// result = this*other
public DMatrix mmul(boolean tA, boolean tB, DMatrix B, DMatrix C) {
int m = tA ? this.columns() : this.rows();
int n = tB ? B.rows() : B.columns();
int k = tA ? this.rows() : this.columns();
int kB = tB ? B.columns() : B.rows();
assert (k == kB);
if (C.rows != m || C.columns != n) {
if (C != this && C != B) {
C.resize(m, n);
} else {
System.err.printf(
"[ALERT] Should not resize result matrix because it is used in-place. But doing it anyway.\n");
}
}
if (C == this || C == B) {
/* actually, blas cannot do multiplications in-place. Therefore, we will fake by
* * allocating a temporary object on the side and copy the result later.
* */
DMatrix temp = new CUDAMatrix(m, n);
if (m == 1) {
SimpleCuBlas.gemv(tB, B, this, temp, 1.0, 0.0);
} else {
SimpleCuBlas.gemm(tA, tB, this, B, temp, 1.0, 0.0);
}
if (temp.rows() == C.rows() && temp.columns() == C.columns()) SimpleCuBlas.copy(temp, C);
else {
C.resize(m, n);
SimpleCuBlas.copy(temp, C);
}
} else {
if (m == 1) {
SimpleCuBlas.gemv(tB, B, this, C, 1.0, 0.0);
} else {
SimpleCuBlas.gemm(tA, tB, this, B, C, 1.0, 0.0);
}
}
return C;
}
public DMatrix dotRows(DMatrix B) {
assert (this.rows() == B.rows() && this.columns() == B.columns());
return this.mul(B).sumColumns();
}
public DMatrix mulRowsi(DMatrix colVector) {
assert (this.rows() == colVector.rows() && colVector.columns() == 1);
SimpleCuBlas.mulRows(colVector, this);
return this;
}
public DMatrix mulRows(DMatrix colVector) {
assert (this.rows() == colVector.rows() && colVector.columns() == 1);
DMatrix m = new CUDAMatrix(this.rows(), this.columns(), this.toArray());
SimpleCuBlas.mulRows(colVector, m);
return m;
}
public DMatrix mmuli(DMatrix B) {
assert (this.columns() == B.rows());
return mmul(false, false, B, this);
}
