Home GPU Comparison NVIDIA L20 vs NVIDIA CMP 90HX

NVIDIA L20 vs NVIDIA CMP 90HX

We compared two Desktop platform GPUs: 48GB VRAM L20 and 10GB VRAM CMP 90HX 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 4 months late
Boost Clock has increased by 47% (2520MHz vs 1710MHz)
More VRAM (48GB vs 10GB)
Larger VRAM bandwidth (864.0GB/s vs 760.3GB/s)
5376 additional rendering cores
Lower TDP (275W vs 320W)

Score

Benchmark

FP32 (float)
L20 +171%
59.35 TFLOPS
CMP 90HX
21.89 TFLOPS
L20
VS

Graphics Card

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

Clock Speeds

1440 MHz
Base Clock
1500 MHz
2520 MHz
Boost Clock
1710 MHz
2250 MHz
Memory Clock
1188 MHz

Memory

48GB
Memory Size
10GB
GDDR6
Memory Type
GDDR6X
384bit
Memory Bus
320bit
864.0GB/s
Bandwidth
760.3GB/s

Render Config

-
-
-
92
SM Count
50
11776
Shading Units
6400
368
TMUs
200
128
ROPs
80
368
Tensor Cores
200
92
RT Cores
50
128 KB (per SM)
L1 Cache
128 KB (per SM)
96 MB
L2 Cache
5 MB
-
-
-

Theoretical Performance

322.6 GPixel/s
Pixel Rate
136.8 GPixel/s
927.4 GTexel/s
Texture Rate
342.0 GTexel/s
59.35 TFLOPS
FP16 (half)
21.89 TFLOPS
59.35 TFLOPS
FP32 (float)
21.89 TFLOPS
927.4 GFLOPS
FP64 (double)
342.0 GFLOPS

Board Design

275W
TDP
320W
600 W
Suggested PSU
700 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
2x 8-pin

Graphics Processor

AD102
GPU Name
GA102
AD102
GPU Variant
GA102-100-A1
Ada Lovelace
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
76.3 billion
Transistors
28.3 billion
609 mm²
Die Size
628 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
8.9
CUDA
8.6
6.7
Shader Model
6.6

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy