AMD Radeon Instinct MI250X vs NVIDIA Tesla K20m
We compared two Professional market GPUs: 128GB VRAM Radeon Instinct MI250X and 5GB VRAM Tesla K20m to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI250X 's Advantages
Released 8 years and 10 months late
Boost Clock1700MHz
More VRAM (128GB vs 5GB)
Larger VRAM bandwidth (3277GB/s vs 208.0GB/s)
11584 additional rendering cores
NVIDIA Tesla K20m 's Advantages
Lower TDP (225W vs 500W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI250X
+1258%
47.87 TFLOPS
Tesla K20m
3.524 TFLOPS
Graphics Card
Nov 2021
Release Date
Jan 2013
Radeon Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1000 MHz
Base Clock
-
1700 MHz
Boost Clock
-
1600 MHz
Memory Clock
1300 MHz
Memory
128GB
Memory Size
5GB
HBM2e
Memory Type
GDDR5
8192bit
Memory Bus
320bit
3277GB/s
Bandwidth
208.0GB/s
Render Config
220
Compute Units
-
-
-
-
14080
Shading Units
2496
880
TMUs
208
0
ROPs
40
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
16 KB (per SMX)
16 MB
L2 Cache
1280 KB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
36.71 GPixel/s
1496 GTexel/s
Texture Rate
146.8 GTexel/s
383.0 TFLOPS
FP16 (half)
-
47.87 TFLOPS
FP32 (float)
3.524 TFLOPS
47.87 TFLOPS
FP64 (double)
1175 GFLOPS
Board Design
500W
TDP
225W
900 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
Aldebaran
GPU Name
GK110
Aldebaran XT
GPU Variant
-
CDNA 2.0
Architecture
Kepler
TSMC
Foundry
TSMC
6 nm
Process Size
28 nm
58.2 billion
Transistors
7.08 billion
Unknown
Die Size
561 mm²
Graphics Features
N/A
DirectX
12 (11_0)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.1
-
CUDA
3.5
N/A
Shader Model
5.1
