NVIDIA RTX 6000 Ada vs NVIDIA L40. Specifications, performance, tests

Comparison of basic technical data of graphics cards NVIDIA RTX 6000 Ada and NVIDIA L40, chip, information processing units.

• GPU Chip
  AD102 AD102
• Execution units
  18176 18176
• Render Output Units
  192 192
• Texture Units
  568 568
• L1 Cache
  128 KB 128 KB
• L2 Cache
  96 MB 96 MB
• RT Cores
  142 142

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

• Memory Size
  48 GB 48 GB
• Memory Type
  GDDR6 GDDR6
• Memory Clock
  2.0 GHz 2.25 GHz
• Memory Speed
  16 Gbps 18 Gbps
• Memory Bandwith
  768.0 GB/s 864.0 GB/s
• Memory Interface
  384 bit 384 bit

Let's compare the memory frequency of graphics cards NVIDIA RTX 6000 Ada and NVIDIA L40. The higher the better.

• Base Clock
  2.175 GHz 0.735 GHz
• Boost Clock
  2.535 GHz 2.49 GHz

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

• TDP
  300 W 300 W
• Power Connectors
  1x 16-pin 1x 16-pin
• Slot
  Dual-slot Dual-slot
• Suggested PSU
  700 W 700 W

Connectivity and connections.

• Max. Displays
  4 4
• DP Ports
  4x DisplayPort 1.4a 4x DisplayPort 1.4a

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

• Max. resolution
  3840x2160 3840x2160
• DirectX
  12.2 12.2
• OpenGL
  4.6 4.6
• OpenCL
  3.0 3.0
• Vulkan
  1.3 1.3
• CUDA
  8.9 8.9
• Shader Model
  6.7 6.7

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

• Length
  267 mm 267 mm
• Width
  112 mm 111 mm

Comparison of interfaces and release dates for GPU NVIDIA L40 and NVIDIA RTX 6000 Ada.

• Architecture
  Ada Lovelace Ada Lovelace
• GPU Interface
  PCIe 4.0 x16 PCIe 4.0 x16
• Structure size
  4 nm 4 nm
• Release date
  Q4/2022 Q3/2022

• Pixel Rate
  486.7 GPixel/s 478.1 GPixel/s
• Texture Rate
  1,440 GTexel/s 1.414 GTexel/s
• FP16 (half)
  92.15 TFLOPS (1:1) 90.52 TFLOPS (1:1)
• FP32 (float)
  92.15 TFLOPS 90.52 TFLOPS
• FP64 (double)
  1,440 GFLOPS (1:64) 1.414 GFLOPS (1:64)