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 Flex 170 Intel |
|---|---|
| Overview | |
| Product name | Intel Data Center GPU Flex 170 |
| Architecture | Xe-HPG |
| Generation / family | Arc A Series |
| Launch date | 2022-08-24 |
| Market segment | Data Center |
| Board type / entry type | Data Center GPU |
| GPU | |
| Process node | TSMC 6 nm |
| Die size | 406 mm² |
| Transistor count | 21.7 billion |
| GPU chip | DG2-512 |
| Execution Units | 4096 |
| RT Units | 32 |
| ROPs | 128 |
| TMUs | 256 |
| Clocks | |
| Base / Core clock | 1,950 MHz |
| Boost clock | 2,050 MHz |
| Memory clock | 2,000 MHz |
| Memory | |
| Memory size | 16 GB |
| Memory type | GDDR6 |
| Memory bus width | 256-bit |
| Memory bandwidth | 512 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 4.0 x16 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 150 W |
| Recommended PSU | 450 W |
| Slot width | Dual-slot |
| Display / Media | |
| Display outputs | 1x HDMI 2.1, 3x DisplayPort 2.0 |
| Features | |
| DirectX support | DirectX 12.2 |
| OpenGL support | OpenGL 4.6 |
| Vulkan support | Vulkan 1.4 |
| Shader Model | 6.6 |
| Ray tracing support | Hardware RT units present |
| Performance / Benchmarks | |
| FP32 throughput | 16.79 TFLOPS |
| FP16 throughput | 33.59 TFLOPS |
Overview
Product name
Data Center GPU Flex 170 (Intel)
Intel Data Center GPU Flex 170
Architecture
Data Center GPU Flex 170 (Intel)
Xe-HPG
Generation / family
Data Center GPU Flex 170 (Intel)
Arc A Series
Launch date
Data Center GPU Flex 170 (Intel)
2022-08-24
Market segment
Data Center GPU Flex 170 (Intel)
Data Center
Board type / entry type
Data Center GPU Flex 170 (Intel)
Data Center GPU
GPU
Process node
Data Center GPU Flex 170 (Intel)
TSMC 6 nm
Die size
Data Center GPU Flex 170 (Intel)
406 mm²
Transistor count
Data Center GPU Flex 170 (Intel)
21.7 billion
GPU chip
Data Center GPU Flex 170 (Intel)
DG2-512
Execution Units
Data Center GPU Flex 170 (Intel)
4096
RT Units
Data Center GPU Flex 170 (Intel)
32
ROPs
Data Center GPU Flex 170 (Intel)
128
TMUs
Data Center GPU Flex 170 (Intel)
256
Clocks
Base / Core clock
Data Center GPU Flex 170 (Intel)
1,950 MHz
Boost clock
Data Center GPU Flex 170 (Intel)
2,050 MHz
Memory clock
Data Center GPU Flex 170 (Intel)
2,000 MHz
Memory
Memory size
Data Center GPU Flex 170 (Intel)
16 GB
Memory type
Data Center GPU Flex 170 (Intel)
GDDR6
Memory bus width
Data Center GPU Flex 170 (Intel)
256-bit
Memory bandwidth
Data Center GPU Flex 170 (Intel)
512 GB/s
Bus / Interface
Bus interface
Data Center GPU Flex 170 (Intel)
PCIe 4.0 x16
AGP / PCI / PCIe distinction
Data Center GPU Flex 170 (Intel)
PCIe
Power
TDP / TBP / board power
Data Center GPU Flex 170 (Intel)
150 W
Recommended PSU
Data Center GPU Flex 170 (Intel)
450 W
Slot width
Data Center GPU Flex 170 (Intel)
Dual-slot
Display / Media
Display outputs
Data Center GPU Flex 170 (Intel)
1x HDMI 2.1, 3x DisplayPort 2.0
Features
DirectX support
Data Center GPU Flex 170 (Intel)
DirectX 12.2
OpenGL support
Data Center GPU Flex 170 (Intel)
OpenGL 4.6
Vulkan support
Data Center GPU Flex 170 (Intel)
Vulkan 1.4
Shader Model
Data Center GPU Flex 170 (Intel)
6.6
Ray tracing support
Data Center GPU Flex 170 (Intel)
Hardware RT units present
Performance / Benchmarks
FP32 throughput
Data Center GPU Flex 170 (Intel)
16.79 TFLOPS
FP16 throughput
Data Center GPU Flex 170 (Intel)
33.59 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.