Moore Threads MTT S4000 vs NVIDIA GeForce GTX 1070 Ti
We compared two Desktop platform GPUs: 48GB VRAM Moore Threads MTT S4000 and 8GB VRAM GeForce GTX 1070 Ti 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 8GB)
Larger VRAM bandwidth (768.0GB/s vs 256.3GB/s)
5760 additional rendering cores
NVIDIA GeForce GTX 1070 Ti 's Advantages
Boost Clock1683MHz
Lower TDP (180W vs 450W)
Score
Benchmark
FP32 (float)
Moore Threads MTT S4000
+200%
24.58 TFLOPS
GeForce GTX 1070 Ti
8.186 TFLOPS
Graphics Card
Unknown
Release Date
Nov 2017
MUSA-Chunxiao
Generation
GeForce 10
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1500 MHz
Base Clock
1607 MHz
-
Boost Clock
1683 MHz
2000 MHz
Memory Clock
2002 MHz
Memory
48GB
Memory Size
8GB
GDDR6
Memory Type
GDDR5
384bit
Memory Bus
256bit
768.0GB/s
Bandwidth
256.3GB/s
Render Config
64
Compute Units
-
-
SM Count
19
8192
Shading Units
2432
512
TMUs
152
512
ROPs
64
128
Tensor Cores
-
-
-
-
-
L1 Cache
48 KB (per SM)
4 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
768.0 GPixel/s
Pixel Rate
107.7 GPixel/s
768.0 GTexel/s
Texture Rate
255.8 GTexel/s
49.15 TFLOPS
FP16 (half)
127.9 GFLOPS
24.58 TFLOPS
FP32 (float)
8.186 TFLOPS
384.0 GFLOPS
FP64 (double)
255.8 GFLOPS
Board Design
450W
TDP
180W
850 W
Suggested PSU
450 W
4x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
MTT Gen 2
GPU Name
GP104
-
GPU Variant
GP104-300-A1
MUSA-Chunxiao
Architecture
Pascal
TSMC
Foundry
TSMC
12 nm
Process Size
16 nm
22 billion
Transistors
7.2 billion
Unknown
Die Size
314 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.4
Vulkan
1.3
-
CUDA
6.1
6.5
Shader Model
6.4
