Friday, December 27, 2019
Report about Students Complaints about Campus Parking Problem at FIU
Introduction This report is about the parking problem raised by the Florida International University (FIU) students to the president. It affected many students within the institution. The problem has been persistent since 1980 when the number of student’s enrollment increased to 12000 from 5500 while parking increased 6000 from 5500 in 1972. The students have been facing a lot of challenges because almost half them misses parking spaces. Due to this complain from the students, we were assigned the responsibility to write a report about the problem and the possible solutions or recommendations. Fig 1: Comparison of students to the available parking space From the findings and data we collected, there was no parking problem from 1972 to 1975; this is seen from the data in figure one that, the number of commuter students enrolled equals to the number of students parking space available of 5500. The university management enrolled students according to the available parking spaces. The problem started in 1980 when 12000 students were enrolled and the available parking space increased to 6000. Half of the students could get parking space. From 1980 to 2005, many students have been missing parking space. We found out the following. Year        Number of commuter          Number of student                   Students enrolled                 parking spaces 1985          19500                                    6500 1990          28000                                    7000 1995          37500                                    7500 2000          45000                                      7500 2005          45000                                     7500 The data I found shows that more than 35000 students miss parking space at Florida International University by the year 2005. Fig 2: Complaints from the students From the survey as we gather the information about the student’s complaints, we found out from the students we interviewed the following information: 28000 of the total students which represent 64% complain of inadequate number of student’s parking space. These were the majority of the students and they wanted more parking spaces. 7650 students complain that, there were too many faculty spaces not utilized or used and the students should be allowed to park there. This represented 17% of the total student’s population. 15% of the total population had an issue with the students without decals. They complained that, there were inadequate attempts to keep students who have no decals from using the spaces. 1800 student’s complaint of the poor or dim marking lines which led to disorganized parking. This represented only 4% of the total student’s population. This information on the pie chart above is important in understanding why the students complain of the unavailable parking space and why it should be expanded. Fig 3: A survey on the number of faculty, staff and the number of students that are in the university In 2010, we conducted a survey and found out that, there were many students, staff and faculty that make up the population. We found out that, there were 2974 full time faculty and had adequate parking space. There were 14602 part time faculty and had excess parking space and some times there are empty parking spaces and students are not allowed to park their. The university students were 45, 833 and they were the majority. From the graph above, we found out that many students lack parking space while both faculty (full and part time) had excess parking spaces. Fig 4: Effects of the improvement to public transportation As we gather information trying to understand about the problem the students was complaining about, we asked the other students, staff and faculty at Florida International University (FIU) their feeling about public transport. We found out the following responses: 28% (4932) believed that it will increase the perception of safety. Majority of them had a feeling that it will reduce time to commute, 5634 (31%) believed that it will lower fare cost and 6% say it be convenient due to more stops. 852 (5%) said it will improve on cleanliness while 18% (3278) believe it will be convenient because there will be fewer transfers. The pie chart above explains the perception of different students on the public transport. Recommendations or solutions On the graph, the university management should increase student’s parking space. If the space for expansion is not enough, public transport system can be introduced in the university where all students will not be allowed to use private vehicles. From the second figure, the unutilized faculty spaces for parking, the students should be allowed to use them. Also, the faculty parking space should be reduced or there should be different parking for students, faculty and staff. From the third graph, the student being the majority, they should use the public transport so that we avoid university parking being congested. The university management should buy university buses that will be used to pick students from their places of residence at some designated points that will be convenient to most of the students. From the last pie chart, most students favored public transport because it will reduce on the fare. This was supported by 31% of the students. Most of the people who use public transport believe that it will increase the perception of safety; hence we recommend that, students should use public transport.
