Tesla K80 vs GRID M3 3020
We compared two Professional market GPUs: 12GB VRAM Tesla K80 and 4GB VRAM GRID M3 3020 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla K80 's Advantages
More VRAM (12GB vs 4GB)
Larger VRAM bandwidth (240.6GB/s vs 83.20GB/s)
1856 additional rendering cores
GRID M3 3020 's Advantages
Released 1 years and 6 months late
Boost Clock has increased by 58% (1306MHz vs 824MHz)
Score
Benchmark
FP32 (float)
Tesla K80
+145%
4113
GRID M3 3020
1672
Graphics Card
Nov 2014
Release Date
May 2016
Tesla
Generation
GRID
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
562 MHz
Base Clock
1033 MHz
824 MHz
Boost Clock
1306 MHz
1253 MHz
Memory Clock
1300 MHz
Memory
12GB
Memory Size
4GB
GDDR5
Memory Type
GDDR5
384bit
Memory Bus
128bit
240.6GB/s
Bandwidth
83.20GB/s
Render Config
2496
Shading Units
640
208
TMUs
40
48
ROPs
16
16 KB (per SMX)
L1 Cache
64 KB (per SMM)
1536 KB
L2 Cache
2 MB
Theoretical Performance
42.85 GPixel/s
Pixel Rate
20.90 GPixel/s
171.4 GTexel/s
Texture Rate
52.24 GTexel/s
4.113 TFLOPS
FP32 (float)
1.672 TFLOPS
1371 GFLOPS
FP64 (double)
52.24 GFLOPS
Board Design
300W
TDP
Unknown
700 W
Suggested PSU
200 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
GK210
GPU Name
GM107
GK210-885-A1
GPU Variant
-
Kepler 2.0
Architecture
Maxwell
TSMC
Foundry
TSMC
28 nm
Process Size
28 nm
7.1 billion
Transistors
1.87 billion
561 mm²
Die Size
148 mm²
Graphics Features
12 (11_1)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.7
CUDA
5.0
5.1
Shader Model
6.7 (5.1)
