Intel Data Center GPU Flex 170 vs NVIDIA L40
GPU Specs Compare
Graphics Card
Release Date
Aug 2022
Oct 2022
Generation
Data Center GPU
Tesla Ada
Type
Professional
Professional
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1950 MHz
735 MHz
Boost Clock
2050 MHz
2490 MHz
Memory Clock
2000 MHz
2250 MHz
Memory
Memory Size
16GB
48GB
Memory Type
GDDR6
GDDR6
Memory Bus
256bit
384bit
Bandwidth
512.0GB/s
864.0GB/s
Render Config
Shading Units
4096
18176
TMUs
256
568
ROPs
128
192
RT Cores
32
142
L2 Cache
16 MB
96 MB
SM Count
-
142
Tensor Cores
-
568
L1 Cache
-
128 KB (per SM)
Theoretical Performance
Pixel Rate
262.4 GPixel/s
478.1 GPixel/s
Texture Rate
524.8 GTexel/s
1414 GTexel/s
FP16 (half)
33.59 TFLOPS
90.52 TFLOPS
FP32 (float)
16.79 TFLOPS
90.52 TFLOPS
FP64 (double)
-
1414 GFLOPS
Graphics Processor
GPU Name
DG2-512
AD102
GPU Variant
ACM-G10
AD102-895-A1
Architecture
Generation 12.7
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
6 nm
4 nm
Transistors
21.7 billion
76.3 billion
Die Size
406 mm²
608 mm²
Board Design
TDP
150W
300W
Suggested PSU
450 W
700 W
Outputs
1x HDMI 2.13x DisplayPort 2.0
4x DisplayPort 1.4a
Power Connectors
1x 8-pin
1x 16-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.3
Shader Model
6.6
6.6
CUDA
-
8.9
📊 Benchmark
Blender
-
3,901