Converting trace data from processors executing in parallel into graphical form

Claim 2

A computer implemented method for converting trace data into graphical form, said trace data being obtained from concurrently executing virtual processors, comprising the steps of: (a) reformatting said trace data into a linked list of successive events evoking parallel activity for at least a first parallel task, said list including at least one link; and (b) selectively traversing said at least one link of said list and causing time process display of processor utilization and any executing hierarchy of parallel activity constructs formed from at least one parallel thread hierarchy of a parallel program, at least one parallel task, and at least one parallel thread (FIG. 3), said time process display being in synchronism with said traversal.

Claim 3

A computer implemented method for converting trace data into graphical form, said trace data being generated by operating system dispatchers representing at least one concurrent execution of tasks of a application upon one or more virtual processors, comprising the steps of: (a) forming a table (FIG.4/33,35; 5(a)/31') from the trace data (FIG.4/31; 5(a)/31') identifying and cross-linking a virtual processor, task ID, parallel activity, and one or more parallel activity metrics for each trace data event, said table having constitutive parts thereof termed "elements", correspondences among table elements being termed "cross links"; and (b) graphically mapping the table elements onto a display (1) as indexed by processor and activity cross links for processor utilization (FIG.7/67-14 93; FIG.8) and (2) as indexed by task and activity cross links for a executing hierarchy of parallel tasks (FIG.7/99-119;FIG.9).

Claim 4

A computer implemented method for converting trace data into graphical form, said trace data being generated by operating system dispatchers representing at least one concurrent execution of tasks of a application upon one or more virtual processors, comprising the steps of: (a) forming a table (FIG.4/33,35; 5(a)/31') from the trace data (FIG.4/31; 5(a)/31') identifying and cross-linking a virtual processor, task ID, parallel activity, and one or more parallel activity metrics for each trace data event, said table having constitutive parts thereof termed "elements", correspondences among table elements being termed "cross links"; and (b) graphically mapping the table elements onto a display (1) as indexed by processor and activity cross links for processor utilization (FIG.7/67-14 93; FIG.8) and (2) as indexed by task and activity cross links for a executing hierarchy of parallel tasks (FIG.7/99-119;FIG.9).

Claim 5

The method according to claim 2, wherein steps (a) and (b) respectively include the steps of (a1) deriving a concordance (FIG. 4-35) of task ID and parallel activities as sorted on the task ID; and (b1) accessing the table by way of the concordance in the mapping table elements onto the display (FIG. 9) of executing the hierarchy of parallel tasks.

Claim 6

The method according to claim 2, wherein the step of graphically mapping the table elements onto a display includes invoking a graphics data display manager (GDDM) and causing the coloring of the display by said GDDM as indexed by selected processor, task ID, and activity.

Claim 7

The method according to claim 2, wherein the display includes a time process diagram depicting virtual processor utilization, said mapping step including processing said table once for each virtual processor ID, each time process diagram being susceptible to a zoom, forward, and backward view expressed as a time range or interval, and said mapping step further including the steps of: (1) expressing parallel activity in the form of primary and secondary threads, each thread having a beginning and an ending time, (2) comparing the beginning and end times for each primary thread to the time range of a selected view (Tmin, Tmax), and (3) selectively adjusting the view to conform the thread activity to the diagram time range to enhance visibility.

Claim 8

A computer implemented method for processing and displaying information about a parallel execution of an application program (FIG.2/21-23) across N virtual processors (FIG.2/15-19) as derived from trace records (FIG.4/31; 5(a)/31'), said trace records being generated by dispatching functions embedded in either the application program or operating system, comprising the steps of: (a) ascertaining and identifying parallel activity by scanning the trace records generated by said processors (typical events include FORK, scheduled tasks, and the like); (b) creating and populating a table (FIG.4/33,35; 5(b)-(c)/33') of time sequence events, said table having constitutive parts thereof termed "elements", said table being formed by any parallel activity identified in step (a), computing average concurrency, and cross-linking the elements of the table (FIG.4/34; 5(b)-(c)/34'); and (c) extracting data from the table as indexed by a selected sub-set of cross links (activity number and pointer) and graphically mapping data extracted from the table onto a visually perceptible medium.

Claim 9

A computer implemented method for processing and displaying information about a parallel execution of an application program (FIG.2/21-23) across N virtual processors (FIG.2/15-19) as derived from trace records (FIG.4/31; 5(a)/31'), said trace records being generated by dispatching functions embedded in either the application program or operating system, comprising the steps of: (a) ascertaining and identifying parallel activity by scanning the trace records generated by said processors (typical events include FORK, scheduled tasks, and the like); (b) creating and populating a table (FIG.4/33,35; 5(b)-(c)/33') of time sequence events, said table having constitutive parts thereof termed "elements", said table being formed by any parallel activity identified in step (a), computing average concurrency, and cross-linking the elements of the table (FIG.4/34; 5(b)-(c)/34'); and (c) extracting data from the table as indexed by a selected sub-set of cross links (activity number and pointer) and graphically mapping data extracted from the table onto a visually perceptible medium.