NVIDIA Tesla K20X vs AMD Radeon Instinct MI250X
We compared two Professional market GPUs: 6GB VRAM Tesla K20X and 128GB VRAM Radeon Instinct MI250X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla K20X 's Advantages
Lower TDP (235W vs 500W)
AMD Radeon Instinct MI250X 's Advantages
Released 9 years late
Boost Clock1700MHz
More VRAM (128GB vs 6GB)
Larger VRAM bandwidth (3277GB/s vs 249.6GB/s)
11392 additional rendering cores
Score
Benchmark
FP32 (float)
Tesla K20X
3.935 TFLOPS
Radeon Instinct MI250X
+1116%
47.87 TFLOPS
Graphics Card
Nov 2012
Release Date
Nov 2021
Tesla
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1000 MHz
-
Boost Clock
1700 MHz
1300 MHz
Memory Clock
1600 MHz
Memory
6GB
Memory Size
128GB
GDDR5
Memory Type
HBM2e
384bit
Memory Bus
8192bit
249.6GB/s
Bandwidth
3277GB/s
Render Config
-
Compute Units
220
-
-
-
2688
Shading Units
14080
224
TMUs
880
48
ROPs
0
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
16 KB (per CU)
1536 KB
L2 Cache
16 MB
-
-
-
Theoretical Performance
40.99 GPixel/s
Pixel Rate
0 MPixel/s
164.0 GTexel/s
Texture Rate
1496 GTexel/s
-
FP16 (half)
383.0 TFLOPS
3.935 TFLOPS
FP32 (float)
47.87 TFLOPS
1312 GFLOPS
FP64 (double)
47.87 TFLOPS
Board Design
235W
TDP
500W
550 W
Suggested PSU
900 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
2x 8-pin
Graphics Processor
GK110
GPU Name
Aldebaran
-
GPU Variant
Aldebaran XT
Kepler
Architecture
CDNA 2.0
TSMC
Foundry
TSMC
28 nm
Process Size
6 nm
7.08 billion
Transistors
58.2 billion
561 mm²
Die Size
Unknown
Graphics Features
12 (11_0)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.1
Vulkan
N/A
3.5
CUDA
-
5.1
Shader Model
N/A