Thursday, December 19, 2019
Platos Allegory Of The Cave And The Matrix By The Wachowskis
Plato once said that, â€Å"Ignorance [is] the root and stem of all evil†. Ignorance is the cause of everything that is wrong and bad in the world since people are unable to see the truth. If people start breaking free from ignorance, mankind will become happier and more transparent. In the short story, â€Å"Allegory of The Cave†by Plato and The Matrix by the Wachowskis, they portray the idea that in order to gain enlightenment, one must break free from ignorance; which opens himself to knowledge; this new truth must then be shared with others for the good of mankind. The cave dweller and Neo both live a life of ignorance by thinking that their world is real, when in reality their world is keeping them from seeing the truth. Both Neo and the†¦show more content†¦Inside his workspace is a cubicle that is identical to the other cubicles on his floor. There are many cubicles in rows of each other. Neo and his coworkers are all trapped in the world of their work. The workers all do the same thing, they work in the same building and work in identical offices. Neo talks to his boss and his boss wants Neo at a specific time. Everyone in the office building is dressed up nicely and dressed uniformly. The color of the offices were gray and monotone(Wachowski). The idea of people being ignorant is seen here because they are all acting and working the same exact way. The colors show how dull and unexciting their life is. It shows that instead of living a life of risk they are living a life as people with no personality. When Neo’s boss t alks to him, he is telling Neo what to do and how to act. Instead of Neo having free choice, he is ordering him to get to work on time and to do work. Neo knows something is wrong in his world. Morpheus tells Neo that â€Å"There’s a splinter in [Neo’s] mind [that is] driving [him] mad†(Wachowski). Neo knows that there is something wrong about his world. He is staying ignorant because he isn’t doing anything to get out of this state. The ignorance is â€Å"driving [Neo] mad†which proves that he is conforming to ignorance. The splinter demonstrates that Neo knows something is wrong about his world which causes him to get mad and find truth. Those people who are ignorant won’t be able to breakShow MoreRelated Breaking Free in The Matrix Essay1115 Words  | 5 PagesBreaking Free in The Matrix      Eighteenth-century Enlightenment philosopher Jean-Jacques Rousseau begins his infamous discourse The Social Contract by stating, Man is born free; and everywhere he is in chains. One thinks himself the master of others, and still remains a greater slave than they. Both Platos Allegory of the Cave from The Republic and the Wachowski Brothers hit film The Matrix discuss mans efforts on his journey towards illumination to break free of his chainsRead MoreComparison of the Matrix and the Allegory of the Cave Essay1240 Words  | 5 Pages2012 The Matrix and the Allegory of the Cave What if one were living through life completely bound and facing a reality that doesnt even exist? The prisoners in Platos Allegory of the Cave are blind from true reality as well as the people in the movie The Matrix. They are given false images and they accept what their senses are telling them. They believe what they are experiencing is not all that really exists. Plato, the ancient Greek philosopher wrote The Allegory of the Cave, to explainRead More Allegory of the Cave vs The Matrix Essay1473 Words  | 6 PagesThe prisoners in Plato’s â€Å"Allegory of the Cave†are blind from true reality as well as the people in the movie â€Å"The Matrix†written and directed by the Wachowski brothers. They are given false images and they accept what their senses are telling them, and they believe what they are experiencing is all that really exists. Plato the ancient Greek philosopher wrote â€Å"The Allegory of the Cave†, to explain the process of enlighten ment and what true reality may be. In the movie â€Å"The Matrix†, Neo (the mainRead MorePlato s Simile Of The Cave1149 Words  | 5 Pagesaction performed by their senses were true. Plato’s Simile of the Cave sheds light on this this idea which is also adapted by the 1999 movie by Andy Wachowski Lana Wachowski, ‘The Matrix.’ Both works have allegorical meanings which explains how people are trapped by some sort of limitations they have which could also serve as a deterrent to their further understanding. This movie ‘The Matrix’ shares a common philosophical basis with Plato’s Simile of the Cave. First, Plato argues that the mind is susceptibleRead MoreThe Matrix the Cave and Meditations Essay1829 Words  | 8 PagesThe Matrix, The Cave And Meditations PHIL 201 John L. Hill II Liberty University John Hill Professor Allyn Kyes Philosophy 201 October 18, 2012 The Matrix, The Cave And Meditations Thesis: There are many similarities in the Matrix ( Wachowski, Andy, and Lana Wachowski 1999 ), The Allegory of the Cave ( Plato ) and Meditation I of The Things of Which We May Doubt ( Decartes, 1641 ). It appears as you take a close look at the Matrix that it is a retelling of â€Å"TheRead MoreThe Allegory of the Cave in the Movie The Matrix Essay1290 Words  | 6 Pagesreturn to the classics, it should not be surprising to find allusions to our more famous Greek philosophers represented in popular films and shows. Andy and Larry Wachowski’s movie The Matrix shows a