Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 26 for “"HW-SW Co-Design"”.
-
Middle-ware pro HW/SW co-design
Práce se zabývá návrhem a implementací nové verze serveru Middleware a komunikační knihovny. Nová verze využívá návrhový vzor Reaktor pro obsluhu požadavků z různých zdrojů. Práce popisuje platformně nezávislé řešení logování zpráv, spouštění a ovládání procesů, zápisu cest k souborům a návrhu …
-
Využití linuxových kontejnerů v HW/SW co-design
Tato práce pojednává o možnostech nahrazení klasických virtuálních strojů linuxovými kontejnery. Cílem je vytvořit funkční systém ke spouštění paralelních úloh, které mají předchystané prostředí a slouží k testování a buildu softwaru. Pro kontejnerizaci byla zvolena platforma Docker, která je …
-
HW-SW co-design techniques for modern programming languages
DSpace SAF Submission Ingestion Package generated from Vireo submission #13218 on 2019-02-05 at 11:15:13
-
List scheduling and simulated annealing in a HW/SW co-design environment
For decades combinatorial problems have been studied in numerous disciplines. The scheduling problem, in which finding the optimal solution cannot be defined in a polynomial time, belongs to this type of problem. Several methodologies for the scheduling problem have been described in order to …
-
Applied HW/SW Co-design: Using the Kendall Tau Algorithm for Adaptive Pacing
Microcontrollers, the brains of embedded systems, have found their way into every aspect of our lives including medical devices such as pacemakers. Pacemakers provide life supporting functions to people therefore it is critical for these devices to meet their timing constraints. This thesis …
-
Parallel code-specific CPU simulation with dynamic phase convergence modeling for HW/SW co-design
… models provide a promising solution to the complex problem of HW/SW co-design within the system-on-chip paradigm, such requires a detailed annotation of transaction level energy and performance data within the model. While this data can be obtained through source code profiling of an …
-
Using scripting languages for hardware/software co-design
… processor Intellectual Property (IP) core and several other hardware blocks, attached as custom co-processors or peripheral units to the processor's main data and control bus. Such a complex architecture can take advantage of the reconfigurable, fast parallel processing and low power …
-
Automated communication and floorplan-aware hardware/software co-design for SoC
The main objective of modern SoC (system-on-chip) designs is to achieve high-performance while maintaining low power consumption and resource usage. However, achieving such a goal is a difficult and time-consuming engineering task due to the vast design space of hardware accelerators and HW/SW task …
-
Non-volatile In-memory Computing for Large Scale Data-Intensive Workloads: Challenges and Opportunities
… etc., suffer from growing overhead of data communication between physically separate logic (i.e., compute) and memory elements in conventional von Neumann computing. The recent progress in processing(/computing)-in-memory (PIM/CIM) or simply, in-memory computing addresses data communication …
-
Structured Sparsity-Aware Hardware-Software Co-Design for Deep Neural Network Acceleration
In diverse areas including, but not limited to, computer vision, natural language processing, and personal recommendation, Deep Neural Networks (DNNs) have shown dramatic performance, even exceeding that of humans for some tasks. DNNs are known for their high computational demands and are widely …
-
A Filtered Multitone (FMT) Implementation with Custom Instructions on an Altera FPGA
… radio frequencies are running out. However, according to a report from the Federal Communications Commission (FCC) in 2002, a different story was told : At any given time and location, much of the prized spectrum lies idle. At the same time, FCC revealed the fact that, in many bands, spectrum …
-
The Kiel Esterel processor
… belong to the class of reactive systems, which continuously react to inputs from the environment by generating corresponding outputs. The programming of reactive systems typically requires the use of non-standard control flow constructs, such as concurrency or exception handling. Most …
-
Achieving a better balance between productivity and performance on FPGAs through Heterogeneous Extensible Multiprocessor Systems
… been a long standing challenge problem for the reconfigurable computing community and remains unsolved today. On one hand, Vendor supplied design flows have tended towards achieving the high levels of performance through gate level customization, but at the cost of very low productivity. On the …
-
Incorporating prior knowledge to efficiently design deep learning accelerators
… in popularity over the past decade, and its computational demand has seen commensurate increase. AI models are getting larger, and AI applications are becoming more widespread. A common strategy to mitigate the cost of this growth—which is estimated to consume 0.5% of the world’s energy by …
-
Adaptive Embedded Systems for Autonomous Vehicles
Modern cars are being equipped with powerful computational resources for autonomous driving systems (ADS) as one of their major parts to provide safer travels on roads. High accuracy and hard real-time requirements of ADS are addressed by HW/SW co-design methodology, which helps in offloading the …
-
Non-intrusive hardware-enhanced anomaly detection systems for embedded devices
… architectural flaws and programming bugs. Conventional defences are largely class-specific: signature checking for adversarial attacks; error-checking memory for environmental faults; OS-level patches for architectural flaws; and static analysis for software defects. In contrast, anomaly …
-
Do we need all the neurons we utilize? An exploration into costs and scalability for large-scale multi-relational graph learning
The first step in HW-SW Co-design is algorithm selection. The algorithm chosen places hard boundaries on the kind of efficiency and scalability that can be achieved through the design of a custom hardware accelerator. A smartly selected algorithm could enable several times more performance gains …
-
Circuit architecture co-design for machine learning and 3D deep learning
… capabilities but also introduce substantial computational and memory demands. In particular, modern AI workloads are increasingly limited by memory bandwidth and data movement, as many emerging algorithms exhibit low arithmetic intensity and require frequent access to large model parameters …
-
Enabling task level parallelism in HandelC
… is similar in syntax to ANSI-C. HandelC offers constructs that allow programmers to express instruction level parallelism. Also, HandelC offers primitives that allow task level parallelism. However, HandelC does not offer any runtime support that enables programmers to express task level …
Page 1 of 2