AMD Radeon Instinct MI60 vs Intel Data Center GPU Max Subsystem
GPU Specs Compare
Graphics Card
Release Date
Nov 2018
Jan 2023
Generation
Radeon Instinct
Data Center GPU
Type
Professional
Professional
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1200 MHz
900 MHz
Boost Clock
1800 MHz
1600 MHz
Memory Clock
1000 MHz
1565 MHz
Memory
Memory Size
32GB
128GB
Memory Type
HBM2
HBM2e
Memory Bus
4096bit
8192bit
Bandwidth
1024GB/s
3205GB/s
Render Config
Compute Units
64
-
Shading Units
4096
16384
TMUs
256
1024
ROPs
64
0
L1 Cache
16 KB (per CU)
64 KB (per EU)
L2 Cache
4 MB
408 MB
Tensor Cores
-
1024
RT Cores
-
128
Theoretical Performance
Pixel Rate
115.2 GPixel/s
0 MPixel/s
Texture Rate
460.8 GTexel/s
1638 GTexel/s
FP16 (half)
29.49 TFLOPS
52.43 TFLOPS
FP32 (float)
14.75 TFLOPS
52.43 TFLOPS
FP64 (double)
7.373 TFLOPS
52.43 TFLOPS
Graphics Processor
GPU Name
Vega 20
Ponte Vecchio
GPU Variant
Vega 20 GL
-
Architecture
GCN 5.1
Generation 12.5
Foundry
TSMC
Intel
Process Size
7 nm
10 nm
Transistors
13.23 billion
100 billion
Die Size
331 mm²
1280 mm²
Board Design
TDP
300W
2400W
Suggested PSU
700 W
2800 W
Outputs
1x mini-DisplayPort 1.4a
No outputs
Power Connectors
1x 6-pin + 1x 8-pin
1x 16-pin
Graphics Features
DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.2
N/A
Shader Model
6.4
6.6