V. Karamcheti and A. Chien. Concert: Efficient runtime support for concurrent object-oriented programming languages on stock hardware. Proceedings SUPERCOMPUTING '93, pp. 598--607. IEEE Comput. Soc. Press, Los Alamitos, CA, Nov. 1993.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....half of a program s execution while B is transmitted during the second half of a program s execution. A more dynamic way of handling uninlining may be more appropriate for such programs. Dolby et al. 14] describe an object inlining technique which has been implemented in the Concert compiler [30] (for a dialect of C ) They replace the pointer to an object immediately by the fields of the object pointed to. Their system disallows pointer overwrites and requires the inlining object to point to the inlined object. Also, their system inlines object X into Y at the position of the pointer to ....

V. Karamcheti and A.A. Chien. Concert--Efficient Runtime Support For Concurrent Object-Oriented Programming Languages On Stock Hardware. In Proceedings of the 1993.

....in some of these other systems, though Cilk s algorithm uses randomness and is provably efficient. Many multithreaded programming languages and runtime systems are based on heuristic scheduling techniques. Though systems such as Charm [91] COOL [27, 28] Id [3, 37, 80] Olden [22] and others [29, 31, 38, 44, 54, 55, 63, 88, 98] are based on sound heuristics that seem to perform well in practice and generally have wider applicability than Cilk, none are able to provide any sort of performance guarantee or accurate machine independent performance model. These systems require that performance minded programmers become ....

....somewhat onerous for the programmer, the decision to break procedures into separate nonsuspending threads with heapallocated closures simplifies the Cilk runtime system. Each Cilk thread runs to completion without suspending and leaves the C runtime stack empty when it dies. A common alternative [22, 47, 52, 63, 77, 81] is to directly support spawn return threads (or procedures) in the runtime system, possibly with stack allocated activation frames. In such a system, threads can suspend waiting for synchronization and leave temporary values on the calling stack. Consequently, this alternative strategy requires ....

[Article contains additional citation context not shown here]

Vijay Karamcheti and Andrew Chien. Concert---efficient runtime support for concurrent object-oriented programming languages on stock hardware. In Supercomputing '93, pages 598--607, Portland, Oregon, November 1993.

....on a small cluster of workstations connected by FDDI . CRL runs on two large scale platforms and has been shown to deliver performance competitive with hardware DSM systems. Several all software DSM systems that employ an object based approach have been developed (e.g. Amber [17] Concert [35], Orca [3] Like these systems, CRL effects coherence at the level of application defined regions of memory ( objects ) Any necessary synchronization, data replication, or thread migration functionality is provided automatically at the entry and exit of methods on shared objects. Existing ....

....regions of memory ( objects ) Any necessary synchronization, data replication, or thread migration functionality is provided automatically at the entry and exit of methods on shared objects. Existing systems of this type either require the use of an entirely new object oriented language [3, 35] or only allow the use of a subset of an existing one [17] In contrast, CRL is not language specific; the basic CRL interface could easily be provided in any imperative programming language. Scales and Lam [69] have described SAM, a shared object system for distributed memory machines. SAM is ....

Vijay Karamcheti and Andrew Chien. Concert -- Efficient Runtime Support for Concurrent Object-Oriented Programming Languages on Stock Hardware. In Proceedings of Supercomputing '93, pages 598--607, November 1993.

.... has been supported by the Ministry of Education of Spain under contracts TIC 429 95 and TIC 439 94, ESPRIT project NANOS (21907) the CIRIT under program ACI and by the CEPBA (European Center for Parallelism of Barcelona) package (Filaments [EAD93] Cilk [BJK 95] COOL [CGH93] Concert [KC93] Programming models in the first group offer a loosely synchronous programming model in which parallel jobs can be executed fully in parallel and synchronize at global points (by means of barriers or critical sections) Services included in most user level thread packages allow the ....

V. Karamcheti and A. Chien. Concert -- efficient run-time support for concurrent object--oriented programming languages on stock hardware. In Supercomputing '93, 1993.

....and each actor object may contain several concurrently executing tasks. Actor based languages include ABCL [145] Cantor [11] and Charm [90] Implementations of actor languages require complicated compilation strategies and sophisticated run time support libraries, such as the Concert system [91] for fine grain object management. Because of this complexity, we have not based the LPARX run time system on an existing concurrent object based language. Instead, we borrowed features that were specifically needed for the LPARX implementation. For example, DPO s distributed object naming ....

