AMD Radeon Instinct MI100 vs Intel Data Center GPU Max Subsystem
We compared two Professional market GPUs: 32GB VRAM Radeon Instinct MI100 and 128GB VRAM Data Center GPU Max Subsystem to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI100 's Advantages
Lower TDP (300W vs 2400W)
Intel Data Center GPU Max Subsystem 's Advantages
Released 2 years and 2 months late
Boost Clock has increased by 7% (1600MHz vs 1502MHz)
More VRAM (128GB vs 32GB)
Larger VRAM bandwidth (3205GB/s vs 1229GB/s)
8704 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon Instinct MI100
23.07 TFLOPS
Data Center GPU Max Subsystem
+127%
52.43 TFLOPS
Graphics Card
Nov 2020
Release Date
Jan 2023
Radeon Instinct
Generation
Data Center GPU
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1000 MHz
Base Clock
900 MHz
1502 MHz
Boost Clock
1600 MHz
1200 MHz
Memory Clock
1565 MHz
Memory
32GB
Memory Size
128GB
HBM2
Memory Type
HBM2e
4096bit
Memory Bus
8192bit
1229GB/s
Bandwidth
3205GB/s
Render Config
120
Compute Units
-
-
-
-
7680
Shading Units
16384
480
TMUs
1024
64
ROPs
0
-
Tensor Cores
1024
-
RT Cores
128
16 KB (per CU)
L1 Cache
64 KB (per EU)
8 MB
L2 Cache
408 MB
-
-
-
Theoretical Performance
96.13 GPixel/s
Pixel Rate
0 MPixel/s
721.0 GTexel/s
Texture Rate
1638 GTexel/s
184.6 TFLOPS
FP16 (half)
52.43 TFLOPS
23.07 TFLOPS
FP32 (float)
52.43 TFLOPS
11.54 TFLOPS
FP64 (double)
52.43 TFLOPS
Board Design
300W
TDP
2400W
700 W
Suggested PSU
2800 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
Arcturus
GPU Name
Ponte Vecchio
Arcturus XL
GPU Variant
-
CDNA 1.0
Architecture
Generation 12.5
TSMC
Foundry
Intel
7 nm
Process Size
10 nm
25.6 billion
Transistors
100 billion
750 mm²
Die Size
1280 mm²
Graphics Features
N/A
DirectX
12 (12_1)
N/A
OpenGL
4.6
2.1
OpenCL
3.0
N/A
Vulkan
N/A
-
-
-
N/A
Shader Model
6.6
