scholarly journals Low-Latency SoC Design with High-Level Accelerators Specific to Sound Effects

2021 ◽  
Author(s):  
Yunus Emre ESEN ◽  
İsmail SAN
Keyword(s):  
Low Latency ◽  
Sound Effects ◽  
High Level

AIgean : An Open Framework for Deploying Machine Learning on Heterogeneous Clusters

2022 ◽  
Vol 15 (3) ◽  
pp. 1-32
Author(s):  
Naif Tarafdar ◽  
Giuseppe Di Guglielmo ◽  
Philip C. Harris ◽  
Jeffrey D. Krupa ◽  
Vladimir Loncar ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Open Source ◽  
Low Latency ◽  
Heterogeneous Cluster ◽  
Open Framework ◽  
The Neural Network ◽  
The Individual ◽  
High Level ◽  
Vivado Hls

  AIgean , pronounced like the sea, is an open framework to build and deploy machine learning (ML) algorithms on a heterogeneous cluster of devices (CPUs and FPGAs). We leverage two open source projects: Galapagos , for multi-FPGA deployment, and hls4ml , for generating ML kernels synthesizable using Vivado HLS. AIgean provides a full end-to-end multi-FPGA/CPU implementation of a neural network. The user supplies a high-level neural network description, and our tool flow is responsible for the synthesizing of the individual layers, partitioning layers across different nodes, as well as the bridging and routing required for these layers to communicate. If the user is an expert in a particular domain and would like to tinker with the implementation details of the neural network, we define a flexible implementation stack for ML that includes the layers of Algorithms, Cluster Deployment & Communication, and Hardware. This allows the user to modify specific layers of abstraction without having to worry about components outside of their area of expertise, highlighting the modularity of AIgean . We demonstrate the effectiveness of AIgean with two use cases: an autoencoder, and ResNet-50 running across 10 and 12 FPGAs. AIgean leverages the FPGA’s strength in low-latency computing, as our implementations target batch-1 implementations.

Declarative data serving

2021 ◽  
Vol 14 (11) ◽  
pp. 2555-2562
Author(s):  
Ted Shaowang ◽  
Nilesh Jain ◽  
Dennis D. Matthews ◽  
Sanjay Krishnan
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Computer Architecture ◽  
Edge Computing ◽  
Low Latency ◽  
Complex Task ◽  
Machine Learning Model ◽  
Data Flows ◽  
The Right ◽  
High Level

Recent advances in computer architecture and networking have ushered in a new age of edge computing, where computation is placed close to the point of data collection to facilitate low-latency decision making. As the complexity of such deployments grow into networks of interconnected edge devices, getting the necessary data to be in "the right place at the right time" can become a challenge. We envision a future of edge analytics where data flows between edge nodes are declaratively configured through high-level constraints. Using machine learning model-serving as a prototypical task, we illustrate how the heterogeneity and specialization of edge devices can lead to complex, task-specific communication patterns even in relatively simple situations. Without a declarative framework, managing this complexity will be challenging for developers and will lead to brittle systems. We conclude with a research vision for database community that brings our perspective to the emergent area of edge computing.

scholarly journals MOTION GRAPHIC ADVERTISING FOR LIL HAJJ WAL UMROH PROMOTION

2020 ◽  
Vol 9 (2) ◽  
pp. 123-127
Author(s):  
Ahmad Rokhi Regar
Keyword(s):  
Moving Objects ◽  
Market Competition ◽  
Production Equipment ◽  
Art Making ◽  
Target Segmentation ◽  
Sound Effects ◽  
The Face ◽  
The Media ◽  
High Level ◽  
Motion Graphic

Dewangga Lil Hajj Wal Umroh in the face of market competition, requires a promotional media with a high level of appeal for its target segmentation, and is able to represent the theme of the pilgrimage properly. Therefore we need a promotional media in the form of Motion Graphic ads. The design of this promotional media advertisement aims to create a promotional media in the form of Motion Graphic advertisement for Dewangga Lil Hajj Wal Umroh, with a persuasive message to increase Dewangga Lil Hajj Wal Umro's customers. The method of making the work of this study project includes five stages: (1) Preparatory / Prelimenary (Research of the Client, Determination of the target audience, and placement of the media); (2) Funding (Material, production, display); (3) Pre Production (Selection of production equipment, making concep art, making storyboards); (4) Production (Creating character assets and environments, moving objects / animatting, dubbing and sound effects, audio and video editing); (5) Post-production (DVD burning, exhibition). The results of this study project were two Dewangga Lil Hajj Wal Umroh Motion Graphic Ads. Work I has a duration of 1 minute 10 seconds with 9 scenes. Work II is 43 seconds long and has 10 scenes. Both of these advertisements have 1280 x 720 px video format.

Sign in / Sign up

Export Citation Format

Share Document