NVIDIA Tesla M10 vs Intel Data Center GPU Max Subsystem
GPU · Specs Compare
Graphics Card
Release Date
May 2016
Jan 2023
Generation
Tesla
Data Center GPU
Type
Professional
Professional
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1033 MHz
900 MHz
Boost Clock
1306 MHz
1600 MHz
Memory Clock
1300 MHz
1565 MHz
Memory
Memory Size
8GB
128GB
Memory Type
GDDR5
HBM2e
Memory Bus
128bit
8192bit
Bandwidth
83.20GB/s
3205GB/s
Render Config
Shading Units
640
16384
TMUs
40
1024
ROPs
16
0
L1 Cache
64 KB (per SMM)
64 KB (per EU)
L2 Cache
2 MB
408 MB
Tensor Cores
—
1024
RT Cores
—
128
Theoretical Performance
Pixel Rate
20.90 GPixel/s
0 MPixel/s
Texture Rate
52.24 GTexel/s
1638 GTexel/s
FP32 (float)
1.672 TFLOPS
52.43 TFLOPS
FP64 (double)
52.24 GFLOPS
52.43 TFLOPS
FP16 (half)
—
52.43 TFLOPS
Graphics Processor
GPU Name
GM107
Ponte Vecchio
GPU Variant
GM107-570-A2
—
Architecture
Maxwell
Generation 12.5
Foundry
TSMC
Intel
Process Size
28 nm
10 nm
Transistors
1.87 billion
100 billion
Die Size
148 mm²
1280 mm²
Board Design
TDP
225W
2400W
Suggested PSU
550 W
2800 W
Outputs
No outputs
No outputs
Power Connectors
1x 8-pin
1x 16-pin
Graphics Features
DirectX
12 (11_0)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
5.0
—
Shader Model
5.1
6.6
▲ Specs Compare
Data sourced from official specifications and benchmark tests.