Intel Data Center GPU Max Subsystem vs AMD Radeon Instinct MI100
GPU Specs Compare
Graphics Card
Release Date
Jan 2023
Nov 2020
Generation
Data Center GPU
Radeon Instinct
Type
Professional
Professional
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
900 MHz
1000 MHz
Boost Clock
1600 MHz
1502 MHz
Memory Clock
1565 MHz
1200 MHz
Memory
Memory Size
128GB
32GB
Memory Type
HBM2e
HBM2
Memory Bus
8192bit
4096bit
Bandwidth
3205GB/s
1229GB/s
Render Config
Shading Units
16384
7680
TMUs
1024
480
ROPs
0
64
Tensor Cores
1024
-
RT Cores
128
-
L1 Cache
64 KB (per EU)
16 KB (per CU)
L2 Cache
408 MB
8 MB
Compute Units
-
120
Theoretical Performance
Pixel Rate
0 MPixel/s
96.13 GPixel/s
Texture Rate
1638 GTexel/s
721.0 GTexel/s
FP16 (half)
52.43 TFLOPS
184.6 TFLOPS
FP32 (float)
52.43 TFLOPS
23.07 TFLOPS
FP64 (double)
52.43 TFLOPS
11.54 TFLOPS
Graphics Processor
GPU Name
Ponte Vecchio
Arcturus
Architecture
Generation 12.5
CDNA 1.0
Foundry
Intel
TSMC
Process Size
10 nm
7 nm
Transistors
100 billion
25.6 billion
Die Size
1280 mm²
750 mm²
GPU Variant
-
Arcturus XL
Board Design
TDP
2400W
300W
Suggested PSU
2800 W
700 W
Outputs
No outputs
No outputs
Power Connectors
1x 16-pin
2x 8-pin
Graphics Features
DirectX
12 (12_1)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
2.1
Vulkan
N/A
N/A
Shader Model
6.6
N/A