Moore Threads MTT S4000 vs NVIDIA GeForce GT 430 PCI
We compared two Desktop platform GPUs: 48GB VRAM Moore Threads MTT S4000 and 512MB VRAM GeForce GT 430 PCI to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Moore Threads MTT S4000 's Advantages
More VRAM (48GB vs 512GB)
Larger VRAM bandwidth (768.0GB/s vs 9.600GB/s)
8096 additional rendering cores
NVIDIA GeForce GT 430 PCI 's Advantages
Lower TDP (49W vs 450W)
Score
Benchmark
FP32 (float)
Moore Threads MTT S4000
+9037%
24.58 TFLOPS
GeForce GT 430 PCI
0.269 TFLOPS
Graphics Card
Unknown
Release Date
Oct 2010
MUSA-Chunxiao
Generation
GeForce 400
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1500 MHz
Base Clock
-
-
-
-
2000 MHz
Memory Clock
600 MHz
Memory
48GB
Memory Size
512MB
GDDR6
Memory Type
DDR3
384bit
Memory Bus
64bit
768.0GB/s
Bandwidth
9.600GB/s
Render Config
64
Compute Units
-
-
SM Count
2
8192
Shading Units
96
512
TMUs
16
512
ROPs
4
128
Tensor Cores
-
-
-
-
-
L1 Cache
64 KB (per SM)
4 MB
L2 Cache
128 KB
-
-
-
Theoretical Performance
768.0 GPixel/s
Pixel Rate
2.800 GPixel/s
768.0 GTexel/s
Texture Rate
11.20 GTexel/s
49.15 TFLOPS
FP16 (half)
-
24.58 TFLOPS
FP32 (float)
268.8 GFLOPS
384.0 GFLOPS
FP64 (double)
22.40 GFLOPS
Board Design
450W
TDP
49W
850 W
Suggested PSU
200 W
4x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 1.3a
1x VGA
2x 8-pin
Power Connectors
None
Graphics Processor
MTT Gen 2
GPU Name
GF108
-
GPU Variant
GF108-300-A1
MUSA-Chunxiao
Architecture
Fermi
TSMC
Foundry
TSMC
12 nm
Process Size
40 nm
22 billion
Transistors
0.585 billion
Unknown
Die Size
116 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
1.1
1.4
Vulkan
N/A
-
CUDA
2.1
6.5
Shader Model
5.1
