https://hal.inria.fr/inria-00075711/document

The ESTEREL synchronous programming language: design, semantics, implementation

Modern embedded computing systems tend to be heterogeneous in the sense of being composed of subsystems with very different characteristics, which communicate and interact in a variety of ways-synchronous or asynchronous, buffered or unbuffered, etc. Obviously, when designing such systems, a modeling language needs to reflect this heterogeneity. Today's modeling environments usually offer a variant of what we call amorphous heterogeneity to address this problem. This paper argues that modeling systems in this manner leads to unexpected and hard-to-analyze interactions between the communication mechanisms and proposes a more structured approach to heterogeneity, called hierarchical heterogeneity, to solve this problem. It proposes a model structure and semantic framework that support this form of heterogeneity, and discusses the issues arising from heterogeneous component interaction and the desire for component reuse. It introduces the notion of domain polymorphism as a way to address these issues.

/pdf/taming-heterogeneity-the-ptolemy-approach-v4qpoppcbo.pdf

Taming heterogeneity - the Ptolemy approach

Image processing pipelines combine the challenges of stencil computations and stream programs. They are composed of large graphs of different stencil stages, as well as complex reductions, and stages with global or data-dependent access patterns. Because of their complex structure, the performance difference between a naive implementation of a pipeline and an optimized one is often an order of magnitude. Efficient implementations require optimization of both parallelism and locality, but due to the nature of stencils, there is a fundamental tension between parallelism, locality, and introducing redundant recomputation of shared values.We present a systematic model of the tradeoff space fundamental to stencil pipelines, a schedule representation which describes concrete points in this space for each stage in an image processing pipeline, and an optimizing compiler for the Halide image processing language that synthesizes high performance implementations from a Halide algorithm and a schedule. Combining this compiler with stochastic search over the space of schedules enables terse, composable programs to achieve state-of-the-art performance on a wide range of real image processing pipelines, and across different hardware architectures, including multicores with SIMD, and heterogeneous CPU+GPU execution. From simple Halide programs written in a few hours, we demonstrate performance up to 5x faster than hand-tuned C, intrinsics, and CUDA implementations optimized by experts over weeks or months, for image processing applications beyond the reach of past automatic compilers.

Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines

We review a model of computation used in industrial practice in signal processing software environments and experimentally and other contexts. We give this model the name "dataflow process networks," and study its formal properties as well as its utility as a basis for programming language design. Variants of this model are used in commercial visual programming systems such as SPW from the Alta Group of Cadence (formerly Comdisco Systems), COSSAP from Synopsys (formerly Cadis), the DSP Station from Mentor Graphics, and Hypersignal from Hyperception. They are also used in research software such as Khoros from the University of New Mexico and Ptolemy from the University of California at Berkeley, among many others. Dataflow process networks are shown to be a special case of Kahn process networks, a model of computation where a number of concurrent processes communicate through unidirectional FIFO channels, where writes to the channel are nonblocking, and reads are blocking. In dataflow process networks, each process consists of repeated "firings" of a dataflow "actor." An actor defines a (often functional) quantum of computation. By dividing processes into actor firings, the considerable overhead of context switching incurred in most implementations of Kahn process networks is avoided. We relate dataflow process networks to other dataflow models, including those used in dataflow machines, such as static dataflow and the tagged-token model. We also relate dataflow process networks to functional languages such as Haskell, and show that modern language concepts such as higher-order functions and polymorphism can be used effectively in dataflow process networks. A number of programming examples using a visual syntax are given. >

/pdf/dataflow-process-networks-3mdwy0uhx2.pdf

Dataflow process networks

For concurrent programming to become mainstream, we must discard threads as a programming model. Nondeterminism should be judiciously and carefully introduced where needed, and it should be explicit in programs. In general-purpose software engineering practice, we have reached a point where one approach to concurrent programming dominates all others namely, threads, sequential processes that share memory. They represent a key concurrency model supported by modern computers, programming languages, and operating systems. In scientific computing, where performance requirements have long demanded concurrent programming, data-parallel language extensions and message-passing libraries such as PVM, MPI, and OpenMP dominate over threads for concurrent programming. Computer architectures intended for scientific computing often differ significantly from so-called general-purpose architectures.

/pdf/the-problem-with-threads-16ucvepvhb.pdf

The problem with threads

Twelve years ago, Proceedings of the IEEE devoted a special section to the synchronous languages. This paper discusses the improvements, difficulties, and successes that have occured with the synchronous languages since then. Today, synchronous languages have been established as a technology of choice for modeling, specifying, validating, and implementing real-time embedded applications. The paradigm of synchrony has emerged as an engineer-friendly design method based on mathematically sound tools.

/pdf/the-synchronous-languages-12-years-later-55re7ed5k3.pdf

The synchronous languages 12 years later

The logic and synchronization characteristics of general dynamical systems called hybrid dynamical systems (HDS) are studied. The theory is related to discrete event dynamical system theory, but handles numerics as well as symbolics. It is supported by the programming language Signal and a mathematical model of general implicit dynamical systems. The core of the theory is the notion of HDS resolution which is based on a coding of any HDS into a dynamic graph which consists of a skew product of a polynomial dynamical system on the finite field of integers modulo 3 (to describe the transitions of the underlying automation) and directed graphs (to describe how data dependencies dynamically evolve). The resolution algorithms are based on the study of this dynamical system. >

Hybrid dynamical systems theory and the Signal language

We present the language SIGNAL which is a data flow-oriented real-time, synchronous, side effect-free language suited to the expression and recovery of the parallelism in signal or image processing algorithms The language is intended to be, at the same time, an executable simulation language, and a specification of a virtual machine implementing the algorithm The language is semantically sound, and is suitable to perform program transforms-a major requirement when the ultimate goal is an aid to the architecture design

/pdf/signal-a-data-flow-oriented-language-for-signal-processing-1xjhr53xm7.pdf

Signal--A data flow-oriented language for signal processing

SIGNAL, a synchronous and data-flow oriented language, allows the user to design safe real-time applications. Its compiler uses a single formalism called "synchronized data-flow graphs" (SDFGs) all along the conception chain from specification to proof and verification. We show how this formalism can be kept on until distributed code generation. The described implementation, called synchronous distribution, respects the semantics of SIGNAL. We finally show the limits of SDFGs and conclude with a discussion on the necessity of another model describing dynamic behaviours of distributed executions.

/pdf/synchronous-distribution-of-signal-programs-32mb1gsj04.pdf

Synchronous distribution of SIGNAL programs

We lay a foundation for modeling and validation of asynchronous designs in a multi-clock synchronous programming model. This allows us to study properties of globally asynchronous systems using synchronous simulation and model-checking toolkits. Our approach can be summarized as automatic transformation of a design consisting of two asynchronously composed synchronous components into a fully synchronous multi-clock model preserving behavioral equivalence. The ultimate goal of this research is to provide the ability to model and build GALS systems in a fully synchronous design framework and deploy it on an asynchronous network preserving all properties of the system proven in the synchronous framework.

https://hal.inria.fr/inria-00071644/document

P. Le Guernic

Papers

The synchronous languages 12 years later

Hybrid dynamical systems theory and the Signal language

Signal--A data flow-oriented language for signal processing

Synchronous distribution of SIGNAL programs

Modeling and validating globally asynchronous design in synchronous frameworks