Jaejin Lee, Samuel P. Midki , and David A. Padua. A constant propagation algorithm for explicitly parallel programs. International Journal of Parallel Programming, 26(5):563-589, 1998. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Hiding the Java Memory Model with Compilers - Lee (Correct)
....of the relaxed memory model. Data races and synchronization make it impossible to apply classical optimization and analysis techniques directly to shared memory parallel programs because the classical methods do not account for updates to variables in threads other than the one being analyzed [12, 13, 15, 11]. Consider the code in Figure 2(A) taken from Pugh [17] We assume that p and q are aliased in this code. Because p.k is not modi ed in between ### and ### if we consider only ###### #,we can use x in ### for the value of p.k in ###, i.e. it is a legal compiler transformation to replace p.k in ....
....concurrent global value numbering [11, 15] is applied in order to detect equivalentvariables. Then, we can safely apply the common subexpression elimination for those equivalentvariables. Some examples of incorrect compiler optimizations for shared memory programs and their solutions are given in [13, 11, 15]. Essentially the same problems can occur in concurrent programs written in Java because Java assumes a shared memory programming model. These optimization techniques include constant propagation, copy propagation, dead code elimination, common subexpression elimination, redundant load store ....
Jaejin Lee, Samuel P. Midki , and David A. Padua. A constant propagation algorithm for explicitly parallel programs. ############# ####### ## ######## ###########, 26(5):563-589, 1998.
Analysis of Multithreaded Programs - Rinard (2001) (13 citations) (Correct)
.... to shared data in ways that may be observed by threads running concurrently with the transformed thread [72] One approach is to generalize standard program representations, analyses, and transformations to safely optimize multithreaded programs even in the presence of accesses to shared data [91, 87, 57, 62, 56, 64]. The presence 3 of multithreading may also inspire optimizations with no obvious counterpart in the optimization of sequential programs. Examples include communication optimizations [59, 100] optimizing mutual exclusion synchronization [30, 31, 79, 3, 98, 11, 13, 21, 82] and optimizing barrier ....
J. Lee, S. Midkiff, and D. Padua. A constant propagation algorithm for explicitly parallel programs. International Journal of Parallel Programming, 26(5), 1998.
Basic Compiler Algorithms for Parallel Programs - Jaejin Lee And (1999) (16 citations) Self-citation (Midki Padua) (Correct)
No context found.
Jaejin Lee, Samuel P. Midki , and David A. Padua. A constant propagation algorithm for explicitly parallel programs. International Journal of Parallel Programming, 26(5):563-589, 1998.
A Compiler for Multiple Memory Models - Samuel Midkiff Ibm (2001) Self-citation (Midkiff Padua) (Correct)
No context found.
Jaejin Lee, Samuel P. Midkiff, and David A. Padua. A constant propagation algorithm for explicitly parallel programs. International Journal of Parallel Programming, 26(5):563--589, 1998.
Compilation Techniques for Explicitly Parallel Programs - Lee (1999) (1 citation) Self-citation (Padua) (Correct)
.... for SPMD programs (scalar pipelining, Eliminatpost wait analysis) ing remote accesses through data reuse Lee, Mid Nondeterminate cobegin coend, Concurrent control flow Synchronization analysis Constant propagation kiff, Padua post wait graph (CCFG) with syn to construct OSSA form [56, 57, 58] chronization and con and compact use der chain fiict edges, Concurrent from OSSA form (scalar static single assignment analysis) OSSA) form based on CCFG Lee, Padua, Nondeterminate, cobegin coend, Concurrent control flow Synchronization analysis Copy propagation, Midkiff [59] sequential ....
....general enough to handle these representative synchronization mechanisms. Moreover, they should handle im plicit synchronization through shared variables, such as busy waiting. Most earlier studies do not handle implicit synchronization through shared variables, except for Lee, Midkiff, and Padua [56, 57, 58, 59]. Knoop, Steffen, and Vollmer [49, 47, 48] presented a unidirectional bit vector data flow analysis framework based on abstract interpretation and showed that it can be used for code motion and partial dead code elimination. However, their framework cannot be applied to parallel programs with ....
[Article contains additional citation context not shown here]
Jaejin Lee, Samuel P. Midkiff, and David A. Padua. A constant propagation algorithm for explicitly parallel programs. International Journal of Parallel Programming, 26(5):563-589, 1998.
Analysis of Multithreaded Programs - Rinard (2001) (13 citations) (Correct)
No context found.
J. Lee, S. Midki#, and D. Padua. A constant propagation algorithm for explicitly parallel programs. International Journal of Parallel Programming, 26(5), 1998.
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