CSC506: Difference between revisions

From Expertiza_Wiki
Jump to navigation Jump to search
No edit summary
No edit summary
Line 27: Line 27:


* Sections 1.2.1 and 1.2.4: Communication architecture   
* Sections 1.2.1 and 1.2.4: Communication architecture   
** Trends in last 10 years.  How has data parallelism found its way into shared-memory and message-passing machines?  An early example would be MMX.   
** Trends in last 10 years.   
** How has data parallelism found its way into shared-memory and message-passing machines?  An early example would be MMX.   
** Would you change the number of layers in Fig. 1.13?
** Would you change the number of layers in Fig. 1.13?


* Section 1.2.2:  Shared address space
* Section 1.2.2:  Shared address space
** Any changes in the organization of address spaces in the last 10 years?  Are the
** Any changes in the organization of address spaces in the last 10 years?   
interconnection structures different in new computers now than they   
** Are the interconnection structures different in new computers now than they   
were 10 years ago?  What is the size and capacity of current SMPs?   
were 10 years ago?   
How have supercomputers evolved since the Cray T3E?
** What is the size and capacity of current SMPs?   
** How have supercomputers evolved since the Cray T3E?


* Section 1.2.3:  Message passing.  Update. Are blade servers an
* Section 1.2.3:  Message passing   
extension of message passing?  How have blade architectures evolved
** Are blade servers an extension of message passing?   
over the past 10 years?
** How have blade architectures evolved over the past 10 years?


* Section 1.2.5:  Trends in vector processing and array   
* Section 1.2.5:  Trends in vector processing and array   
processing.  New machines have recently been announced.  Why will
processing.   
this be an important architectural dimension in the coming years?
** New machines have recently been announced.  Why will this be an important architectural dimension in the coming years?


* Section 1.2.6: New developments in dataflow and systolic
* Section 1.2.6   
architectures, if any.  Or if not, why are these styles not evolving
** New developments in dataflow and systolic architectures, if any.   
with time?
** Or if not, why are these styles not evolving with time?


* Sections 1.3.1 and 1.3.2:  Communication and programming model.    
* Sections 1.3.1 and 1.3.2:  Communication and programming model   
How have reordering strategies evolved to accommodate larger
** How have reordering strategies evolved to accommodate larger multicomputers?   
multicomputers?  Have new kinds of synchronization operations been
** Have new kinds of synchronization operations been developed?   
developed?  I doubt that other topics covered in these sections have
** I doubt that other topics covered in these sections have changed much, but do check.
changed much, but do check.


* Sections 1.3.3 and 1.3.4:  Most changes here are probably related
* Sections 1.3.3 and 1.3.4:  Most changes here are probably related to performance metrics.   
to performance metrics.  Cite other models for measuring artifacts
** Cite other models for measuring artifacts such as data-transfer time, overhead, occupancy, and communication cost.   
such as data-transfer time, overhead, occupancy, and communication
** Focus on the models that are most useful in practice.
cost.  Focus on the models that are most useful in practice.

Revision as of 20:53, 28 August 2007

Formatting Resources

Formatting Help Guide from MetaWiki


Peer-reviewed Assignment 1

  • Sections 1.1 and 1.1.2
    • Update performance trends in multiprocessors.
  • Section 1.1.1, first half: Scientific/engineering application trends
    • What characterizes present-day applications?
    • How much memory, processor time, etc.?
    • How high is the speedup?
  • Section 1.1.1, second half: Commercial application trends
    • What characterizes present-day applications?
    • How much memory, processor time, etc.?
    • How high is the speedup?
  • Section 1.1.3: Architectural trends
    • How have architectures changed in the past 10 years?
    • Update Figs. 1.8 and 1.9 with new points, for 2000, 2002, 2004, 2006, and 2007.
  • Section 1.1.4: Supercomputers
    • Compare current supercomputers with those of 10 yrs. ago.
    • Update Figures 1.10 to 1.12 with new data points. For 1.12, consult top500.org.
  • Sections 1.2.1 and 1.2.4: Communication architecture
    • Trends in last 10 years.
    • How has data parallelism found its way into shared-memory and message-passing machines? An early example would be MMX.
    • Would you change the number of layers in Fig. 1.13?
  • Section 1.2.2: Shared address space
    • Any changes in the organization of address spaces in the last 10 years?
    • Are the interconnection structures different in new computers now than they

were 10 years ago?

    • What is the size and capacity of current SMPs?
    • How have supercomputers evolved since the Cray T3E?
  • Section 1.2.3: Message passing
    • Are blade servers an extension of message passing?
    • How have blade architectures evolved over the past 10 years?
  • Section 1.2.5: Trends in vector processing and array

processing.

    • New machines have recently been announced. Why will this be an important architectural dimension in the coming years?
  • Section 1.2.6
    • New developments in dataflow and systolic architectures, if any.
    • Or if not, why are these styles not evolving with time?
  • Sections 1.3.1 and 1.3.2: Communication and programming model
    • How have reordering strategies evolved to accommodate larger multicomputers?
    • Have new kinds of synchronization operations been developed?
    • I doubt that other topics covered in these sections have changed much, but do check.
  • Sections 1.3.3 and 1.3.4: Most changes here are probably related to performance metrics.
    • Cite other models for measuring artifacts such as data-transfer time, overhead, occupancy, and communication cost.
    • Focus on the models that are most useful in practice.