NVIDIA H100 PCIe vs Intel Arc A350M. Specifications

Comparison of basic technical data of graphics cards NVIDIA H100 PCIe and Intel Arc A350M, chip, information processing units.

• Architecture
  Hopper Xe HPG / Generation 12.7
• Execution Units
  7296 768
• GPU Chip
  GH100 DG2-128 / Alchemist
• Render Output Units
  24 24
• Texture Units
  456 48
• L1 Cache
  - No
• L2 Cache
  - 4 MB
• RT Cores
  - 6

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 112 GB/s
• Memory Bus
  5120 bit 64 bit
• Memory Clock
  1000 MHz 1750 MHz
• Memory Data Rate
  2 Gbps 14 Gbps
• Memory Size
  80 GB 4 GB
• Memory Type
  HBM2e GDDR6

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

• Base Clock
  1065 MHz 300 MHz
• Boost Clock
  1650 MHz 1150 MHz

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

• System Power Supply
  750 W (PSU recommendation) -
• TDP
  350 W 25 W

Connectivity and connections.

• Max. Displays
  1 1
• PCIe Interface
  PCIe 5.0 x16 PCIe 4.0 x8
• Power Connectors
  8-pin EPS No

Technical data that is used to its full potential in computer games.

• CUDA
  9.0 -
• DirectX
  No 12.2
• OpenCL
  3.0 3.0
• OpenGL
  No 4.6
• Shader Model
  No 6.6
• Vulkan
  No 1.3
• Max. resolution
  - 2560 × 1440

The difference in size, weight and slot of the compared devices

• Slot Size
  - IGP

Comparison of interfaces and release dates for GPU Intel Arc A350M and NVIDIA H100 PCIe.

• Process Technology
  4 nm 6 nm
• Release date
  Q2/2022 Q2/2022

• FP16 (theoretical)
  96.31 TFLOPS 3.533 TFLOPS
• FP32 (theoretical)
  24.08 TFLOPS 1.766 TFLOPS
• FP64 (theoretical)
  12.04 TFLOPS 0.4416 TFLOPS
• Pixel Rate
  39.60 GPixel/s 27.60 GPixel/s
• Texture Rate
  752.4 GTexel/s 55.20 GTexel/s