AMD Instinct MI300A vs NVIDIA Tesla M40
We compared two Professional market GPUs: 128GB VRAM AMD Instinct MI300A and 12GB VRAM Tesla M40 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Instinct MI300A 's Advantages
Released 8 years and 1 months late
Boost Clock has increased by 89% (2100MHz vs 1112MHz)
More VRAM (128GB vs 12GB)
Larger VRAM bandwidth (5300GB/s vs 288.4GB/s)
11520 additional rendering cores
NVIDIA Tesla M40 's Advantages
Lower TDP (250W vs 760W)
Score
Benchmark
FP32 (float)
AMD Instinct MI300A
+1694%
122.6 TFLOPS
Tesla M40
6.832 TFLOPS
Graphics Card
Dec 2023
Release Date
Nov 2015
Instinct
Generation
Tesla Maxwell
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1000 MHz
Base Clock
948 MHz
2100 MHz
Boost Clock
1112 MHz
5200 MHz
Memory Clock
1502 MHz
Memory
128GB
Memory Size
12GB
HBM3
Memory Type
GDDR5
8192bit
Memory Bus
384bit
5300GB/s
Bandwidth
288.4GB/s
Render Config
228
Compute Units
-
-
-
-
14592
Shading Units
3072
880
TMUs
192
0
ROPs
96
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
48 KB (per SMM)
16 MB
L2 Cache
3 MB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
106.8 GPixel/s
1496 GTexel/s
Texture Rate
213.5 GTexel/s
980.6 TFLOPS
FP16 (half)
-
122.6 TFLOPS
FP32 (float)
6.832 TFLOPS
61.3 TFLOPS
FP64 (double)
213.5 GFLOPS
Board Design
760W
TDP
250W
1000 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
None
Power Connectors
8-pin EPS
Graphics Processor
MI300
GPU Name
GM200
-
GPU Variant
GM200-895-A1
CDNA 3.0
Architecture
Maxwell 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
28 nm
146 billion
Transistors
8 billion
1017 mm²
Die Size
601 mm²
Graphics Features
N/A
DirectX
12 (12_1)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
5.2
N/A
Shader Model
6.7
