Jure Vreča

Mr. Jure Vreča

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 September 2020 in IEEE Access
Verified
Journal Article
Open access
JVJure Vreča
Jure Vreča
KSKarl J. X. Sturm
Karl J. X. Sturm
EGErnest Gungl
Ernest Gungl
FMFarhad Merchant
Farhad Merchant
PBPaolo Bientinesi
Paolo Bientinesi
ZBZmago Brezočnik
Zmago Brezočnik
Deep learning algorithms have seen success in a wide variety of applications, such as machine translation, image and speech recognition, and self-driving cars. However, these algorithms have only recently gained a foothold in the embedded systems domain. Most embedded systems are based on cheap microcontrollers with limited memory capacity, and, thus, are typically seen as not capable of running deep learning algorithms. Nevertheless, we consider that advancements in compression of neural networks and neural network architecture, coupled with an optimized instruction set architecture, could make microcontroller-grade processors suitable for specific low-intensity deep learning applications. We propose a simple instruction set extension with two main components—hardware loops and dot product instructions. To evaluate the effectiveness of the extension, we developed optimized assembly functions for the fully connected and convolutional neural network layers. When using the extensions and the optimized assembly functions, we achieve an average clock cycle count decrease of 73% for a small scale convolutional neural network. On a per layer base, our optimizations decrease the clock cycle count for fully connected layers and convolutional layers by 72% and 78%, respectively. The average energy consumption per inference decreases by 73%.We have shown that adding just hardware loops and dot product instructions has a significant positive effect on processor efficiency in computing neural network functions.

24 February 2024 in Electronics
Verified
Journal Article
Open access
PDF file
JVJure Vreča
Jure Vreča
Ratko PilipovićRatko Pilipović
Ratko Pilipović
ABAnton Biasizzo
Anton Biasizzo
Keyword spotting is an important part of modern speech recognition pipelines. Typical contemporary keyword-spotting systems are based on Mel-Frequency Cepstral Coefficient (MFCC) audio features, which are relatively complex to compute. Considering the always-on nature of many keyword-spotting systems, it is prudent to optimize this part of the detection pipeline. We explore the simplifications of the MFCC audio features and derive a simplified version that can be more easily used in embedded applications. Additionally, we implement a hardware generator that generates an appropriate hardware pipeline for the simplified audio feature extraction. Using Chisel4ml framework, we integrate hardware generators into Python-based Keras framework, which facilitates the training process of the machine learning models using our simplified audio features.

21 February 2025 in Electronics
Verified
Journal Article
Open access
PDF file
JVJure Vreča
Jure Vreča
ABAnton Biasizzo
Anton Biasizzo
Deploying deeply quantized neural networks on FPGA devices can be a time-consuming task. This has led to research on tools to automate this procedure, specifically for the case of fast machine learning. This is a specialized field concerned with the very low latency processing of machine learning algorithms as opposed to the more usual task where throughput is the main goal. Existing automated solutions are mainly based on high-level synthesis, which tends to be inefficient for larger neural networks due to the use of polynomial time algorithms. In this paper, we present chisel4ml, a tool for generating fully parallel and very low latency hardware implementations of deeply quantized neural networks for FPGA devices. The circuits generated by chisel4ml utilize up to 40% fewer look-up tables for a reasonably sized neural network compared to fully parallel implementations based on high-level synthesis. As chisel4ml uses structural descriptions of deeply quantized neural networks in the form of Chisel generators, it is able to generate the hardware in two orders of magnitude less time than solutions based on high-level synthesis.