Data Center GPU Flex 170 vs L40 CNX
We compared two Professional market GPUs: 16GB VRAM Data Center GPU Flex 170 and 24GB VRAM L40 CNX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Data Center GPU Flex 170 's Advantages
Lower TDP (150W vs 300W)
L40 CNX 's Advantages
Boost Clock has increased by 21% (2475MHz vs 2050MHz)
More VRAM (24GB vs 16GB)
Larger VRAM bandwidth (864.0GB/s vs 512.0GB/s)
14080 additional rendering cores
Score
Benchmark
FP32 (float)
Data Center GPU Flex 170
16790
L40 CNX
+435%
89970
Graphics Card
Aug 2022
Release Date
Oct 2022
Data Center GPU
Generation
Tesla Ada
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1950 MHz
Base Clock
1005 MHz
2050 MHz
Boost Clock
2475 MHz
2000 MHz
Memory Clock
2250 MHz
Memory
16GB
Memory Size
24GB
GDDR6
Memory Type
GDDR6
256bit
Memory Bus
384bit
512.0GB/s
Bandwidth
864.0GB/s
Render Config
-
SM Count
142
4096
Shading Units
18176
256
TMUs
568
128
ROPs
192
-
Tensor Cores
568
32
RT Cores
142
-
L1 Cache
128 KB (per SM)
16 MB
L2 Cache
48 MB
Theoretical Performance
262.4 GPixel/s
Pixel Rate
475.2 GPixel/s
524.8 GTexel/s
Texture Rate
1406 GTexel/s
33.59 TFLOPS
FP16 (half)
89.97 TFLOPS
16.79 TFLOPS
FP32 (float)
89.97 TFLOPS
-
FP64 (double)
1406 GFLOPS
Board Design
150W
TDP
300W
450 W
Suggested PSU
700 W
1x HDMI 2.1
3x DisplayPort 2.0
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
DG2-512
GPU Name
AD102
ACM-G10
GPU Variant
AD102-???-A1
Generation 12.7
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
6 nm
Process Size
4 nm
21.7 billion
Transistors
76.3 billion
406 mm²
Die Size
608 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
8.9
6.6
Shader Model
6.6