strong resemblance in its central theme to that of Plato’s The Allegory of the Cave. In The Allegory of the Cave, Plato sets forth the idea that mankind is only living in an illusion of life, that the reality is beyond the scope of our own senses and can only be reached through the intellect. InRead MoreThe Matrix And Karl Marxs Allegory Of The Cave1631 Words  | 7 Pages The Matrix movie conveys what man has been trying to do in a cinematic masterpiece. The creator’s main influences to making The Matrix were Karl Marx and Plato’s Allegory of the Cave (Who Inspired). Karl Marx’s Communist Manifesto tries to highlight the social inequalities that have occurred during the industrial revolution between man and machine while Plato’s Allegory of the Cave tries to help inform people that they need to become more self-aware of their oppressors. The film The Matrix combinesRead MoreAngelabrafford-Phil Essay830 Words  | 4 Pagesprocesses of many. These theories today are still influencing the lives of others. The Matrix, a very well-kno wn movie released in 1999, retelling Plato’s theory, questioned the existence of reality and /or what we perceive as reality. The Matrix, Plato’s ‘Allegory of the Cave’ and Descartes ‘Meditation I’, all have similar views on reality, illusion and truth. Allegory of the Cave is a metaphor that describes what Plato believed reality to be. Plato believed thatRead MoreTrue Reality In Platos Allegory And The Matrix873 Words  | 4 PagesIn the Plato’s Allegory of The Cave, prisoners are kept since child birth in a cave, they are only able to see nothing but shadowy figures move on the wall of the cave. They perceive that as their true reality. A prisoner breaks free from his shackles and is blinded by the light of the sun. He realized that his reality in the cave was not real, he sees people and understands what reality is now. The prisoner goes back to explain to the others what he has seen but they don’t believe him. The WachowskiRead MoreAllegory Of The Cave And The Matrix Analysis1986 Words  | 8 Pagespossible,†(The Matrix). These words spoken at the conclusion of the Wachowski Brothers’ 1999 film, The Matrix, by the main character Neo represent a deeper meaning and a connection to ancient literature many people viewing the film might not realize. This quote relates to a work of literature more than two millennia old, the narrative by Plato called The Allegory of the Cave. Much like how Neo must endure the stages of enlightenment to rise from the blissful ignorance controlled by the matrix in the movie
Tuesday, December 10, 2019
Health Safety And Well Being free Samples †MyAssignmenthelp.com
Question: Discuss about the Health Safety And Well Being. Answer: Introduction Economic disadvantage makes children vulnerable. It usually has a magnified effect since it interacts with other disadvantages to threaten child development. These effect has been examined using family process or family stress models. Economically disadvantaged children are usually at risk for several socioemotional disadvantages. They also tend to form insecure attachment relationships, behavior problems and also greater physiological markers of stress(Barnett). Economic disadvantage contributes a great deal to poor results eventually in the final examinations of the children. The education system offers opportunities for children to have wider experiences and also interact with different social levels. Children tend to inherit the social position of their parents and then they may go even higher as adults (Beaver, M., Brewster, J., Jones, P., 2001, p.534). Economic disadvantage can be defined by the lack of employment of the mother of the child. It can also be deduced from the health and level of education of the mother and also from the eligibility for free school meals of the child. Economically disadvantaged children mostly have poor speech and language as compared to other children of the same age and in the same stage of development. Some of these children usually have teenage or young parents. These children may be under the care of someone else other than their parents for example their grandparents. They may also have been born in a family that is known to be involved in crime (Barnett). Strategies Educators have got some strategies at their disposal to work with this group of children. For the 3 years old bracket, they may put in place a school meals programme. In this way they will supplement the diets of the children attending their school. When the children are well fed in school they will not miss attending and will also long to attend to enjoy a meal they would otherwise have missed out on at home. This meal is not a replacement to meals from home but just an additional one. Another strategy is using integrated services for the economically disadvantaged children. The children can be kept longer in school so that they can enjoy that they lack at home. They can have their nap in school under the teachers watch and then have a play afternoon with the schools toys. In this way, their curiosity will be roused and in that way they will find school fun. The children will also learn how to share and also team spirit from their play interactions (Nicaise). Another strategy that can be adopted for the three year olds is to develop skills in the children so that they can easily adapt to their coursework in primary school. A very key skill to be developed here is