Home GPU Comparison AMD Radeon Instinct MI60 vs NVIDIA L40 CNX

AMD Radeon Instinct MI60 vs NVIDIA L40 CNX

We compared two Professional market GPUs: 32GB VRAM Radeon Instinct MI60 and 24GB VRAM L40 CNX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

AMD Radeon Instinct MI60 's Advantages
More VRAM (32GB vs 24GB)
Larger VRAM bandwidth (1024GB/s vs 864.0GB/s)
NVIDIA L40 CNX 's Advantages
Released 3 years and 11 months late
Boost Clock has increased by 38% (2475MHz vs 1800MHz)
14080 additional rendering cores

Score

Benchmark

FP32 (float)
Radeon Instinct MI60
14.75 TFLOPS
L40 CNX +509%
89.97 TFLOPS
VS

Graphics Card

Nov 2018
Release Date
Oct 2022
Radeon Instinct
Generation
Tesla Ada
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

1200 MHz
Base Clock
1005 MHz
1800 MHz
Boost Clock
2475 MHz
1000 MHz
Memory Clock
2250 MHz

Memory

32GB
Memory Size
24GB
HBM2
Memory Type
GDDR6
4096bit
Memory Bus
384bit
1024GB/s
Bandwidth
864.0GB/s

Render Config

64
Compute Units
-
-
SM Count
142
4096
Shading Units
18176
256
TMUs
568
64
ROPs
192
-
Tensor Cores
568
-
RT Cores
142
16 KB (per CU)
L1 Cache
128 KB (per SM)
4 MB
L2 Cache
48 MB
-
-
-

Theoretical Performance

115.2 GPixel/s
Pixel Rate
475.2 GPixel/s
460.8 GTexel/s
Texture Rate
1406 GTexel/s
29.49 TFLOPS
FP16 (half)
89.97 TFLOPS
14.75 TFLOPS
FP32 (float)
89.97 TFLOPS
7.373 TFLOPS
FP64 (double)
1406 GFLOPS

Board Design

300W
TDP
300W
700 W
Suggested PSU
700 W
1x mini-DisplayPort 1.4a
Outputs
1x HDMI 2.1 3x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
1x 16-pin

Graphics Processor

Vega 20
GPU Name
AD102
Vega 20 GL
GPU Variant
AD102-???-A1
GCN 5.1
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
7 nm
Process Size
4 nm
13.23 billion
Transistors
76.3 billion
331 mm²
Die Size
608 mm²

Graphics Features

12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.2
Vulkan
1.3
-
CUDA
8.9
6.4
Shader Model
6.6

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy