Tutorial on Parallel Computing and Message Passing Model - C1
•
18 j'aime•4,849 vues
The document provides an overview of parallel computing concepts and programming models. It discusses parallel computing terminology like Flynn's taxonomy and parallel memory architectures like shared memory, distributed memory, and hybrid models. It also explains common parallel programming models including shared memory with threads, message passing with MPI, and data parallel models.
![Tutorial on Parallel Computing and Message Passing Model Marcirio Silveira Chaves [email_address]](https://image.slidesharecdn.com/c1pcmpishort-124612674397-phpapp02/85/Tutorial-on-Parallel-Computing-and-Message-Passing-Model-C1-1-320.jpg)
![Course Structure ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],June - 2009 LNEC-DHA-NTI](data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7)
Recommandé
Contenu connexe
Tendances
Tendances (20)
Similaire à Tutorial on Parallel Computing and Message Passing Model - C1
Similaire à Tutorial on Parallel Computing and Message Passing Model - C1 (20)
Plus de Marcirio Chaves
Plus de Marcirio Chaves (16)
Tutorial on Parallel Computing and Message Passing Model - C1
- 1. Tutorial on Parallel Computing and Message Passing Model Marcirio Silveira Chaves [email_address]
- 22. Any questions, so far?
- 34. Any questions, so far?
- 46. Any questions, so far? Pit-stop ?
- 66. Collective Communications June - 2009 LNEC-DHA-NTI
- 68. Any questions, so far?
- 69. Nano-Self-Test http://ci-tutor.ncsa.uiuc.edu/content.php?cid=1294
Notes de l'éditeur
- Limits to serial computing: - Transmission speeds - the speed of a serial computer is directly dependent upon how fast data can move through hardware. - Limits to miniaturization - processor technology is allowing an increasing number of transistors to be placed on a chip. - However, even with molecular or atomic-level components, a limit will be reached on how small components can be. Economic limitations - it is increasingly expensive to make a single processor faster.
- Coarse: grossa
- overhead é geralmente considerado qualquer processamento ou armazenamento em excesso, seja de tempo de computação , de memória , de largura de banda ou qualquer outro recurso que seja requerido para ser utilizado ou gasto para executar uma determinada tarefa. Como consequência pode piorar o desempenho do aparelho que sofreu o overhead.
- Rendering is the process of generating an image from a model , by means of computer programs. The model is a description of three-dimensional objects in a strictly defined language or data structure. It would contain geometry, viewpoint, texture , lighting , and shading information.
- Uniform Memory Access (UMA): Non-Uniform Memory Access (NUMA):
- Uniform Memory Access (UMA): Non-Uniform Memory Access (NUMA):
- Uniform Memory Access (UMA): Non-Uniform Memory Access (NUMA):
- Uniform Memory Access (UMA): Non-Uniform Memory Access (NUMA):
- Symmetric Multi-Processor (SMP): Hardware architecture where multiple processors share a single address space and access to all resources ; shared memory computing.
- Shared memory model on a distributed memory machine: Kendall Square Research (KSR) ALLCACHE approach . Machine memory was physically distributed, but appeared to the user as a single shared memory (global address space). Generically, this approach is referred to as "virtual shared memory". Note: although KSR is no longer in business, there is no reason to suggest that a similar implementation will not be made available by another vendor in the future. Message passing model on a shared memory machine : MPI on SGI Origin . The SGI Origin employed the CC-NUMA type of shared memory architecture, where every task has direct access to global memory. However, the ability to send and receive messages with MPI, as is commonly done over a network of distributed memory machines, is not only implemented but is very commonly used.
- The remainder of this section applies to the manual method of developing parallel codes.
- The majority of scientific and technical programs usually accomplish most of their work in a few places.
- The majority of scientific and technical programs usually accomplish most of their work in a few places.
- The majority of scientific and technical programs usually accomplish most of their work in a few places.
- The majority of scientific and technical programs usually accomplish most of their work in a few places.
- The majority of scientific and technical programs usually accomplish most of their work in a few places.
- The majority of scientific and technical programs usually accomplish most of their work in a few places.
- The majority of scientific and technical programs usually accomplish most of their work in a few places.
- The elapsed time between when a process starts to run and when it is finished. This is usually longer than the processor time consumed by the process because the CPU is doing other things besides running the process such as running other user and operating system processes or waiting for disk or network I/O .
- The elapsed time between when a process starts to run and when it is finished. This is usually longer than the processor time consumed by the process because the CPU is doing other things besides running the process such as running other user and operating system processes or waiting for disk or network I/O .