Locality Transformations for Nested Recursive Iteration Spaces

Sundararajah, Kirshanthan; Sakka, Laith; Kulkarni, Milind

doi:10.1145/3093336.3037720

Cited by 4 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventional data locality optimizations: Conventional data locality optimizations strive to improve hit rate in cache hierarchy and reduce the amount of data requests reaching lower level caches and memory system [6,14,17,20,23,27,30,32,34,46,47,51,52,54,55]. Sundararajah et al [48] targeted nested recursions in programs, and proposed a set of scheduling transformations to automatically improves locality at all levels of memory hierarchy. Focusing on GPUs, Li et al [33] characterized the data locality opportunities in GPUs and proposed thread block scheduling policies which are data locality aware.…”

Section: Related Workmentioning

confidence: 99%

“…There exists a substantial body of prior research efforts including data locality-oriented cache optimizations [6,11,22,33,53,57,61], data layout transformations [23,35,37,39,48,59], and neardata computing (NDC) techniques [7,9,19,21,24,29,50], aiming to reduce the cost of data accesses in single-core and manycore systems. Among them, NDC is one popular execution paradigm that offloads computations to execute near data, instead of the traditional approaches that fetch data to computation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mix and Match: Reorganizing Tasks for Enhancing Data Locality

Tang

Kandemir

Karakoy

2021

Proc. ACM Meas. Anal. Comput. Syst.

View full text Add to dashboard Cite

Application programs that exhibit strong locality of reference lead to minimized cache misses and better performance in different architectures. However, to maximize the performance of multithreaded applications running on emerging manycore systems, data movement in on-chip network should also be minimized. Unfortunately, the way many multithreaded programs are written does not lend itself well to minimal data movement. Motivated by this observation, in this paper, we target task-based programs (which cover a large set of available multithreaded programs), and propose a novel compiler-based approach that consists of four complementary steps. First, we partition the original tasks in the target application into sub-tasks and build a data reuse graph at a sub-task granularity. Second, based on the intensity of temporal and spatial data reuses among sub-tasks, we generate new tasks where each such (new) task includes a set of sub-tasks that exhibit high data reuse among them. Third, we assign the newly-generated tasks to cores in an architecture-aware fashion with the knowledge of data location. Finally, we re-schedule the execution order of sub-tasks within new tasks such that sub-tasks that belong to different tasks but share data among them are executed in close proximity in time. The detailed experiments show that, when targeting a state of the art manycore system, our proposed compiler-based approach improves the performance of 10 multithreaded programs by 23.4% on average, and it also outperforms two state-of-the-art data access optimizations for all the benchmarks tested. Our results also show that the proposed approach i) improves the performance of multiprogrammed workloads, and ii) generates results that are close to maximum savings that could be achieved with perfect profiling information. Overall, our experimental results emphasize the importance of dividing an original set of tasks of an application into sub-tasks and constructing new tasks from the resulting sub-tasks in a data movement- and locality-aware fashion.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Mix and Match: Reorganizing Tasks for Enhancing Data Locality

Tang

Kandemir

Karakoy

2021

Proc. ACM Meas. Anal. Comput. Syst.

View full text Add to dashboard Cite

show abstract

“…3), we wish to tile the array based on how its elements are updated in different iterations of the loop, reason about the effect of each loop iteration on the corresponding tile, and then compose the tile-wise reasoning to prove/disprove the overall assertion. Note that the idea of tiling an array based on access patterns in a loop is not new, and has been used earlier in the context of parallelizing and optimizing compilers [7,8]. However, its use in the context of verification has been limited [9].…”

Section: Tiling In a Simple Settingmentioning

confidence: 99%

Verifying Array Manipulating Programs by Tiling

Chakraborty¹,

Gupta²,

Unadkat³

2017

Static Analysis

View full text Add to dashboard Cite

Formally verifying properties of programs that manipulate arrays in loops is computationally challenging. In this paper, we focus on a useful class of such programs, and present a novel property-driven verification method that first infers array access patterns in loops using simple heuristics, and then uses this information to compositionally prove universally quantified assertions about arrays. Specifically, we identify tiles of array accesses patterns in a loop, and use the tiling information to reduce the problem of checking a quantified assertion at the end of a loop to an inductive argument that checks only a slice of the assertion for a single iteration of the loop body. We show that this method can be extended to programs with sequentially composed loops and nested loops as well. We have implemented our method in a tool called Tiler. Initial experiments show that Tiler outperforms several state-of-the-art tools on a suite of interesting benchmarks.Comment: Published in SAS 201

show abstract

Composable, sound transformations of nested recursion and loops

Sundararajah

Kulkarni

2019

Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation

Self Cite

View full text Add to dashboard Cite

Scheduling transformations reorder a program's operations to improve locality and/or parallelism. The polyhedral model is a general framework for composing and applying instancewise scheduling transformations for loop-based programs, but there is no analogous framework for recursive programs. This paper presents an approach for composing and applying scheduling transformations-like inlining, interchange, and code motion-to nested recursive programs. This paper describes the phases of the approach-representing dynamic instances, composing and applying transformations, reasoning about correctness-and shows that these techniques can verify the soundness of composed transformations.

show abstract

Locality Transformations for Nested Recursive Iteration Spaces

Cited by 4 publications

References 29 publications

Mix and Match: Reorganizing Tasks for Enhancing Data Locality

Mix and Match: Reorganizing Tasks for Enhancing Data Locality

Verifying Array Manipulating Programs by Tiling

Composable, sound transformations of nested recursion and loops

Contact Info

Product

Resources

About