public void Execute(int colB)
{
unsafe
{
int sz = bs * bs * 4;
; float *blockA = (float *)UnsafeUtility.Malloc(sz, 4, Allocator.TempJob);
float * blockB = (float *)UnsafeUtility.Malloc(sz, 4, Allocator.TempJob);
float * blockC = (float *)UnsafeUtility.Malloc(sz, 4, Allocator.TempJob);
for (int rowA = 0; rowA < AN; rowA += bs)
{
//for (int colB = 0; colB < BM; colB += bs)
{
for (int l = 0; l < AM; l += bs)
{
MatrixUtils.CopyBlockWithPadding(A, rowA, AN, l, AM, blockA, bs, transposeA);
MatrixUtils.CopyBlockWithPadding(B, l, BN, colB * bs, BM, blockB, bs, transposeB);
MatrixUtils.CopyBlockWithPadding(C, rowA, CN, colB * bs, CM, blockC, bs);
MatrixUtils.MultiplyBlockUnroll8xhPadded(blockA, blockB, blockC, bs);
MatrixUtils.CopyBlockWithPadding(blockC, C, rowA, CN, colB * bs, CM, bs);
}
}
}
UnsafeUtility.Free(blockA, Allocator.TempJob);
UnsafeUtility.Free(blockB, Allocator.TempJob);
UnsafeUtility.Free(blockC, Allocator.TempJob);
}
}
private unsafe void ExecutOverRowA(float *blockA, float *blockB, float *blockC, int rowA)
{
//for (int rowA = 0; rowA < AN; rowA += bs)
{
for (int colB = 0; colB < BM; colB += bs)
{
for (int l = 0; l < AM; l += bs)
{
MatrixUtils.CopyBlockWithPadding(A, rowA, AN, l, AM, blockA, bs, transposeA);
MatrixUtils.CopyBlockWithPadding(B, l, BN, colB, BM, blockB, bs, transposeB);
MatrixUtils.CopyBlockWithPadding(C, rowA, CN, colB, CM, blockC, bs);
MatrixUtils.MultiplyBlockUnroll8xhPadded(blockA, blockB, blockC, bs);
MatrixUtils.CopyBlockWithPadding(blockC, C, rowA, CN, colB, CM, bs);
}
}
}
}