Soonhoi Ha

PeaCE: A hardware-software codesign environment for multimedia embedded systems

Existent hardware-software (HW-SW) codesign tools mainly focus on HW-SW cosimulation to build a virtual prototyping environment that enables software design and system verification without need of making a hardware prototype. Not only HW-SW cosimulation, but also HW-SW codesign methodology involves system specification, functional simulation, design-space exploration, and hardware-software cosynthesis. The PeaCE codesign environment is the first full-fledged HW-SW codesign environment that provides seamless codesign flow from functional simulation to system synthesis. Targeting for multimedia applications with real-time constraints, PeaCE specifies the system behavior with a heterogeneous composition of three models of computation and utilizes features of the formal models maximally during the whole design process. It is also a reconfigurable framework in the sense that third-party design tools can be integrated to build a customized tool chain. Experiments with industry-strength examples prove the viability of the proposed technique.

Heterogeneous Simulation—Mixing Discrete-Event Models with Dataflow

This paper relates to system-level design of signal processing systems, which are often heterogeneous in implementation technologies and design styles. The heterogeneous approach, by combining small, specialized models of computation, achieves generality and also lends itself to automatic synthesis and formal verification. Key to the heterogeneous approach is to define interaction semantics that resolve the ambiguities when different models of computation are brought together. For this purpose, we introduce a tagged signal model as a formal framework within which the models of computation can be precisely described and unambiguously differentiated, and their interactions can be understood. In this paper, we will focus on the interaction between dataflow models, which have partially ordered events, and discrete-event models, with their notion of time that usually defines a total order of events. A variety of interaction semantics, mainly in handling the different notions of time in the two models, are explored to illustrate the subtleties involved. An implementation based on the Ptolemy system from U.C. Berkeley is described and critiqued.

A Static Scheduling Heuristic for Heterogeneous Processors

This paper presents a static scheduling heuristic called bestimaginary-level (BIL) scheduling for heterogeneous processors. The input graph is an acyclic precedence graph, where a node has different execution times on different processors. The static level of a node, or BIL, incorporates the effect of interprocessor communication (IPC) overhead and processor heterogeneity. The proposed scheduling technique is proven to produce the optimal scheduling result if the topology of the input task graph is linear. The performance of the BIL scheduling is compared with an existing technique called the general dynamic level (GDL) scheduling with various classes of randomly generated input graphs, resulting in about 20% performance improvement.

Dynamic voltage scheduling technique for low-power multimedia applications using buffers

As multimedia applications are used increasingly in many embedded systems, power efficient design for the applications becomes more important than ever. This paper proposes a simple dynamic voltage scheduling technique, which suits the multimedia applications well. The proposed technique fully utilizes the idle intervals with buffers in a variable speed processor. The main theme of this paper is to determine the minimum buffer size to achieve the maximum energy saving in three cases: single-task, multiple subtasks, and multi-task. Experimental results show that the proposed technique is expected to obtain significant power reduction for several real-world multimedia applications.

Hardware-software cosynthesis of multi-mode multi-task embedded systems with real-time constraints

An embedded system is called multi-mode when it supports multiple applications by dynamically reconfiguring the system functionality. This paper proposes a hardware-software cosynthesis technique for multi-mode multi-task embedded systems with real-time constraints. The cosynthesis problem involves three subproblems: selection of appropriate processing elements, mapping and scheduling of function modules to the selected processing elements, and schedule analysis. The proposed cosynthesis framework defines an iteration loop of three steps that solve the subproblems separately. One of the key benefits of such a modular approach is extensibility and adaptability. Moreover, unlike the previous approaches, the proposed technique considers task sharing between modes and hardware sharing between tasks at the same time. We demonstrate the usefulness of the proposed technique with a realistic multimode embedded system that supports three modes of operation with 5 different tasks.

Pipelined data parallel task mapping/scheduling technique for MPSoC

In this paper, we propose a multi-task mapping/scheduling technique for heterogeneous and scalable MPSoC. To utilize the large number of cores embedded in MPSoC, the proposed technique considers temporal and data parallelisms as well as task parallelism. We define a multi-task mapping/scheduling problem with all these parallelisms and propose a QEA(quantum-inspired evolutionary algorithm)-based heuristic. Compared with an ILP (Integer Linear Programming) approach, experiments with real-life examples show the feasibility and the efficiency of the proposed technique.

