AMD Instinct MI300A vs NVIDIA GRID A100A
We compared two Professional market GPUs: 128GB VRAM AMD Instinct MI300A and 48GB VRAM GRID A100A to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Instinct MI300A 's Advantages
Released 3 years and 7 months late
Boost Clock has increased by 109% (2100MHz vs 1005MHz)
More VRAM (128GB vs 48GB)
Larger VRAM bandwidth (5300GB/s vs 1866GB/s)
7680 additional rendering cores
NVIDIA GRID A100A 's Advantages
Lower TDP (400W vs 760W)
Score
Benchmark
FP32 (float)
AMD Instinct MI300A
+782%
122.6 TFLOPS
GRID A100A
13.89 TFLOPS
Graphics Card
Dec 2023
Release Date
May 2020
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
5200 MHz
Memory Clock
1215 MHz
Memory
128GB
Memory Size
48GB
HBM3
Memory Type
HBM2e
8192bit
Memory Bus
6144bit
5300GB/s
Bandwidth
1866GB/s
Render Config
228
Compute Units
-
-
SM Count
108
14592
Shading Units
6912
880
TMUs
432
0
ROPs
192
-
Tensor Cores
432
-
-
-
16 KB (per CU)
L1 Cache
192 KB (per SM)
16 MB
L2 Cache
48 MB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
193.0 GPixel/s
1496 GTexel/s
Texture Rate
434.2 GTexel/s
980.6 TFLOPS
FP16 (half)
55.57 TFLOPS
122.6 TFLOPS
FP32 (float)
13.89 TFLOPS
61.3 TFLOPS
FP64 (double)
6.947 TFLOPS
Board Design
760W
TDP
400W
1000 W
Suggested PSU
800 W
No outputs
Outputs
No outputs
None
Power Connectors
None
Graphics Processor
MI300
GPU Name
GA100
-
-
-
CDNA 3.0
Architecture
Ampere
TSMC
Foundry
TSMC
5 nm
Process Size
7 nm
146 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
