AMD Radeon Pro W7900 vs NVIDIA H100 PCIe. Specifications, performance, tests

Comparison of basic technical data of graphics cards AMD Radeon Pro W7900 and NVIDIA H100 PCIe, chip, information processing units.

• GPU Chip
  Navi 31 (RDNA 3.0) GH100
• Render Output Units
  192 24
• Texture Units
  384 456

Comparison of the amount of memory on board graphics cards. The more the better.

• Memory Size
  48 GB 80 GB
• Memory Type
  GDDR6 HBM2e
• Memory Clock
  2.250 GHz 1 GHz
• Memory Speed
  18 Gbps 2 Gbps
• Memory Interface
  384 bit 5120 bit

Let's compare the memory frequency of graphics cards AMD Radeon Pro W7900 and NVIDIA H100 PCIe. The higher the better.

• Base Clock
  1.855 GHz 1.065 GHz
• Boost Clock
  2.495 GHz 1.65 GHz

Connectors, the number of thermal watts emitted in normal mode and at overclocking.

• TDP
  295 W 350 W

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

• DirectX
  12_2 (Ultimate) No

Comparison of interfaces and release dates for GPU NVIDIA H100 PCIe and AMD Radeon Pro W7900.

• GPU Interface
  PCIe 4.0 x 16 PCIe 5.0 x16
• Release date
  Q2/2023 Q2/2022
• Structure size
  5 nm 4 nm

• Pixel Rate
  479.0 GPixel/s 39.60 GPixel/s
• Texture Rate
  958.1 GTexel/s 752.4 GTexel/s
• FP16 (half)
  122.6 TFLOPS (2:1) 96.31 TFLOPS
• FP32 (float)
  61.32 TFLOPS 24.08 TFLOPS
• FP64 (double)
  1.916 TFLOPS (1:32) 12.04 TFLOPS