NVIDIA L40 vs Intel Arc Pro A40. Specifications, performance, tests

Comparison of basic technical data of graphics cards NVIDIA L40 and Intel Arc Pro A40, chip, information processing units.

• GPU Chip
  AD102 DG2-128
• Execution units
  18176 1024
• Render Output Units
  192 32
• Texture Units
  568 64
• L1 Cache
  128 KB No
• L2 Cache
  96 MB 4 MB
• RT Cores
  142 8

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

• Memory Size
  48 GB 6 GB
• Memory Type
  GDDR6 GDDR6
• Memory Clock
  2.25 GHz 2 GHz
• Memory Speed
  18 Gbps 16 Gbps
• Memory Bandwith
  864.0 GB/s 192.0 GB/s
• Memory Interface
  384 bit 96 bit

Let's compare the memory frequency of graphics cards NVIDIA L40 and Intel Arc Pro A40. The higher the better.

• Base Clock
  0.735 GHz 1.5 GHz
• Boost Clock
  2.49 GHz 1.7 GHz

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

• TDP
  300 W 50 W
• Power Connectors
  1x 16-pin No
• Suggested PSU
  700 W 250 W

Connectivity and connections.

• DP Ports
  4x DisplayPort 1.4a 4x mini-DisplayPort 2.0

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
• Shader Model
  6.7 6.6

Comparison of interfaces and release dates for GPU Intel Arc Pro A40 and NVIDIA L40.

• Architecture
  Ada Lovelace Generation 12.7 / Alchemist (Pro-Series)
• GPU Interface
  PCIe 4.0 x16 PCIe 4.0 x8
• Structure size
  4 nm 6 nm
• Release date
  Q3/2022 Q3/2022

• Pixel Rate
  478.1 GPixel/s 54.40 GPixel/s
• Texture Rate
  1.414 GTexel/s 108.8 GTexel/s
• FP16 (half)
  90.52 TFLOPS (1:1) 6.963 TFLOPS (2:1)
• FP32 (float)
  90.52 TFLOPS 3.482 TFLOPS
• FP64 (double)
  1.414 GFLOPS (1:64) 870.4 GFLOPS