NVIDIA L20 vs NVIDIA CMP 40HX

GPU Specs Compare

G

NVIDIA L20

NVIDIA 2023-11
G

NVIDIA CMP 40HX

NVIDIA 2021-02

Graphics Card

Release Date
Nov 2023
Feb 2021
Generation
Server Ada
Mining GPUs
Type
Desktop
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 1.0 x4

Clock Speeds

Base Clock
1440 MHz
1470 MHz
Boost Clock
2520 MHz
1650 MHz
Memory Clock
2250 MHz
1750 MHz

Memory

Memory Size
48GB
8GB
Memory Type
GDDR6
GDDR6
Memory Bus
384bit
256bit
Bandwidth
864.0GB/s
448.0GB/s

Render Config

SM Count
92
36
Shading Units
11776
2304
TMUs
368
144
ROPs
128
64
Tensor Cores
368
288
RT Cores
92
36
L1 Cache
128 KB (per SM)
64 KB (per SM)
L2 Cache
96 MB
4 MB

Theoretical Performance

Pixel Rate
322.6 GPixel/s
105.6 GPixel/s
Texture Rate
927.4 GTexel/s
237.6 GTexel/s
FP16 (half)
59.35 TFLOPS
15.21 TFLOPS
FP32 (float)
59.35 TFLOPS
7.603 TFLOPS
FP64 (double)
927.4 GFLOPS
237.6 GFLOPS

Graphics Processor

GPU Name
AD102
TU106
GPU Variant
AD102
TU106-100-A1
Architecture
Ada Lovelace
Turing
Foundry
TSMC
TSMC
Process Size
5 nm
12 nm
Transistors
76.3 billion
10.8 billion
Die Size
609 mm²
445 mm²

Board Design

TDP
275W
185W
Suggested PSU
600 W
450 W
Outputs
4x DisplayPort 1.4a
No outputs
Power Connectors
1x 16-pin
1x 8-pin

Graphics Features

DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.4
1.3
CUDA
8.9
7.5
Shader Model
6.9
6.8

📊 Benchmark

Blender
-
1,174