language skills. Language skills will come in very handy for the children because their primary school coursework will be manageable. For the children lacking good language skills they will lag far much behind thus failing their final exams. Another strategy would also be to increase the contact between the teachers and the childrens parents. Hence the birth of parent teacher associations. This ensure that the parents and the teachers can work hand in hand in the childrens development. For those families that see harder hit economically, social workers can intervene so as to implement a home-based intervention programme. In this way the mothers gain confidence in the home and they also educate their children outside class. This task should not only be left to the teacher for it to be effective. Thus the childs language and communication skills will be superior allowing them to compete effectively in the primary school course work(Nicaise). Educators can use language play elicitation games to improve the verbal and social abilities of the three year olds. The children are guided into playing word creation games, creating rhymes, word switching and hyperbolic play as well. These games allow the educators to assess the childrens verbal and peer interaction skills. From the results it was concluded that the childrens verbal skills scores were related with the scores they received in their wordplay sessions (Read, 2017). There is also a huge need to ensure that there is available staff to institute these strategies otherwise they will just remain on paper. The early childhood teachers need to be attracted, retained and developed. There is a need to provide them with the necessary skills through training. They should also have good working conditions and salaries as well as future plans to promote them in their careers. There has also been an argument against free childcare for all parents by the state. Some proponents suggest that it should be directed at the disadvantaged children only since they need it the most. These people claim that by availing it for all, has made it expensive by international standards especially towards the parents. In this way, low cost childminders have been driven out of the market. Thus, the report concludes that though the amount of regulation over the quality of childcare has increased, it has not necessarily resulted in producing better outcomes. A report found out that the numbers of new teachers for the early years education are dwindling drastically. This can be assigned to the reason that the new graduates are put off by the very low salaries offered for those jobs. There is therefore a need for the government to invest in that sector to safeguard the future workforce of the country. If the disadvantaged children are not helped at that juncture in their early ages, there is a risk of them falling behind and staying behind for the rest of their lives. This is due to the shortage of nursery school teachers. For the success of the early year intervention strategies to succeed, there is a huge need to develop a strong workforce of early years teachers who will deliver high quality training to the children(save the children). The teachers and students require better spaces for learning to take place efficiently. This is key to ensure that the strategies are implemented properly. Poor learning conditions will damage the students health and their education will suffer. These poor conditions may also lead to teachers quitting citing them to be crowded and stressful. Thus proper design should be placed high on the priority list and to be constantly reviewed (Royal Institute for British Architects). Conclusion Various studies have revealed that there is a large proportion of children who start primary school without sufficient language skills for their educational success. For most disadvantaged children, high quality early education is their best bet to learning early language skills since their homes and social interactions do not offer this. Thus, once their foundations in English and Maths are secured they have a much better chance at attaining success in their future academic aspirations. These children will therefore compete effectively with other children from more privileged backgrounds. They will therefore have a better chance of changing their social status and not merely remaining in the same level their parents are at. Education in this case is the key to success(Early Language Development and Children's Primary School Attainment in English and Maths). References Barnett, M. (n.d.). Economic Disadvantage in Complex Family Systems: Expansion of Family Stress Models. NCBI. Beaver, M. B. (2001). Babies and Young Children: Diploma in ChildCare and Education. Nelson Thorne. Early Language Development and Children's Primary School Attainment in English and Maths. (n.d.). Retrieved from Save the Children: https://www.savethechildren.org.uk/resources/online-library/early-language-development-and-children%E2%80%99s-primary-school-attainment-english Nicaise, I. D. (n.d.). Success for all? Education-Line. Read, K. J. (2017). Journal of Early Childhood Research. (n.d.). Royal Institute for British Architects. (n.d.). save the children. Ting, T. C. (n.d.). Policy Developments in Pre-School Education in Singapore: A Focus on the Key Reforms of Kindergarten Education. International Journal of Child Care and Education Policy.
Tuesday, December 3, 2019
Parallelization of Pagerank and Hits Algorithm on Cuda Essay Example
Parallelization of Pagerank and Hits Algorithm on Cuda Paper Page Rank algorithm and HITS algorithm are widely known approaches to determine the importance and popularity of web pages. Due to large number of documents available on World Wide Web, huge amount of computations are required to determine the rank of web pages making it very time consuming. Researchers have devoted much attention In parallelizing Pageant on PC Cluster, Grids, and Multi- core processors Like Cell Broadband Engine to overcome this Issue but with little or no success. In this paper, we discuss the Issues In porting these algorithms on Compute unified Device Architecture (CODA) and Introduce efficient parallel implementation of these algorithms on CUD by exploiting the block structure of web, which not only cut down the computation time but also significantly reduces of the cost of hardware required (only few thousands). 1 . Introduction In present days, the unceasing growth of World Wide Web has lead to a lot of research in page ranking algorithms used by the search engines to provide the most relevant results to the user for any particular query. The dynamic and diverse nature of web graph further exaggerates the challenges in achieving the optimum results. Web link analysis provides a way to order the web pages by studying the link structure of web graphs. Pageant and HITS (Hyperlink Induced Topic Search) are two such most popular algorithms widely used by the current search engines either In same or modified form to rank the documents based on the ink structure of the documents. Pageant, originally introduced by Bring and Page is based on the fact that a web page is more important if many other web pages link to it. We will write a custom essay sample on Parallelization of Pagerank and Hits Algorithm on Cuda specifically for you for only $16.38 $13.9/page Order now We will write a custom essay sample on Parallelization of Pagerank and Hits Algorithm on Cuda specifically for you FOR ONLY $16.38 $13.9/page Hire Writer We will write a custom essay sample on Parallelization of Pagerank and Hits Algorithm on Cuda specifically for you FOR ONLY $16.38 $13.9/page Hire Writer In core, it contains continuously iterating over the web graph until the Rank assigned to all of the pages converges to a stable value. In contrast to Pageant, a similar HITS algorithm, developed by Glibber [1 1], ranks the documents on the basis of two scores which it assigns to a particular set of documents dependent on a specific query, although basis for computation are same for both. Enormous size of web [1 5] makes the need of fast Implementation of these algorithms very clear. Till date, several approaches have been designed to accelerate this algorithm Like exploiting the block structure of web [6], running on parallel environment like PC cluster [4, 5, 10] but they have brought their own overheads like nudge nearer cost Ana approximate result TTS. Some research NAS also Eden cone on implementing this algorithm on Multi-core processors like Cell Broadband Engine [9] but due to the issues involved like random read and writes from large memory, this has lead to even poorer performance. In [9], it is shown that its implementation on Cell is 22 times slower than Intel Xenon Quad Core 2. GHz. Parallel implementation of these algorithms involves issues like no specific order in the number of pages that points to a particular page and randomness in the links of the nodes hindering the load balancing, which is the basis of any parallel implementation. This paper addresses these issues in an interesting manner and proposes an innovative way of exploiting the block structure of web existing at much lower level. Our approach in parallel implementation of these algorithms on Invalids Multi-core CUD Architecture not only reduces the computation time but also requires much cheaper rearward. In our study, we have used the standard input of approximately one million documents generated through the widely accepted Hebraic framework from publicly available datasets in [16]. This paper is organized as follows. Section 2 describes block structure of web, issues involved in porting Pageant on CUD architecture, the proposed parallel implementation and results. Section 3 discusses parallel implementation of HITS algorithm and results. And finally section 4 ends with conclusion. 2. Pageant 2. 1 . Algorithm Let Rank(p) denotes the rank of web page p from set of all web pages P. Let Sp bet a set of all web pages that points to page p and Nu be the outgrew of the page u ? Sp. Then the importance given by a page u to the page p due to its link is measured as Rank(u)/Nu. So total importance given to a page is the sum of all the importance due to incoming link to page p. This is computed iteratively n times for each page rank to converge. This iteration is as follows. V e , ? 