Home GPU Comparison NVIDIA L20 vs NVIDIA CMP 30HX

NVIDIA L20 vs NVIDIA CMP 30HX

We compared two Desktop platform GPUs: 48GB VRAM L20 and 6GB VRAM CMP 30HX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA L20 's Advantages
Released 2 years and 9 months late
Boost Clock has increased by 41% (2520MHz vs 1785MHz)
More VRAM (48GB vs 6GB)
Larger VRAM bandwidth (864.0GB/s vs 336.0GB/s)
10368 additional rendering cores
NVIDIA CMP 30HX 's Advantages
Lower TDP (125W vs 275W)

Score

Benchmark

FP32 (float)
L20 +1080%
59.35 TFLOPS
CMP 30HX
5.027 TFLOPS
L20
VS

Graphics Card

Nov 2023
Release Date
Feb 2021
Tesla Ada
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x4

Clock Speeds

1440 MHz
Base Clock
1530 MHz
2520 MHz
Boost Clock
1785 MHz
2250 MHz
Memory Clock
1750 MHz

Memory

48GB
Memory Size
6GB
GDDR6
Memory Type
GDDR6
384bit
Memory Bus
192bit
864.0GB/s
Bandwidth
336.0GB/s

Render Config

-
-
-
92
SM Count
22
11776
Shading Units
1408
368
TMUs
88
128
ROPs
48
368
Tensor Cores
-
92
RT Cores
-
128 KB (per SM)
L1 Cache
64 KB (per SM)
96 MB
L2 Cache
1536 KB
-
-
-

Theoretical Performance

322.6 GPixel/s
Pixel Rate
85.68 GPixel/s
927.4 GTexel/s
Texture Rate
157.1 GTexel/s
59.35 TFLOPS
FP16 (half)
10.05 TFLOPS
59.35 TFLOPS
FP32 (float)
5.027 TFLOPS
927.4 GFLOPS
FP64 (double)
157.1 GFLOPS

Board Design

275W
TDP
125W
600 W
Suggested PSU
300 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
1x 8-pin

Graphics Processor

AD102
GPU Name
TU116
AD102
GPU Variant
TU116-100-A1
Ada Lovelace
Architecture
Turing
TSMC
Foundry
TSMC
5 nm
Process Size
12 nm
76.3 billion
Transistors
6.6 billion
609 mm²
Die Size
284 mm²

Graphics Features

12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.9
CUDA
7.5
6.7
Shader Model
6.6

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy