DAG-consistent distributed shared memory

Blumofe, Robert D.; Frigo, Matteo; Joerg, Christopher F.; Leiserson, Charles E.; Randall, Keith H.

doi:10.1109/ipps.1996.508049

Cited by 50 publications

(52 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results led to the development of a performance model that accurately predicts the efficiency of a Cilk program using two simple parameters: work and critical-path length [5,7,2]. More recent research has included page faults as a measure of locality [3,4,17].…”

Section: Background and Goalsmentioning

confidence: 99%

“…Cilk-3 featured an implementation of dag-consistent distributed shared memory [4,17]. With this addition of shared memory, Cilk could be applied to solve a much wider class of applications.…”

Section: Background and Goalsmentioning

confidence: 99%

“…In this example, f oo() passes variable x to bar() by reference, and then it proceeds to read x before the sync. 4 Concurrently, bar() reads x through the pointer px. This way of sharing the value of x is safe, because the shared variable x is assigned in foo() before barQ is spawned, and no write accesses happen on x thereafter.…”

Section: Shared Memorymentioning

confidence: 99%

“…Three world-class chess programs, *Tech [19], *Socrates [18], and Cilkchess, were written in Cilk by the Cilk group at MIT. Cilk provides an effective platform for programming dense and sparse numerical algorithms, such as matrix factorization [4] and JV-body simulations. Unlike many other multithreaded programming systems, Cilk is algorithmic, in that the runtime system employs a scheduler that allows the performance of programs to be estimated accurately [5] based on abstract complexity measures.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

CILK: A Multi-Threaded Programming System for Meta-Computers

Snyder¹

2001

View full text Add to dashboard Cite

Public reporting burden for this collection of information is estimated to avenge 1 hour pet response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed end the collection ol information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services Di. 12b. DISTRIBUTION CODE ABSTRACT (Maximum 200 words!Contracts F30602-97-1-0150 and F30602-97-1-0270 were a joint effort but funded using different contract vehicles at the request of DARPA, the sponsoring agency. This report documents the design and development of CILK, a language for multi-threaded parallel programming based on ANSI C. CILK is designed for genera-purpose parallel programming, but it is especially effective for exploiting dynamic, highly asynchronous parallelism, which can be difficult to write in data-parallel or message-passing style. Three world-class chess programs were written in CILK by the CILK group at MIT. CILK provides an effective platform for programming dense and sparse numerical algorithms, such as matrix factorization and N-body simulations. Unlike many other multithreaded programming systems, CILK is algorithmic, in that the runtime system employs a scheduler that allows the performance of programs to be estimated accurately based on abstract complexity measures. CILK is available for download at

show abstract

Section: Background and Goalsmentioning

confidence: 99%

Section: Background and Goalsmentioning

confidence: 99%

Section: Shared Memorymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CILK: A Multi-Threaded Programming System for Meta-Computers

Snyder¹

2001

View full text Add to dashboard Cite

show abstract

“…The second column of table 5.2 describes how the annotations are implemented for software cache coherency. This protocol resembles the Backer cache coherency protocol [19]. Exclusive access is enforced by acquiring a lock on a mutex that is related to the object that is protected.…”

Section: Back-end Example: Three Views On Starburstmentioning

confidence: 99%

Programming models for many-core architectures: a co-design approach

Rutgers¹

View full text Add to dashboard Cite

It is unlikely that general-purpose single-core performance will improve much in the coming years. The clock speed is limited by physical constraints, and recent architectural improvements are not as beneficial for performance as those were several years ago. However, the transistor count and density per chip still increase, as feature sizes reduce, and material and processing techniques improve. Given a limited single-core performance, but plenty of transistors, the logical next step is towards many-core.A many-core processor contains at least tens of cores and usually distributed memory, which are connected (but physically separated) by an interconnect that has a communication latency of multiple clock cycles. In contrast to a multicore system, which only has a few tightly coupled cores sharing a single bus and memory, several complex problems arise. Notably, many cores require many parallel tasks to fully utilize the cores, and communication happens in a distributed and decentralized way. Therefore, programming such a processor requires the application to exhibit concurrency. Moreover, a concurrent application has to deal with memory state changes with an observable (non-deterministic) intermediate state, whereas singlecore applications observe all state changes to happen atomically. The complexity introduced by these problems makes programming a many-core system with a single-core-based programming approach notoriously hard.The central concept of this thesis is that abstractions, which are related to (manycore) programming, are structured in a single platform model. A platform is a layered view of the hardware, a memory model, a concurrency model, a model of computation, and compile-time and run-time tooling. Then, a programming model is a specific view on this platform, which is used by a programmer.In this view, some details can be hidden from the programmer's perspective, some details cannot. For example, an operating system presents an infinite number of parallel virtual execution units to the application-details regarding scheduling and context switching of processes on one core are hidden from the programmer. On the other hand, a programmer usually has to take full control over separation, distribution, and balancing of workload among different worker threads. To what extent a programmer can rely on automated control over low-level platform-specific details is part of the programming model. This thesis presents modifications to different abstraction layers of a many-core architecture, in order to make the system as a whole more efficient, and to reduce the complexity that is exposed to the programmer via the programming model. viFor evaluation of many-core hardware and corresponding (concurrent) programming techniques, a 32-core MicroBlaze system, named Starburst, is designed and implemented on FPGA. On the hardware architecture level, a network-on-chip is presented that is tailored towards a typical many-core application communication pattern. All cores can access a shared memory, but as this ...

show abstract