GeekRadar / The comparison desk
COMPARE.
GPUAdvantech EAI-3100
Graphics processor
- Video memory
- 4 GB*
- Memory bus
- 64 bit*
- Rated memory bandwidth
- 112 GB/s*
No matched benchmark results are available for this entry yet.
Processing & platform
- Architecture
- Xe-HPG*
- Process node
- 6 nm*
- GPU cores
- 1,024*
- Graphics interface
- PCIe 4.0 x8*
- Reported chip die area
- 157 mm²*
- Transistors
- 7,200 million*
- GPU L2 cache
- 4 MB*
- Graphics processor
- DG2*
- Texture mapping units
- 64*
- Raster output units
- 32*
- Ray tracing cores
- 8*
- Chip foundry
- TSMC*
- Card or module format
- Dual-slot*
- Declared GPU TDP
- 60 W*
- External power connectors
- 1x 8-pin*
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenGL
- 4.6*
- OpenCL
- 3.0*
- Vulkan
- 1.4*
- Shader model
- 6.6*
Memory & storage
- Memory options
- 4*
- Video memory
- 4 GB*
- Video memory type
- GDDR6*
- Memory bus
- 64 bit*
- Rated memory bandwidth
- 112 GB/s*
Power specifications
- Thermal design power
- 60 W*
System configuration
Detailed specifications
Specifications 1 · 26 fields
- proc transistors
- 7,200 million*
- proc die size
- 157* mm²
- cores
- 1,024*
- rt cores
- 8*
- base clock
- 1,550*
- boost clock
- 2,050*
- memory clock
- 1,750*
- ram
- 4*
- name
- Advantech EAI-3100*
- ram type
- GDDR6*
- bus width
- 64*
- bus interface
- PCIe 4.0 x8*
- ram bandwidth
- 112* GB/s
- fp16 performance
- 8.397*
- fp32 performance
- 4.198*
- fp64 performance
- 1.0496*
- tdp
- 60* W
- slot width
- Dual-slot*
- power connectors
- 1x 8-pin*
- is retail board
- Yes*
- gpi value
- 2.56*
- manufacturer
- ADVANTECH*
- arch name
- Xe-HPG*
- card release date
- 2022-03-30*
- proc foundry
- TSMC*
- proc process size
- 6* nm
Specifications 2 · 34 fields
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenCL
- 3.0*
- OpenGL
- 4.6*
- Shader model
- 6.6*
- Vulkan
- 1.4*
- Reported theoretical BF16 peak
- 4.198* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Graphics interface
- PCIe 4.0 x8*
- Memory bus
- 64* bit
- Reported shader processors
- 1,024*
- Reported theoretical FP16 peak
- 8.397* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP32 peak
- 4.198* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Declared GPU L2 cache
- 4 MB*
- Reported display outputs
- Active
- 2x HDMI 2.1, 2x DisplayPort 2.0*
- Struck-out declarations
- Portable Device Dependent*
- Theoretical pixel fill rate
- 65.60 GPixel/s*
- External power connectors
- 1x 8-pin*
- Reported chip die area
- 157 mm²*
- Chip foundry
- TSMC*
- Process node declaration
- 6 nm*
- Transistors
- 7,200 million*
- Graphics processor
- DG2*
- Reported video memory
- 4* GB
- Rated memory bandwidth
- 112.0 GB/s*
- Video memory type
- GDDR6*
- Raster output units
- 32*
- Ray tracing cores
- 8*
- Reported shading units
- 1,024*
- Card or module format
- Dual-slot*
- 2:4 tensor sparsity
- No*
- Declared GPU TDP
- 60 W*
- Theoretical texture fill rate
- 131.2 GTexel/s*
- Texture mapping units
- 64*
- GPU cores
- 1,024*
- Video memory
- 4* GB
- Video memory type
- GDDR6*
0 selected Compare 0
* Provisional data