2. 2. Sequential implementation of Pageant Algorithm 1: , 2: 3: 4: 5: 7: 8: 9: 10: V ,11: 6: 32 h h 2. 3. Comparison with Related Works Where d is the damping factor from the random surfer model [1]. The range for alee of d is from Tot 1. D is the probability that a random surfer will get bored at page p and will Jump to another random page with probability (1- d). We will be using 0. 85 as the value of d further in this paper as given in [1]. The use of d insures the convergence of Pageant algorithm [5]. The input file containing the web graph s o a De converted to Dollar link structure Tile I . Nils Tile consist AT all nodes as numbers, with their number of outguesses and the pages (also in the numerical form) to which it points to as shown in Fig 1 . The above equation (1) is the Jacobin iterative solution to system of linear equations. The extensive use of Jacobin method is because it can be easily parallelized, as the calculation of the rank of a page is dependent on the initial rank of pages. There is another efficient method to solve system of linear equations called Gauss-Sidle method. In Gauss-Sidle method for calculating the rank of page p in the iteration I, the recently calculated rank of the all pages before p is used and previous iterations rank is used for pages after page p. The iterative formula is as follows: V e , = 1- * + (2) The main advantage of this algorithm is its usage of less space during calculation. In this only one array containing the rank of pages is used and both retrieving and updating of pages rank can be done on the same array. But the disadvantage is that it cannot be easily parallelized. Since Pageant involves huge amount of computation, therefore many researchers have attempted with their own approaches towards its parallel implementation. Here we list most notable works and discuss the advantage of our approach over their work. 1. Block rank: This algorithm by Wavelike et al. [6], splits the web graph into blocks according to their domain and then calculates Pageant of each block locally. It then uses an approximation to merge these results and calculate global Pageant. This implementation increases the performance by 2 times. 2. Partition-Based Parallel Pageant Algorithm: Orangutans and Namesakes [3] discusses about three algorithms and their implementation on PC cluster. He compares PC cluster implementation of block based algorithm, split accumulate algorithm and partition based parallel algorithm, with results favoring last implementation. . Pageant Computation Using PC Cluster: This is another implementation by Orangutans and Namesakes [4] in which they divide the input graph into equal sets and lactate them on each PC cluster nodes. Each cluster node solves them for 5 iterations locally and then updates the new rank on other nodes. This implementation achieves 4 times speed up. 4. Another efficient paral lel implementation of Pageant on PC cluster by Schoolhouses et al. [5] achieves gain of 10 times by using block structure of web page and reformulating the algorithm by combining Jacobin and Gauss-Sidle method. Most researchers have implemented Pageant algorithm on PC cluster, which increases the efficiency but not in comparison to the added hardware cost. Very less research, with success has been one in the field of implementing Pageant algorithm on rapid evolving multi core architectures. The implementation on multi core 6 SPUN based Cell BE has shown that ten Pageant Algorithm runs 22 times slowly. We odometer Implement It on more efficient SIMI based multi core CUD architecture, containing large number of processors, using an entirely innovative approach. Our approach also exploits the block structure of web but dont involve approximation like in [6]. We further show that if we merge both the use of PC cluster implementation and CUD device a huge increase in performance can be achieved in comparison to ere small increase in hardware cost. 2. 4. The Block Structure of Web Graph 2. 3. As discussed in section 2. 