Beng-Hong Lim and Anant Agarwal. Waiting Algorithms for Synchronization in Large-Scale Multiprocessors. ACM Transactions on Computer Systems, 11(3):253-- 294, August 1993. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Dribble-Back Registers: A Technique For Latency Tolerance In.. - Soundararajan (1992) (5 citations) (Correct)
....load 2 3 in a runnable thread 4runs Figure 3 6: Comparing latency tolerance in dribbler vs. multiple register sets 28 unloading the thread is potentially more costly than waiting out the thread (this is rarely true for a synchronization fault, as loading is generally on the order of 100 cycles[8]) and usually switching to and running other processes provides enough time for the remote request to be serviced and for that context to become runnable again. The most obvious gain of this polling is that we reduce the cost of waiting for a context to load in the rare case that everything has ....
....to the time required to load in the new register. 42 5.2 Experiments Because the register traces are randomly produced, no real benchmark programs are actually run through the simulators. However, parameters for the workload model are average numbers taken from real parallel applications[6, 8]. The workload model provides trace lengths for each of the threads. The simulator runs until one thread completes. This methodology is chosen in order to prevent end effects like running out of threads and waiting continually as threads complete from corrupting the data measured. Some ....
Beng-Hong Lira. Waiting Algorithms for Synchronization in Large-Scale Multiprocessors. Technical Report, S.M. Thesis, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, January 1991.
Scalable Reader-Writer Locks for Parallel Systems - Hsieh, Weihl (1991) (2 citations) (Correct)
....for a readier writer lock [1] the valid list is analogous to a directory of possible readers. Similarly, the static lock can be viewed as generalizing a bus based (broadcast) cache consistency scheme. Recent work has explored two phase (spin, then block) algorithms for waiting in multiprocessors [11, 13]. This work has shown that two phase algorithms perform better than pure spinning or blocking, and that some two phase strategies perform within a constant factor of the offline optimal decision to spin or block. In generalizing our algorithms to handle multiple processes per processor, it would ....
Beng-Hong Lim and Anant AgarwaJ. Waiting Algorithms for Synchronization in Large-Scale Mul- tiprocessors. MIT VLSI Memo 91-632, July 1991.
Waiting Algorithms for Synchronization in Large-Scale.. - Lira, Agarwal (1991) (3 citations) Self-citation (Lira) (Correct)
No context found.
Beng-Hong Lira. Waiting Algorithms for Synchronization in Large-Scale Multiprocessors. MIT/LCS TR-498, Massachusetts Institute of Technology, Cambridge, MA, February 1991. S.M. Thesis.
Implicit Coscheduling: Coordinated Scheduling with Implicit.. - Arpaci-Dusseau (1998) (5 citations) (Correct)
No context found.
Beng-Hong Lim and Anant Agarwal. Waiting Algorithms for Synchronization in Large-Scale Multiprocessors. ACM Transactions on Computer Systems, 11(3):253-- 294, August 1993.
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