....of class DistributedParallelObject) actually allocates the data for the array. Execution Model DPO provides a very simple execution model that avoids many of the implementation difficulties and overheads such as execution dispatch, multiple execution streams, frame allocation, and scheduling [91] found in more complicated systems. All processors execute the same code in SPMD fashion, and only the owner of an object (as reported by the DPO registry) executes the computation for that object (i.e. the owner computes rule) For example, recall that LPARX s forall loop iterates in parallel ....

V. Karamcheti and A. Chien, Concert: Efficient runtime support for concurrent object-oriented programming languages on stock hardware, in Proceedings of Supercomputing '93, November 1993.

....abstract models have been proposed for parallel programming,most multicomputer applications are still written using low level message passing libraries. The advantages of high level (e.g. functional, logical, or object oriented) parallel languages have been described extensively in the literature [8, 21, 27, 29, 23, 40, 13]. Most parallel programmers, however, still choose message passing systems like PVM [42] or MPI [16] which are used in combination with traditional imperative languages. The reasons for this choice have to do with efficiency, compatibility with existing sequential code, and the unfamiliarity with ....

V. Karamcheti and A.A. Chien. Concert - Efficient Runtime Support for Concurrent Object-Oriented. Supercomputing'93, pages 15--19, November 1993.

....language report, and the current release of the Concert software can be found at: http: www csag.cs.uiuc.edu ftp: cs.uiuc.edu pub csag Email addresses: group Gamma concert red herring cs.uiuc.edu Andrew A. Chien Gamma achien cs.uiuc.edu References: 65] 66] 67] 68] 69] 70] 71] [129] [177] 2.29 ConcurrentSmalltalk Developer: Description: oo. memory model. parallelism. Asynchronous method call plus futures (CBox) Post processing. Synchronous messages are also available. The caller decides which mode to use. scheduling. mapping. synchronization. There are two types of ....

Vijay Karamcheti and Andrew Chien. Concert -- efficient runtime support for concurrent object-oriented programming languages on stock hardware. In Proc. of ACM Supercomputing'93, pages 598--607, Portland, Oregon, November 15--19, 1993.

.... Concurrency Class for Eiffel [138, 139] Phi Phi Delta Delta H H A A Phi Phi Delta Delta H H A A y t i v i t c a y r a d n u o b Murat Karaorman Gamma murat cs.ucsb.edu John Bruno Gamma bruno cs.ucsb.edu Concurrent Aggregates, CA [74] 75] [137, 196] Phi Phi Delta Delta H H A A Phi Phi Delta Delta H H A A Phi Phi Delta Delta H H A A Phi Phi Delta Delta H H A A Phi Phi Delta Delta H H A A Phi Phi Delta Delta H H A A y t i v i t c a y r a d n u o b ....

Vijay Karamcheti and Andrew Chien. Concert -- efficient runtime support for concurrent objectoriented programming languages on stock hardware. In Proc. of ACM Supercomputing'93, pages 598--607, Portland, Oregon, November 15-- 19, 1993.

....because shared objects can be accessed by multiple local processing elements, and the complexity of managing this at user level can be high. The Concert system execution model is one of dynamic multithreading. It is implemented with runtime support from the Illinois Concert Runtime Library [13]. The Concert Runtime provides efficient primitives for synchronization and communication with remote nodes. It also provides functionality of memory management and garbage collection. We will detail the implementation of some of these runtime services in later sections. The Concert compiler is ....

Vijay Karamcheti and Andrew Chien. Concert---efficient runtime support for concurrent object-oriented programming languages on stock hardware. In Proceedings of Supercomputing '93, Portland, Oregon, November 1993. Available from http://www-csag.cs.uiuc.edu/papers/runtime.ps.

....an interpreter which supports incremental program development and debugging, a source level symbolic debugger, and performance tools to evaluate parallel program performance. These tools are described in greater detail in the next section. More information on the Concert System can be found in [7, 18, 14, 19, 5]. 1 3.3 Concert Tools for Program Development and Tuning The Concert System supports the development of irregular parallel applications. The challenges for program development are much greater for explicitly parallel programs than for models which retain sequential program semantics; ....

Vijay Karamcheti and Andrew Chien. Concert -- efficient runtime support for concurrent object-oriented programming languages on stock hardware. In Proceedings of Supercomputing'93, 1993.

....for allocating data objects, for asynchronous reading of a data object, and for synchronous writing of an object. This object system is intended to be used in explicitly parallel programs and like Split C has a work allocation model different from Olden s. The Concert system [Chien et al. 1993; Karamcheti and Chien 1993] provides compiler and runtime support for efficient execution of fine grained concurrent object oriented programs. Concert provides a globally shared object space, common programming idioms (such as RPC and tail forwarding) inheritance, and some concurrency control. Objects are single threaded ....

