Lower and upper bounds on time for multiprocessor optimal schedules

The lower and upper bounds on the minimum time needed to process a given directed acyclic task graph for a given number of processors are derived. It is proved that the proposed lower bound on time is not only sharper than the previously known values but also easier to calculate. The upper bound on time, which is useful in determining the worst case behavior of a given task graph, is presented. The lower and upper bounds on the minimum number of processors required to process a given task graph in the minimum possible time are also derived. It is seen with a number of randomly generated dense task graphs that the lower and upper bounds we derive are equal, thus giving the optimal time for scheduling directed acyclic task graphs on a given set of processors     

Execution-Time Analysis of Process Control Algorithms on Microprocessors

One of the basic problems in the area of microprocessor-based process control is the estimation of execution time and storage required to implement a given control algorithm on a specified microprocessor. With improvements in the capability of microprocessors and increases, in sophistication and cost of control software higher level languages particularly, Pascal is becoming popular in control applications. In this paper, a methodology is suggested for estimating the execution-time bound and storage requirements of control algorithms coded in Pascal when they are run on a specified microprocessor. The method consists of some modifications of the Pascal P-compiler, which yields the P-code and together with it a subsidiary sequential file of records to facilitate timing and storage calculation. This sequential file, together with the parameters used in program loops in the PASCAL application program and P-code instruction execution time and code size for a specified microprocessor, yields the execution-time bound and memory requirements. Using this methodology, the performance of a set of recently announced 16-bit microprocessors in some control applications is evaluated.     

A FIFO-based multicast network and its use in multicomputers

We present an implementation of a multicast network of processors. The processors are connected in a fully connected network and it is possible to broadcast data in a single instruction. The network works at the processor-memory speed and therefore provides a fast communication link among processors. A number of interesting architectures are possible using such a network. We show some of these architectures which have been implemented and are functional. We also show the system software calls which allow programming of these machines in parallel mode.     

Theory and design of part-winding starting

When a three-phase cage induction motor is started on a half winding, space harmonic MMFs occur, and the machine usually fails to accelerate beyond the speed of the principal harmonic. A mathematical theory is presented in this paper which not only explains such behavior observed in the past, but also predicts whether, and at what speed, a motor will hang up or crawl on any particular arrangement of half winding. The theory also provides a basis for the design of harmonic-free half windings on which the machine will accelerate smoothly to full speed. This is illustrated by application to a 6-pole motor     

Effects of replacement of native fat in colostrum and milk with coconut oil on fat-soluble vitamins in serum and immune function in calves

Fat-soluble vitamins and their metabolites modulate immune function in a variety of animal species. The objective of the present study was to determine the role of fat-soluble vitamins in colostrum and milk in the development of specific aspects of immune function in the calf during the 1st wk postpartum. During this period, control calves (n = 6) were fed normal colostrum and milk, and calves in the treatment group (n = 6) were fed skimmed colostrum and skimmed milk supplemented with coconut oil. Treated calves did not experience the progressive increase in concentrations of retinol, beta-carotene, alpha-tocopherol, 1,25-dihydroxyvitamin D, or retinoic acids in serum that was observed in control calves. Acquisition of passive immunity, which is indicated by concentrations of immunoglobulin G1 in serum, was unaffected by treatment. Composition and functional capacities of populations of blood mononuclear leukocytes that were collected from birth to 7 d postpartum were also unaffected by treatment. Major changes in the function and composition of mononuclear leukocyte populations from all calves occurred during the experimental period and were unrelated to the concentrations of fat-soluble vitamins in serum. Populations of blood mononuclear leukocytes from calves were functionally hyporesponsive and compositionally different from populations of blood mononuclear leukocytes from adult nongravid cows. These differences likely reflected the immaturity of the immune system of the neonatal calf and may contribute to the increased susceptibility of the calf to infectious disease.     

Detection of mitochondrial genome depletion by a novel cDNA in renal cell carcinoma

A cDNA isolated by a subtractive hybridization procedure detected loss of mtDNA and the mRNA coding for NADH dehydrogenase subunit 3 in 8 of 13 tumor kidney tissues obtained from patients with renal cell carcinoma. Sequencing revealed a stretch of nucleotides homologous to the mitochondrial NADH dehydrogenase subunit 3 gene in the middle of the cDNA. The depletion phenomenon was also observed in five of six renal carcinoma cell lines. In the case of a benign renal oncocytoma, however, the mtDNA content was increased 200% more than that of the adjacent normal tissue. The frequency with which this phenomenon occurs in renal cell carcinomas, but not in other types of cancers, suggests that this may be an important phenotype associated with renal cell neoplastic transformation. However, the absence of any structural alterations within the mitochondrial genome suggests that the depletion may be a secondary event associated with the oncogenic transformation process.     

