Abstract: A system and method for determining where bottlenecks in a program's data accesses occur and providing information to a software developer as to why the bottlenecks occur and what may be done to correct them. A stream of data access references is analyzed to determine data access patterns (also called data access sequences). The stream is analyzed to find frequently repeated data access sequences (called hot data streams). Properties of the hot data streams are calculated and upon selection of a hot data stream are displayed in a development tool that associates lines of code with the hot data streams.

Abstract: A memory footprint interface visibly displays one or more memory footprints of an application program during a selected time interval. In one implementation, the memory footprint interface receives one or more application program address traces, which include data regarding minimum and maximum memory addresses that are being accessed during execution of the program in the selected time interval. The memory footprint interface can animate playback of memory address reference with various timed fadeout, so as to indicate memory reuse or working set size. The memory footprint interface can also then provide a number of visible indicia for the corresponding memory access patterns over the particular time interval. The visible indicia can be used to color code a wide range of data items displayed through the memory footprint interface, so as to differentiate such things as read and/or write access requests, frequency, threads, and so forth.

Abstract: A system and method for analyzing data accesses to determine data access patterns. Data address accesses are traced and transformed into Whole Program Streams (WPS). WPS may then be used to discover higher-level data abstractions, such as hot data streams and data flow graphs. Hot data streams provide information related to sequences of data addresses that are repeatedly accessed together. Data flow graphs indicate how hot data streams are related and include frequencies of each hot data stream following another. Hot data streams and data flow graphs may be used with pre-fetching and/or cache managers to improve program performance.

Abstract: A system and method for determining where bottlenecks in a program's data accesses occur and providing information to a software developer as to why the bottlenecks occur and what may be done to correct them. A stream of data access references is analyzed to determine data access patterns (also called data access sequences). The stream is analyzed to find frequently repeated data access sequences (called hot data streams). Properties of the hot data streams are calculated and upon selection of a hot data stream are displayed in a development tool that associates lines of code with the hot data streams.

Abstract: Fields which are individually addressable data elements in data structures are reordered to improve the efficiency of cache line access. Temporal data regarding the referencing of such fields is obtained, and a tool is used to construct a field affinity graph of temporal access affinities between the fields. Nodes in the graph represent fields, and edges between the nodes are weighted to indicate field affinity. A first pass greedy algorithm attempts to combine high affinity fields in the same cache line or block. Constraints are used to reject invalid combinations of fields. The constraints may be provided by program analysis, programmer, or actual dynamically generated.

Abstract: Fields which are individually addressable data elements in data structures are reordered to improve the efficiency of cache line access. Temporal data regarding the referencing of such fields is obtained, and a tool is used to construct a field affinity graph of temporal access affinities between the fields. Nodes in the graph represent fields, and edges between the nodes are weighted to indicate field affinity. A first pass greedy algorithm attempts to combine high affinity fields in the same cache line or block. Constraints are used to reject invalid combinations of fields. Data structures such as class are partitioned into heavily referenced and less heavily referenced portions. The partitioning is based on profile information about field access counts with indirect addressing used to reference the less heavily referenced partitioned class. A class co-location scheme is used to ensure that temporally correlated classes are placed near each other in cache blocks.

Abstract: Fields which are individually addressable data elements in data structures are reordered to improve the efficiency of cache line access. Temporal data regarding the referencing of such fields is obtained, and a tool is used to construct a field affinity graph of temporal access affinities between the fields. Nodes in the graph represent fields, and edges between the nodes are weighted to indicate field affinity. A first pass greedy algorithm attempts to combine high affinity fields in the same cache line or block. Constraints are used to reject invalid combinations of fields. Data structures such as class are partitioned into heavily referenced and less heavily referenced portions. The partitioning is based on profile information about field access counts with indirect addressing used to reference the less heavily referenced partitioned class. A class co-location scheme is used to ensure that temporally correlated classes are placed near each other in cache blocks.