6.1.7 vsip_dgems_p - General Matrix Scaling and Addition

typedef enum _vsip_mat_op { 
  VSIP_MAT_NTRANS = 0, // op(A) = A 
  VSIP_MAT_TRANS  = 1, // op(A) = A^T 
  VSIP_MAT_HERM   = 2, // op(A) = A^H (complex only) 
  VSIP_MAT_CONJ   = 3  // op(X) = A^* (complex only) 
} vsip_mat_op; 
 
void vsip_gems_f(vsip_scalar_f alpha, const vsip_mview_f *a, vsip_mat_op OpA, vsip_scalar_f beta, const vsip_mview_f *r); 
void vsip_cgems_f(vsip_cscalar_f alpha, const vsip_cmview_f *a, vsip_mat_op OpA, vsip_cscalar_f beta, const vsip_cmview_f *r);

Description

This function performs a generalized matrix scaling and addition operation of the form:

where can be , , or .

Parameters

• vsip_dscalar_p alpha: Scalar multiplier for matrix .

• const vsip_dmview_p* a: Input matrix.

• vsip_mat_op OpA: Operation to perform on matrix .

  • VSIP_MAT_NTRANS: Use as is

  • VSIP_MAT_TRANS: Use the transpose of,

  • VSIP_MAT_HERM: Use the conjugate transpose of

  • VSIP_MAT_CONJ: Use the conjugate of

• vsip_dscalar_p beta: Scalar multiplier for matrix .

• const vsip_dmview_p* r: Input/output matrix that contains the initial values and will store the result.

Example

vsip_mview_f *A, *R; 
vsip_length m = 3, n = 3; 
 
// Create matrices 
A = vsip_mcreate_f(m, n, VSIP_ROW, VSIP_MEM_NONE); 
R = vsip_mcreate_f(m, n, VSIP_ROW, VSIP_MEM_NONE); 
 
// Initialize matrices with some values 
 
// Basic scaling: R = 2.0 * A 
vsip_gems_f(2.0f, A, VSIP_MAT_NTRANS, 0.0f, R); 
 
// Scale and add: R = 1.5*A + R 
vsip_gems_f(1.5f, A, VSIP_MAT_NTRANS, 1.0f, R); 
 
// Transpose operation: R = A^T 
vsip_gems_f(1.0f, A, VSIP_MAT_TRANS, 0.0f, R); 
 
// Linear combination: R = 0.5*A + 0.5*R 
vsip_gems_f(0.5f, A, VSIP_MAT_NTRANS, 0.5f, R); 
 
// Overwrite with scaled transpose: R = 3.0*A^T 
vsip_gems_f(3.0f, A, VSIP_MAT_TRANS, 0.0f, R); 
 
// Clean up 
vsip_malldestroy_f(A); 
vsip_malldestroy_f(R);

Notes

• The dimensions of matrices and must be compatible with the operation:

  • If OpA = VSIP_MAT_NTRANS, rows of must match rows of .

  • If OpA = VSIP_MAT_TRANS or VSIP_MAT_HERM, columns of must match rows of .

• This function performs the operation in-place on matrix .

• Setting results in being overwritten with the scaled matrix.

• Setting results in the scaled matrix being added to .