3, several researches have been done on utilizing the block structure of web for efficient implementation of Pageant. They reveal that in most cases the numbers of intra-host links are much larger than the inter-host links leading to creation of block structures in the web graph. Here, we take it to a further extent and analyses this property in a more magnified view which reveals that this kind of block structure also exists at lower level of hierarchy. For instance, most of the inks for a certain block of pages say BBC. Ex./docs are in and around BBC. Ex./docs. For studying the structure of web, the link structured file, generated using Hebraic, has been used. To visualize it further, we construct dot plots such that if there is a link from node J to node I, then there is black point in the graph at (I, J). Since, our full dataset is too large to observe the individual points, a slice of graph are shown in Figure 2. The following things are noticeable: 1. There is a dense diagonal line indicating that most of the pages link in and around themselves. 2. There are several blocks of points which show that a certain blocks of pages have large number of intra-linkages between them. This clearly shows that the block structure at domain or host level is also prevalent at smaller level. 3. There are several horizontal lines highlighting that some blocks of pages are pointed by a narrow set of pages and few isolated vertical lines that indicate that a certain block of pages points to a very narrow set of pages. . There are number of isolated points which highlight the degree of randomness in the link structure. 2. 5. CUD Architecture CAUDAL, introduced by INVALID, is a general purpose parallel computing that leverages the parallel compute engine in INVALID Spies to solve many complex computational problems in a more efficient way than on a CAP]. These Spies are used as coprocessor to assist CPU for compu tational intensive task. More details about this architecture can be explored at [10]. Here, we highlight the features that need special mention in relation to our work. 4. SIMI Architecture: Employs Single Instruction Multiple Thread Architecture leading to the execution of a single instruction by a huge number of threads. Asynchronous Concurrent Execution: In order to facilitate concurrent execution between host and evolve, Kernel launches are asynchronous I. E. Control Is returned to ten most Athena before the device has completed the requested task. Warps: A warp is a group of 32 parallel threads which executes one common instruction at a time, so full efficiency is realized when all 32 threads of a warp agree on their execution path. Memory Coalescing: Global memory bandwidth is most efficiently used if the simultaneous memory accesses by threads in a half-warp (during the execution of a single read or rite instruction) are such that they can be coalesced into a single memory transaction of 32, 64, or 128 bytes, leading to minimum access time. 2. 6. Porting issues on CUD Architecture Porting issues with the Pageant algorithm are mainly concerned with hardware restrictions of CUD architecture. CUD demands the execution of all threads in a warp to be similar for the thread to execute in parallel, hence, if the execution paths of threads in a warp become divergent then it causes the CUD to suspend the parallel execution of threads and executes them sequentially (or become serialized), hence decreasing throughput. As he number of industries of nodes can be very dissimilar, the loop involved in calculation, iterating for number of industries, can make the threads control flow to become divergent or different from other threads. Another constraint of the device is related to memory accesses. Due to the huge size of link structure arrays containing the industries and rank of nodes, it has to be stored in the global memory. But the latency of global memory is very low, hundreds of memory cycles, compared to shared memory. The protocol followed by the CUD architecture for memory transaction ensures that all the threads referencing memory in the same segment re serviced simultaneously. Therefore bandwidth will be used most efficiently only if, simultaneous memory accesses by threads in a half warp belongs to a segment. But due to uneven and random nature of industries of nodes the memory reference sometimes become non coalesced hindering the simultaneous service of memory transactions leading to the wastage of memory bandwidth. There are different structures of input file for the Pageant algorithm. It can be either nodes with their industries or nodes with their outguesses. The problem with the outgrew is that while iterating through the list of outguesses of a particular node, calculation squires dividing the initial Pageant of the node with its number of outguesses and adding the result to the memory location for storing the new Pageant of the node which it points to. The pseudo code for parallel implementation of this on CUD architecture is described in pseudopodia [1]. : ? Result: Since, step 2 in [1] will be simultaneously executed by large number of threads, this may lead to conflict between them while updating the same memory