Identify the source of performance degradations or low performance gains of applications running on systems that support Hyper-Threading Technology. Once applications have been tuned for the Pentium® 4 processor, they can be tuned for processors that support Hyper-Threading Technology as a separate process. In some cases, however, the tuning process may not yield acceptable increases in performance.
Apply threading to functional-decomposition problems in the Implementation Phase of application development. Functional-decomposition problems are situations where the roles of different threads are defined by having different functionality (as opposed to identical functionality that is applied to different data).
Develop a methodology for the tuning phase of the development cycle. The tuning phase increases performance incrementally where possible.
Develop a methodology for the analysis phase of the development cycle. Typically, the analysis stage for a threaded application involves profiling a serial application to determine regions of the application that are potential candidates for parallelization.
Develop a methodology for the debugging & testing phase of the development cycle. In most situations, the debug and testing stages of threading go hand in hand.
Develop a methodology for the design phase of the development cycle. Regions identified by the analysis phase are examined during the design phase to determine changes that must be made to accommodate a threading paradigm.
Determine whether performance degradation (or lower-than-expected performance benefit) from Hyper-Threading Technology is due to exceeding the write-combining buffer capacity. A write-combining (WC) store buffer accumulates multiple stores in the same cache line before eventually writing the combined data farther out into the memory hierarchy, to accelerate processor write performance.
Implement data decomposition on a serial function in order to produce a threaded version. The threaded version creates threads, each performing individual pieces of a computationally intensive operation.
Choose task-level or data-parallel threading for various parts of an application. Choosing the right threading method minimizes the amount of time spent modifying, debugging, and tuning threaded code.
Describe your application (or an individual operation in that application) in terms of one of two models based on fit for the particular job:
