The fifth release of the multithreaded language Cilk uses a provably good "work-stealing" scheduling algorithm similar to the first system, but the language has been completely redesigned and the runtime system completely reengineered. The efficiency of the new implementation was aided by a clear strategy that arose from a theoretical analysis of the scheduling algorithm: concentrate on minimizing overheads that contribute to the work, even at the expense of overheads that contribute to the critical path. Although it may seem counterintuitive to move overheads onto the critical path, this "work-first" principle has led to a portable Cilk-5 implementation in which the typical cost of spawning a parallel thread is only between 2 and 6 times the cost of a C function call on a variety of contemporary machines. Many Cilk programs run on one processor with virtually no degradation compared to equivalent C programs. This paper describes how the work-first principle was exploited in the design...

A lambda-calculus schema is an expression of the lambda calculus augmented by uninterpreted constant and operator symbols. It is an abstraction of programming languages such as LISP which permit functions to be passed to and returned from other functions. When given an interpretation for its constant and operator symbols, certain schemata, called lambda abstractions, naturally define partial functions over the domain of interpretation. Two implementation strategies are considered: the retention strategy in which all variable bindings are retained until no longer needed (implying the use of some sort of garbage-collected store) and the deletion strategy, modeled after the usual stack implementation of ALGOL 60, in which variable bindings are destroyed when control leaves the procedure (or block) in which they were created. Not all lambda abstractions evaluate correctly under the deletion strategy. Nevertheless, both strategies are equally powerful in the sense that any lambda abstraction can be mechanically translated into another that evaluates correctly under the deletion strategy and defines the same partial function over the domain of interpretation as the original. Proof is by translation into continuation-passing style.

We introduce dag consistency, a relaxed consistency model for distributed shared memory which is suitable for multithreaded programming. We have implemented dag-consistency in software for the Cilk multithreaded runtime system running on a Connection Machine CM5. Our implementation includes a dag-consistent distributed cactus stack for storage allocation. We provide empirical evidence of the flexibility and efficiency of dag consistency for applications that include blocked matrix multiplication, Strassen’s matrix multiplication algorithm, and a Barnes-Hut code. Although Cilk schedules the executions of these programs dynamically, their performances are competitive with statically scheduled implementations in the literature. We also prove that the number FP of page faults incurred by a user program running onPprocessors can be related to the numberF1of page faults running serially by the formula FP F1+2Cs, where C is the cache size andsis the number of thread migrations executed by Cilk’s scheduler.

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.

Abstract not found

This article presents a model of the reflective tower based on the formal semantics of its levels. They are related extensionally by their mutual interpretation and intensionally by reification and reflection. The key points obtained here are: a formal relation between the semantic domains of each level; a formal identification of reification and reflection; the visualisation of intensional snapshots of a tower of interpreters; a formal justification and a generalization of Brown's meta-continuation; a (structural) denotational semantics for a compositional subset of the model; the distinction between making continuations jumpy and pushy; the discovery of the tail-reflection property; and a Scheme implementation of a properly tail-reflective and single-threaded reflective tower. Section 1 presents the new approach taken here: rather than implementing reification and reflection leading to a tower, we consider an infinite tower described by the semantics of each level and relate these ...

. Dynamic binding, which has always been associated with Lisp, is still semantically obscure to many. Although largely replaced by lexical scoping, not only does dynamic binding remain an interesting and expressive programming technique in specialised circumstances, but also it is a key notion in semantics. This paper presents a syntactic theory that enables the programmer to perform equational reasoning on programs using dynamic binding. The theory is proved to be sound and complete with respect to derivations allowed on programs in "dynamic-environment passing style". From this theory, we derive a sequential evaluation function in a context-rewriting system. Then, we exhibit the power and usefulness of dynamic binding in two different ways. First, we prove that dynamic binding adds expressiveness to a purely functional language. Second, we show that dynamic binding is an essential notion in semantics that can be used to define the semantics of exceptions. Afterwards, we further refin...

right notice and this permission notice are preserved on all copies.

Cilk (pronounced "silk") is a C-based language for multithreaded parallel programming. Cilk makes it easy to program irregular parallel applications, especially as compared with data-parallel or message-passing programming systems. A Cilk programmer need not worry about protocols and load balancing, which are handled by Cilk's provably efficient runtime system. Many regular and irregular Cilk applications run nearly as fast on one processor as comparable C programs, and they scale well to many processors. 1 Background and goals Cilk is an algorithmic multithreaded language. The philosophy behind Cilk is that a programmer should concentrate on structuring his program to expose parallelism and exploit locality, leaving the runtime system with the responsibility of scheduling the computation to run efficiently on a given platform. Cilk's runtime system takes care of details like load balancing and communication protocols. Unlike other multithreaded languages, however, Cilk is algor...