AMD Instinct MI300A vs NVIDIA Tesla D870
We compared two Professional market GPUs: 128GB VRAM AMD Instinct MI300A and 1536MB VRAM Tesla D870 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Instinct MI300A 's Advantages
Released 16 years and 7 months late
Boost Clock2100MHz
More VRAM (128GB vs 1536GB)
Larger VRAM bandwidth (5300GB/s vs 76.80GB/s)
14464 additional rendering cores
NVIDIA Tesla D870 's Advantages
Lower TDP (520W vs 760W)
Score
Benchmark
FP32 (float)
AMD Instinct MI300A
+35333%
122.6 TFLOPS
Tesla D870
0.346 TFLOPS
Graphics Card
Dec 2023
Release Date
May 2007
Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 1.0 x16
Clock Speeds
1000 MHz
Base Clock
-
2100 MHz
Boost Clock
-
5200 MHz
Memory Clock
800 MHz
Memory
128GB
Memory Size
1536MB
HBM3
Memory Type
GDDR3
8192bit
Memory Bus
384bit
5300GB/s
Bandwidth
76.80GB/s
Render Config
228
Compute Units
-
-
SM Count
16
14592
Shading Units
128
880
TMUs
32
0
ROPs
24
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
-
16 MB
L2 Cache
96 KB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
14.40 GPixel/s
1496 GTexel/s
Texture Rate
38.40 GTexel/s
980.6 TFLOPS
FP16 (half)
-
122.6 TFLOPS
FP32 (float)
345.6 GFLOPS
61.3 TFLOPS
FP64 (double)
-
Board Design
760W
TDP
520W
1000 W
Suggested PSU
900 W
No outputs
Outputs
No outputs
None
Power Connectors
-
Graphics Processor
MI300
GPU Name
G80
-
-
-
CDNA 3.0
Architecture
Tesla
TSMC
Foundry
TSMC
5 nm
Process Size
90 nm
146 billion
Transistors
0.681 billion
1017 mm²
Die Size
484 mm²
Graphics Features
N/A
DirectX
11.1 (10_0)
N/A
OpenGL
3.3
3.0
OpenCL
1.1 (1.0)
N/A
Vulkan
N/A
-
CUDA
1.0
N/A
Shader Model
4.0
