NVIDIA GeForce RTX 4070 SUPER vs NVIDIA A800 SXM4 80 GB. Specifications, performance, tests

Comparison of basic technical data of graphics cards NVIDIA GeForce RTX 4070 SUPER and NVIDIA A800 SXM4 80 GB, chip, information processing units.

• Architecture
  Ada Lovelace Ampere
• Based on
  NVIDIA GeForce RTX 4070 SUPER -
• CUDA Cores
  7168 -
• Shader
  7168 -
• Execution Units
  - 6912
• GPU Chip
  - GA100
• L1 Cache
  - 192 KB
• L2 Cache
  - 40 MB
• Render Output Units
  - 160
• Texture Units
  - 432

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

• Memory Bus
  192 bit 5120 bit
• Memory Size
  12 GB 80 GB
• Memory Type
  GDDR6X HBM2e
• Memory Bandwidth
  - 0.255 GB/s
• Memory Clock
  - 1593 MHz

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

• Base Clock
  1980 MHz 1275 MHz
• Boost Clock
  2480 MHz 1410 MHz

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

• Maximum GPU Temperature
  90 °C -
• System Power Supply
  650 W (System power requirement) -
• TDP
  220 W 400 W

Connectivity and connections.

• PCIe Interface
  4.0 PCIe 4.0 x16
• Max. Displays
  - 1
• Power Connectors
  - No

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

• CUDA
  - 8.0
• DirectX
  - 12.2
• Max. resolution
  - 3840 × 2160
• OpenCL
  - 3.0

Built-in support for video and image compression standards.

• AV1
  Decode / Encode -

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

• Slot Size
  - IGP

Comparison of interfaces and release dates for GPU NVIDIA A800 SXM4 80 GB and NVIDIA GeForce RTX 4070 SUPER.

• Process Technology
  - 7 nm
• Release date
  - Q3/2022

• FP16 (theoretical)
  - 77.97 TFLOPS (4:1)
• FP32 (theoretical)
  - 19.49 TFLOPS
• FP64 (theoretical)
  - 9.746 TFLOPS (1:2)
• Pixel Rate
  - 225.6 GPixel/s
• Texture Rate
  - 609.1 GTexel/s