. Lazy task creation (LTC) is an efficient approach for executing divide and conquer parallel programs that has been used in the implementation of Multilisp's future construct. Unfortunately it requires a specialized memory management scheme, in particular for stack frames, which makes it hard to use in the context of conventional languages. We have designed a variant of LTC which has a stack management discipline that is compatible with the semantics of conventional languages. This mechanism, which we call lazy remote procedure call, has been used to implement a parallel variant of C. A first prototype of our system has been ported to shared-memory multiprocessors and network of workstations. Experimental results on a Cray T3D multipr...
Many modern parallel languages support dynamic creation of threads or require multithreading in thei...
This paper presents three novel language implementation primitives—lazy threads, stacklets, and sync...
This thesis studies efficient runtime systems for parallelism management (multithreading) and memory...
Many parallel algorithms are naturally expressed at a fine level of granularity, often finer than a ...
This thesis describes a high-performance implementation technique for Multilisp's "future&...
In this paper we describe lazy threads, a new approach for implementing multi-threaded execution mod...
this paper we describe the features and semantics of ParC. The rest of this section explains the mot...
Higher-level parallel programming languages can be difficult to implement efficiently on parallel ma...
One of the major problems in writing programs to take advantage of parallel processing has been the ...
This thesis describes Cilk, a parallel multithreaded language for programming contemporary shared me...
A new parallel programming, ELC, Experimental Language Based on C, is designed and implemented. A ru...
We have extended the task management scheme for the parallel computer algebra package PACLIB. This e...
Many modern parallel languages support dynamic creation of threads or require multithreading in thei...
Lightweight Remote Procedure Call (LRPC) is a communication facility designed and optimized for comm...
. Research into automatic extraction of instruction-level parallelism and data parallelism from sequ...
Many modern parallel languages support dynamic creation of threads or require multithreading in thei...
This paper presents three novel language implementation primitives—lazy threads, stacklets, and sync...
This thesis studies efficient runtime systems for parallelism management (multithreading) and memory...
Many parallel algorithms are naturally expressed at a fine level of granularity, often finer than a ...
This thesis describes a high-performance implementation technique for Multilisp's "future&...
In this paper we describe lazy threads, a new approach for implementing multi-threaded execution mod...
this paper we describe the features and semantics of ParC. The rest of this section explains the mot...
Higher-level parallel programming languages can be difficult to implement efficiently on parallel ma...
One of the major problems in writing programs to take advantage of parallel processing has been the ...
This thesis describes Cilk, a parallel multithreaded language for programming contemporary shared me...
A new parallel programming, ELC, Experimental Language Based on C, is designed and implemented. A ru...
We have extended the task management scheme for the parallel computer algebra package PACLIB. This e...
Many modern parallel languages support dynamic creation of threads or require multithreading in thei...
Lightweight Remote Procedure Call (LRPC) is a communication facility designed and optimized for comm...
. Research into automatic extraction of instruction-level parallelism and data parallelism from sequ...
Many modern parallel languages support dynamic creation of threads or require multithreading in thei...
This paper presents three novel language implementation primitives—lazy threads, stacklets, and sync...
This thesis studies efficient runtime systems for parallelism management (multithreading) and memory...