DistOS 2014W Lecture 24: Difference between revisions
36chambers (talk | contribs) |
36chambers (talk | contribs) |
||
| (4 intermediate revisions by the same user not shown) | |||
| Line 11: | Line 11: | ||
==7 Dwarfs== | ==7 Dwarfs== | ||
* Dense Linear Algebra | * Dense Linear Algebra (hard to parallelize) | ||
* Sparse Linear Algebra | * Sparse Linear Algebra | ||
* Spectral Methods | * Spectral Methods | ||
| Line 18: | Line 17: | ||
* Structured Grids | * Structured Grids | ||
* Unstructured Grids | * Unstructured Grids | ||
* Monte Carlo | * Monte Carlo (parallelizable) | ||
==Extended Dwarfs== | ==Extended Dwarfs== | ||
* Combinational Logic | * Combinational Logic | ||
| Line 41: | Line 41: | ||
* Massive change in mobile and cloud over the past five years | * Massive change in mobile and cloud over the past five years | ||
* Linux a very general operating system when it started at first - hard coded to 8086 processor specialized to run on the box. Now it runs everywhere. It has all the abstractions dealing with various aspects of hardware, architecture. Multiple layers abstraction because it was useful. | * Linux a very general operating system when it started at first - hard coded to 8086 processor specialized to run on the box. Now it runs everywhere. It has all the abstractions dealing with various aspects of hardware, architecture. Multiple layers abstraction because it was useful. | ||
==Summary== | |||
Standard programming languages can be modeled as finite state machines (their execution models are finite state machines). It is advisable to concede defeat in the area of parallelizing finite state machines and focus on parallelizing other areas. We need to find multiple system architectures that can deal with each of these problems. How do we find abstractions to deal with these things? | |||
Generalizations are rarely generalized in the right way. Generalization has to be made at some level, but at the same time, you do not want to make generalizations without a clear justification. Otherwise, you’re likely to generalize it wrong. | |||
==Class Feedback for the Course== | |||
* Challenging questions given in advance to lead and direct the group discussions | |||
* Having required questions on the Wiki | |||
* Share and highlight any good reading responses with the rest of the class | |||
* Having essay assignments replace essay format of midterm | |||
* Incorporate more information about the history of computer science | |||
Latest revision as of 15:11, 24 April 2014
The Landscape of Parallel Computing Research: A View from Berkeley
- What sort of applications can you expect to run on distributed OS/parallize?
- How do you scale up
- We can't rely on processor improvements to provide speed-ups
- The proposed computational models that need more processor power don't really apply to regular
- Users would see the advances with games primarily
- More reliance in cloud computing in recent years
- In general you can model modern programs (Java, C, etc.) as finite state machines which are not parallizable
- Today we deal with processor limitations by using "experts" to build the system which results in a very specialized solution usually in the cloud
- Authors have found the problem but not really the process
7 Dwarfs
- Dense Linear Algebra (hard to parallelize)
- Sparse Linear Algebra
- Spectral Methods
- N-Body Methods
- Structured Grids
- Unstructured Grids
- Monte Carlo (parallelizable)
Extended Dwarfs
- Combinational Logic
- Graph Traversal
- Dynamic Programming
- Backtrack/Branch + Bound
- Construct Graphical Models
- Finite State Machines (hardest to parallelize)
Features
- Pretty impressive on getting everyone to sign off on the report
- Connection to MapReduce
- Programs that run on distributed operating systems - applications that can be expected to be massively parallel - what sort of computational model is needed - Abstractions needed on top of the stack.
- Predictions about the processing power
- GPU's do have 1000 or more cores
- Desktop cores have not gotten that fast over the past years. They just don't run fast enough.
- Games are the only things that can't be run over the time on single thread
- Low power
- Being able to run a smart phone with 100's of transistors - stalled with the sequential processing
- Why do we need the additional processing power for ? - Games - Games - Games
- Doomsday of the IT industry
- Massive change in mobile and cloud over the past five years
- Linux a very general operating system when it started at first - hard coded to 8086 processor specialized to run on the box. Now it runs everywhere. It has all the abstractions dealing with various aspects of hardware, architecture. Multiple layers abstraction because it was useful.
Summary
Standard programming languages can be modeled as finite state machines (their execution models are finite state machines). It is advisable to concede defeat in the area of parallelizing finite state machines and focus on parallelizing other areas. We need to find multiple system architectures that can deal with each of these problems. How do we find abstractions to deal with these things?
Generalizations are rarely generalized in the right way. Generalization has to be made at some level, but at the same time, you do not want to make generalizations without a clear justification. Otherwise, you’re likely to generalize it wrong.
Class Feedback for the Course
- Challenging questions given in advance to lead and direct the group discussions
- Having required questions on the Wiki
- Share and highlight any good reading responses with the rest of the class
- Having essay assignments replace essay format of midterm
- Incorporate more information about the history of computer science