A reordering technique for efficient code motion

Dutt

IEE Proc., Comput. Digit. Tech.

et al. 2003

The quality of high-level synthesis results for designs with complex and nested conditionals and loops can be improved significantly by employing speculative code motions. Two techniques are presented that add scheduling steps to the branch of a conditional construct with fewer scheduling steps. This 'balances' or equalises the number of scheduling steps in the conditional branches and increases the scope for application of speculative code motions. These branch balancing techniques have been applied 'dynamically' during scheduling. The authors have implemented algorithms for dynamic branch balancing techniques in a C-to-VHDL high-level synthesis framework called Spark. The utility of these techniques is demonstrated by experimental results on four designs derived from two moderately complex applications, namely, MPEG-1 and the GIMP image processing tool. These results show that the two branch balancing techniques can reduce the cycles on the longest path through the design by up to 38% and the number of states in the controller by up to 37%.

Section: Related Workmentioning

confidence: 99%

Dynamically increasing the scope of code motions during the high-level synthesis of digital circuits

Dutt

IEE Proc., Comput. Digit. Tech.

et al. 2003

Proceedings of the 2006 Conference on Asia South Pacific Design Automation - ASP-DAC '06

“…Those new techniques are well known in the software compilers area [7,5], and their application to the high level synthesis problem has been proposed by Santos et al [4] and Rim et al [23]. Several works such as the Waveschedule approach [12] have introduced the speculative execution as an efficient method to achieve the goal of the minimization of the expected number of cycles.…”

Section: Introductionmentioning

confidence: 99%

Using speculative computation and parallelizing techniques to improve scheduling of control based designs

Cordone¹,

Feffandi²,

Santambrogio³

et al. 2006

Recent research results have seen the application of parallelizing techniques to high-level synthesis. In particular, the effect of speculative code transformations on mixed control-data flow designs has demonstrated effective results on schedule lengths. In this paper we first analyze the use of the control and data dependence graph as an intermediate representation that provides the possibility of extracting the maximum parallelism. Then we analyze the scheduling problem by formulating an approach based on Integer Linear Programming (ILP) to minimize the number of control steps given the amount of resources. We improve the already proposed ILP scheduling approaches by introducing a new conditional resource sharing constraint which is then extended to the case of speculative computation. The ILP formulation has been solved by using a Branch and Cut framework which provides better results than standard branch and bound techniques.

2003 Design, Automation and Test in Europe Conference and Exhibition

“…The "Waveschedule" approach [7] incorporates speculative execution into high-level synthesis to achieve its objective of minimizing the expected number of cycles. Recent work by Rim [8], Santos [1] and Kountouris [9] supports generalized speculative code motions for scheduling in high-level synthesis.…”

Section: Related Workmentioning

confidence: 99%

“…These code motions enable the movement of operations through, beyond, and into conditionals with the objective of maximizing performance [1,2,3]. However, this means that the heuristics that guide these code motions have to carefully manage the resource utilization across several basic blocks.…”

Section: Introductionmentioning

confidence: 99%

Dynamic conditional branch balancing during the high-level synthesis of control-intensive designs

Cupta¹,

Dutt²,

Gupta³

et al.

We present two novel strategies to increase the scope for application of speculative code motions: (1) Adding scheduling steps dynamically during scheduling to conditional branches with fewer scheduling steps. This increases the opportunities to apply code motions such as conditional speculation that duplicate operations into the branches of a conditional block. (2) Determining if an operation can be conditionally speculated into multiple basic blocks either by using existing idle resources or by creating new scheduling steps. These strategies lead to balancing of the number of steps in the conditional branches without increasing the longest path through the conditional block. Algorithms for these strategies have been implemented within the Spark high-level synthesis framework that accepts a behavioral description in ANSI-C as input and produces synthesizable register-transfer level VHDL. Experiments on two moderately complex industrial-strength applications, namely, MPEG-1 and the GIMP image processing tool, demonstrate that conditional speculation is ineffective without using these strategies.