Karamcheti, V. and Chien, A. 1993. Concert -- efficient runtime support for concurrent objectoriented programming languages on stock hardware. In Proceedings of Supercomputing 93, pp. 598--607.

....substrate [Bhoedjang et al. 1998a] Lessons learned from the implementation of other languages for cluster computing were found to be useful. These implementations are built around user level communication primitives, such as Active Messages [von Eicken et al. 1992] Examples are Concert [Karamcheti and Chien 1993], CRL [Johnson et al. 1995] Orca [Bal et al. 1998; Bal et al. 1997] Split C [Culler et al. 1993] and Jade [Rinard et al. 1993] Other projects on fast communication in extensible systems are SPIN [Bershad et al. 1995] Exo kernel [Kaashoek et al. 1997] and Scout [Mosberger and Peterson 1996] ....

KARAMCHETI, V. AND CHIEN, A. 1993. Concert - Efficient Runtime Support for Concurrent ObjectOriented. In Supercomputing'93 (Portland, Oregon, Nov. 1993), pp. 15--19.

....Chien and Dally [70] proposed a pure actor language, Concurrent Aggregates (CA) which in addition to having the features of actors, aggregates, and intraaggregate addressing, provides support for first class continuations and messages. The Concert system of Chien, Karamcheti and Plevyak [27] [71], is a compiler and run time support system for a version of Concurrent Aggregates on stock hardware, i.e. such contemporary parallel machines as Thinking Machines CM 5 and Intel s Paragon. The objective of the Concert system is to take a fine grain concurrent language, CA, and through 53 ....

V. Karamcheti and A. Chien, "Concert --- efficient runtime support for concurrent object-oriented programming languages on stock hardware," in Proceedings, Supercomputing '93, pp. 33--36, 1993.

.... platforms [88, 121, 56, 13, 16, 89, 11, 70] and implemented directly on silicon [12, 37] With the availability of low cost, high performance microprocessors, it becomes a challenge to implement actor based programming systems on stock hardware multicomputers in an efficient and scalable way [119, 117, 28, 75]. It is challenging because actors are inherently concurrent and fine grained while current generation microprocessors support coarser grained, sequential execution semantics. Furthermore, the cost difference between local and remote access is visible to applications on distributed memory ....

....actors share the same name. A message sent to the aggregates is processed by one and only one constituent but which constituent receives the message is left unspecified (i.e. one toone of many type of communication) Unlike the Actor model, every message send in CA expects a reply by default [28, 75]. All of the above mentioned actor languages have been designed and implemented from scratch. A different approach involves extending an existing sequential object oriented language with the concurrency semantics of actors. In this approach, actors inherit their actions from a single Actor class ....

[Article contains additional citation context not shown here]

V. Karamcheti and A. A. Chien. Concert -- Efficient Runtime Support for Concurrent Object-Oriented Programming Languages on Stock Hardware. In Proceedings of Supercomputing '93, November 1993.

.... are described in [27] Third, ongoing research on distributed objects is contributing language and compiler support for describing objects and then compiling object interactions into efficient runtime invocations, using custom communication protocols[3] and or exploiting active message paradigms[25, 48, 21]. We share with such work the assumption that communications between different object fragments can often benefit from the use of active messages and that the use of active messages can improve the locality of parallel programs[47] However, we also posit that the compilation techniques and ....

V. Karamcheti and A. Chien. Concert -- efficient runtime support for concurrent objectoriented programming languages on stock hardware. In Proceedings of Supercomputing, Portland, OR. ACM, May 1993.

....a lack of portability between different operating systems, architectures, and even changes in the physical layout of the files. This paper proposes a design for high level parallel I O templates within the auspices of a parallel programming system (PPS) Examples of these systems can be found in [1 3, 7, 12, 13, 15, 23, 31]. A PPS could use these parallel I O templates along with templates for parallel computation to implement the desired parallel behaviour. The PPS integrates all components of developing, compiling, running, debugging, and evaluating the performance of a parallel application. That is, the ....

V. Karamcheti and A. Chien, "Concert - Efficient Runtime Support for Concurrent Object Oriented Programming Languages on Stock Hardware," In proceedings of Supercomputing'93, pp. 598-607, Portland, Oregon, 1993.

....tools may exploit most of the useful parallelism. However, an unaided compiler may be less successful in more general cases. In our model, actors are the unit of concurrency and all forms of parallelism is expressed explicitly in the programs themselves. ABCL onAP1000 [25] and the Concert system [14] are similar to our work: all are based on the Actor model and rely on software technology (i.e. compiler and runtime system) for efficient execution of application programs on stock hardware multicomputers. However, they differ in specific extensions to the Actor model that they employed [4, ....