location, producing unpredictable results. Though this problem can be solved using atomic operation, but there are no atomic operations for floating point values yet incorporated in the architecture. Hence the input files format should be, each node with their number of industries and a list of nodes pointing to the node. The outgrew of each node required in calculation can be stored in a separate file or in the sane file. The structure of input file used in our experiment is shown in the Figure When this implementation is executed on the device then the running time is more than the sequential implementation on the hardware specified in section 2. . The reason for this can be easily attributed to porting issues we mentioned in section 2. 6. 2. 7. 1 . Solving the problem of non coalesced memory access Figure 2: Topple of all links One of the reasons for poor performance of naive implementation is that the global memory accesses were not coalesced. As discussed while considering the porting issues in section 2. 6, for better p erformance, the simultaneous memory accesses done by all threads in a half warp should belong to same segment for lesser transactions to occur. The Figure 1: Input File Structure The problem with implementation of Guidelines for calculating Pageant is that for calculating the rank of a page we need the new ranks of all pages before it, but due to personalization the calculation of some of them may e still in process. This happens especially for threads belonging to same block, as all threads in a block execute in parallel. 2. 7. Parallel implementation using Jacobin method The naive implementation involves each thread is assigned one node for the calculation. The thread iterates though can I TTS Menageries Detecting tenet Nominal rank Ana teen Livelong It Walt outgrew and adding it up. Finally multiply it with the damping factor d and add (1 d) to the sum. The initial Pageant before starting to iterate is kept 1 . The decent number of iteration is 32 as normally the algorithm converges in 32 iteration. Figure 3: Topple of links calculated on device nodes generally link in the locality, with few links to farther nodes as described in section 2. 4. To improve the rank calculation of a node, say p, we process only those nodes on kernel which belong to locality of p, determined by the range. And the rest of the nodes are processed on host processor as shown in Figure 4. So we create two link structured input file, one to be processed by kernel, which contains nodes lying in locality, and other contains rest of the nodes to be processed on host processor. 2. 7. 2. Solving the problem of divergence in control flow Another season for poor performance of naive implementation is the divergence in the program control flow. The main problem causing divergence is uneven number of industries, which causes different threads to end up with different number of iteration, also discussed in section 2. . The solution to this problem is to allow maximum possible threads to iterate same number of times, so that the program execution path does not diverge much from the normal flow. For this we calculate the average of all nodes number of industries for the kernel link structured input file. And then each thread is allowed to calculate up to the average number of industries if it is less t han average number) and the rest calculation is done simultaneously on the host processor. Those points that are included in the calculation of rank on the device. Figure 5: Topple of links calculated on host The number of calculation on host can be further decreased if we use some constant multiple of the average value. This constant for peak performance is different for different input graphs depending on the distribution of the number of industries among the nodes. This constant if too large can also increase the number of threads going divergent. But if perfect balance exist between the increase in time due to increase in calculation on the host processor and number of threads going divergent, then further decreases in time can be achieved. This constant can be called as average factor which is a function of the distribution of number of industries among nodes and block size. The final implementation is shown in Parallel Algorithm 1. Figure 4: Processing the input File The total number of calculations done on host processor is considerably decreased. But in order to increase the performance the block structure of web can be exploited. As we showed in section 2. There exists block structure even at small level. So in our next improvement instead of calculating the average of the industries of all nodes, we divide all the nodes into blocks.
Subscribe to:
Posts (Atom)