniques de base des cartes graphiques NVIDIA H100 PCIe et NVIDIA GeForce RTX 3090 Ti, puce, unités de traitement de l'information.

• Architecture
  Hopper Ampere
• Execution Units
  7296 -
• Puce GPU
  GH100 GA102-350-A1
• Unités de sortie de rendu
  24 112
• Unités de texture
  456 336
• Sur la base de
  - GA102
• CUDA Cores
  - 10752
• L1 Cache
  - 128 KB
• L2 Cache
  - 6 MB
• Shader
  - 10752

Video memory capacity, type, bus width and bandwidth describe different properties. These values alone do not determine graphics performance.

• Memory Bandwidth
  1,280 GB/s 1,008 GB/s
• Memory Bus
  5120 bit 384 bit
• Memory Clock
  1000 MHz -
• Memory Data Rate
  2 Gbps -
• Taille de la mémoire
  80 GB 24 GB
• Type de mémoire
  HBM2e GDDR6X
• Memory Speed (legacy frequency label)
  - 1300 MHz

Published GPU clock frequencies describe different operating modes. Clock speed alone does not determine graphics performance.

• Fréquence de base
  1065 MHz 1560 MHz
• Fréquence maximale
  1650 MHz 1860 MHz
• Overclocking
  - Non

Graphics card power limits and recommended system power supply describe different specifications.

• System Power Supply
  750 W (PSU recommendation) 850 W (System power requirement)
• TDP
  350 W 450 W
• Graphics Card Power
  - 450 W
• Maximum GPU Temperature
  - 92 °C

Connectivité et connexions.

• Max. Affichages
  1 4
• PCIe Interface
  PCIe 5.0 x16 PCIe 4.0 x16
• Power Connectors
  8-pin EPS 3x PCIe 8-pin cables (adapter in box) OR 450W or greater PCIe Gen 5 cable
• DisplayPort Ports
  - 3 × DisplayPort 1.4a
• HDCP Version
  - 2.3
• Ports HDMI
  - 1 × HDMI 2.1
• Other Display Outputs (unparsed)
  - HDMI

Des données techniques utilisées à leur plein potentiel dans les jeux informatiques.

• CUDA
  9.0 -
• DirectX
  Non 12_2
• OpenCL
  3.0 3.0
• OpenGL
  Non 4.6
• Shader Model
  Non 6.6
• Vulkan
  Non 1.3
• Résolution maximale
  - 7680 × 4320

Comparaison des interfaces et des dates de sortie des GPU NVIDIA GeForce RTX 3090 Ti et NVIDIA H100 PCIe.

• Process Technology
  4 nm 8 nm
• Date de sortie
  Q2/2022 -
• Manufacturer specification scope
  - NVIDIA Founders Edition/reference design. Clock specifications apply to gaming use. AIB shipping specifications and complete-system power needs may differ.

• FP16 (theoretical)
  96.31 TFLOPS 40 TFLOPS
• FP32 (theoretical)
  24.08 TFLOPS 40 TFLOPS
• FP64 (theoretical)
  12.04 TFLOPS 0.625 TFLOPS
• Pixel Rate
  39.60 GPixel/s 208.3 GPixel/s
• Texture Rate
  752.4 GTexel/s 625.0 GTexel/s