Tesla K20s vs Radeon Instinct MI6
We compared two Professional market GPUs: 5GB VRAM Tesla K20s and 8GB VRAM Radeon Instinct MI6 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla K20s 's Advantages
192 additional rendering cores
Radeon Instinct MI6 's Advantages
Released 3 years and 10 months late
Boost Clock1233MHz
More VRAM (8GB vs 5GB)
Larger VRAM bandwidth (224.0GB/s vs 208.0GB/s)
Lower TDP (150W vs 225W)
Score
Benchmark
FP32 (float)
Tesla K20s
2870
Radeon Instinct MI6
+97%
5682
Graphics Card
Feb 2013
Release Date
Dec 2016
Tesla
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
Base Clock
1120 MHz
-
Boost Clock
1233 MHz
1300 MHz
Memory Clock
1750 MHz
Memory
5GB
Memory Size
8GB
GDDR5
Memory Type
GDDR5
320bit
Memory Bus
256bit
208.0GB/s
Bandwidth
224.0GB/s
Render Config
-
Compute Units
36
2496
Shading Units
2304
208
TMUs
144
40
ROPs
32
16 KB (per SMX)
L1 Cache
16 KB (per CU)
1280 KB
L2 Cache
2 MB
Theoretical Performance
29.90 GPixel/s
Pixel Rate
39.46 GPixel/s
119.6 GTexel/s
Texture Rate
177.6 GTexel/s
-
FP16 (half)
5.682 TFLOPS
2.870 TFLOPS
FP32 (float)
5.682 TFLOPS
956.8 GFLOPS
FP64 (double)
355.1 GFLOPS
Board Design
225W
TDP
150W
550 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
-
Power Connectors
1x 6-pin
Graphics Processor
GK110
GPU Name
Ellesmere
-
GPU Variant
Ellesmere XT
Kepler
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
28 nm
Process Size
14 nm
7.08 billion
Transistors
5.7 billion
561 mm²
Die Size
232 mm²
Graphics Features
12 (11_0)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.1
Vulkan
1.2
3.5
CUDA
-
5.1
Shader Model
6.4
