@Patent {78.pat20080134187PATENT, title = {Hardware scheduled SMP architectures}, number = {US 11/947,278}, year = {2008}, month = {06/2008}, type = {Application}, chapter = {US 20080134187 A1}, abstract = {A symmetric multiprocessor system employing a hardware constituted real-time operating system.}, issn = {US 20080134187 A1}, author = {Lajolo, Marcello and Nacul, Andre Costi and Regazzoni, Francesco} } @conference {53.CoReLa07, title = {HardwareScheduling Support in SMP Architecture}, booktitle = {Design, Automation and Test in Europe(DATE)}, year = {2007}, month = {April 16-20}, address = {Nice, France}, abstract = {In this paper the authors propose a hardware real time operating system (HW-RTOS) that implements the OS layer in a dual-processor SMP architecture. Intertask communication is specified by means of dedicated APIs and the HW-RTOS takes care of the communication requirements of the application and also implements the task scheduling algorithm. The HW-RTOS allows to have smaller footprints, since it avoids the need to link to the final executables traditional software RTOS libraries. Moreover, the HW-RTOS is able to exploit the easy task migration feature provided by an SMP architecture much more efficiently than a traditional software RTOS, due to its faster execution and the authors show how this significantly overcomes the performance achievable with optimal static task partitioning among two processors. Preliminary results show that the hardware overhead in a dual processor architecture is less than 20K gates.}, keywords = {HW/SW co-design, multiprocessor system-on-chip (MPSoC), real time operating systems}, doi = {http://dx.doi.org/10.1109/DATE.2007.364666}, author = {Nacul, Andre Costi and Regazzoni, Francesco and Lajolo, Marcello} } @conference {73.OtReLa07, title = {Rapid Creation of Application Models from Bandwidth Aware Core Graphs}, booktitle = {Proceedings of: IP Based SoC Design 2007}, year = {2007}, month = {December 5-6}, address = {Grenoble, France}, abstract = {We present a methodology that allows rapid creation of application models from bandwidth aware core graphs that are available in the literature for a wide range of applications and we discuss their applicability to the rapid exploration of multiple Networks on Chip (NoCs) layout organizations. In a bandwidth aware core graph, each node represents a core and the numbers on the edges represent the bandwidth requirements between cores. We describe core graphs in a UML object model diagram and we then have an automatic code generation tool which produces a SystemC description whose behaviour results in a packet generation on every output connection that respects the bandwidth requirements specified in the core graph. We can then rapidly derive a NoC mapping in which a specific floorplan of the cores can be evaluated and compared with alternate floorplan options for rapid design space exploration.}, keywords = {network-on-chip (NoC), rapid prototyping}, author = {Otero, Jo{\~a}o and Regazzoni, Francesco and Lajolo, Marcello} } @conference {40.1127983, title = {Hardware/software partitioning of operating systems: a behavioral synthesis approach}, booktitle = {GLSVLSI {\textquoteright}06: Proceedings of the 16th ACM Great Lakes symposium on VLSI}, year = {2006}, pages = {324{\textendash}329}, publisher = {ACM Press, New York, USA}, organization = {ACM Press, New York, USA}, address = {Philadelphia, PA, USA}, abstract = {In this paper we propose a hardware real time operating system(HW-RTOS) solution that makes use of a dedicated hardware in order to replace the standard support provided by the POSIX layer of a general purpose RTOS for implementing task synchronization and scheduling. By redefining only the I/O APIs of the tasks, the HW-RTOS then takes care of the communication requirements of the original application and also implements the task scheduling algorithm. The new software application can then be compiled without any need for POSIX support. The main advantages are smaller and faster executables. We present results that show how a small hardware area, less than 10K gates, can result in a 15X performance improvement when the original software scheduler is replaced by a dedicated HW-RTOS.}, keywords = {HW/SW co-design, real time operating systems, system-on-chip (SoC)}, isbn = {1-59593-347-6}, doi = {http://doi.acm.org/10.1145/1127908.1127983}, author = {Chandra, Satish and Regazzoni, Francesco and Lajolo, Marcello} } @conference {36.RegNacLaj2005, title = {Automatic Synthesis of the Hardware/Software Interface in Multiprocessor Architectures}, booktitle = {FDL{\textquoteright}05 - Forum on Specification and Design Languages}, year = {2005}, month = {September 27-30}, address = {Lausanne, Switzerland}, abstract = {Although Moore{\textquoteright}s Law, in principle, enables a huge number of components to be integrated into a single chip, design methods that will allow system architects to put the components together to achieve cost, power and time-to-market targets are severely lacking. System-level design and optimization techniques can significantly reduce the design gap by providing solutions that achieve correct-by-construction rather than the correct-by-iteration approach. This paper presents a programmatic interface generation tool for automating the generation of the hardware/software interfaces in the context of multiprocessor Systems-On-Chips. The solutions that we present are of crucial importance in a platform based design environment for building a flexible system with reusable IPs and CPU cores.}, keywords = {HW/SW co-design, system-on-chip (SoC)}, author = {Regazzoni, Francesco and Nacul, Andre Costi and Lajolo, Marcello} } @conference {34.BaLaPrevos2005, title = {Design and Synthesis of Reusable Platforms with Programmable Interconnects}, booktitle = {UML-SoC 2005}, year = {2005}, month = {June 12}, pages = {43-48}, address = {Anaheim, California}, abstract = {Platform based design requires to restrict the number of possible design choices in order to make it possible to come up with programmable solutions able to cope with the current complexity of System-On-Chip (SoC) designs. Nowadays there is a general consensus toward the fact that an effective Electronic System Level (ESL) design methodology must provide a specific support for platform specification, hardware/software partitioning and programmatic interfaces synthesis in order to allow designers to exploit the potentials of state-of-the-art technologies. In this work we present a methodology that leverages on UML for building new architectural platforms to be used to be used in the system design process. We show how our methodology can allow to reuse pre-designed platforms by adding new architectural components and by customizing their interconnections}, keywords = {HW/SW co-design, system-on-chip (SoC), unified modeling language (UML)}, author = {Basu, Ananda Shankar and Lajolo, Marcello and Prevostini, Mauro} } @conference {37.RegLaj2005, title = {Hardware/Software Partitioning and Interface Synthesis in Networks On Chip}, booktitle = {IP Based SoC Design 2005}, year = {2005}, month = {December 7-8}, address = {Grenoble, France}, abstract = {With deep sub-micron technology, chip designers are expected to create System-On-Chip (SOC) solutions by connecting different Intellectual Property (IP) blocks using efficient and reliable interconnection schemes. On chip networks are quite compelling because, by applying networking techniques to on-chip communication, they allow to implement a fully distributed communication pattern with little or no global coordination. This avoids the problems due to the difficulty of implementing future chips with one single clock source and negligible skew. On the other hand, in order to benefit from the NOC communication paradigm, designers should perform a careful functional mapping for taking advantage of spatial locality, by placing the blocks that communicate more frequently closer together. This reduces the use of long global paths and the corresponding energy dissipation. In this work we show how a tile based NOC architecture can be exploited in order to support a flexible hardware/software partitioning of a system-level specification and we present a methodology for the automatic synthesis of the hardware/software interfaces.}, keywords = {HW/SW co-design, network-on-chip (NoC), system-on-chip (SoC)}, author = {Regazzoni, Francesco and Lajolo, Marcello} } @inbook {30.BaLaPre2005, title = {A Methodology for Bridging the Gap between UML and Codesign}, booktitle = {UML for SOC Design}, year = {2005}, pages = {119-146}, publisher = {Springer}, organization = {Springer}, address = {Dordrecht, The Netherlands}, abstract = {The Unified Modeling Language (UML) is getting more popular among system designers due to the need to raise the level of abstraction in system specifications. We present here a methodology that integrates UML specifications with a hardware/software codesign platform. This work aims to give a contribution toward SoC Design Automation starting from system level specification down to hardware/software partitioning and integration.}, keywords = {HW/SW co-design, methodology, system specifications, unified modeling language (UML)}, author = {Basu, Ananda Shankar and Lajolo, Marcello and Prevostini, Mauro}, editor = {Martin, Grant and Muller, Wolfgang} } @conference {27.RegLaj2004, title = {Interface Synthesis in Multiprocessing Systems-on-Chips}, booktitle = {IP Based SoC Design 2004}, year = {2004}, month = {December}, address = {Grenoble}, abstract = {Although Moore{\textquoteright}s Law, in principle, enables a huge number of components to be integrated into a single chip, design methods that will allow system architects to put the components together to achieve cost, power and time-to-market targets are severely lacking. System-level design and optimization techniques can significantly reduce the design gap by providing solutions that achieve correct-by-construction approach rather than the correct-by-iteration approach. This paper presents a programmatic interface generation tool for automating the generation of the hardware/software interfaces in the context of multi-processor Systems-On-Chips. The solutions that we present are of crucial importance in a platform based design environment for building a flexible system with reusable IPs and CPU cores.}, keywords = {HW/SW co-design, system-on-chip (SoC)}, author = {Regazzoni, Francesco and Lajolo, Marcello} } @conference {23.BaLaPre2004, title = {UML in an Electronic System Level Design Methodology}, booktitle = {UML-SOC{\textquoteright}04}, year = {2004}, month = {June 6}, pages = {47-52}, address = {San Diego, California}, abstract = {The interest in System-On-Chip (SoC) design using the Unifed Modeling Language (UML) has been growing significantly during the last couple of years. In this paper we would like to present a methodology that aims to address embedded systems design issues at multiple levels of abstraction and to support a function/architecture codesign process. Our approach integrates UML with high-level synthesis and hardware/software co-verification techniques in order to provide an automated flow for SoC design starting from system-level specifications down to hardware/software partitioning and integration. UML has been selected because it is platform independent and helps team members to share very efficiently relevant information during the various design phases, while high-level synthesis helps to evaluate constraints that the embedded system must satisfy: e.g. performance, power and cost starting from behavioral specifications. The paper aims to give a contribution towards SoC Design automation from System-level specification to hardware/software partitioning.}, keywords = {HW/SW co-design, methodology, system-on-chip (SoC), unified modeling language (UML)}, author = {Basu, Ananda Shankar and Lajolo, Marcello and Prevostini, Mauro} } @conference {24.LaBaPre2004, title = {UML Specifications Towards a Codesign Environment}, booktitle = {FDL{\textquoteright}04}, year = {2004}, month = {September 14-17}, pages = {313-324}, address = {Lille, France}, abstract = {The Unified Modeling Language (UML) is receiving more and more attention from system designers that need to model both hardware and software related aspects of a system. On the ground of the growing consensus toward the need to raise the level of abstraction in system specifications, we would like to present a methodology that aims to address embedded systems design issues at multiple levels of abstraction and to support a function/architecture codesign process. Our approach integrates UML with high-level synthesis and hardware/software co-verification techniques in order to provide an automated flow for SoC design starting from system-level specifications down to hardware/software partitioning and integration. UML has been selected because it is platform independent and helps team member to share very efficiently relevant information during the various design phases, while high-level synthesis helps to evaluate constraints that the embedded system must satisfy: e.g. performance, power and cost starting from behavioral specifications.}, keywords = {embedded systems, HW/SW co-design, system-on-chip (SoC), unified modeling language (UML)}, author = {Lajolo, Marcello and Basu, Ananda Shankar and Prevostini, Mauro} }