Philippe Coussy

An Introduction to High-Level Synthesis

The basic problem of high-level synthesis is the mapping of a behavioral description of a digital system into an RTL design consisting of a data path and a control unit. The authors introduce the FSMD model, which forms the basis for synthesis. They discuss the main considerations in a high-level synthesis environment: the input description language, the internal representation, and the main synthesis tasks-allocation, scheduling, and binding. They conclude with some problems that must be solved to make high-level synthesis a widely accepted methodology.<<ETX>>

GAUT: A High-Level Synthesis Tool for DSP Applications

This chapter presents GAUT, an academic and open-source high-level synthesis tool dedicated to digital signal processing applications. Starting from an algorithmic bit-accurate specification written in C/C++, GAUT extracts the potential parallelism before processing the allocation, the scheduling and the binding tasks. Mandatory synthesis constraints are the throughput and the clock period while the memory mapping and the I/O timing diagram are optional. GAUT next generates a potentially pipelined architecture composed of a processing unit, a memory unit and a communication with a GALS/LIS interface.

A design flow dedicated to multi-mode architectures for DSP applications

This paper addresses the design of multi-mode architectures for digital signal processing applications. We present a dedicated design flow and its associated high-level synthesis tool, named GAUT. Given a unified description of a set of time-wise mutually exclusive tasks and their associated throughput constraints, a single RTL hardware architecture optimized in area is generated. In order to reduce the register, steering logic (multiplexers) and controller (decoding logic) complexities, we propose a joint-scheduling algorithm which maximizes the similarities between control steps and specific binding approaches for both functional units and storage elements which maximize the similarities between the datapaths. We show through a set of test cases that our approach offers significant area saving relative to the state-of-the-art.

A formal method for hardware IP design and integration under I/O and timing constraints

IP integration, which is one of the most important SoC design steps, requires taking into account communication and timing constraints. In that context, design and reuse can be improved using IP cores described at a high abstraction level. In this paper, we present an IP design approach that relies on three main phases: (1) constraint modeling, (2) IP constraint analysis steps for feasibility checking, and (3) synthesis. We propose a set of techniques dedicated to the digital signal processing domain that lead to an optimized IP core integration. Based on a generic architecture of components, the method we propose provides automatic generation of IP cores designed under integration constraints. We show the effectiveness of our approach with a DCT core design case study.

A memory mapping approach for parallel interleaver design with multiples read and write accesses

For high throughput applications, turbo-like iterative decoders are implemented with parallel architectures. However, to be efficient parallel architectures require to avoid collision accesses i.e. concurrent read/write accesses should not target the same memory block. This consideration applies to the two main classes of turbo-like codes which are Low Density Parity Check (LDPC) and Turbo-Codes. In this paper we propose a methodology which always finds a collision-free mapping of the variables in the memory banks and which optimizes the resulting interleaving architecture. Finally, we show through a pedagogical example the interest our approach. This research was supported by the European project DAVINCI.

A Design Approach to Automatically Synthesize ANSI-C Assertions during High-Level Synthesis of Hardware Accelerators

Evolution of Systems-On-Chip (SoC) increases the challenge of verification and post-silicon debug. Nowadays, Assertion Based Verification (ABV) is a widely used methodology. Languages like PSL (Property Specification Language) or SVA (System Verilog Assertions) allows engineers to define properties at Register Transfer Level (RTL). Properties can then be used to generate simulation/hardware assertion checkers for dynamic verification. In this paper, we propose to consider ANSI-C assertions during High-Level Synthesis (HLS) of hardware accelerators (HWacc) to automatically generate on-chip monitors (OCM). The proposed method is portable to any HLS tool and supports both static and dynamic application behaviors. OCM is implemented separately from the HWacc and an original technique is introduced for their synchronization. Two synthesis options are proposed for the OCM design i.e. speed and area. Experimental results show the interest of the proposed approach: while the cost of the OCMs mainly depends on the complexity of input assertions, setting synthesis option is area allows reducing the complexity of the OCM by 2.37x on average compared to the option for speed optimization.

Static Address Generation Easing: a design methodology for parallel interleaver architectures

For high throughput applications, turbo-like iterative decoders are implemented with parallel architectures. However, to be efficient parallel architectures require to avoid collision accesses i.e. concurrent read/write accesses should not target the same memory block. This consideration applies to the two main classes of turbo-like codes which are Low Density Parity Check (LDPC) and Turbo-Codes. In this paper we propose a methodology which finds a collision-free mapping of the variables in the memory banks and which optimizes the resulting interleaving architecture. Finally, we show through a pedagogical example the interest of our approach compared to state-of-the-art techniques.

High-level synthesis under I/O timing and memory constraints

In the design of complex systems-on-chips, it is necessary to take into account communication and memory access constraints for the integration of a dedicated hardware accelerator. We present a methodology and a tool that allow the high-level synthesis of a DSP algorithm, under both I/O timing and memory constraints. Based on formal models and a generic architecture, this tool helps the designer to find a reasonable trade-off between the required I/O timing behavior and the internal memory access parallelism of the circuit. The interest of our approach is demonstrated by the case study of an FFT algorithm.

A design methodology for IP integration

Successful integration of IP/VC blocks requires a set of view that provides the appropriate information for each IP block through the design flow for an IP-integration system. In this paper, we present a methodology of IP integration in a System-on a chip (SOC) design, that exploits both IP designer and SOC integrator constraints. First, we describe a method to extract and specify IP functional and timing constraints (I/O sequence transfer constraints) from the IP core. Second, we propose a modeling style of the integration constraints and a technique for merging them with IP constraints. This technique allows the specification and design of an optimized IP interface unit required for IP-socketization. The synthesis output is synthesizable VHDL RT of the interface, a detailed bus-functional model of the IP core towards cosimulation.

A First Step Toward On-Chip Memory Mapping for Parallel Turbo and LDPC Decoders: A Polynomial Time Mapping Algorithm

To meet the higher data rate requirement of current and future communication standards, numerous techniques to decode Turbo and LDPC codes on hardware architecture are developed. Unfortunately, interleaving laws that are used in these codes often result in memory access conflicts when massively parallel architectures are targeted which considerably limits the throughput. In this article, the first dedicated approach that finds conflict free memory mapping for every type of codes and for every type of parallelism in polynomial time is presented. The implementation of this highly efficient algorithm shows significant improvement in terms of computational time compared to state of the art approaches. Ultimately, this could enable memory mapping algorithm to be embedded on chips and executed on the fly to support multiple block lengths and standards.