Effect of ileo-jejunal transposition on the growth of the GI tract and pancreas in young and aged rats

BACKGROUND: Ileo-jejunal transposition (IJT; transposition of the distal quarter of the small intestine into the proximal jejunum) is known to stimulate mucosal growth of the transposed ileum, but the effects on other parts of the small intestine are controversial. The effect of aging on the trophic action of IJT is not known. METHODS: We examined the trophic effect of IJT (3 weeks post-operation) on the gastrointestinal tract and pancreas, and on plasma levels of neurotensin and gastrin in three different aged groups of Fischer 344 rats (4, 12, and 24 months old). RESULTS: Three weeks after IJT, the mucosal mass, villus height, and crypt depth increased significantly in the transposed ileum as well as in the remainder of the small intestine. The weights of the colon and pancreas increased significantly after IJT. These responses were not affected by aging. In each of the three age groups, IJT did not affect plasma gastrin level, but significantly increased plasma level of neurotensin. CONCLUSIONS: The distal ileum appears to play an important role in the regulation of growth in the intestine and pancreas; this role is preserved in aged rats. Neurotensin may play an important role in this mechanism.     

Buffered stack memory organisation

Slow unidirectional shift registers can be used to realise a large-size inexpensive stack. A simple configuration of such a shift-register stack will frequently force a processing unit needing access to it into an idle state. In the letter, a scheme using a small number of fast bidirectional shift registers appended to a unidirectional shift-register stack is suggested. This configuration makes the entire stack look, for most of the time, as if it were made of fast bidirectional shift registers. A design method is presented to determine the number of bits needed in the bidirectional shift register to meet given specifications.     

An efficient distributed algorithm for constructing small dominating sets

The dominating set problem asks for a small subset D of nodes in a graph such that every node is either in D or adjacent to a node in D. This problem arises in a number of distributed network applications, where it is important to locate a small number of centers in the network such that every node is nearby at least one center. Finding a dominating set of minimum size is NP-complete, and the best known approximation is logarithmic in the maximum degree of the graph and is provided by the same simple greedy approach that gives the well-known logarithmic approximation result for the closely related set cover problem. We describe and analyze new randomized distributed algorithms for the dominating set problem that run in polylogarithmic time, independent of the diameter of the network, and that return a dominating set of size within a logarithmic factor from optimal, with high probability. In particular, our best algorithm runs in rounds with high probability, where n is the number of nodes, is one plus the maximum degree of any node, and each round involves a constant number of message exchanges among any two neighbors; the size of the dominating set obtained is within of the optimal in expectation and within of the optimal with high probability. We also describe generalizations to the weighted case and the case of multiple covering requirements. Received: January 2002 / Accepted: August 2002 RID="*" ID="*" Supported by NSF CAREER award NSF CCR-9983901 RID="*" ID="*" Supported by NSF CAREER award NSF CCR-9983901     

Time-Constrained Scheduling of Weighted Packets on Trees and Meshes

The time-constrained packet routing problem is to schedule a set of packets to be transmitted through a multinode network, where every packet has a source and a destination (as in traditional packet routing problems) as well as a release time and a deadline. The objective is to schedule the maximum number of packets subject to deadline constraints. This problem is studied in [1], where it is shown that the problem is NP-Complete even when the underlying topology is a linear array. Approximation algorithms are also provided in [1] for the linear array and the unidirectional ring for both the case where packets may be buffered in transit and the case where they may not be. In this paper we extend the results of [1] in two directions. First, we consider the more general network topologies of trees and two-dimensional meshes. Second, we associate with each packet a measure of utility, called a weight, and study the problem of maximizing the total weight of the packets that are scheduled subject to their timing constraints. For the bufferless case, we provide constant factor approximation algorithms for the time-constrained scheduling problem with weighted packets on trees and meshes. We also provide logarithmic approximations for the same problems in the buffered case. These results are complemented by new lower bounds, which demonstrate that we cannot hope to achieve the same results for general network topologies. For example, we show that if k packets are required to follow prescribed paths in an arbitrary graph, then unless NP = ZPP, there is no polynomial-time k1-ε -approximation, for any ε > 0 , to the optimal set of packets that can be scheduled.