Moore Threads MTT S1000M vs NVIDIA H100 CNX
GPU · Specs Compare
Graphics Card
Release Date
Jul 2022
Mar 2023
Generation
MUSA-Chunxiao
Tesla Hopper
Type
Desktop
AI GPU
Bus Interface
PCIe 4.0 x8
PCIe 5.0 x16
Clock Speeds
Base Clock
1000 MHz
690 MHz
Memory Clock
1750 MHz
1593 MHz
Boost Clock
—
1845 MHz
Memory
Memory Size
4GB
80GB
Memory Type
GDDR6
HBM2e
Memory Bus
128bit
5120bit
Bandwidth
224.0GB/s
2039GB/s
Render Config
Compute Units
8
—
Shading Units
1024
14592
TMUs
64
456
ROPs
64
24
L2 Cache
1024 KB
50 MB
SM Count
—
114
Tensor Cores
—
456
L1 Cache
—
256 KB (per SM)
Theoretical Performance
Pixel Rate
64.00 GPixel/s
44.28 GPixel/s
Texture Rate
64.00 GTexel/s
841.3 GTexel/s
FP16 (half)
4.096 TFLOPS
215.4 TFLOPS
FP32 (float)
2.048 TFLOPS
53.84 TFLOPS
FP64 (double)
32.00 GFLOPS
26.92 TFLOPS
Graphics Processor
GPU Name
MTT Gen 1
GH100
Architecture
MUSA-Chunxiao
Hopper
Foundry
TSMC
TSMC
Process Size
12 nm
4 nm
Transistors
Unknown
80 billion
Die Size
Unknown
814 mm²
Board Design
TDP
35W
350W
Suggested PSU
200 W
750 W
Outputs
2x DisplayPort 1.2
No outputs
Power Connectors
None
8-pin EPS
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.4
N/A
Shader Model
6.5
N/A
CUDA
—
9.0
▲ Specs Compare
Data sourced from official specifications and benchmark tests.