Radeon Instinct MI300X vs GRID A100B
We compared two Professional market GPUs: 192GB VRAM Radeon Instinct MI300X and 48GB VRAM GRID A100B to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon Instinct MI300X 's Advantages
Released 3 years and 7 months late
Boost Clock has increased by 109% (2100MHz vs 1005MHz)
More VRAM (192GB vs 48GB)
Larger VRAM bandwidth (5171GB/s vs 1866GB/s)
12544 additional rendering cores
GRID A100B 's Advantages
Lower TDP (400W vs 750W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI300X
+488%
81720
GRID A100B
13890
Graphics Card
Dec 2023
Release Date
May 2020
Radeon Instinct
Generation
GRID
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1000 MHz
Base Clock
900 MHz
2100 MHz
Boost Clock
1005 MHz
2525 MHz
Memory Clock
1215 MHz
Memory
192GB
Memory Size
48GB
HBM3
Memory Type
HBM2e
8192bit
Memory Bus
6144bit
5171GB/s
Bandwidth
1866GB/s
Render Config
304
Compute Units
-
-
SM Count
108
19456
Shading Units
6912
1216
TMUs
432
0
ROPs
192
1216
Tensor Cores
432
16 KB (per CU)
L1 Cache
192 KB (per SM)
16 MB
L2 Cache
48 MB
256 MB
L3 Cache
-
Theoretical Performance
0 MPixel/s
Pixel Rate
193.0 GPixel/s
2554 GTexel/s
Texture Rate
434.2 GTexel/s
653.7 TFLOPS
FP16 (half)
55.57 TFLOPS
81.72 TFLOPS
FP32 (float)
13.89 TFLOPS
81.72 TFLOPS
FP64 (double)
6.947 TFLOPS
Board Design
750W
TDP
400W
1150 W
Suggested PSU
800 W
No outputs
Outputs
No outputs
None
Power Connectors
None
Graphics Processor
Aqua Vanjaram
GPU Name
GA100
CDNA 3.0
Architecture
Ampere
TSMC
Foundry
TSMC
5 nm
Process Size
7 nm
153 billion
Transistors
54.2 billion
1017 mm²
Die Size
826 mm²
Graphics Features
N/A
DirectX
N/A
N/A
OpenGL
N/A
3.0
OpenCL
3.0
N/A
Vulkan
N/A
-
CUDA
8.0
N/A
Shader Model
N/A
