| 1. |
- Grahn, Håkan, et al.
(author)
-
Comparative evaluation of latency-tolerating and -reducing techniques for hardware-only and software-only directory protocols
- 2000
-
In: Journal of Parallel and Distributed Computing. - SAN DIEGO : ACADEMIC PRESS INC. - 0743-7315 .- 1096-0848. ; 60:7, s. 807-834
-
Journal article (peer-reviewed)abstract
- We study in this paper how effective latency-tolerating and -reducing techniques are at cutting the memory access times for shared-memory multiprocessors with directory cache protocols managed by hardware and software. A critical issue for the relative efficiency is how many protocol operations such techniques trigger. This paper presents a framework that makes it possible to reason about the expected relative efficiency of a latency-tolerating or -reducing technique by focusing on whether the technique increases, decreases, or does not change the number of protocol operations at the memory module. Since software-only directory protocols handle these operations in software they will perform relatively worse unless the technique reduces the number of protocol operations. Our experimental results from detailed architectural simulations driven by six applications from the SPLASH-2 parallel program suite confirm this expectation, We find that while prefetching performs relatively worse on software-only directory protocols due to useless prefetches, there are examples of protocol optimizations, e.g., optimizations For migratory data, that do relatively better on software-only directory protocols. Overall, this study shows that latency-tolerating techniques must be more carefully selected for software-centric than for hardware-centric implementations of distributed shared-memory systems. (C) 2000 Academic Press.
|
|
| 2. |
- Hoepman, Jaap-Henk, et al.
(author)
-
Self-Stabilization in Wait-Free Shared Memory Objects
- 2002
-
In: Journal of Parallel and Distributed Computing. - : Elsevier BV. - 1096-0848 .- 0743-7315. ; 62:5, s. 818-842
-
Journal article (peer-reviewed)abstract
- This paper proposes a general definition of self-stabilizing wait-free shared memory objects. The definition ensures that, even in the face of processor failures, every execution after a transient memory failure is linearizable except for an a priori bounded number of actions. Shared registers have been used extensively as communication medium in self-stabilizing protocols. As an application of our theory, we therefore focus on self-stabilizing implementation of such registers, thus providing a large body of previous research with a more solid foundation. In particular, we prove that one cannot construct a self-stabilizing single-reader single-writer regular bit from self-stabilizing single-reader single-writer safe bits, using only a single bit for the writer. This leads us to postulate a self-stabilizing dual-reader single-writer safe bit as the minimal hardware needed to achieve self-stabilizing wait-free interprocess communication and synchronization. Based on this hardware, adaptations of well-known wait-free implementations of regular and atomic shared registers are proven to be self-stabilizing.
|
|
| 3. |
- Kennedy, K., et al.
(author)
-
Telescoping languages : A strategy for automatic generation of scientific problem-solving systems from annotated libraries
- 2001
-
In: Journal of Parallel and Distributed Computing. - : Elsevier BV. - 0743-7315 .- 1096-0848. ; 61:12, s. 1803-1826
-
Journal article (peer-reviewed)abstract
- As machines and programs have become more complex., the process of programming applications that can exploit the power of high-performance systems has become more difficult and correspondingly more labor-intensive. This has substantially widened the software gap the discrepancy between the need for new software and the aggregate capacity of the workforce to produce it. This problem has been compounded by the slow growth of programming productivity, especially for high-performance programs, over the past two decades. One way to bridge this gap is to make it possible for end users to develop programs in high-level domain-specific programming systems. In the past, a major impediment to the acceptance of such systems has been the poor performance of the resulting applications. To address this problem, we are developing a new compiler-based infrastructure, called TeleGen, that will make it practical to construct efficient domain-specific high-level languages from annotated component libraries. We call these languages telescoping languages, because they can be nested within one another. For programs written in telescoping languages. high performance and reasonable compilation times can be achieved by exhaustively analyzing the component libraries in advance to produce a language processor that recognizes and optimizes library operations as primitives in the language. The key to making this strategy practical is to keep compile times low by generating a custom compiler with extensive built-in knowledge of the underlying libraries. The goal is to achieve compile times that tire linearly proportional to the size of the program presented by the user. rather than to the aggregate size of that program plus the base libraries.
|
|
| 4. |
|
|
