AMD Radeon Instinct MI8 vs AMD Radeon Instinct MI100
We compared two Professional market GPUs: 4GB VRAM Radeon Instinct MI8 and 32GB VRAM Radeon Instinct MI100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI8 's Advantages
Lower TDP (175W vs 300W)
AMD Radeon Instinct MI100 's Advantages
Released 3 years and 11 months late
Boost Clock1502MHz
More VRAM (32GB vs 4GB)
Larger VRAM bandwidth (1229GB/s vs 512.0GB/s)
3584 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon Instinct MI8
8.192 TFLOPS
Radeon Instinct MI100
+181%
23.07 TFLOPS
Graphics Card
Dec 2016
Release Date
Nov 2020
Radeon Instinct
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1000 MHz
-
Boost Clock
1502 MHz
500 MHz
Memory Clock
1200 MHz
Memory
4GB
Memory Size
32GB
HBM
Memory Type
HBM2
4096bit
Memory Bus
4096bit
512.0GB/s
Bandwidth
1229GB/s
Render Config
64
Compute Units
120
-
-
-
4096
Shading Units
7680
256
TMUs
480
64
ROPs
64
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
16 KB (per CU)
2 MB
L2 Cache
8 MB
-
-
-
Theoretical Performance
64.00 GPixel/s
Pixel Rate
96.13 GPixel/s
256.0 GTexel/s
Texture Rate
721.0 GTexel/s
8.192 TFLOPS
FP16 (half)
184.6 TFLOPS
8.192 TFLOPS
FP32 (float)
23.07 TFLOPS
512.0 GFLOPS
FP64 (double)
11.54 TFLOPS
Board Design
175W
TDP
300W
450 W
Suggested PSU
700 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
2x 8-pin
Graphics Processor
Fiji
GPU Name
Arcturus
Fiji XT CA
(215-0862120)
GPU Variant
Arcturus XL
GCN 3.0
Architecture
CDNA 1.0
TSMC
Foundry
TSMC
28 nm
Process Size
7 nm
8.9 billion
Transistors
25.6 billion
596 mm²
Die Size
750 mm²
Graphics Features
12 (12_0)
DirectX
N/A
4.6
OpenGL
N/A
2.1
OpenCL
2.1
1.2.170
Vulkan
N/A
-
-
-
6.5
Shader Model
N/A
