Home GPU Comparison NVIDIA L20 vs NVIDIA L40

NVIDIA L20 vs NVIDIA L40

We compared a Desktop platform GPU: 48GB VRAM L20 and a Professional market GPU: 48GB VRAM L40 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA L20 's Advantages
Released 1 years and 1 months late
Boost Clock has increased by 1% (2520MHz vs 2490MHz)
Lower TDP (275W vs 300W)
NVIDIA L40 's Advantages
6400 additional rendering cores

Score

Benchmark

FP32 (float)
L20
59.35 TFLOPS
L40 +52%
90.52 TFLOPS
L20
VS
L40

Graphics Card

Nov 2023
Release Date
Oct 2022
Tesla Ada
Generation
Tesla Ada
Desktop
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

1440 MHz
Base Clock
735 MHz
2520 MHz
Boost Clock
2490 MHz
2250 MHz
Memory Clock
2250 MHz

Memory

48GB
Memory Size
48GB
GDDR6
Memory Type
GDDR6
384bit
Memory Bus
384bit
864.0GB/s
Bandwidth
864.0GB/s

Render Config

92
SM Count
142
-
Compute Units
-
11776
Shading Units
18176
368
TMUs
568
128
ROPs
192
368
Tensor Cores
568
92
RT Cores
142
128 KB (per SM)
L1 Cache
128 KB (per SM)
96 MB
L2 Cache
96 MB

Theoretical Performance

322.6 GPixel/s
Pixel Rate
478.1 GPixel/s
927.4 GTexel/s
Texture Rate
1414 GTexel/s
59.35 TFLOPS
FP16 (half)
90.52 TFLOPS
59.35 TFLOPS
FP32 (float)
90.52 TFLOPS
927.4 GFLOPS
FP64 (double)
1414 GFLOPS

Graphics Processor

AD102
GPU Name
AD102
AD102
GPU Variant
AD102-895-A1
Ada Lovelace
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
5 nm
Process Size
4 nm
76.3 billion
Transistors
76.3 billion
609 mm²
Die Size
608 mm²

Board Design

275W
TDP
300W
600 W
Suggested PSU
700 W
4x DisplayPort 1.4a
Outputs
4x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 16-pin

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
8.9
CUDA
8.9
6.7
Shader Model
6.6

Related GPU Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy