Jochen Kreuzinger

Real-time event-handling and scheduling on a multithreaded Java microcontroller

Abstract Our aim is to investigate the suitability of hardware multithreading for real-time event handling in combination with appropriate real-time scheduling techniques. We designed and evaluated a multithreaded microcontroller based on a Java processor core. Java threads are used as Interrupt Service Threads (ISTs) instead of the Interrupt Service Routines (ISRs) of conventional processors. Our proposed Komodo microcontroller supports multiple ISTs with zero-cycle context switching overhead. A so-called priority manager implements several real-time scheduling algorithms in hardware. We show the feasibility of a hardware real-time scheduler integrated deeply into the processor pipeline with a VHDL design and its synthesis. Evaluations with a software simulator and real-time applications as benchmarks show that hardware multithreading reaches a 1.2–1.4 performance increase for hard real-time applications (multithreading without latency utilization) and a 2.0–2.6 speedup by latency utilization for programs without hard real-time requirements. With respect to real-time scheduling on a multithreaded microcontroller, the Least Laxity First (LLF) scheme outperforms the Fixed Priority Preemptive (FPP), Earliest Deadline First (EDF), and Guaranteed Percentage (GP) schemes, but suffers from the highest implementation costs.

Real-time scheduling on multithreaded processors

This paper investigates real-time scheduling algorithms on upcoming multithreaded processors. As evaluation testbed we introduce a multithreaded processor kernel which is specifically designed as core processor of a micro-controller or system-on-a-chip. Handling of external real-time events is performed through multithreading. Real-time threads are used as interrupt service threads (ISTs) instead of interrupt service routines (ISRs). Our proposed micro-controller supports multiple ISTs with zero-cycle context switching overhead. We investigate the behavior of fixed priority preemptive, earliest deadline first, least laxity first and guaranteed percentage scheduling with respect to multithreaded processors. Our finding is that the strategies GP and LLF result in a good blending of instructions of different threads thus enabling a multithreaded processor to utilize latencies best. Assuming a zero-cycle context switch LLF performs best, however implementation cost context, are prohibitive.

A multithreaded Java microcontroller for thread-oriented real-time event-handling

We propose a multithreaded Java microcontroller (called Komodo microcontroller) with a new hardware event handling mechanism that allows handling of simultaneous overlapping events with hard real-time requirements. Real-time Java threads are used as interrupt service threads (ISTs) instead of interrupt service routines (ISRs). Our proposed Komodo microcontroller supports multiple ISTs with zero-cycle context switching overhead. We evaluate the basic architectural attributes using real-time event parameters of an autonomous guided vehicle. When calculating the maximum vehicle speed without violating the real-time constraints, ISTs dominate ISRs by a speed increase of 28%.

The Komodo project: thread-based event handling supported by a multithreaded Java microcontroller

The Komodo project concerns the handling of multiple real-time events by Java threads that are supported by a multithreaded Java microcontroller. The architecture of the processor core and resulting implications are considered. The use of thread-based event handling is introduced and explained in combination with an Automatic Guided Vehicle (AGV) application. The advantages of thread-based event handling over a normal Interrupt Service Routine (ISR) strategy are demonstrated by the development of the AGV example.

Real-time garbage collection for a multithreaded Java microcontroller

We envision the upcoming of microcontrollers and systems-on-chip that are based on multithreaded processor kernels due to the fast context switching ability of hardware multithreading. Moreover we envision an extensive market for Java-based applications in embedded real-time systems. This paper introduces two new garbage collection algorithms that are dedicated to real-time garbage collection on a multithreaded Java microcontroller. Our garbage collector runs in a thread slot in parallel to real-time applications. We show that our algorithms require only about 5–10% of the processor time for an effective garbage collection concerning our real-time benchmarks.

A microkernel middleware architecture for distributed embedded real-time systems

Today more and more embedded real-time systems are implemented in a distributed way. These distributed embedded systems consist of a few controllers up to several hundreds. Distribution and parallelism in the design of embedded real-time systems increase the engineering challenges and require new methodological framework based on middleware. Our research work focuses on the development of a middleware that supports the design of heterogeneous distributed real-time systems and allows the use of small microcontrollers as computation nodes. Our study is aimed to a new approach that led to the development of OSA+-a scalable service-oriented real-time middleware architecture. This middleware has been used as the basic platform for different domain applications: (i) conception of an autonomous guided vehicle system based on multithreaded Java microcontrollers and (ii) development of a permanent monitoring distributed system for an oil drilling application. This paper presents the basic architecture of OSA+ and its implementation for the distributed real-time embedded systems design.

A scheduling technique providing a strict isolation of real-time threads

Highly dynamic programming environments for embedded real-time systems require a strict isolation of real-time threads from each other to achieve dependable systems. We propose a new real-time scheduling technique, called guaranteed percentage (GP) scheme that assigns each thread a specific percentage of the processor power. A hardware scheduler in conjunction with a multithreaded processor guarantees the execution of instructions of each thread according to their assigned percentages within a time interval of 100 processor cycles. We compare performance and implementation overhead of GP scheduling against fixed priority, preemptive (FPP), earliest deadline first (EDF), and least laxity first (LLF) scheduling using several benchmarks on our Komodo microcontroller that features a multithreaded Java processor kernel. Our evaluations show that GP scheduling reaches a speed-up similar to EDF and FPP but worse than LLF. However its hardware implementation costs are still reasonable, whereas the LLF overhead is prohibitive. Only GP reaches the isolation goal among the examined scheduling schemes.

Context-switching techniques for decoupled multithreaded processors

Multithreading techniques use coarse grain parallelism to speed up computation of a multithreaded workload by better utilization of the resources of a single processor. The paper surveys context switching techniques for multithreaded single-issue processors and classifies the techniques due to the events that trigger a context switch. We survey static and dynamic block interleaving techniques and demonstrate the application of several techniques in the decoupled multithreaded Rhamma processor. We show that a speed-up of up to 2.1 can be reached with four threads over a single-threaded base processor.

Agent-Based Distributed Computing with JMessengers

JMessengers is a Java-based mobile agent system particularly designed for distributed computing in heterogeneous computer networks. This paper explains JMessengers programming environment, evaluates JMessengers performance, and compares it to the mobile agent systems MESSENGERS-C and Grasshoppers. The evaluation showed that JMessengers is an optimal compromise between the two systems. It offers the same flexibility as Grasshoppers and reaches almost the execution speed of MESSENGERS-C.