changeset 30:0d7177551bff perf_tuning_paper lots of cores version

optimization for large number of cores: dedicate core 0 to create/receive
author Nina Engelhardt <nengel@mailbox.tu-berlin.de>
date Wed, 18 Apr 2012 15:50:14 +0200
parents c35cb1f48f89
children 3477d7443620
files SSR_Matrix_Mult/Divide_Pr.c
diffstat 1 files changed, 2 insertions(+), 2 deletions(-) [+]
line diff
     1.1 --- a/SSR_Matrix_Mult/Divide_Pr.c	Tue Apr 17 20:13:26 2012 +0200
     1.2 +++ b/SSR_Matrix_Mult/Divide_Pr.c	Wed Apr 18 15:50:14 2012 +0200
     1.3 @@ -261,7 +261,7 @@
     1.4     idealNumWorkUnits = SSR__giveIdealNumWorkUnits();
     1.5     
     1.6     idealSizeOfSide2 = leftMatrix->numRows / rint(cbrt( idealNumWorkUnits ));
     1.7 -   idealSizeOfSide2 *= 0.5; //finer granularity to help load balance
     1.8 +   idealSizeOfSide2 *= 0.6; //finer granularity to help load balance
     1.9  
    1.10     if( idealSizeOfSide1 > idealSizeOfSide2 )
    1.11        idealSizeOfSide = idealSizeOfSide1;
    1.12 @@ -412,7 +412,7 @@
    1.13  
    1.14                    //Move to next core, max core-value to incr to is numCores -1
    1.15                 coreToAssignOnto += 1;
    1.16 -               if( coreToAssignOnto >= numCores ) coreToAssignOnto = 0;
    1.17 +               if( coreToAssignOnto >= numCores ) coreToAssignOnto = 1;
    1.18               } //if
    1.19            } //for( vecIdx
    1.20         } //for( resColIdx