Andreas Gerstlauer

RTOS Modeling for System Level Design

System level synthesis is widely seen as the solution for closing the productivity gap in system design. High level system models are used in system level design for early design exploration. While real time operating systems (RTOS) are an increasingly important component in system design, specific RTOS implementations can not be used directly in high level models. On the other hand, existing system level design languages (SLDL) lack support for RTOS modeling. In this paper we propose a RTOS model built on top of existing SLDLs which, by providing the key features typically available in any RTOS, allows the designer to model the dynamic behavior of multi-tasking systems at higher abstraction levels to be incorporated into existing design flows. Experimental result shows that our RTOS model is easy to use and efficient while being able to provide accurate results.

Electronic System-Level Synthesis Methodologies

With ever-increasing system complexities, all major semiconductor roadmaps have identified the need for moving to higher levels of abstraction in order to increase productivity in electronic system design. Most recently, many approaches and tools that claim to realize and support a design process at the so-called electronic system level (ESL) have emerged. However, faced with the vast complexity challenges, in most cases at best, only partial solutions are available. In this paper, we develop and propose a novel classification for ESL synthesis tools, and we will present six different academic approaches in this context. Based on these observations, we can identify such common principles and needs as they are leading toward and are ultimately required for a true ESL synthesis solution, covering the whole design process from specification to implementation for complete systems across hardware and software boundaries.

Embedded System Design: Modeling, Synthesis and Verification

Embedded System Design: Modeling, Synthesis and Verification introduces a model-based approach to system level design. It presents modeling techniques for both computation and communication at different levels of abstraction, such as specification, transaction level and cycle-accurate level. It discusses synthesis methods for system level architectures, embedded software and hardware components. Using these methods, designers can develop applications with high level models, which are automatically translatable to low level implementations. This book, furthermore, describes simulation-based and formal verification methods that are essential for achieving design confidence. The book concludes with an overview of existing tools along with a design case study outlining the practice of embedded system design. Specifically, this book addresses the following topics in detail: . System modeling at different abstraction levels . Model-based system design . Hardware/Software codesign . Software and Hardware component synthesis . System verification This book is for groups within the embedded system community: students in courses on embedded systems, embedded application developers, system designers and managers, CAD tool developers, design automation, and system engineering.

System-on-chip environment: a SpecC-based framework for heterogeneous MPSoC design

The constantly growing complexity of embedded systems is a challenge that drives the development of novel design automation techniques. C-based system-level design addresses the complexity challenge by raising the level of abstraction and integrating the design processes for the heterogeneous system components. In this article, we present a comprehensive design framework, the system-on-chip environment (SCE) which is based on the influential SpecC language and methodology. SCE implements a top-down system design flow based on a specify-explore-refine paradigm with support for heterogeneous target platforms consisting of custom hardware components, embedded software processors, dedicated IP blocks, and complex communication bus architectures. Starting from an abstract specification of the desired system, models at various levels of abstraction are automatically generated through successive step-wise refinement, resulting in a pin-and cycle-accurate system implementation. The seamless integration of automatic model generation, estimation, and verification tools enables rapid design space exploration and efficient MPSoC implementation. Using a large set of industrial-strength examples with a wide range of target architectures, our experimental results demonstrate the effectiveness of our framework and show significant productivity gains in design time.

Modeling and synthesis of quality-energy optimal approximate adders

Recent interest in approximate computation is driven by its potential to achieve large energy savings. This paper formally demonstrates an optimal way to reduce energy via voltage over-scaling at the cost of errors due to timing starvation in addition. We identify a fundamental trade-off between error frequency and error magnitude in a timing-starved adder. We introduce a formal model to prove that for signal processing applications using a quadratic signal-to-noise ratio error measure, reducing bit-wise error frequency is sub-optimal. Instead, energy-optimal approximate addition requires limiting maximum error magnitude. Intriguingly, due to possible error patterns, this is achieved by reducing carry chains significantly below what is allowed by the timing budget for a large fraction of sum bits, using an aligned, fixed internal-carry structure for higher significance bits. We further demonstrate that remaining approximation error is reduced by realization of conditional bounding (CB) logic for lower significance bits. A key contribution is the formalization of an approximate CB logic synthesis problem that produces a rich space of Pareto-optimal adders with a range of quality-energy tradeoffs. We show how CB logic can be customized to result in over-and under-estimating approximate adders, and how a dithering adder that mixes them produces zero-centered error distributions, and, in accumulation, a reduced-variance error. We demonstrate synthesized approximate adders with energy up to 60% smaller than that of a conventional timing-starved adder, where a 30% reduction is due to the superior synthesis of inexact CB logic. When used in a larger system implementing an image-processing algorithm, energy savings of 40% are possible.