V. Karamcheti and A. A. Chien. Concert -- Efficient Runtime Support for Concurrent Object-Oriented Programming Languages on Stock Hardware. In Proceedings of Supercomputing '93, November 1993.

....Associated tools are: DagTool (allows specification of dependences between messages and sub computations within a single process, provides a pictorial view) and Projections (a performance visualization and feedback tool) further tools are planned. 5.3. 3 Concert The goal of the Concert project [27] is to develop portable, efficient implementations of concurrent object oriented languages on workstation clusters and other parallel machines. The Concert system consists of a high performance compiler and runtime (language implementations) as well as a complete set of tools (emulator, debugger, ....

A. A. Chien and V. Karamcheti. Concert -- Efficient Runtime Support for Concurrent Object--Oriented Programming Languages on Stock Hardware. In Proceedings of SUPERCOMPUTING, 1993.

....equals the efficiency of the sequential language C on the Livermore Kernels, a demanding set of numerical benchmarks. While 1 We consider only languages that support object level concurrency. For a discussion of the alternatives see Section 5. 2 We defer to the wealth of research in this area [30, 39, 22, 36, 3]. the Livermore Kernels do not benefit greatly from object orientation, all the arrays in the COOP version of the kernels are implemented as concurrent objects, and accessed via object method invocation. Thus to achieve efficiency comparable to C, our compiler must eliminate virtually all of the ....

....in Section 6. 2 Background We describe the programming model, execution model, and the compiler framework. The mapping of the programming model to the execution model described here is largely conceptual; further information about our approach and actual implementation of COOP can be found in [9, 30]. 2.1 Programming Model The programming model we assume is the synergistic union of Actors [1, 12, 21] and the objectoriented model [17] Each object can act concurrently to update its own state, create new objects or invoke methods on other objects. An object provides a set of abstract ....

[Article contains additional citation context not shown here]

Vijay Karamcheti and Andrew Chien. Concert -- efficient runtime support for concurrent objectoriented programming languages on stock hardware. In Proceedings of Supercomputing'93, 1993.

....[36, 32] A previous study [36] discusses some of the optimizations in detail and shows that sequential performance equivalent to C is achieved for the Livermore kernels [30] a demanding numerical benchmark. and a runtime system with high performance implementation of COOP primitives [22] and a hybrid execution model [35] that creates parallel threads lazily to optimize sequential execution. We found that even given high data locality and achieving good sequential efficiency, an implementation that relies only on thread oriented compiler and runtime optimizations and software ....

....[32, 36] including the Livermore kernels [30] a demanding numerical benchmark. The Concert runtime implements a flexible hybrid execution model [35] which utilizes stack based sequential execution and creates threads lazily only when required. The runtime system exposes specialized versions [22] of important runtime primitives, such as remote method invocation and synchronization via futures [15] to the compiler to exploit compile time information. In addition, communication is realized via low overhead messaging layers: Fast Messages [23, 24] on the CRAY T3D and Active Messages [48] ....

Vijay Karamcheti and Andrew Chien. Concert -- efficient runtime support for concurrent object-oriented programming languages on stock hardware. In Proceedings of Supercomputing'93, 1993.

No context found.

V. Karamcheti and A. Chien. Concert: Efficient runtime support for concurrent object-oriented programming languages on stock hardware. Proceedings SUPERCOMPUTING '93, pp. 598--607. IEEE Comput. Soc. Press, Los Alamitos, CA, Nov. 1993.

No context found.

V. Karamcheti and A. Chien, "Concert - Efficient Runtime Support for Concurrent ObjectOriented Programming Languages on Stock Hardware." In Proceedings of Supercomputing '93, pgs 598-607, 1993.

No context found.

Vijay Karamcheti and Andrew Chien. Concert -- Efficient Runtime Support for Concurrent Object-Oriented Programming Languages on Stock Hardware. In Proceedings of Supercomputing'93, 1993.

No context found.

Vijay Karamcheti and Andrew Chien. Concert --- Efficient Runtime Support for Concurrent Object-Oriented Programming Languages on Stock Hardware. In Proceedings of Supercomputing, 1993.

No context found.

Karamcheti, V., Chien, A.: "Concert-Efficient Runtime Support for Concurrent ObjectOriented Programming Languajes on Stock Hardware". In Proceedings of Supercomputing'93, Portland, Oregon. November 1993.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC