GPU Wiki
Compare GPUs
Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.
Popular comparisons
| Spec | Data Center GPU Max Subsystem Intel |
|---|---|
| Overview | |
| Product name | Intel Data Center GPU Max Subsystem |
| Architecture | Generation 12.5 |
| Generation / family | Data Center GPU Max Series |
| Launch date | 2023-01-10 |
| Market segment | Data Center |
| Board type / entry type | Data Center GPU |
| GPU | |
| Process node | Intel 10 nm |
| Die size | 1280 mm² |
| Transistor count | 100 billion |
| GPU chip | Ponte Vecchio |
| Execution Units | 16384 |
| RT Units | 128 |
| TMUs | 1024 |
| Clocks | |
| Base / Core clock | 900 MHz |
| Boost clock | 1,600 MHz |
| Memory clock | 1,565 MHz |
| Memory | |
| Memory size | 128 GB |
| Memory type | HBM2e |
| Memory bus width | 8192-bit |
| Memory bandwidth | 3210 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 5.0 x16 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 2400 W |
| Recommended PSU | 2800 W |
| Slot width | Dual-slot |
| Features | |
| DirectX support | DirectX 12.1 |
| OpenGL support | OpenGL 4.6 |
| Shader Model | 6.6 |
| Ray tracing support | Hardware RT units present |
| Performance / Benchmarks | |
| FP32 throughput | 52.43 TFLOPS |
| FP16 throughput | 52.43 TFLOPS |
Overview
Product name
Data Center GPU Max Subsystem (Intel)
Intel Data Center GPU Max Subsystem
Architecture
Data Center GPU Max Subsystem (Intel)
Generation 12.5
Generation / family
Data Center GPU Max Subsystem (Intel)
Data Center GPU Max Series
Launch date
Data Center GPU Max Subsystem (Intel)
2023-01-10
Market segment
Data Center GPU Max Subsystem (Intel)
Data Center
Board type / entry type
Data Center GPU Max Subsystem (Intel)
Data Center GPU
GPU
Process node
Data Center GPU Max Subsystem (Intel)
Intel 10 nm
Die size
Data Center GPU Max Subsystem (Intel)
1280 mm²
Transistor count
Data Center GPU Max Subsystem (Intel)
100 billion
GPU chip
Data Center GPU Max Subsystem (Intel)
Ponte Vecchio
Execution Units
Data Center GPU Max Subsystem (Intel)
16384
RT Units
Data Center GPU Max Subsystem (Intel)
128
TMUs
Data Center GPU Max Subsystem (Intel)
1024
Clocks
Base / Core clock
Data Center GPU Max Subsystem (Intel)
900 MHz
Boost clock
Data Center GPU Max Subsystem (Intel)
1,600 MHz
Memory clock
Data Center GPU Max Subsystem (Intel)
1,565 MHz
Memory
Memory size
Data Center GPU Max Subsystem (Intel)
128 GB
Memory type
Data Center GPU Max Subsystem (Intel)
HBM2e
Memory bus width
Data Center GPU Max Subsystem (Intel)
8192-bit
Memory bandwidth
Data Center GPU Max Subsystem (Intel)
3210 GB/s
Bus / Interface
Bus interface
Data Center GPU Max Subsystem (Intel)
PCIe 5.0 x16
AGP / PCI / PCIe distinction
Data Center GPU Max Subsystem (Intel)
PCIe
Power
TDP / TBP / board power
Data Center GPU Max Subsystem (Intel)
2400 W
Recommended PSU
Data Center GPU Max Subsystem (Intel)
2800 W
Slot width
Data Center GPU Max Subsystem (Intel)
Dual-slot
Features
DirectX support
Data Center GPU Max Subsystem (Intel)
DirectX 12.1
OpenGL support
Data Center GPU Max Subsystem (Intel)
OpenGL 4.6
Shader Model
Data Center GPU Max Subsystem (Intel)
6.6
Ray tracing support
Data Center GPU Max Subsystem (Intel)
Hardware RT units present
Performance / Benchmarks
FP32 throughput
Data Center GPU Max Subsystem (Intel)
52.43 TFLOPS
FP16 throughput
Data Center GPU Max Subsystem (Intel)
52.43 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
Frame rates compare runs of the same game at the same quality preset on one test system. DLAA counts as native resolution, because it applies anti-aliasing at full render resolution rather than upscaling; DLSS and FSR upscaling are never counted as native. Where a capture named ray tracing without a readable on or off value, it is read as on.