# HG changeset patch
# User Merten Sach <msach@mailbox.tu-berlin.de>
# Date 1308227868 -7200
# Node ID 16a32ca59bef02f35f23137cbc326a8a71fcee3d
# Parent  4007d97740a5d58cbd582c8f026cc65153ca8e18
free before use & made hardware independent

diff -r 4007d97740a5 -r 16a32ca59bef src/Application/VPThread__Matrix_Mult/Divide_Pr.c
--- a/src/Application/VPThread__Matrix_Mult/Divide_Pr.c	Thu Jun 02 14:43:18 2011 +0200
+++ b/src/Application/VPThread__Matrix_Mult/Divide_Pr.c	Thu Jun 16 14:37:48 2011 +0200
@@ -10,6 +10,7 @@
 #include "VPThread__Matrix_Mult.h"
 #include <math.h>
 #include <string.h>
+#include "../../VPThread_lib/VPThread.h"
 
    //The time to compute this many result values should equal the time to
    // perform this division on a matrix of size gives that many result calcs
@@ -118,8 +119,7 @@
  { VirtProcr       *resultPr;
    DividerParams   *dividerParams;
    ResultsParams   *resultsParams;
-   Matrix          *leftMatrix, *rightMatrix, *resultMatrix;
-   void            *msg;
+   Matrix          *leftMatrix, *rightMatrix;
    SlicingStrucCarrier *slicingStrucCarrier;
    float32             *resultArray; //points to array inside result matrix
    MatrixMultGlobals   *globals;
@@ -162,8 +162,9 @@
          //transpose the right matrix
       float32 *
       transRightArray  = 
-         VPThread__malloc( rightMatrix->numRows * rightMatrix->numCols *
-                           sizeof(float32), animatingThd );
+         VPThread__malloc( (size_t)rightMatrix->numRows * 
+                                (size_t)rightMatrix->numCols *
+                                sizeof(float32), animatingThd );
 
          //copy values from orig matrix to local
       copyTranspose( rightMatrix->numRows, rightMatrix->numCols,
@@ -289,7 +290,7 @@
       (float64)minWorkUnitCycles / (float64)primitiveCycles;
 
       //take cubed root -- that's number of these in a "side" of sub-matrix
-      // then multiply by 5 because the primitive is 5x5
+      // then multiply by 5 because the primitive is 5x5src/Application/VPThread__Matrix_Mult/Divide_Pr.c:403: warning: implicit declaration of function ‘VPThread__give_number_of_cores_to_schedule_onto’
    idealSizeOfSide1 = 5 * cbrt( numPrimitiveOpsInMinWorkUnit );
 
    idealNumWorkUnits = VPThread__giveIdealNumWorkUnits();
@@ -357,9 +358,6 @@
       createSubMatrices( vecSlices, rightColSlices, leftRowSlices->numVals,
                          rightMatrix, animPr );
 
-   freeSlicingStruc( leftRowSlices, animPr );
-   freeSlicingStruc( vecSlices, animPr );
-   freeSlicingStruc( rightColSlices, animPr );
 
    //==============  pair the sub-matrices and make processors ==============
    int32 numRowIdxs, numColIdxs, numVecIdxs;
@@ -367,6 +365,11 @@
    numRowIdxs = leftRowSlices->numVals;
    numColIdxs = rightColSlices->numVals;
    numVecIdxs = vecSlices->numVals;
+   
+   freeSlicingStruc( leftRowSlices, animPr );
+   freeSlicingStruc( vecSlices, animPr );
+   freeSlicingStruc( rightColSlices, animPr );
+   
    pairUpSubMatricesAndMakeProcessors( leftSubMatrices,
                                        rightSubMatrices,
                                        numRowIdxs, numColIdxs,
@@ -454,7 +457,7 @@
              { coreToScheduleOnto += 1;
              }
           }
- 
+
        }
     }
  }
@@ -479,8 +482,8 @@
    rowStartVals = rowSlices->startVals;
    colStartVals = colSlices->startVals;
 
-   subMatrices = VPThread__malloc(numRowIdxs * numColIdxs * sizeof(SubMatrix*),
-                                 animPr );
+   subMatrices = VPThread__malloc((size_t)numRowIdxs *
+                            (size_t)numColIdxs * sizeof(SubMatrix*),animPr );
 
    for( rowIdx = 0; rowIdx < numRowIdxs; rowIdx++ )
     {
@@ -550,7 +553,7 @@
       //calc size of matrix need to hold start vals --
    numSlices = (int32)( (float32)(endVal -startVal +1) / idealSizeOfSide);
 
-   startVals = VPThread__malloc( (numSlices + 1) * sizeof(int32), animPr );
+   startVals = VPThread__malloc( ((size_t)numSlices + 1) * sizeof(int32), animPr );
 
       //Calc the upper limit of start value -- when get above this, end loop
       // by saving highest value of the matrix dimension to access, plus 1
diff -r 4007d97740a5 -r 16a32ca59bef src/Application/VPThread__Matrix_Mult/subMatrix_Pr.c
--- a/src/Application/VPThread__Matrix_Mult/subMatrix_Pr.c	Thu Jun 02 14:43:18 2011 +0200
+++ b/src/Application/VPThread__Matrix_Mult/subMatrix_Pr.c	Thu Jun 16 14:37:48 2011 +0200
@@ -73,8 +73,8 @@
    leftArray      = leftSubMatrix->array;
    rightArray     = rightSubMatrix->array;
 
-   int32
-   resSize = leftSubMatrix->numRows * rightSubMatrix->numCols * sizeof(float32);
+   size_t resSize = (size_t)leftSubMatrix->numRows * 
+                        (size_t)rightSubMatrix->numCols * sizeof(float32);
    resArray = VPThread__malloc( resSize, animatingPr );
    memset( resArray, 0, resSize );
 
@@ -234,7 +234,7 @@
 
 void inline
 copyTransposeFromOrig( SubMatrix *subMatrix, VirtProcr *animPr )
- { int numCols, numRows, origStartRow, origStartCol, origStride, stride;
+ { int numCols, numRows, origStartRow, origStartCol, origStride;
    Matrix *origMatrix;
    float32 *origArray, *subArray;
 
@@ -248,7 +248,8 @@
    origStartCol = subMatrix->origStartCol;
    origStride   = origMatrix->numCols;
 
-   subArray    = VPThread__malloc( numRows * numCols *sizeof(float32),animPr);
+   subArray    = VPThread__malloc( (size_t)numRows * 
+                                        (size_t)numCols *sizeof(float32),animPr);
    subMatrix->array = subArray;
 
       //copy values from orig matrix to local
@@ -285,7 +286,8 @@
    origStartCol  = subMatrix->origStartCol;
    origStride    = origMatrix->numCols;
 
-   subArray    = VPThread__malloc( numRows * numCols *sizeof(float32),animPr);
+   subArray    = VPThread__malloc( (size_t)numRows * 
+                                        (size_t)numCols *sizeof(float32),animPr);
    subMatrix->array = subArray;
 
       //copy values from orig matrix to local