Managing Asynchronous Operations in Coarray Fortran 2.0

ACM Trans. Parallel Comput.

Herta

Cunningham

et al. 2016

X10 is a high-performance, high-productivity programming language aimed at large-scale distributed and shared-memory parallel applications. It is based on the Asynchronous Partitioned Global Address Space (APGAS) programming model, supporting the same fine-grained concurrency mechanisms within and across shared-memory nodes.We demonstrate that X10 delivers solid performance at petascale by running (weak scaling) eight application kernels on an IBM Power 775 supercomputer utilizing up to 55,680 Power7 cores (for 1.7Pflop/s of theoretical peak performance). For the four HPC Class 2 Challenge benchmarks, X10 achieves 41% to 87% of the system's potential at scale (as measured by IBM's HPCC Class 1 optimized runs). We also implement KMeans, Smith-Waterman, Betweenness Centrality, and Unbalanced Tree Search (UTS) for geometric trees. Our UTS implementation is the first to scale to petaflop systems.We describe the advances in distributed termination detection, distributed load balancing, and use of high-performance interconnects that enable X10 to scale out to tens of thousands of cores. We discuss how this work is driving the evolution of the X10 language, core class libraries, and runtime systems.

Section: Related Workmentioning

confidence: 86%

X10 and APGAS at Petascale

ACM Trans. Parallel Comput.

Herta

Cunningham

et al. 2016

“…An implementation of the life-line algorithm in Co-Array Fortran achieved 58% efficiency at 8192 nodes [23]. A more recent UTS code using CAF 2.0 finish construct achieves a 74% parallel efficiency on 32,768 Jaguar cores [42]. In comparison, our code reaches 98% parallel efficiency with 55,680 Power7 cores.…”

Section: Related Workmentioning

confidence: 94%

X10 and APGAS at Petascale

Proceedings of the 19th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

Herta

Cunningham

et al. 2014

X10 is a high-performance, high-productivity programming language aimed at large-scale distributed and sharedmemory parallel applications. It is based on the Asynchronous Partitioned Global Address Space (APGAS) programming model, supporting the same fine-grained concurrency mechanisms within and across shared-memory nodes.We demonstrate that X10 delivers solid performance at petascale by running (weak scaling) eight application kernels on an IBM Power 775 supercomputer utilizing up to 55,680 Power7 cores (for 1.7 Pflop/s of theoretical peak performance). We detail our advances in distributed termination detection, distributed load balancing, and use of highperformance interconnects that enable X10 to scale out to tens of thousands of cores.For the four HPC Class 2 Challenge benchmarks, X10 achieves 41% to 87% of the system's potential at scale (as measured by IBM's HPCC Class 1 optimized runs). We also implement K-Means, Smith-Waterman, Betweenness Centrality, and Unbalanced Tree Search (UTS) for geometric trees. Our UTS implementation is the first to scale to petaflop systems.

“…An implementation of the life-line algorithm in Co-Array Fortran achieved 58% efficiency at 8192 nodes [16]. A more recent UTS code using CAF 2.0 finish construct achieves a 74% parallel efficiency on 32,768 Jaguar cores [30]. …”

Section: Related Workmentioning

confidence: 99%

GLB

Zhang

Proceedings of the First Workshop on Parallel Programming for Analytics Applications

Grove

et al. 2014

We present GLB, a programming model and an associated implementation that can handle a wide range of irregular parallel programming problems running over large-scale distributed systems. GLB is applicable both to problems that are easily load-balanced via static scheduling and to problems that are hard to statically load balance. GLB hides the intricate synchronizations (e.g., inter-node communication, initialization and startup, load balancing, termination and result collection) from the users. GLB internally uses a version of the lifeline graph based work-stealing algorithm proposed by Saraswat et al [25]. Users of GLB are simply required to write several pieces of sequential code that comply with the GLB interface. GLB then schedules and orchestrates the parallel execution of the code correctly and efficiently at scale.We have applied GLB to two representative benchmarks: Betweenness Centrality (BC) and Unbalanced Tree Search (UTS). Among them, BC can be statically load-balanced whereas UTS cannot. In either case, GLB scales wellachieving nearly linear speedup on different computer architectures (Power, Blue Gene/Q, and K) -up to 16K cores.