Which AI models can run at the Very Edge? Artificial Intelligent (AI) has already become pervasive in our everyday life. Nowadays, we are surrounded by numerous intelligent agents that support the human decision process based on real-time data. Typically, our personal data sensed through our own devices, e.g. smartwatches and smartphones, flows to [...]
GVSOC The Full System Simulator for profiling GAP Applications https://youtu.be/XpoeASt8Alo GVSOC is functionally equivalent to the real chip. The compiled code that can run on the chip will also run as it is on the simulator. To properly profile applications, it contains timing models to properly report performance within [...]
Visual Wakewords on GAP8 Sample trace of execution of visual wake words network In the latest GAP SDK, released on the 7th February 2020, we have included a GAPflow example that converts the winner of the Google Visual Wake Words challenge to a working model on GAP8. [...]
Face Identification on mW power budget using GAP8 Face Identification has attracted a lot of press relating to uses in security applications. It is, however, an interesting feature in many applications. Identifying the owner of a device versus another person can have many uses in creating user experiences. [...]
New GAP8 SDK V3.0 release from GreenWaves Technologies NEW FEATURES NNTool New flow for neural networks which is replacing tf2gap8. This allows mapping high-level graphs (e.g. from Keras) directly to gap8 with automatic quantization. PMSIS New system layer to have portable Gap applications accross several operating systems. This comes [...]
GAPPoc : A family of GAP8-centric Proof Of Concept boards for edge AI Our GAP8 application processor chip is great at analyzing and understanding data from IoT sensors, from the simplest to the most complex, in a very tight power envelope – from a few tens of milliwatt in active [...]
GAP8 CNN Benchmarks The GAP8 CNN Benchmark package provides a test suite to evaluate the performance and energy efficiency of GAP8's cluster on a representative subset of Convolution Neural Networks (CNN) Layers. This guide shows you how to run the benchmarks and check cycle and energy results. Benchmarks Description Here [...]
New GAP8 SDK release from GreenWaves Technologies Release V2.1 of the GAP8 SDK is now available on Github athttps://github.com/GreenWaves-Technologies/gap_sdkThe headline changes in this SDK are …- The addition of an instruction accurate simulator for GAP8 based on the PULP GVSOC project. This simulator greatly simplifies development by allowing code to be [...]
Loic Lietar, CEO of GreenWaves Technologies, talks about GAP8, and RISC-V on IoT PodCast This week Loic Lietar, CEO of Greenwaves Technologies, talked about the new open-source RISC-V architecture and low-power IoT processor GAP8. Lietar explained what RISC-V is, how difficult it is to get the industry to adopt [...]
A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones Really interesting paper by Daniele Palossi on using GAP8 to autonomously navigate a microdrone. This is a great example of porting a significant CNN to GAP8. Eric Flamand, GreenWave's CTO assisted with the CNN model creation and use of [...]
