03_Intel_VTune_Session_04.pptVIP

In this session, you will learn to: Measure performance-related data for processors Identify the hierarchy of memory Benchmark processor performance Processor: Computes the instructions in a program and calculates the result. Should be used optimally by the application. Performance also affects application performance. Performance should be measured to know how the processor is utilized. Processors consists of functional units that execute specific instructions. Different types of processors have different speed of executing instructions. Before beginning to optimize the application performance, you need to: Identify processor speed Identify the execution process Identify the functional units of a processor Pipelining is an important concept used in high-performance computing. Pipelining is shown in the following figure. Pipelining has multiple stages. Different parts of pipeline perform different jobs. Some parts of the pipeline can be duplicated so that less work is done at each stage. Pipelining has substantial impact on the performance of the application. Explain the different levels of memory hierarchy as displayed on the slide. Registers enable fast execution of instructions as they provide fast access to values computed during calculation. Explain the multiple levels of cache memory Main memory is the primary storage of computer and is directly connected to the processor. Explain the process of paging in virtual memory. Ask how mismatch in memory and processor speed can decrease the performance of an application. Ask how you can calculate the time taken for memory access. Explain the Hit and Miss ratios as given in the slide. Ask the following question: If the data is requested 78 times and it is found in the cache 56 times, and for all the other times it has to be loaded from the main memory. What is the cache miss ratio? Ans: The miss ratio is 78-56/78 = 0.28 Ask students the reason for data that the processor requested to be at the nearest