Retargetable profiling for rapid, early system-level design space exploration

Fast and accurate estimation is critical for exploration of any design space in general. As we move to higher levels of abstraction, estimation of complete system designs at each level of abstraction is needed. Estimation should provide a variety of useful metrics relevant to design tasks in different domains and at each stage in the design process.In this paper, we present such a system-level estimation approach based on a novel combination of dynamic profiling and static retargeting. Co-estimation of complete system implementations is fast while accurately reflecting even dynamic effects. Furthermore, retargetable profiling is supported at multiple levels of abstraction, providing multiple design quality metrics at each level. Experimental results show the applicability of the approach for efficient design space exploration.

System-level abstraction semantics

Raising the level of abstraction is widely seen as the solution for closing the productivity gap in system design. They key for the success of this approach, however, axe well-defined abstraction levels and models. In this paper, we present such system level semantics to cover the system design process. We define properties and features of each model. Formalization of the flow enables design automation for synthesis and verification to achieve the required productivity gains. Through customization, the semantics allow creation of specific design methodologies. We applied the concepts to system languages SystemC and SpecC. Using the example of a JPEG encoder, we will demonstrate the feasibility and effectiveness of the approach.

RTOS scheduling in transaction level models

Raising the level of abstraction in system design promises to enable faster exploration of the design space at early stages. While scheduling decision for embedded software has great impact on system performance, its much desired that the designer can select the right scheduling algorithm at high abstraction levels so as to save him from the error-prone and time consuming task of tuning code delays or task priority assignments at the final stage of system design. In this paper we tackle this problem by introducing a RTOS model and an approach to refine any unscheduled transaction level model (TLM) to a TLM with RTOS scheduling support. The refinement process provides a useful tool to the system designer to quickly evaluate different dynamic scheduling algorithms and make the optimal choice at an early stage of system design.

Codesign Tradeoffs for High-Performance, Low-Power Linear Algebra Architectures

As technology is reaching physical limits, reducing power consumption is a key issue on our path to sustained performance. In this paper, we study fundamental tradeoffs and limits in efficiency (as measured in energy per operation) that can be achieved for an important class of kernels, namely the level-3 Basic Linear Algebra Subprograms (BLAS). It is well-accepted that specialization is the key to efficiency. This paper establishes a baseline by studying GEneral Matrix-matrix Multiplication (GEMM) on a variety of custom and general-purpose CPU and GPU architectures. Our analysis shows that orders of magnitude improvements in efficiency are possible with relatively simple customizations and fine-tuning of memory hierarchy configurations. We argue that these customizations can be generalized to perform other representative linear algebra operations. In addition to exposing the sources of inefficiencies in current CPUs and GPUs, our results show our prototype Linear Algebra Processor (LAP) implementing Double-precision GEMM (DGEMM) can achieve 600 GFLOPS while consuming less than 25 Watts in standard 45 nm technology, which is up to 50 × more energy efficient than cutting-edge CPUs.

Approximate logic synthesis under general error magnitude and frequency constraints

Recent interest in approximate circuit design is driven by its potential for large energy savings. In this paper, we address the problem of approximate logic synthesis (ALS). ALS is concerned with formally synthesizing a minimum-cost approximate Boolean network whose behavior deviates in a well-defined manner from a specified exact Boolean function, where in this work, we allow the deviation to be constrained by both the magnitude and frequency of the error. We make two contributions in solving this general ALS problem: The first contribution is to establish that the approximate synthesis problem un-constrained by the frequency of errors is isomorphic with the Boolean relations (BR) minimization problem. That equivalence allows us to exploit recently developed fast algorithms for BR problems to solve the error magnitude-only constrained ALS problem. The second contribution is an efficient heuristic algorithm for iteratively refining the magnitude-constrained solution to arrive at a solution also satisfying the error frequency constraint. Our combined greedy approximate logic synthesis (GALS) approach is able to operate on any Boolean network for which the deviation measures can be specified and is most immediately applicable to arithmetic blocks. Experiments on adder and multiplier blocks demonstrate literal count reductions of up to 60% under tight error frequency and magnitude constraints.