Ex Parte Walterscheidt et al - Page 6


                 Appeal No.  2006-0537                                                     Page 6                   
                 Application No.  09/753,766                                                                        


                       latency event, since it requires numerous cycles to resolve, and it is                       
                       ‘one of the more serious impediments to realizing even higher                                
                       processor performance (Bondi column 1, lines 62-64).’  Parady has                            
                       taught that a thread switch occurs on a long latency event (see                              
                       above) and multi-threading reduces the impact of long latency                                
                       events (Parady column 1, lines 58-59).  A person of ordinary skill in                        
                       the art would have recognized that a branch mispredict is a type of                          
                       long latency event and reducing the performance penalty due to the                           
                       misprediction would increase processor performance.  Therefore, it                           
                       would have been obvious to modify Parady to switch threads on a                              
                       branch misprediction in order to reduce the performance penalty                              
                       suffered by the misprediction.  The test of obviousness is not what                          
                       has been taught explicitly by each reference, as suggested by                                
                       Applicant’s arguments, but what the two references suggest to a                              
                       person of ordinary skill in the art at the time the invention was made                       
                       (In re Bozek, 163 USPQ 545 (CCPA 1969) ‘The test for                                         
                       obviousness is not whether the features of one reference may be                              
                       bodily incorporated into the other to produce the claimed subject                            
                       matter by simply what the combination of references makes                                    
                       obvious to one of ordinary skill in the pertinent art.’; In re Van                           
                       Beckum, 169 USPQ 47 (CCPA 1971) ‘We would note that it is well                               
                       settled that the test of obviousness is not whether the features of                          
                       one reference can be bodily incorporated in to the structure of                              
                       another and proper inquiry should not be limited to the specific                             
                       structure shown by the references, but should be into the concepts                           
                       fairly contained therein, and the overriding question to be                                  
                       determined is whether those concepts would suggest to one skilled                            
                       in the art the modifications called for by the claims.’, In re Sheckler,                     
                       168 USPQ 716 (CCPA 1971) ‘…It is, of course, not necessary that                              
                       either Barnes or Dryden actually suggest, expressly or in so many                            
                       words, the changes or possible improvements appellant has                                    
                       made’).                                                                                      
                       As noted by the examiner, the teaching at column 4, lines 6 through 8 of                     
                 Parady indicates that his invention “could be added to other potentially long-                     
                 latency operations, such as jump instructions.”  These jump instructions are                       











Page:  Previous  1  2  3  4  5  6  7  8  9  Next 

Last modified: November 3, 2007