NVIDIA L40G vs NVIDIA Tesla K20m
We compared two Professional market GPUs: 24GB VRAM L40G and 5GB VRAM Tesla K20m to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L40G 's Advantages
Released 9 years and 9 months late
Boost Clock2475MHz
More VRAM (24GB vs 5GB)
Larger VRAM bandwidth (864.0GB/s vs 208.0GB/s)
15680 additional rendering cores
NVIDIA Tesla K20m 's Advantages
Lower TDP (225W vs 300W)
Score
Benchmark
FP32 (float)
L40G
+2453%
89.97 TFLOPS
Tesla K20m
3.524 TFLOPS
Graphics Card
Oct 2022
Release Date
Jan 2013
Tesla Ada
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1005 MHz
Base Clock
-
2475 MHz
Boost Clock
-
2250 MHz
Memory Clock
1300 MHz
Memory
24GB
Memory Size
5GB
GDDR6
Memory Type
GDDR5
384bit
Memory Bus
320bit
864.0GB/s
Bandwidth
208.0GB/s
Render Config
-
-
-
142
SM Count
-
18176
Shading Units
2496
568
TMUs
208
192
ROPs
40
568
Tensor Cores
-
142
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per SMX)
48 MB
L2 Cache
1280 KB
-
-
-
Theoretical Performance
475.2 GPixel/s
Pixel Rate
36.71 GPixel/s
1406 GTexel/s
Texture Rate
146.8 GTexel/s
89.97 TFLOPS
FP16 (half)
-
89.97 TFLOPS
FP32 (float)
3.524 TFLOPS
1406 GFLOPS
FP64 (double)
1175 GFLOPS
Board Design
300W
TDP
225W
700 W
Suggested PSU
550 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
AD102
GPU Name
GK110
AD102-???-A1
GPU Variant
-
Ada Lovelace
Architecture
Kepler
TSMC
Foundry
TSMC
4 nm
Process Size
28 nm
76.3 billion
Transistors
7.08 billion
608 mm²
Die Size
561 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.1
8.9
CUDA
3.5
6.6
Shader Model
5.1
