When RTL designers define the hierarchy of a system, they exploit their knowledge about the conceptual abstractions devised during the design and the functional interactions between the logical components. This valuable information is often lost during physical synthesis. This article proposes HiDaP, a novel multilevel algorithm that uses RTL information and analytical methods for the macro placement problem of modern designs dominated by multicycle connection pipelines. By taking advantage of the hierarchy tree, the netlist is divided into blocks containing macros and standard cells, and their dataflow affinity is inferred considering the register latency and flow width of their interaction. The layout is represented using slicing structures and generated with a top-down algorithm capable of handling blocks with both hard and soft components. An adaptive multiobjective cost function is used to simultaneously minimize wirelength, timing, overlap, and distance to preferred locations, which can be user defined or generated by analytic methods (spectral and force directed). These techniques have been applied to a set of large industrial circuits and compared against state-of-the-art commercial and academic placers, and also to handcrafted floorplans generated by expert backend engineers. The proposed approach outperforms previous algorithmic methods and can produce solutions with better wirelength and timing than the best handcrafted floorplans. Post-routing layouts are almost brought to timing closure and DRC cleanness with minimal engineer modification, showing that the generated floorplans provide an excellent starting point for the physical design flow and contribute to reduce turn-around time significantly.

When RTL designers define the hierarchy of a system, they exploit their knowledge about the conceptual abstractions devised during the design and the functional interactions between the logical components. This valuable information is often lost during physical synthesis. This paper proposes a novel multi-level approach for the macro placement problem of complex designs dominated by macro blocks, typically memories. By taking advantage of the hierarchy tree, the netlist is divided into blocks containing macros and standard cells, and their dataflow affinity is inferred considering the latency and flow width of their interaction. The layout is represented using slicing structures and generated with a top-down algorithm capable of handling blocks with both hard and soft components, aimed at wirelength minimization. These techniques have been applied to a set of large industrial circuits and compared against both a commercial floorplanner and handcrafted floorplans by expert back-end engineers. The proposed approach outperforms the commercial tool and produces solutions with similar quality to the best handcrafted floorplans. Therefore, the generated floorplans provide an excellent starting point for the physical design iterations and contribute to reduce turn-around time significantly.

Design automation has been one of the main propellers of the semiconductor industry with logic synthesis being one of the core technologies in this field. This article reviews the evolution of logic synthesis until the advent of techniques for automatic pipelining based on elastic timing, either synchronous or asynchronous. The emergence of these techniques can enable a productive interaction with tools that can do microarchitectural exploration of complex designs.

Elasticity is a paradigm that tolerates the variations in computation and communication delays. By applying elastic transformations that allow varying the original timing, circuits can be optimized beyond the conventional rigid transformations that do not modify the external timing. Pipelining is one of the classical techniques to improve the throughput of a circuit. This article reveals how elasticity can be effectively and practically used to derive pipelined circuits by using correct-by-construction transformations that can be fully automated. Two designs, one of them industrial, are used to demonstrate how the area-performance trade-off can be explored using elasticity.

This paper presents a method for automatic microarchitectural pipelining of systems with loops. The original specification is pipelined by performing provably-correct transformations including conversion to a synchronous elastic form, early evaluation, inserting empty buffers, anti-tokens, and retiming. The design exploration is done by solving an optimization problem followed by simulation of solutions. The method is explained on a DLX microprocessor example. The impact of different microarchitectural parameters on the performance is analyzed.

Elastic systems, either synchronous or asynchronous, can be optimized for the average-case performance when they have units with early evaluation or variable latency. The performance evaluation of such systems using analytical methods is a complex problem and may become a bottleneck when an extensive exploration of different architectural configurations must be done. This paper proposes an analytical method for performance evaluation using symbolic expressions. Two version of the method are presented: an exact method that has high run time complexity and an efficient approximate method that computes the lower bound of the system throughput.

Elastic systems provide tolerance to the variations in computation and communication delays. The incorporation of elasticity opens new opportunities for optimization using new correct-by-construction transformations that cannot be applied to rigid non-elastic systems. The basics of synchronous and asynchronous elastic systems will be reviewed. A set of behavior-preserving transformations will be presented: retiming, recycling, early evaluation, variable-latency units and speculative execution. The application of these transformations for performance and power optimization will be discussed. Finally, a novel framework for microarchitectural exploration will be introduced, showing that the optimal pipelining of a circuit can be automatically obtained by using the previous transformations.

Retiming and recycling are two transformations used to optimize the performance of latency-insensitive (a.k.a. synchronous elastic) systems. This paper presents an approach that combines these two transformations for performance optimization of elastic systems with early evaluation. The method is based on Mixed Integer Linear Programming.

Speculation is a well-known technique for increasing parallelism of the microprocessor pipelines and hence their performance. While implementing speculation in modern design practice is error-prone and mostly ad-hoc, this paper proposes a correct-by-construction method for implementing speculation in Elastic Systems. The technique is based on applying provably correct transformations. The benefits of speculation are illustrated with two examples in which these transformations are systematically applied. The method proposed in this paper is amenable for automation in a synthesis flow.

This paper presents a method for correct-by-construction microarchitectural pipelining that handles cyclic systems with dependencies between iterations. Our method combines previously known bypass and retiming transformations with a few transformations valid only for elastic systems with early evaluation (namely, empty FIFO insertion, FIFO capacity sizing, insertion of anti-tokens, and introducing early evaluation multiplexors). By converting the design to a synchronous elastic form and then applying this extended set of transformations, one can pipeline a functional specification with an automatically generated distributed controller that implements stalling logic resolving data hazards off the critical path of the design. We have developed an interactive toolkit for exploring elastic microarchitectural transformations. The method is illustrated by pipelining a few simple examples of instruction set architecture ISA specifications.