Ex Parte BITAR et al - Page 11




          Appeal No. 2002-0792                                                        
          Application 08/801,646                                                      


               shared arena requesting that one or more processors from the           
               plurality of processors be assigned to process the plurality           
               of threads from the first program;                                     
                    setting, via the first kernel level scheduler, a number           
               allocated variable within the first shared arena indicating            
               the number of first processors that are assigned to process            
               the plurality of threads from the first program;                       
                    assigning one or more threads of the plurality of                 
               threads from the first program to each of the assigned first           
               processors, wherein the step of assigning includes the step            
               of reading register context from one of the plurality of               
               register save areas within the first shared arena;                     
                    adding to the number allocated variable within the                
               first shared arena a number indicating the number of second            
               processors that are assigned to process the plurality of               
               threads from the first program;                                        
                    assigning one or more threads of the plurality of                 
               threads from the first program to each of the assigned                 
               second processors, wherein the step of assigning includes              
               the step of reading register context from one of the                   
               plurality of register save areas within the first shared               
               arena;                                                                 
                    setting a number requested variable within the second             
               shared arena requesting that one or more processors from the           
               plurality of processors be assigned to process the plurality           
               of threads from the second program;                                    
                    setting, via the first kernel level scheduler, a number           
               allocated variable within the second shared arena indicating           
               the number of first processors that are assigned to process            
               the plurality of threads from the second program; and                  
                    assigning one or more threads of the plurality of                 
               threads from the second program to each of the assigned                
               first processors, wherein the step of assigning includes the           
               step of reading register context from one of the plurality             
               of register save areas within the second shared arena.                 

                                          11                                          





Page:  Previous  1  2  3  4  5  6  7  8  9  10  11  12  13  Next 

Last modified: November 3, 2007