MADNESS: A Multiresolution, Adaptive Numerical Environment for Scientific Simulation

Harrison, Robert J.; Beylkin, Gregory; Bischoff, Florian A.; Calvin, Justus A.; Fann, George I.; Fosso-Tande, Jacob; Galindo, Diego; Hammond, Jeff R.; Hartman-Baker, Rebecca; Hill, Judith; Jia, Jun; Kottmann, Jakob S.; Ou, M-J. Yvonne; Pei, Junchen; Ratcliff, Laura E.; Reuter, Matthew G.; Richie-Halford, Adam; Romero, Nichols A.; Sekino, Hideo; Shelton, W. A.; Sundahl, Bryan; Thornton, W. Scott; Valeev, Edward F.; Vázquez-Mayagoitia, Álvaro; Vence, Nicholas; Yanai, Takeshi; Yokoi, Yukina

doi:10.1137/15m1026171

Cited by 96 publications

(105 citation statements)

References 40 publications

Supporting

Mentioning

104

Contrasting

Unclassified

Order By: Relevance

“…Therefore tensors B and

\overset{B}{true}

are distributed to make it possible to perform CCSD computations with several thousand basis functions on machines with modest per‐node memory size. Remote tiles of B and

\overset{B}{true}

are fetched asynchronously so that their communication overlaps with the computation of W via the use of remote messaging layer of the MADNESS parallel runtime that TiledArray is built on. Note that the lazy evaluation of W trades space for time: the memory requirement is reduced at the cost of reconstructing tensor W every CCSD iteration.…”

Section: Methodsmentioning

confidence: 99%

Coupled‐cluster singles, doubles and perturbative triples with density fitting approximation for massively parallel heterogeneous platforms

Peng

Calvin

Valeev

2019

Int J of Quantum Chemistry

Self Cite

View full text Add to dashboard Cite

A high‐performance implementation of the coupled‐cluster singles, doubles, and perturbative triples [CCSD(T)] is developed in the Massively Parallel Quantum Chemistry program. Novel features include: (1) reduced memory requirements via a density‐fitting (DF) CCSD implementation utilizing distributed lazy evaluation for tensors with more than two unoccupied indices and (2) the ability to utilize efficiently many‐core nodes (Intel Xeon Phi) and heterogeneous nodes with multiple NVIDIA GPUs on each node. All data that are greater than quadratic in the system size are distributed among processes. Excellent strong scaling is observed on distributed‐memory computers equipped with conventional CPUs, Intel Xeon Phi processors, and heterogeneous nodes with multiple NVIDIA GPUs Canonical CCSD(T) energies can be evaluated for systems containing 200 electrons and 1000 basis functions in a few days using a small size commodity cluster, with even larger computations possible on leadership‐class computing resources.

show abstract

“…Therefore tensors B and

\overset{B}{true}

are distributed to make it possible to perform CCSD computations with several thousand basis functions on machines with modest per‐node memory size. Remote tiles of B and

\overset{B}{true}

Section: Methodsmentioning

confidence: 99%

Coupled‐cluster singles, doubles and perturbative triples with density fitting approximation for massively parallel heterogeneous platforms

Peng

Calvin

Valeev

2019

Int J of Quantum Chemistry

Self Cite

View full text Add to dashboard Cite

show abstract

“…Assignment in Grafter only allows writing to data fields, and hence tree nodes can not be modified in an assignment statement. Local variables in the body of the traversal can either be data definitions (primitive or objects), or aliases to tree nodes (rules 13,14). Note that an alias variable is a constant pointer to a tree node that can only be assigned once to a descendant tree node and cannot be changed.…”

Section: Languagementioning

confidence: 99%

“…MADNESS (Multiresolution, Adaptive Numerical Environment for Scientific Simulation) [13] uses kd-trees to compactly represent piecewise functions over a multi-dimensional domain. The inner nodes of the tree divide the domain of the function into different sub-domains, while leaf nodes store the coefficients of a polynomial that estimates the function within the node's sub-domain.…”