Compile-time scheduling of dynamic constructs in dataflow program graphs

Scheduling dataflow graphs onto processors consists of assigning actors to processors, ordering their execution within the processors, and specifying their firing time. While all scheduling decisions can be made at runtime, the overhead is excessive for most real systems. To reduce this overhead, compile-time decisions can be made for assigning and/or ordering actors on processors. Compile-time decisions are based on known profiles available for each actor at compile time. The profile of an actor is the information necessary for scheduling, such as the execution time and the communication patterns. However, a dynamic construct within a macro actor, such as a conditional and a data-dependent iteration, makes the profile of the actor unpredictable at compile time. For those constructs, we propose to assume some profile at compile-time and define a cost to be minimized when deciding on the profile under the assumption that the runtime statistics are available at compile-time. Our decisions on the profiles of dynamic constructs are shown to be optimal under some bold assumptions, and expected to be near-optimal in most cases. The proposed scheduling technique has been implemented as one of the rapid prototyping facilities in Ptolemy. This paper presents the preliminary results on the performance with synthetic examples.

A task remapping technique for reliable multi-core embedded systems

With the continuous scaling of semiconductor technology, the life-time of circuit is decreasing so that processor failure becomes an important issue in MPSoC design. A software solution to tolerate run-time processor failure is to migrate tasks from the failed processors to the live processors when failure occurs. Previous works on run-time task migration usually aim to minimize the migration overhead with or without a given latency constraint. For streaming applications, however, it is more important to minimize the throughput degradation than the migration overhead or the latency. Hence, we propose a task remapping technique to minimize the throughput degradation assuming that the migration overhead can be amortized safely. The target multi-core system assumed in this paper consists of processor pools and each pool consists of homogeneous processors. The proposed technique is based on an intensive compile-time analysis for all possible failure scenarios. It involves the following steps; 1) Determine the static mapping of tasks onto the live processors, aiming to minimize the throughput degradation: 2) Find an optimal processor-to-processor mapping to minimize the task migration overhead: and 3) Store the resultant task remapping information that includes task mapping and processor-to-processor mapping results. Since the task remapping information is pre-computed at compile-time for all possible failure scenarios, it should be efficiently represented and stored. At run-time, we simply remap the tasks following the compile-time decision. We examine the scalability of the proposed technique on both space and run-time overhead for compile-time analysis varying the number of failed processors. Through intensive experiments, we show that the proposed technique outperforms the previous works with respect to application throughput.

Efficient hardware controller synthesis for synchronous dataflow graph in system level design

This paper concerns automatic hardware synthesis from data flow graph (DFG) specification in system level design. In the presented design methodology, each node of a data flow graph represents a hardware library module that contains a synthesizable VHDL code. Our proposed technique automatically synthesizes a clever control structure, cascaded counter controller, that supports asynchronous interaction with outside modules while efficiently implementing the synchronous dataflow semantics of the graph at the same time. Through comparison with previous works with some examples, the novelty of the proposed technique is demonstrated.

A retargetable parallel-programming framework for MPSoC

As more processing elements are integrated in a single chip, embedded software design becomes more challenging: It becomes a parallel programming for nontrivial heterogeneous multiprocessors with diverse communication architectures, and design constraints such as hardware cost, power, and timeliness. In the current practice of parallel programming with MPI or OpenMP, the programmer should manually optimize the parallel code for each target architecture and for the design constraints. Thus, the design-space exploration of MPSoC (multiprocessor systems-on-chip) costs become prohibitively large as software development overhead increases drastically. To solve this problem, we develop a parallel-programming framework based on a novel programming model called common intermediate code (CIC). In a CIC, functional parallelism and data parallelism of application tasks are specified independently of the target architecture and design constraints. Then, the CIC translator translates the CIC into the final parallel code, considering the target architecture and design constraints to make the CIC retargetable. Experiments with preliminary examples, including the H.263 decoder, show that the proposed parallel-programming framework increases the design productivity of MPSoC software significantly.