AMD Instinct MI300A vs NVIDIA Tesla S1070
We compared two Professional market GPUs: 128GB VRAM AMD Instinct MI300A and 4GB VRAM Tesla S1070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Instinct MI300A 's Advantages
Released 15 years and 6 months late
Boost Clock2100MHz
More VRAM (128GB vs 4GB)
Larger VRAM bandwidth (5300GB/s vs 102.4GB/s)
14352 additional rendering cores
Lower TDP (760W vs 800W)
Score
Benchmark
FP32 (float)
AMD Instinct MI300A
+19610%
122.6 TFLOPS
Tesla S1070
0.622 TFLOPS
Graphics Card
Dec 2023
Release Date
Jun 2008
Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1000 MHz
Base Clock
-
2100 MHz
Boost Clock
-
5200 MHz
Memory Clock
800 MHz
Memory
128GB
Memory Size
4GB
HBM3
Memory Type
GDDR3
8192bit
Memory Bus
512bit
5300GB/s
Bandwidth
102.4GB/s
Render Config
228
Compute Units
-
-
SM Count
30
14592
Shading Units
240
880
TMUs
80
0
ROPs
32
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
-
16 MB
L2 Cache
256 KB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
19.52 GPixel/s
1496 GTexel/s
Texture Rate
48.80 GTexel/s
980.6 TFLOPS
FP16 (half)
-
122.6 TFLOPS
FP32 (float)
622.1 GFLOPS
61.3 TFLOPS
FP64 (double)
77.76 GFLOPS
Board Design
760W
TDP
800W
1000 W
Suggested PSU
1200 W
No outputs
Outputs
No outputs
None
Power Connectors
-
Graphics Processor
MI300
GPU Name
GT200B
-
-
-
CDNA 3.0
Architecture
Tesla 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
55 nm
146 billion
Transistors
1.4 billion
1017 mm²
Die Size
470 mm²
Graphics Features
N/A
DirectX
11.1 (10_0)
N/A
OpenGL
3.3
3.0
OpenCL
1.1
N/A
Vulkan
N/A
-
CUDA
1.3
N/A
Shader Model
4.0