Section: Case Study 3: Piecewise Functionsmentioning

confidence: 99%

Sound, fine-grained traversal fusion for heterogeneous trees

Sakka

Sundararajah

Newton

et al. 2019

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

View full text Add to dashboard Cite

Applications in many domains are based on a series of traversals of tree structures, and fusing these traversals together to reduce the total number of passes over the tree is a common, important optimization technique. In applications such as compilers and render trees, these trees are heterogeneous: different nodes of the tree have different types. Unfortunately, prior work for fusing traversals falls short in different ways: they do not handle heterogeneity; they require using domain-specific languages to express an application; they rely on the programmer to aver that fusing traversals is safe, without any soundness guarantee; or they can only perform coarse-grain fusion, leading to missed fusion opportunities. This paper addresses these shortcomings to build a framework for fusing traversals of heterogeneous trees that is automatic, sound, and fine-grained. We show across several case studies that our approach is able to allow programmers to write simple, intuitive traversals, and then automatically fuse them to substantially improve performance.

show abstract

“…Figure 3 shows per process memory consumption versus job size when running the Sequoia AMG benchmark [1] on the prototype with both the eager and lazy VC initialization strategies. The benchmark was configured to solve a Laplace-type problem 4 with two different three-dimensional processor layouts. The first layout was cubic (e.g., 36 processes organized as P x ⇥P y ⇥P z = 6⇥6⇥6).…”

Section: Application Impactmentioning

confidence: 99%

“…Kiki uses dedicated "server processes" that only process such messages but perform no application computation, again wasting some user-defined number of cores for these processes. Applications in other domains, such as MADNESS [4] (computational chemistry), are similarly restricted and emulate AM functionality using MPI SEND / MPI RECV with threads.…”

Section: Data Accessmentioning

confidence: 99%

Runtime Support for Irregular Computation in MPI-Based Applications

Zhao

Balaji

Gropp

2015

2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing

View full text Add to dashboard Cite

In recent years there are increasing number of applications that have been using irregular computation models in various domains, such as computational chemistry, bioinformatics, nuclear reactor simulation and social network analysis. Due to the irregular and datadependent communication patterns and sparse data structures involved in those applications, the traditional parallel programming model and runtime need to be carefully designed and implemented in order to accommodate the performance and scalability requirements of those irregular applications on large-scale systems. This thesis consists of two subtopics. The first subtopic focuses on improving MPI runtime to support the irregular applications from perspective of scalability and performance. The first three parts in this subtopic focus on MPI one-sided communication. In the first part, we present a thorough survey of current MPI one-sided implementations and illustrate scalability limitations in those implementations. In the second part, we propose a new design and implementation of MPI one-sided communication, called ScalaRMA, to effectively address those scalability limitations. The third part in this subtopic focuses on various issuing strategies in MPI one-sided communication. We propose an adaptive issuing strategy which can adaptively choose between delayed issuing strategy and eager issuing strategy in MPI ii runtime to achieve high performance based on current communication volume in MPI-based application. The last part in this subtopic is to tackle the scalability limitations in the virtual connection (VC) objects in MPI implementation. We propose a scalable design to reduce the memory consumption of VC objects in MPI runtime.The second subtopic of this thesis focuses on improving MPI programming model to better support the irregular applications. Traditional two-sided data movement model in MPI standard designed for scientific computation provides a paradigm for user to specify how to move the data between processes, however, it does not provide interface to flexibly manage the computation, which means user needs to explicitly manage where the computation should be performed. This model is not well suited for irregular applications which involve irregular and data-dependent communication pattern. In this work, we combine Active Messages (AM), an alternative programming paradigm which is more suitable for irregular computations, with traditional MPI data movement model, and propose a generalized MPI-interoperable Active Messages framework (MPI-AM). The framework allows MPI-based applications to incrementally use AMs only when necessary, avoiding rewriting the entire MPI-based application. Such framework integrates data movement and computation together in the programming model and MPI can coordinate the computation and communication in a much more flexible manner. In this subtopic, we propose several strategies including message streaming, buffer management and asynchronous processing, in order to efficiently handle AMs inside MPI. We al...

show abstract

MADNESS: A Multiresolution, Adaptive Numerical Environment for Scientific Simulation

Cited by 96 publications

References 40 publications

Coupled‐cluster singles, doubles and perturbative triples with density fitting approximation for massively parallel heterogeneous platforms

Coupled‐cluster singles, doubles and perturbative triples with density fitting approximation for massively parallel heterogeneous platforms

Sound, fine-grained traversal fusion for heterogeneous trees

Runtime Support for Irregular Computation in MPI-Based Applications

Contact Info

Product

Resources

About