Home GPU Comparison NVIDIA L40 vs AMD Radeon Instinct MI250

NVIDIA L40 vs AMD Radeon Instinct MI250

We compared two Professional market GPUs: 48GB VRAM L40 and 128GB VRAM Radeon Instinct MI250 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA L40 's Advantages
Released 11 months late
Boost Clock has increased by 46% (2490MHz vs 1700MHz)
4864 additional rendering cores
Lower TDP (300W vs 500W)
AMD Radeon Instinct MI250 's Advantages
More VRAM (128GB vs 48GB)
Larger VRAM bandwidth (3277GB/s vs 864.0GB/s)

Score

Benchmark

FP32 (float)
L40 +100%
90.52 TFLOPS
Radeon Instinct MI250
45.26 TFLOPS
L40
VS

Graphics Card

Oct 2022
Release Date
Nov 2021
Tesla Ada
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

735 MHz
Base Clock
1000 MHz
2490 MHz
Boost Clock
1700 MHz
2250 MHz
Memory Clock
1600 MHz

Memory

48GB
Memory Size
128GB
GDDR6
Memory Type
HBM2e
384bit
Memory Bus
8192bit
864.0GB/s
Bandwidth
3277GB/s

Render Config

-
Compute Units
208
142
SM Count
-
18176
Shading Units
13312
568
TMUs
832
192
ROPs
0
568
Tensor Cores
-
142
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
96 MB
L2 Cache
16 MB
-
-
-

Theoretical Performance

478.1 GPixel/s
Pixel Rate
0 MPixel/s
1414 GTexel/s
Texture Rate
1414 GTexel/s
90.52 TFLOPS
FP16 (half)
362.1 TFLOPS
90.52 TFLOPS
FP32 (float)
45.26 TFLOPS
1414 GFLOPS
FP64 (double)
45.26 TFLOPS

Board Design

300W
TDP
500W
700 W
Suggested PSU
900 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
2x 8-pin

Graphics Processor

AD102
GPU Name
Aldebaran
AD102-895-A1
GPU Variant
Aldebaran
Ada Lovelace
Architecture
CDNA 2.0
TSMC
Foundry
TSMC
4 nm
Process Size
6 nm
76.3 billion
Transistors
58.2 billion
608 mm²
Die Size
Unknown

Graphics Features

12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
8.9
CUDA
-
6.6
Shader Model
N/A

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy