NVIDIA L40S vs AMD Radeon Instinct MI210
We compared two Professional market GPUs: 48GB VRAM L40S and 64GB VRAM Radeon Instinct MI210 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L40S 's Advantages
Released 10 months late
Boost Clock has increased by 48% (2520MHz vs 1700MHz)
11520 additional rendering cores
AMD Radeon Instinct MI210 's Advantages
More VRAM (64GB vs 48GB)
Larger VRAM bandwidth (1638GB/s vs 864.0GB/s)
Score
Benchmark
FP32 (float)
L40S
+304%
91.61 TFLOPS
Radeon Instinct MI210
22.63 TFLOPS
Graphics Card
Oct 2022
Release Date
Dec 2021
Tesla Ada
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1110 MHz
Base Clock
1000 MHz
2520 MHz
Boost Clock
1700 MHz
2250 MHz
Memory Clock
1600 MHz
Memory
48GB
Memory Size
64GB
GDDR6
Memory Type
HBM2e
384bit
Memory Bus
4096bit
864.0GB/s
Bandwidth
1638GB/s
Render Config
-
Compute Units
104
142
SM Count
-
18176
Shading Units
6656
568
TMUs
416
192
ROPs
0
568
Tensor Cores
-
142
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
48 MB
L2 Cache
16 MB
-
-
-
Theoretical Performance
483.8 GPixel/s
Pixel Rate
0 MPixel/s
1431 GTexel/s
Texture Rate
707.2 GTexel/s
91.61 TFLOPS
FP16 (half)
181.0 TFLOPS
91.61 TFLOPS
FP32 (float)
22.63 TFLOPS
1431 GFLOPS
FP64 (double)
22.63 TFLOPS
Board Design
300W
TDP
300W
700 W
Suggested PSU
700 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
AD102
GPU Name
Aldebaran
AD102-???-A1
GPU Variant
Aldebaran
Ada Lovelace
Architecture
CDNA 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
6 nm
76.3 billion
Transistors
58.2 billion
609 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
-
6.7
Shader Model
N/A
