NVIDIA L40 vs Intel Arctic Sound M
We compared two Professional market GPUs: 48GB VRAM L40 and 16GB VRAM Intel Arctic Sound M to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L40 's Advantages
Released 9 months late
Boost Clock2490MHz
More VRAM (48GB vs 16GB)
9984 additional rendering cores
Lower TDP (300W vs 500W)
Intel Arctic Sound M 's Advantages
Larger VRAM bandwidth (1229GB/s vs 864.0GB/s)
Score
Benchmark
FP32 (float)
L40
+513%
90.52 TFLOPS
Intel Arctic Sound M
14.75 TFLOPS
Graphics Card
Oct 2022
Release Date
Jan 2022
Tesla Ada
Generation
Xe Graphics
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
735 MHz
Base Clock
-
2490 MHz
Boost Clock
-
2250 MHz
Memory Clock
1200 MHz
Memory
48GB
Memory Size
16GB
GDDR6
Memory Type
HBM2e
384bit
Memory Bus
4096bit
864.0GB/s
Bandwidth
1229GB/s
Render Config
-
-
-
142
SM Count
-
18176
Shading Units
8192
568
TMUs
256
192
ROPs
128
568
Tensor Cores
-
142
RT Cores
-
128 KB (per SM)
L1 Cache
-
96 MB
L2 Cache
8 MB
-
-
-
Theoretical Performance
478.1 GPixel/s
Pixel Rate
115.2 GPixel/s
1414 GTexel/s
Texture Rate
230.4 GTexel/s
90.52 TFLOPS
FP16 (half)
29.49 TFLOPS
90.52 TFLOPS
FP32 (float)
14.75 TFLOPS
1414 GFLOPS
FP64 (double)
3.686 TFLOPS
Board Design
300W
TDP
500W
700 W
Suggested PSU
900 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
8-pin EPS
Graphics Processor
AD102
GPU Name
DG2-512
AD102-895-A1
GPU Variant
-
Ada Lovelace
Architecture
Generation 12.7
TSMC
Foundry
TSMC
4 nm
Process Size
6 nm
76.3 billion
Transistors
21.7 billion
608 mm²
Die Size
406 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
-
6.6
Shader Model
6.6
