Moore Threads MTT S3000 vs NVIDIA L40G
GPU · Specs Compare
Graphics Card
Release Date
Unknown
Oct 2022
Generation
MUSA-Chunxiao
Tesla Ada
Type
Desktop
Professional
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1900 MHz
1005 MHz
Boost Clock
0 MHz
2475 MHz
Memory Clock
1750 MHz
2250 MHz
Memory
Memory Size
32GB
24GB
Memory Type
GDDR6
GDDR6
Memory Bus
256bit
384bit
Bandwidth
448.0GB/s
864.0GB/s
Render Config
Compute Units
32
—
Shading Units
4096
18176
TMUs
256
568
ROPs
256
192
L2 Cache
4 MB
48 MB
SM Count
—
142
Tensor Cores
—
568
RT Cores
—
142
L1 Cache
—
128 KB (per SM)
Theoretical Performance
Pixel Rate
486.4 GPixel/s
475.2 GPixel/s
Texture Rate
486.4 GTexel/s
1406 GTexel/s
FP16 (half)
31.13 TFLOPS
89.97 TFLOPS
FP32 (float)
15.56 TFLOPS
89.97 TFLOPS
FP64 (double)
243.2 GFLOPS
1406 GFLOPS
Graphics Processor
GPU Name
MTT Gen 2
AD102
Architecture
MUSA-Chunxiao
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
12 nm
4 nm
Transistors
22 billion
76.3 billion
Die Size
Unknown
608 mm²
GPU Variant
—
AD102-???-A1
Board Design
TDP
250W
300W
Suggested PSU
600 W
700 W
Outputs
2x DisplayPort 1.4a
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
1x 8-pin
1x 16-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
Shader Model
6.5
6.6
CUDA
—
8.9
▲ Specs Compare
Data sourced from official specifications and benchmark tests.