diff -r pario/web/bibtex/barve:competitive2.bib pario/web/new/barve:competitive2.bib
12c12,43
<   keyword = {disk prefetching, file caching, parallel I/O, pario-bib}
---
>   keyword = {disk prefetching, file caching, parallel I/O, pario-bib},
>   abstract = {We provide a competitive analysis framework for online
>   prefetching and buffer management algorithms in parallel I/O systems, using a
>   read-once model of block references. This has widespread applicability to key
>   I/O-bound applications such as external merging and concurrent playback of
>   multiple video streams. Two realistic lookahead models, global lookahead and
>   local lookahead, are defined. Algorithms NOM and GREED based on these two
>   forms of lookahead are analyzed for shared buffer and distributed buffer
>   configurations, both of which occur frequently in existing systems. An
>   important aspect of our work is that we show how to implement both the models
>   of lookahead in practice using the simple techniques of forecasting and
>   flushing. \par Given a D-disk parallel I/O system and a globally shared I/O
>   buffer that can hold upto M disk blocks, we derive a lower bound of
>   $\Omega(\sqrt{D}$) on the competitive ratio of any deterministic online
>   prefetching algorithm with O(M) lookahead. NOM is shown to match the lower
>   bound using global M-block lookahead. In contrast, using only local lookahead
>   results in an $\Omega(D)$ competitive ratio. When the buffer is distributed
>   into D portions of M/D blocks each, the algorithm GREED based on local
>   lookahead is shown to be optimal, and NOM is within a constant factor of
>   optimal. Thus we provide a theoretical basis for the intuition that global
>   lookahead is more valuable for prefetching in the case of a shared buffer
>   configuration whereas it is enough to provide local lookahead in case of the
>   distributed configuration. Finally, we analyze the performance of these
>   algorithms for reference strings generated by a uniformly-random stochastic
>   process and we show that they achieve the minimal expected number of I/Os.
>   These results also give bounds on the worst-case expected performance of
>   algorithms which employ randomization in the data layout.},
>   comment = {See also barve:competitive. They propose two methods for
>   scheduling prefetch operations in the situation where the access pattern is
>   largely known in advance, in such a way as to minimize the total number of
>   parallel I/Os. The two methods are quite straightforward, and yet match the
>   optimum lower bound for an on-line algorithm.}
diff -r pario/web/bibtex/cormen:fft3.bib pario/web/new/cormen:fft3.bib
12a13,29
>   abstract = {This paper extends an earlier out-of-core Fast Fourier Transform
>   (FFT) method for a uniprocessor with the Parallel Disk Model (PDM) to use
>   multiple processors. Four out-of-core multiprocessor methods are examined.
>   Operationally, these methods differ in the size of "mini-butterfly" computed
>   in memory and how the data are organized on the disks and in the distributed
>   memory of the multiprocessor. The methods also perform differing amounts of
>   I/O and communication. Two of them have the remarkable property that even
>   though they are computing the FFT on a multiprocessor, all interprocessor
>   communication occurs outside the mini-butterfly computations; communication
>   that ordinarily occurs in a butterfly is folded into other data-movement
>   operations. An analysis program shows that the two methods that use no
>   butterfly communication usually use less communication overall than the other
>   methods. The analysis program is fast enough that it can be invoked at run
>   time to determine which of the four methods uses the least communication. One
>   set of performance results on a small workstation cluster indicates that the
>   methods without butterfly communication are approximately 9.5\% faster.
>   Moreover, they are much easier to implement.},
14c31,34
<   in the out-of-core FFT into a single BMMC permutation between}
---
>   in the out-of-core FFT into a single BMMC permutation between "super-levels",
>   where each super-level involves log(M) stages of the FFT. This usually leads
>   to less communication and to better overall performance. See also cormen:fft
>   and cormen:fft2.}
diff -r pario/web/bibtex/cortes:cooperative.bib pario/web/new/cortes:cooperative.bib
12c12,29
<   pario-bib}
---
>   pario-bib},
>   abstract = {In this paper, we examine some of the important problems observed
>   in the design of cooperative caches. Solutions to the coherence,
>   load-balancing and fault-tolerance problems are presented. These solutions
>   have been implemented as a part of PAFS, a parallel/distributed file system,
>   and its performance has been compared to the one achieved by xFS. Using the
>   comparison results, we have observed that the proposed ideas not only solve
>   the main problems of cooperative caches, but also increase the overall system
>   performance. Although the solutions presented in this paper were targeted to
>   a parallel machine, reasonable good results have also been obtained for
>   networks of workstations.},
>   comment = {They make the claim that it is better not to replicate data into
>   local client caches, rather, it is better to simply make remote read and
>   write requests to the cached block in whatever memory it may be. That reduces
>   the overhead (space and time) of replication and coherency, and leads to
>   better performance. They also present a range of parity-based fault-tolerance
>   mechanisms, and a load-balancing technique that reassigns cache buffers to
>   cache-manager processes.}
diff -r pario/web/bibtex/kandaswamy:hartree-fock.bib pario/web/new/kandaswamy:hartree-fock.bib
9a10
>   earlier = {kandaswamy:hartree},
diff -r pario/web/bibtex/kandaswamy:hartree.bib pario/web/new/kandaswamy:hartree.bib
12,13c12,14
<   note = {To appear},
<   keyword = {verify pages, parallel I/O, scientific computing, pario-bib},
---
>   later = {kandaswamy:hartree-fock},
>   URL = {http://scxy.tc.cornell.edu/sc97/proceedings/TECH/KANDASWA/INDEX.HTM},
>   keyword = {parallel I/O, scientific computing, pario-bib},
32c33,35
<   improvement in the overall application performance with these optimizations.}
---
>   improvement in the overall application performance with these
>   optimizations.},
>   comment = {No page numbers: proceedings on CDROM and web only.}
diff -r pario/web/bibtex/madhyastha:adaptive.bib pario/web/new/madhyastha:adaptive.bib
9a10
>   later = {madhyastha:thesis},
25c26,27
<   benchmarks and input/output intensive scientific applications.}
---
>   benchmarks and input/output intensive scientific applications.},
>   comment = {See also madhyastha:thesis, and related papers.}
diff -r pario/web/bibtex/madhyastha:classification.bib pario/web/new/madhyastha:classification.bib
11a12
>   later = {madhyastha:thesis},
29c30,31
<   much better performance in future runs. See also her paper in SC97.}
---
>   much better performance in future runs. See also madhyastha:thesis, and
>   related papers.}