Our Approach<\/strong><\/p>\n We formulate our problem using Global Call Control Flow Graph (GCCFG)<\/strong>, which captures both aggregate and temporal information about the function callls.<\/p>\n In the graph above, we show how to formulate the GCCFG from the code. In the GCCFG, there is strict ordering among the nodes, i.e. left child is called before the right child. L-node means loop node and I-node means conditional node.The node weights indicate execution count of functions, e.g. 100 for node F6 means the L2 loop will execute 100 times. In addition, GCCFG will also indetify the recursive functions.<\/p>\n We also proposed a cost model, interfenrence cost graph, to evaluate the performance based on the GCCFG of that application. Finally, two heuristics are proposed – FMUM<\/strong> Heuristic and FMUP<\/strong> Heuristic.<\/p>\n FMUM<\/strong> Heuristic: Start from non-overlap code regions and unify different regions to decrese the total size of the code region until it meets the requirement.<\/p>\n FMUP<\/strong> Heuristic: Start from a unified code region and partition it into different regions until it meets the restriction of the total size of the code region.<\/p>\n The details can be found in the paper “Dynamic Code Mapping for Limited Local Memory Systems<\/a>“.<\/p>\n Publications<\/strong><\/p>\n![\"\"](\"http:\/\/www.public.asu.edu\/%7Ekbai3\/figures\/gccfg.png\")
<\/p>\n
![\"pdf\"](\"http:\/\/www.public.asu.edu\/%7Ekbai3\/figures\/pdf.png\")
<\/a><\/td>\n![\"\"](\"http:\/\/www.public.asu.edu\/%7Ekbai3\/figures\/ppt.png\")
<\/a><\/td>\n![\"\"](\"http:\/\/www.public.asu.edu\/%7Ekbai3\/figures\/rar.png\")
<\/a><\/td>\n