Cilk (pronounced "silk") is a C-based runtime system for multithreaded parallel programming. In this paper, we document the efficiency of the Cilk work-stealing scheduler, both empirically and analytically. We show that on real and synthetic applications, the "work" and "critical-path length" of a Cilk computation can be used to model performance accurately. Consequently, a Cilk programmer can focus on reducing the computation's work and critical-path length, insulated from load balancing and other runtime scheduling issues. We also prove that for the class of "fully strict" (well-structured) programs, the Cilk scheduler achieves space, time, and communication bounds all within a constant factor of optimal. The Cilk

This paper studies the problem of efficiently scheduling fully strict (i.e., well-structured) multithreaded computations on parallel computers. A popular and practical method of scheduling this kind of dynamic MIMD-style computation is "work stealing," in which processors needing work steal computational threads from other processors. In this paper, we give the first provably good work-stealing scheduler for multithreaded computations with dependencies. Specifically,

Many high-level parallel programming languages allow for fine-grained parallelism. As in the popular work-time framework for parallel algorithm design, programs written in such languages can express the full parallelism in the program without specifying the mapping of program tasks to processors. A common concern in executing such programs is to schedule tasks to processors dynamically so as to minimize not only the execution time, but also the amount of space (memory) needed. Without careful scheduling, the parallel execution on p processors can use a factor of p or larger more space than a sequential implementation of the same program. This paper first identifies a class of parallel schedules that are provably efficient in both time and space. For any

An operating system’s design is often influenced by the architecture of the target hardware. While uniprocessor and multiprocessor architectures are well understood, such is not the case for multithreaded chip multiprocessors (CMT) – a new generation of processors designed to improve performance of memory-intensive applications. The first systems equipped with CMT processors are just becoming available, so it is critical that we now understand how to obtain the best performance from such systems. The goal of our work is to understand the fundamentals of CMT performance and identify the implications for operating system design. We have analyzed how the performance of a CMT processor is affected by contention for the processor pipeline, the L1 data cache, and the L2 cache, and have investigated operating system approaches to the management of these performance-critical resources. Having found that contention for the L2 cache can have the greatest negative impact on processor performance, we have quantified the potential performance improvement that can be achieved from L2-aware OS scheduling. We evaluated a scheduling policy based on the balance-set principle and found that it has a potential to reduce miss ratios in the L2 by 19-37 % and improve processor throughput by 27-45%. To achieve a similar improvement in hardware requires doubling the size of the L2 cache. 1.

Abstract not found

Although cost-effective parallel machines are now commercially available, the widespread use of parallel processing is still being held back, due mainly to the troublesome nature of parallel programming. In particular, it is still diiticult to build eiticient implementations of parallel applications whose communication patterns are either highly irregular or dependent upon dynamic information. Multithreading has become an increasingly popular way to implement these dynamic, asynchronous, concurrent programs. Cilk (pronounced "silk") is our C-based multithreaded computing system that provides provably good performance guarantees. This thesis describes the evolution of the Cilk language and runtime system, and describes applications which affected the evolution of the system.

This paper presents a new asynchronous programming library (libasync-smp) that allows event-driven applications to take advantage of multiprocessors by running code for event handlers in parallel. To control the concurrency between events, the programmer can specify a color for each event: events with the same color (the default case) are handled serially; events with different colors can be handled in parallel. The programmer can incrementally expose parallelism in existing event-driven applications by assigning different colors to computationally-intensive events that do not share mutable state. An

Distributed implementations of programming languages with implicit parallelism hold out the prospect that the parallel programs are immediately scalable. This paper presents some of the results of our part of Esprit 415, in which we considered the implementation of lazy functional programming languages on distributed architectures. A compiler and abstract machine were designed to achieve this goal. The abstract parallel machine was formally specified, using Miranda 1 . Each instruction of the abstract machine was then implemented as a macro in the Transputer Assembler. Although macro expansion of the code results in non-optimal code generation, use of the Miranda specification makes it possible to validate the compiler before the Transputer code is generated. The hardware currently available consists of five T800--25's, each board having 16M bytes of memory. Benchmark timings using this hardware are given. In spite of the straight forward code-generation, the resulting system compar...

Recent work on scheduling algorithms has resulted in provable bounds on the space taken by parallel computations in relation to the space taken by sequential computations. The results for online versions of these algorithms, however, have been limited to computations in which threads can only synchronize with ancestor or sibling threads. Such computations do not include languages with futures or user-specified synchronization constraints. Here we extend the results to languages with synchronization variables. Such languages include languages with futures, such as Multilisp and Cool, as well as other languages such asid. The main result is an online scheduling algorithm which, given a computation with w work (total operations), synchronizations, d depth (critical path) and s1 sequential space, will run in O(w=p + log(pd)=p + d log(pd)) time and s1 + O(pd log(pd)) space, on a p-processor crcw pram with a fetch-and-add primitive. This includes all time and space costs for both the computation and the scheduler. The scheduler is non-preemptive in the sense that it will only move a thread if the thread suspends on a synchronization, forks a new thread, or exceeds a threshold when allocating space. For the special case where the computation is a planar graph with left-to-right synchronization edges, the scheduling algorithm can be implemented in O(w=p+d log p) time and s1 + O(pd log p) space. These are the first nontrivial space bounds described for such languages.

This article presents an on-line scheduling algorithm that is provably space e#cient and time e#cient for nested-parallel languages. For a computation with depth D and serial space requirement S1 , the algorithm generates a schedule that requires at most S1 +O(K D p)space (including scheduler space) on p processors. Here, K is a user-adjustable runtime parameter specifying the net amount of memory that a thread may allocate before it is preempted by the scheduler. Adjusting the value of K provides a trade-o# between the running time and the memory requirement of a parallel computation. To allow the scheduler to scale with the number of processors, we also parallelize the scheduler and analyze the space and time bounds of the computation to include scheduling costs. In addition to showing that the scheduling algorithm is space and time e#cient in theory, we demonstrate that it is e#ective in practice. We have implemented a runtime system that uses our algorithm to schedule lightweight parallel threads. The results of executing parallel programs on this system show that our scheduling algorithm significantly reduces memory usage compared to previous techniques, without compromising performance