Product Compare

Intel Data Center GPU Max Subsystem vs AMD Radeon Vega 8 Mobile

GPU GPU
Graphics Card
Release Date Jan 2023 Jan 2021
Generation Data Center GPU Cezanne
Type Professional Integrated
Bus Interface PCIe 5.0 x16 IGP
Clock Speeds
Base Clock 900 MHz 300 MHz
Boost Clock 1600 MHz 2000 MHz
Memory Clock 1565 MHz System Shared
Memory
Memory Size 128GB System Shared
Memory Type HBM2e System Shared
Memory Bus 8192bit System Shared
Bandwidth 3205GB/s System Dependent
Render Config
Shading Units 16384 512
TMUs 1024 32
ROPs 0 8
Tensor Cores 1024
RT Cores 128
L1 Cache 64 KB (per EU)
L2 Cache 408 MB
Compute Units 8
Theoretical Performance
Pixel Rate 0 MPixel/s 16.00 GPixel/s
Texture Rate 1638 GTexel/s 64.00 GTexel/s
FP16 (half) 52.43 TFLOPS 4.096 TFLOPS
FP32 (float) 52.43 TFLOPS 2.048 TFLOPS
FP64 (double) 52.43 TFLOPS 128.0 GFLOPS
Graphics Processor
GPU Name Ponte Vecchio Cezanne
Architecture Generation 12.5 GCN 5.1
Foundry Intel TSMC
Process Size 10 nm 7 nm
Transistors 100 billion 9.8 billion
Die Size 1280 mm² 156 mm²
Board Design
TDP 2400W 45W
Suggested PSU 2800 W
Outputs No outputs No outputs
Power Connectors 1x 16-pin None
Graphics Features
DirectX 12 (12_1) 12 (12_1)
OpenGL 4.6 4.6
OpenCL 3.0 2.1
Vulkan N/A 1.2
Shader Model 6.6 6.4