NVIDIA Tesla K20s vs NVIDIA L20
GPU Specs Compare
Graphics Card
Release Date
Feb 2013
Nov 2023
Generation
Tesla
Server Ada
Type
Professional
Desktop
Bus Interface
PCIe 2.0 x16
PCIe 4.0 x16
Clock Speeds
Memory Clock
1300 MHz
2250 MHz
Base Clock
-
1440 MHz
Boost Clock
-
2520 MHz
Memory
Memory Size
5GB
48GB
Memory Type
GDDR5
GDDR6
Memory Bus
320bit
384bit
Bandwidth
208.0GB/s
864.0GB/s
Render Config
Shading Units
2496
11776
TMUs
208
368
ROPs
40
128
L1 Cache
16 KB (per SMX)
128 KB (per SM)
L2 Cache
1280 KB
96 MB
SM Count
-
92
Tensor Cores
-
368
RT Cores
-
92
Theoretical Performance
Pixel Rate
29.90 GPixel/s
322.6 GPixel/s
Texture Rate
119.6 GTexel/s
927.4 GTexel/s
FP32 (float)
2.870 TFLOPS
59.35 TFLOPS
FP64 (double)
956.8 GFLOPS
927.4 GFLOPS
FP16 (half)
-
59.35 TFLOPS
Graphics Processor
GPU Name
GK110
AD102
Architecture
Kepler
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
28 nm
5 nm
Transistors
7.08 billion
76.3 billion
Die Size
561 mm²
609 mm²
GPU Variant
-
AD102
Board Design
TDP
225W
275W
Suggested PSU
550 W
600 W
Outputs
No outputs
4x DisplayPort 1.4a
Power Connectors
-
1x 16-pin
Graphics Features
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.1
1.4
CUDA
3.5
8.9
Shader Model
5.1
6.9