Bisiani, R. and Forin, A., Architectural Support for Multilanguage Parallel Programming on Heterogenous Systems, Proc. 2nd Int. Conf. on Architectural Support for Programming Languages and Operating Systems, pp. 21-30, Palo Alto, Calif., Oct. 1987.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....virtual memory [Li 1988] which simulates physical shared memory. These and other systems are surveyed in [Bal and Tanenbaum 1988] Also, several researchers have looked at distributed applications that can be implemented with logically shared data. Example applications are: speech recognition [Bisiani and Forin 1987], linear equation solving, three dimensional partial differential equations [Li 1988] and global scheduling and replicated files [Cheriton 1985] The rest of the paper is structured as follows. In Section 2, we will give a brief description of the shared data object model and Orca. In Section 3, ....

Bisiani, R. and Forin, A., Architectural Support for Multilanguage Parallel Programming on Heterogenous Systems, Proc. 2nd Int. Conf. on Architectural Support for Programming Languages and Operating Systems, pp. 21-30, Palo Alto, Calif., Oct. 1987.

....the user the illusion of a shared memory. It stores multiple read only copies of the same page on different processors. Each processor having a copy can read the page as if it were in normal local memory. Other systems providing replicated shared data are described in [Carriero and Gelernter 1986; Bisiani and Forin 1987; Cheriton 1985; Stenstrm et al. 1988; Fleisch and Popek 1989] The model studied in this paper is called the shared data object model. It is intended for implementing parallel applications on distributed systems. The unit of replication in our model is not dictated by the system (as in the SVM) ....

Bisiani, R. and Forin, A., Architectural Support for Multilanguage Parallel Programming on Heterogenous Systems, Proc. 2nd Int. Conf. on Architectural Support for Programming Languages and Operating Systems, pp. 21-30, Palo Alto, Calif., Oct. 1987.

....the relaxed semantics. Most important, it does not have to use complicated schemes to atomically update all copies of the same data. 3.5. The Agora shared memory The Agora shared memory allows processes written in different languages and executing on different types of machines to communicate [Bisiani and Forin 1987]. It has been implemented on closely coupled as well as loosely coupled architectures, using the Mach operating system. The memory contains shared data structures, accessible through an (extendible) set of standard functions. These functions are available (e.g. as library routines) in all ....

Bisiani, R. and Forin, A., Architectural Support for Multilanguage Parallel Programming on Heterogenous Systems, Proc. 2nd Int. Conf. on Architectural Support for Programming Languages and Operating Systems, pp. 21-30, Palo Alto, Oct. 1987.

....a disadvantage [Kaashoek et al. 1989a] Many designers of distributed operating systems have also proposed or implemented abstract shared memory models. Examples are: Cheriton s Problem oriented Shared Memory [Cheriton 1985] Li s Shared Virtual Memory [Li and Hudak 1986] the Agora Shared Memory [Bisiani and Forin 1987], and Mirage [Fleisch and Popek 1989] In these systems, the unit of sharing typically is a physical page, rather than a logical, programmer defined entity (as in our model) For a comparison of several of these systems, we refer the reader to [Bal and Tanenbaum 1988] We have built a compiler and ....

Bisiani, R. and Forin, A., Architectural Support for Multilanguage Parallel Programming on Heterogenous systems, Proc. 2nd Int. Conf. on Architectural Support for Programming Languages and Operating Systems, pp. 21-30, Palo Alto, CA, Oct. 1987.

....The literature contains numerous other examples of distributed applications and 4 algorithms that would greatly benefit from support for shared data, even if no physical shared memory is available. Applications described in the literature include: a distributed speech recognition system [10]; linear equation solving, three dimensional partial differential equations, and split merge sort [11] computer chess [12] distributed system services (e.g. name service, time service) global scheduling, and replicated files [13] So, the difficulty in providing (logically) shared data makes ....

R. Bisiani and A. Forin, "Architectural Support for Multilanguage Parallel Programming on Heterogenous Systems," Proc. 2nd Int. Conf. on Architectural Support for Programming Languages and Operating Systems, Palo Alto, Calif., pp. 21-30 (Oct. 1987).

....Mike Accetta, Bob Baron, Bob Beck (Sequent) David Black, Bill Bolosky, Jonathan Chew, David Golub, Glenn Marcy, Fred Olivera (Encore) Rick Rashid, Avie Tevanian, Jim Van Schiver (Encore) and Mike Young. 4 e.g. for transaction processing, database management [9] and AI knowledge representation [2, 3] 14 ....

Bisiani,R. and Forin,A. Architectural Support for Multilanguage Parallel Programming on Heterogeneous Systems. In 2nd International Conference on Architectural Support for Programming Languages and Operating Systems. IEEE, Palo Alto , October, 1987.

....5 representation, transport and control prototols, instead of legislating a single standard. Other proposals use a more low level approach. HRPC [12] being developed at the University of Washington provides remote procedure calls (RPC) to machines with different architectures. The Agora System [14] offers shared memory for coordination between and writing of parallel applications in multiple programming languages. ARCADE [21] offers shared memory with operations to transmit memory blocks to other machines and sharing of blocks with other processes. The Parallel Virtual Machine (PVM) 39] ....

Roberto Bisiani and Alessandro Forin. Architectural Support for Multilanguage Parallel Programming on Heterogenous Systems. ACM Operating Systems Review, 21(10):21--30, October 1987.

....to the X11 get and change property commands. Data is maintained by memory control modules located at specific network nodes. To improve efficiency, data may be cached locally. Because a read is not always preceded by the most recent write this creates a coherency problem. 2. Agora shared memory [16]. This uses shared data structures accessed by library routines. Data structures consist of immutable typed data (records) accessed via mutable maps. Data is modified by the addition of new data, with corresponding map amendment; the defunct data is eventually reclaimed (garbage collected) 13, ....

....[16] This uses shared data structures accessed by library routines. Data structures consist of immutable typed data (records) accessed via mutable maps. Data is modified by the addition of new data, with corresponding map amendment; the defunct data is eventually reclaimed (garbage collected) [13, 16]. The (Mach) operating system makes the single copy of data held at a given node accessible to all tasks within the node s address space. Other nodes receive a copy of the data. Thus there is a difference in data access between tightly and loosely coupled architectures. The modification of data ....

[Article contains additional citation context not shown here]

Bisiani.R. & Forin.A., Architectural Support for Multilanguage Parallel Programming on Heterogeneous Systems., Prod. 2nd. Int. Conf. on. Architectural Support Programming Languages & Operating Systems., 1987.

No context found.

R. Bisiani and A. Forin, "Architectural Support for Multilanguage Parallel Programming on Heterogeneous Systems," Proc. Second International Conference on Architectural Support for Programming Languages and Operating Systems , Palo Alto, CA, pp. 21-30 (Oct. 1987).

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