NeuralScope Engineering Edition
For mobile devices, which care about battery life, we provide an engineering edition to measure how much energy has been consumed during a test application. The edition is named as "NeuralScope AI Benchmark Engineering Edition."
NeuralScope AI Benchmark Engineering Edition is a special edition that focuses helping engineers to create a better runtime for determining the power consumption for their deep learning accelerating solution. Users who wants to measure the power consumption of the deep learning applications through this engineering edition need an external power monitor. This edition has been added with idle periods between each test application in NeuralScope AI Benchmark. As shown in Figure 1., the idle periods consume very little power, where users could know the power consumption of each test application. With the idle periods, users can determine and understand when a test application starts (as Figure 2 shows) and when a test application finishes (as Figure3 shows).
Figure 1. Power measurement of NeuralScope AI benchmark with idle periods.
Figue 2. Idle to start
Figure 3. Finish to idle
This edition features the following modes:
* Small Dataset Mode - this mode will set the inference number of each test to a smaller number for quick demo purpose
* Power Measure Mode - this mode will dim the screen and minimizes the rendering frequency to create a more stable testing runtime for power measurement