NVIDIA A800 PCIe 80 GB vs NVIDIA H100 PCIe. Specifications, performance, tests

Comparison of basic technical data of graphics cards NVIDIA A800 PCIe 80 GB and NVIDIA H100 PCIe, chip, information processing units.

• GPU Chip
  GA100 GH100
• Execution units
  6912 7296
• Render Output Units
  160 24
• Texture Units
  432 456

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

• Memory Size
  80 GB 80 GB
• Memory Type
  HBM2e HBM2e
• Memory Clock
  1.512 GHz 1 GHz
• Memory Speed
  3 Gbps 2 Gbps
• Memory Bandwith
  1,935 GB/s 1,280 GB/s
• Memory Interface
  5120 bit 5120 bit

Let's compare the memory frequency of graphics cards NVIDIA A800 PCIe 80 GB and NVIDIA H100 PCIe. The higher the better.

• Base Clock
  1.065 GHz 1.065 GHz
• Boost Clock
  1.41 GHz 1.65 GHz

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

• TDP
  250 W 350 W
• Power Connectors
  8-pin EPS 8-pin EPS
• Suggested PSU
  600 W 750 W

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

• DirectX
  12.2 No
• OpenGL
  4.6 No
• OpenCL
  3.0 3.0
• CUDA
  8.0 9.0

Comparison of interfaces and release dates for GPU NVIDIA H100 PCIe and NVIDIA A800 PCIe 80 GB.

• Architecture
  Ampere Hopper
• GPU Interface
  PCIe 4.0 x16 PCIe 5.0 x16
• Structure size
  7 nm 4 nm
• Release date
  Q3/2022 Q2/2022

• Pixel Rate
  225.6 GPixel/s 39.60 GPixel/s
• Texture Rate
  609.1 GTexel/s 752.4 GTexel/s
• FP16 (half)
  77.97 TFLOPS (4:1) 96.31 TFLOPS
• FP32 (float)
  19.49 TFLOPS 24.08 TFLOPS
• FP64 (double)
  9.746 TFLOPS (1:2) 12.04 TFLOPS