Optimized process placement for collective I/O operations

Venkatesan, Vishwanath; Anand, Rakhi; Subhlok, Jaspal; Gabriel, Edgar

doi:10.1145/2488551.2488567

Cited by 5 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various collective I/O write algorithms are evaluated by Chaarawi et al [6]. Some researches try to optimize collective I/O with techniques such as automatic collective I/O tuning with machine learning [7] and process placement based on the I/O pattern [8]. Twophase I/O is the de facto collective I/O algorithm [9].…”

Section: Related Workmentioning

confidence: 99%

Topology-Aware Strategy for MPI-IO Operations in Clusters

Liu

Zhou

Guo

2018

Journal of Optimization

View full text Add to dashboard Cite

This paper presents the topology-aware two-phase I/O (TATP), which optimizes the most popular collective MPI-IO implementation of ROMIO. In order to improve the hop-bytes metric during the file access, topology-aware two-phase I/O employs the Linear Assignment Problem (LAP) for finding an optimal assignment of file domain to aggregators, an aspect which is not considered in most two-phase I/O implementations. The distribution is based on the local data stored by each process, and its main purpose is to reduce the total hop-bytes of the I/O collective operation. Therefore, the global execution time can be improved. In most of the considered scenarios, topology-aware two-phase I/O obtains important improvements when compared with the original two-phase I/O implementations.

show abstract

Section: Related Workmentioning

confidence: 99%

Topology-Aware Strategy for MPI-IO Operations in Clusters

Liu

Zhou

Guo

2018

Journal of Optimization

View full text Add to dashboard Cite

show abstract

“…From a file system perspective, GPFS [7] [9] evaluate various collective I/O write algorithms. Other approaches to optimizing collective I/O have also been undertaken using techniques such as process placement based on the I/O pattern [10] or collective I/O autotuning with machine learning [11].…”

Section: Related Workmentioning

confidence: 99%

TAPIOCA: An I/O Library for Optimized Topology-Aware Data Aggregation on Large-Scale Supercomputers

Tessier

Vishwanath

Jeannot

2017

2017 IEEE International Conference on Cluster Computing (CLUSTER)

View full text Add to dashboard Cite

Reading and writing data efficiently from storage system is necessary for most scientific simulations to achieve good performance at scale. Many software solutions have been developed to decrease the I/O bottleneck. One well-known strategy, in the context of collective I/O operations, is the twophase I/O scheme. This strategy consists of selecting a subset of processes to aggregate contiguous pieces of data before performing reads/writes. In this paper, we present TAPIOCA, an MPI-based library implementing an efficient topology-aware twophase I/O algorithm. We show how TAPIOCA can take advantage of double-buffering and one-sided communication to reduce as much as possible the idle time during data aggregation. We also introduce our cost model leading to a topology-aware aggregator placement optimizing the movements of data. We validate our approach at large scale on two leadership-class supercomputers: Mira (IBM BG/Q) and Theta (Cray XC40). We present the results obtained with TAPIOCA on a micro-benchmark and the I/O kernel of a large-scale simulation. On both architectures, we show a substantial improvement of I/O performance compared with the default MPI I/O implementation. On BG/Q+GPFS, for instance, our algorithm leads to a performance improvement by a factor of twelve while on the Cray XC40 system associated with a Lustre filesystem, we achieve an improvement of four.

show abstract

“…A number of algorithms have been developed to optimize collective I/O. Venkatesan et al [4] have proposed an approch based on process placement while Isaila et al [5] have chosen to combine autotuning with machine learning techniques. From a more general point of view, studies have been made to evaluate various collective I/O algorithms [6].…”

Section: Related Workmentioning

confidence: 99%

Reproducibility and Variability of I/O Performance on BG/Q: Lessons Learned from a Data Aggregation Algorithm

Tessier

Vishwanath

2017

View full text Add to dashboard Cite

Reading and writing data efficiently from different tiers of storage is necessary for most scientific simulations to achieve good performance at scale. Many software solutions have been developed to decrease the I/O bottleneck. One wellknown strategy, in the context of collective I/O operations, is the two-phase I/O scheme. This strategy consists of selecting a subset of processes to aggregate contiguous pieces of data before performing reads/writes. In our previous work, we implemented the two-phase I/O scheme with a MPI-based topology-aware algorithm. Our algorithm showed very good performance at scale compared to the standard I/O libraries such as POSIX I/O and MPI I/O. However, the algorithm had several limitations hindering a satisfying reproducibility of our experiments. In this paper, we extend our work by 1) identifying the obstacles we face to reproduce our experiments and 2) discovering solutions that reduce the unpredictability of our results.

show abstract

Optimized process placement for collective I/O operations

Cited by 5 publications

References 10 publications

Topology-Aware Strategy for MPI-IO Operations in Clusters

Topology-Aware Strategy for MPI-IO Operations in Clusters

TAPIOCA: An I/O Library for Optimized Topology-Aware Data Aggregation on Large-Scale Supercomputers

Reproducibility and Variability of I/O Performance on BG/Q: Lessons Learned from a Data Aggregation Algorithm

Contact Info

Product

Resources

About