ForestGOMP: An Efficient OpenMP Environment for NUMA Architectures

Broquedis, François; Furmento, Nathalie; Goglin, Brice; Wacrenier, Pierre‐André; Namyst, Raymond

doi:10.1007/s10766-010-0136-3

Cited by 68 publications

(62 citation statements)

References 21 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, we control the allocation policy to favor the physical memory attached to the thread NUMA domain. Managing NUMA locality while load-balancing workload is typically achieved either through migrating data to workers [3] or assigning workers based on their proximity to data [2]. For Libtensor, a large fraction of the working set is created after task assignment making traditional techniques not directly applicable.…”

Section: A Explicit Locality Managementmentioning

confidence: 99%

Analysis and tuning of libtensor framework on multicore architectures

Ibrahim

Williams

Epifanovsky

et al. 2014

2014 21st International Conference on High Performance Computing (HiPC)

View full text Add to dashboard Cite

Abstract-Libtensor is a framework designed to implement the tensor contractions arising form the coupled cluster and equations of motion computational quantum chemistry equations. It has been optimized for symmetry and sparsity to be memory efficient. This allows it to run efficiently on the ubiquitous and cost-effective SMP architectures. Unfortunately, movement of memory controllers on chip has endowed these SMP systems with strong NUMA properties. Moreover, the manycore trend in processor architecture demands that the implementation be extremely thread-scalable on node. To date, Libtensor has been generally agnostic of these effects. To that end, in this paper, we explore a number of optimization techniques including a thread-friendly and NUMA-aware memory allocator and garbage collector, tuning the tensor tiling factor, and tuning the scheduling quanta. In the end, our optimizations can improve the performance of contractions implemented in Libtensor by up to 2× on representative Ivy Bridge, Nehalem, and Opteron SMPs.Index Terms-tensor algebra, parallel programming, quantum chemistry software.

show abstract

Section: A Explicit Locality Managementmentioning

confidence: 99%

Analysis and tuning of libtensor framework on multicore architectures

Ibrahim

Williams

Epifanovsky

et al. 2014

2014 21st International Conference on High Performance Computing (HiPC)

View full text Add to dashboard Cite

show abstract

“…The approach taken in the ForestGOMP [25,26] runtime system is particularly relevant to our work. The ForestGOMP approach focuses on two aspects of the memory association problem.…”

Section: Memory Association and Distributionmentioning

confidence: 99%

“…These models do not define explicit mappings of data to devices, but rather associate data to threads. Some examples of this include Forest-GOMP [25,26] and UPMLib [74]. Even some approaches explored in the Linux kernel for automatic page migration could fall into this category, mapping data to threads by tracking remote-access faults in the system.…”

Section: Memory Association and Distributionmentioning

confidence: 99%

Runtime Adaptation for Autonomic Heterogeneous Computing

Scogland

Feng

2014

2014 14th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing

View full text Add to dashboard Cite

Heterogeneity is increasing across all levels of computing, with the rise of accelerators such as GPUs, FPGAs, and other coprocessors into everything from cell phones to supercomputers. More quietly it is increasing with the rise of NUMA systems, hierarchical caching, OS noise, and a myriad of other factors. As heterogeneity becomes a fact of life, efficiently managing heterogeneous compute resources is becoming a critical, and ever more complex, task. The focus of this dissertation is to lay the foundation for an autonomic system for heterogeneous computing, employing runtime adaptation to improve performance portability and performance consistency while maintaining or increasing programmability. We investigate heterogeneity arising from a myriad of factors, grouped into the dimensions of locality and capability. This work has resulted in runtime schedulers capable of automatically detecting and mitigating heterogeneity in physically homogeneous systems through MPI and adaptive coscheduling for physically heterogeneous accelerator based systems as well as a synthesis of the two to address multiple levels of heterogeneity as a coherent whole. We also discuss our current work towards the next generation of fine-grained scheduling and synchronization across heterogeneous platforms in the design of a highly-scalable and portable concurrent queue for many-core systems. Each component addresses aspects of the urgent need for automated management of the extreme and ever expanding complexity introduced by heterogeneity. I have also had the good fortune to collaborate with both Lawrence Livermore National Laboratory and Argonne National Laboratory. Experiences as an intern at each lab has had a significant effect on the final shape of my dissertation. Special thanks go to Dr. Pavan Balaji (again), Dr. Bronis de Supinski (again) and Dr. Barry Rountree. These collaborations proved to be major turning points for me, both in my research and my life as a whole.

show abstract

“…ForestGOMP [9] made some modification to STREAM benchmark. STREAM measures sustainable memory bandwidth and the corresponding computation rate for simple vectors.…”

Section: Related Workmentioning

confidence: 99%

“…Linux traditionally had ways to bind threads to specific CPUs/Cores and NUMA API extends that to allow programs to specify on which node memory should be allocated. Some more complicated APIs are based on these basic policies, such as MAi [7] and MaMI [9].It is not an easy task to apply these API because it is much difficult to find the communication pattern in shared memory platform than message passing platform, because it is implicit and occurs through the memory accesses. Recently, some tools are available to guide a program developer on where to judiciously apply these API within a large parallel code [10][11] [12].…”

Section: Introductionmentioning

confidence: 99%

MAP-numa: Access Patterns Used to Characterize the NUMA Memory Access Optimization Techniques and Algorithms

Luo

Liu

Kong

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Some typical memory access patterns are provided and programmed in C, which can be used as benchmark to characterize the various techniques and algorithms aim to improve the performance of NUMA memory access. These access patterns, called MAP-numa (Memory Access Patterns for NUMA), currently include three classes, whose working data sets are corresponding to 1-dimension array, 2-dimension matrix and 3-dimension cube. It is dedicated for NUMA memory access optimization other than measuring the memory bandwidth and latency. MAP-numa is an alternative to those exist benchmarks such as STREAM, pChase, etc. It is used to verify the optimizations' (made automatically/manually to source code/executive binary) capacities by investigating what locality leakage can be remedied. Some experiment results are shown, which give an example of using MAP-numa to evaluate some optimizations based on Oprofile sampling.

show abstract

ForestGOMP: An Efficient OpenMP Environment for NUMA Architectures

Cited by 68 publications

References 21 publications

Analysis and tuning of libtensor framework on multicore architectures

Analysis and tuning of libtensor framework on multicore architectures

Runtime Adaptation for Autonomic Heterogeneous Computing

MAP-numa: Access Patterns Used to Characterize the NUMA Memory Access Optimization Techniques and Algorithms

Contact Info

Product

Resources

About