NVIDIA RTX A2000 vs NVIDIA RTX 6000 Ada. Specifications, performance, tests

Comparison of basic technical data of graphics cards NVIDIA RTX A2000 and NVIDIA RTX 6000 Ada, chip, information processing units.

• Architecture
  Ampere Ada Lovelace
• Execution Units
  26 18176
• GPU Chip
  GA106 AD102
• Render Output Units
  48 192
• Shader
  3328 -
• Texture Units
  104 568
• L1 Cache
  - 128 KB
• L2 Cache
  - 96 MB
• RT Cores
  - 142

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

• Memory Size
  6 GB 48 GB
• Memory Speed (legacy frequency label)
  1500 MHz -
• Memory Type
  GDDR6 GDDR6
• Memory Bandwidth
  - 768 GB/s
• Memory Bus
  - 384 bit
• Memory Clock
  - 2000 MHz
• Memory Data Rate
  - 16 Gbps

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

• Base Clock
  562 MHz 2175 MHz
• Boost Clock
  1200 MHz 2535 MHz

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

• TDP
  70 W 300 W
• System Power Supply
  - 700 W (PSU recommendation)

Connectivity and connections.

• Max. Displays
  4 4
• PCIe Interface
  PCIe 4.0 x16 PCIe 4.0 x16
• DisplayPort Ports
  - 4 × DisplayPort 1.4a
• Power Connectors
  - 1x 16-pin

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

• DirectX
  12.2 12.2
• DLSS / FSR
  Yes -
• Max. resolution
  7680 × 4320 3840 × 2160
• Raytracing
  Yes -
• CUDA
  - 8.9
• OpenCL
  - 3.0
• OpenGL
  - 4.6
• Shader Model
  - 6.7
• Vulkan
  - 1.3

Built-in support for video and image compression standards.

• AV1
  Decode -
• h264
  Decode / Encode -
• h265 / HEVC
  Decode / Encode -
• VP8
  Decode -
• VP9
  Decode -

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

• Length
  - 267 mm
• Slot Size
  - Dual-slot
• Width
  - 112 mm

Comparison of interfaces and release dates for GPU NVIDIA RTX 6000 Ada and NVIDIA RTX A2000.

• Manufacturer
  NVIDIA -
• Process Technology
  8 nm 4 nm
• Release date
  Q3/2021 Q4/2022

• FP16 (theoretical)
  - 92.15 TFLOPS (1:1)
• FP32 (theoretical)
  - 92.15 TFLOPS
• FP64 (theoretical)
  - 1,440 GFLOPS (1:64)
• Pixel Rate
  - 486.7 GPixel/s
• Texture Rate
  - 1,440 GTexel/s