NVIDIA P104 100 vs Moore Threads MTT S4000
We compared two Desktop platform GPUs: 4GB VRAM P104 100 and 48GB VRAM Moore Threads MTT S4000 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA P104 100 's Advantages
Boost Clock1733MHz
Moore Threads MTT S4000 's Advantages
More VRAM (48GB vs 4GB)
Larger VRAM bandwidth (768.0GB/s vs 320.3GB/s)
6272 additional rendering cores
Score
Benchmark
FP32 (float)
P104 100
6.655 TFLOPS
Moore Threads MTT S4000
+269%
24.58 TFLOPS
Graphics Card
Dec 2017
Release Date
Unknown
Mining GPUs
Generation
MUSA-Chunxiao
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 5.0 x16
Clock Speeds
1607 MHz
Base Clock
1500 MHz
1733 MHz
Boost Clock
-
1251 MHz
Memory Clock
2000 MHz
Memory
4GB
Memory Size
48GB
GDDR5X
Memory Type
GDDR6
256bit
Memory Bus
384bit
320.3GB/s
Bandwidth
768.0GB/s
Render Config
-
Compute Units
64
15
SM Count
-
1920
Shading Units
8192
120
TMUs
512
64
ROPs
512
-
Tensor Cores
128
-
-
-
48 KB (per SM)
L1 Cache
-
2 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
110.9 GPixel/s
Pixel Rate
768.0 GPixel/s
208.0 GTexel/s
Texture Rate
768.0 GTexel/s
104.0 GFLOPS
FP16 (half)
49.15 TFLOPS
6.655 TFLOPS
FP32 (float)
24.58 TFLOPS
208.0 GFLOPS
FP64 (double)
384.0 GFLOPS
Board Design
Unknown
TDP
450W
200 W
Suggested PSU
850 W
No outputs
Outputs
4x DisplayPort 1.4a
1x 8-pin
Power Connectors
2x 8-pin
Graphics Processor
GP104
GPU Name
MTT Gen 2
GP104-100-A1
GPU Variant
-
Pascal
Architecture
MUSA-Chunxiao
TSMC
Foundry
TSMC
16 nm
Process Size
12 nm
7.2 billion
Transistors
22 billion
314 mm²
Die Size
Unknown
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.4
6.1
CUDA
-
6.8
Shader Model
6.5
