W. Williams and Bobrowicz, "Speedup predictions for large scientific parallel programs on Cray X-MP-like architectures," in Proceedings of the 1985 International Conference on Parallel Processing, pp. 541--543, August 1985. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Techniques for Cache and Memory Simulation Using Address.. - Holliday (1990) (9 citations) (Correct)
....messagepassing on a hypercube. Stunkel and Fuchs [62] noted that execution driven simulation can be adapted to address tracing and did so in a package named TRAPEDS (TRAce Producing Execution Driven Simulation) A number of uses of inline simulation for addresses or other events have occurred [63, 64, 65, 66, 67, 68, 69, 70]. We mention two recent uniprocessor implementations [29, 38] and two recent multiprocessor implementations [62, 71] Borg, Kessler, and Wall [29] trace the address references of multiple processes including operating system references for a uniprocessor. The linker inserts the code to ensure ....
W. Williams and Bobrowicz, "Speedup predictions for large scientific parallel programs on Cray X-MP-like architectures," in Proceedings of the 1985 International Conference on Parallel Processing, pp. 541--543, August 1985.
The Efficient Simulation of Parallel Computer Systems - Covington, Dwarkada, al. (1991) (47 citations) (Correct)
....target machines are identical or nearly so) execution driven simulation simply executes the machine language instructions of the program directly on the simulation host. Similar techniques based on the basic concept exploited by execution driven simulation have also been proposed in references [7, 9, 10, 11]. A principle disadvantage of execution driven simulation is that some of the timing details of instruction execution are lost since individual instructions are not emulated. As a result, the time required to execute a sequence of instructions can not be predicted as accurately as with ....
.... have different instruction sets [14] Yet another approach for dealing with heterogeneous host and target processor instruction sets, similar to the one utilized in the RPPT, is described in [15] The basic concept inherent in execution driven simulation was also used by Williams and Bobrowicz [11] to simulate an N processor Cray X MP with a simulator running on only one of the processors of a Cray X MP 24. They used measured user code execution times to drive the simulation. An execution driven approach was also proposed by [7] as a means of dynamically generating and interleaving ....
E. Williams and F. Bobrowicz, "Speedup Predictions for Large Scientific Parallel Programs on Cray X-MP-Like Architectures," in Proc. 1985 International Conference on Parallel Processing, Aug. 1985, pp. 541-543.
The Evaluation Of Massively Parallel Array Architectures - Herbordt (1994) (4 citations) (Correct)
....al. have shown that execution driven simulation can work well for multiprocessors with overheads less than a factor of 20 typical. They have also verified their simulations to within 10 for several machines [47] Several other systems have also been developed that use execution driven simulation [151, 55, 133, 34, 31, 122, 53]. One difficulty of execution driven simulation is that for processors where H does not resemble the processing elements of T , the basic block matching process can be difficult. Another difficulty is that code must be recompiled and reexecuted for every change in the design of the target ....
Williams, E., and Bobrowicz, F. Speedup predictions for large scientific parallel programs on Cray X-MP-like architectures. In Proceedings of the 1985 International Conference on Parallel Processing (1985), pp. 541--543.
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