Sharing idled processor execution resources

Abstract

A processor including a plurality of logical processors, and an instruction set, the instruction set including of one or more instructions which when executed by a first logical processor, cause the first logical processor to make a processor execution resource previously reserved for the first processor available to a second processor in the plurality of processors in response to the first logical processor being scheduled to enter an idle state.

1 . (canceled) 
     
     
         2 . A method comprising:
 detecting a page fault;   switching out from executing a thread due to the detection of the page fault; and   releasing any resources held by the executing thread.   
     
     
         3 . The method of  claim 1  including idling the processor executing the thread. 
     
     
         4 . The method of  claim 2  including determining that the processor is no longer idle and reacquiring the resource. 
     
     
         5 . The method of  claim 3  including continuing to execute the thread using the reacquired resource. 
     
     
         6 . The method of  claim 1  including checking to determine whether anymore tasks are scheduled for the processor executing the thread before switching out from the executing thread. 
     
     
         7 . The method of  claim 6  including checking only once before switching out from the executing thread. 
     
     
         8 . One or more non-transitory computer readable media storing instructions executed to perform a sequence comprising:
 detecting a page fault;   switching out from executing a thread due to the detection of the page fault; and   releasing any resources held by the executing thread.   
     
     
         9 . The media of  claim 8 , said sequence including idling the processor executing the thread. 
     
     
         10 . The media of  claim 9 , said sequence including determining that the processor is no longer idle and reacquiring the resource. 
     
     
         11 . The media of  claim 10 , said sequence including continuing to execute the thread using the reacquired resource. 
     
     
         12 . The media of  claim 8 , said sequence including checking to determine whether anymore tasks are scheduled for the processor executing the thread before switching out from the executing thread. 
     
     
         13 . The media of  claim 12 , said sequence including checking only once before switching out from the executing thread. 
     
     
         14 . An apparatus comprising:
 a processor to detect a page fault, switch out from executing a thread due to the detection of the page fault, and release any resources held by the executing thread; and   a storage coupled to said processor.   
     
     
         15 . The apparatus of  claim 14 , said processor to idle. 
     
     
         16 . The apparatus of  claim 15 , said processor to determine that the processor is no longer idle and reacquiring the resource. 
     
     
         17 . The apparatus of  claim 16 , said processor to continue to execute the thread using the reacquired resource. 
     
     
         18 . The apparatus of  claim 14 , said processor to check to determine whether anymore tasks are scheduled for the processor executing the thread before switching out from the executing thread. 
     
     
         19 . The apparatus of  claim 18 , said processor to check only once before switching out from the executing thread.