INTEL
Intel Data Center GPU Max Subsystem
The Intel Data Center GPU Max Subsystem is a GPU manufactured by Intel, built on Intel's officially announced 10 nm process technology, released in January 2023. This graphics card is equipped with 128GB HBM2e memory, suitable for gaming and professional graphics applications.
Process Size
10 nm
Tensor Cores
1024
Boost Clock
1600 MHz
Base Clock
900 MHz
TDP
2400W
L1 Cache
64 KB (per EU)
Memory Size
128GB
Memory Type
HBM2e
Bandwidth
3205GB/s
Shader Model
6.6
Graphics Card
Release Date
Jan 2023
Generation
Data Center GPU
Type
Professional
Bus Interface
PCIe 5.0 x16
Clock Speeds
Base Clock
900 MHz
Boost Clock
1600 MHz
Memory Clock
1565 MHz
Memory
Memory Size
128GB
Memory Type
HBM2e
Memory Bus
i
8192bit
Bandwidth
i
3205GB/s
Render Config
Shading Units
i
16384
TMUs
i
1024
ROPs
i
0
Tensor Cores
i
1024
RT Cores
128
L1 Cache
64 KB (per EU)
L2 Cache
408 MB
Theoretical Performance
Pixel Rate
i
0 MPixel/s
Texture Rate
i
1638 GTexel/s
FP16 (half)
i
52.43 TFLOPS
FP32 (float)
i
52.43 TFLOPS
FP64 (double)
i
52.43 TFLOPS
Graphics Processor
GPU Name
Ponte Vecchio
Architecture
Generation 12.5
Foundry
Intel
Process Size
10 nm
Transistors
100 billion
Die Size
1280 mm²
Board Design
TDP
2400W
Suggested PSU
2800 W
Outputs
No outputs
Power Connectors
1x 16-pin
Graphics Features
DirectX
12 (12_1)
OpenGL
4.6
OpenCL
3.0
Vulkan
i
N/A
Shader Model
6.6