BeBOP Optimized Sparse Kernel Interface Library File List

Here is a list of all documented files with brief descriptions:
GCSR/MatMult/1x1.cThe $1\times 1$ GCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatMult/1x1.cMBCSR 1x1 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/1x1.cThe $1\times 1$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/1x1.cThe $1\times 1$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/1x1.cThe $1\times 1$ MBCSR implementation of sparse triangular solve
GCSR/MatMult/1x2.cThe $1\times 2$ GCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatMult/1x2.cMBCSR 1x2 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/1x2.cThe $1\times 2$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/1x2.cThe $1\times 2$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/1x2.cThe $1\times 2$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/1x3.cMBCSR 1x3 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/1x3.cThe $1\times 3$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/1x3.cThe $1\times 3$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/1x3.cThe $1\times 3$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/1x4.cMBCSR 1x4 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/1x4.cThe $1\times 4$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/1x4.cThe $1\times 4$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/1x4.cThe $1\times 4$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/1x5.cMBCSR 1x5 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/1x5.cThe $1\times 5$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/1x5.cThe $1\times 5$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/1x5.cThe $1\times 5$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/1x6.cMBCSR 1x6 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/1x6.cThe $1\times 6$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/1x6.cThe $1\times 6$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/1x6.cThe $1\times 6$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/1x7.cMBCSR 1x7 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/1x7.cThe $1\times 7$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/1x7.cThe $1\times 7$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/1x7.cThe $1\times 7$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/1x8.cMBCSR 1x8 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/1x8.cThe $1\times 8$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/1x8.cThe $1\times 8$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/1x8.cThe $1\times 8$ MBCSR implementation of sparse triangular solve
GCSR/MatMult/2x1.cThe $2\times 1$ GCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatMult/2x1.cMBCSR 2x1 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/2x1.cThe $2\times 1$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/2x1.cThe $2\times 1$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/2x1.cThe $2\times 1$ MBCSR implementation of sparse triangular solve
GCSR/MatMult/2x2.cThe $2\times 2$ GCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatMult/2x2.cMBCSR 2x2 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/2x2.cThe $2\times 2$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/2x2.cThe $2\times 2$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/2x2.cThe $2\times 2$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/2x3.cMBCSR 2x3 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/2x3.cThe $2\times 3$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/2x3.cThe $2\times 3$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/2x3.cThe $2\times 3$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/2x4.cMBCSR 2x4 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/2x4.cThe $2\times 4$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/2x4.cThe $2\times 4$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/2x4.cThe $2\times 4$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/2x5.cMBCSR 2x5 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/2x5.cThe $2\times 5$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/2x5.cThe $2\times 5$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/2x5.cThe $2\times 5$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/2x6.cMBCSR 2x6 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/2x6.cThe $2\times 6$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/2x6.cThe $2\times 6$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/2x6.cThe $2\times 6$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/2x7.cMBCSR 2x7 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/2x7.cThe $2\times 7$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/2x7.cThe $2\times 7$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/2x7.cThe $2\times 7$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/2x8.cMBCSR 2x8 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/2x8.cThe $2\times 8$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/2x8.cThe $2\times 8$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/2x8.cThe $2\times 8$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/3x1.cMBCSR 3x1 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/3x1.cThe $3\times 1$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/3x1.cThe $3\times 1$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/3x1.cThe $3\times 1$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/3x2.cMBCSR 3x2 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/3x2.cThe $3\times 2$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/3x2.cThe $3\times 2$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/3x2.cThe $3\times 2$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/3x3.cMBCSR 3x3 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/3x3.cThe $3\times 3$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/3x3.cThe $3\times 3$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/3x3.cThe $3\times 3$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/3x4.cMBCSR 3x4 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/3x4.cThe $3\times 4$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/3x4.cThe $3\times 4$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/3x4.cThe $3\times 4$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/3x5.cMBCSR 3x5 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/3x5.cThe $3\times 5$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/3x5.cThe $3\times 5$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/3x5.cThe $3\times 5$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/3x6.cMBCSR 3x6 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/3x6.cThe $3\times 6$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/3x6.cThe $3\times 6$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/3x6.cThe $3\times 6$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/3x7.cMBCSR 3x7 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/3x7.cThe $3\times 7$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/3x7.cThe $3\times 7$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/3x7.cThe $3\times 7$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/3x8.cMBCSR 3x8 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/3x8.cThe $3\times 8$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/3x8.cThe $3\times 8$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/3x8.cThe $3\times 8$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/4x1.cMBCSR 4x1 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/4x1.cThe $4\times 1$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/4x1.cThe $4\times 1$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/4x1.cThe $4\times 1$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/4x2.cMBCSR 4x2 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/4x2.cThe $4\times 2$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/4x2.cThe $4\times 2$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/4x2.cThe $4\times 2$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/4x3.cMBCSR 4x3 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/4x3.cThe $4\times 3$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/4x3.cThe $4\times 3$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/4x3.cThe $4\times 3$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/4x4.cMBCSR 4x4 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/4x4.cThe $4\times 4$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/4x4.cThe $4\times 4$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/4x4.cThe $4\times 4$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/4x5.cMBCSR 4x5 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/4x5.cThe $4\times 5$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/4x5.cThe $4\times 5$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/4x5.cThe $4\times 5$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/4x6.cMBCSR 4x6 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/4x6.cThe $4\times 6$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/4x6.cThe $4\times 6$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/4x6.cThe $4\times 6$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/4x7.cMBCSR 4x7 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/4x7.cThe $4\times 7$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/4x7.cThe $4\times 7$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/4x7.cThe $4\times 7$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/4x8.cMBCSR 4x8 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/4x8.cThe $4\times 8$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/4x8.cThe $4\times 8$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/4x8.cThe $4\times 8$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/5x1.cMBCSR 5x1 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/5x1.cThe $5\times 1$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/5x1.cThe $5\times 1$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/5x1.cThe $5\times 1$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/5x2.cMBCSR 5x2 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/5x2.cThe $5\times 2$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/5x2.cThe $5\times 2$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/5x2.cThe $5\times 2$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/5x3.cMBCSR 5x3 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/5x3.cThe $5\times 3$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/5x3.cThe $5\times 3$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/5x3.cThe $5\times 3$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/5x4.cMBCSR 5x4 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/5x4.cThe $5\times 4$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/5x4.cThe $5\times 4$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/5x4.cThe $5\times 4$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/5x5.cMBCSR 5x5 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/5x5.cThe $5\times 5$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/5x5.cThe $5\times 5$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/5x5.cThe $5\times 5$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/5x6.cMBCSR 5x6 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/5x6.cThe $5\times 6$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/5x6.cThe $5\times 6$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/5x6.cThe $5\times 6$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/5x7.cMBCSR 5x7 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/5x7.cThe $5\times 7$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/5x7.cThe $5\times 7$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/5x7.cThe $5\times 7$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/5x8.cMBCSR 5x8 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/5x8.cThe $5\times 8$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/5x8.cThe $5\times 8$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/5x8.cThe $5\times 8$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/6x1.cMBCSR 6x1 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/6x1.cThe $6\times 1$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/6x1.cThe $6\times 1$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/6x1.cThe $6\times 1$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/6x2.cMBCSR 6x2 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/6x2.cThe $6\times 2$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/6x2.cThe $6\times 2$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/6x2.cThe $6\times 2$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/6x3.cMBCSR 6x3 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/6x3.cThe $6\times 3$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/6x3.cThe $6\times 3$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/6x3.cThe $6\times 3$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/6x4.cMBCSR 6x4 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/6x4.cThe $6\times 4$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/6x4.cThe $6\times 4$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/6x4.cThe $6\times 4$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/6x5.cMBCSR 6x5 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/6x5.cThe $6\times 5$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/6x5.cThe $6\times 5$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/6x5.cThe $6\times 5$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/6x6.cMBCSR 6x6 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/6x6.cThe $6\times 6$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/6x6.cThe $6\times 6$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/6x6.cThe $6\times 6$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/6x7.cMBCSR 6x7 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/6x7.cThe $6\times 7$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/6x7.cThe $6\times 7$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/6x7.cThe $6\times 7$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/6x8.cMBCSR 6x8 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/6x8.cThe $6\times 8$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/6x8.cThe $6\times 8$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/6x8.cThe $6\times 8$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/7x1.cMBCSR 7x1 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/7x1.cThe $7\times 1$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/7x1.cThe $7\times 1$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/7x1.cThe $7\times 1$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/7x2.cMBCSR 7x2 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/7x2.cThe $7\times 2$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/7x2.cThe $7\times 2$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/7x2.cThe $7\times 2$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/7x3.cMBCSR 7x3 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/7x3.cThe $7\times 3$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/7x3.cThe $7\times 3$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/7x3.cThe $7\times 3$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/7x4.cMBCSR 7x4 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/7x4.cThe $7\times 4$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/7x4.cThe $7\times 4$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/7x4.cThe $7\times 4$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/7x5.cMBCSR 7x5 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/7x5.cThe $7\times 5$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/7x5.cThe $7\times 5$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/7x5.cThe $7\times 5$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/7x6.cMBCSR 7x6 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/7x6.cThe $7\times 6$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/7x6.cThe $7\times 6$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/7x6.cThe $7\times 6$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/7x7.cMBCSR 7x7 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/7x7.cThe $7\times 7$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/7x7.cThe $7\times 7$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/7x7.cThe $7\times 7$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/7x8.cMBCSR 7x8 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/7x8.cThe $7\times 8$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/7x8.cThe $7\times 8$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/7x8.cThe $7\times 8$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/8x1.cMBCSR 8x1 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/8x1.cThe $8\times 1$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/8x1.cThe $8\times 1$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/8x1.cThe $8\times 1$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/8x2.cMBCSR 8x2 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/8x2.cThe $8\times 2$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/8x2.cThe $8\times 2$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/8x2.cThe $8\times 2$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/8x3.cMBCSR 8x3 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/8x3.cThe $8\times 3$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/8x3.cThe $8\times 3$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/8x3.cThe $8\times 3$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/8x4.cMBCSR 8x4 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/8x4.cThe $8\times 4$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/8x4.cThe $8\times 4$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/8x4.cThe $8\times 4$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/8x5.cMBCSR 8x5 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/8x5.cThe $8\times 5$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/8x5.cThe $8\times 5$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/8x5.cThe $8\times 5$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/8x6.cMBCSR 8x6 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/8x6.cThe $8\times 6$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/8x6.cThe $8\times 6$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/8x6.cThe $8\times 6$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/8x7.cMBCSR 8x7 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/8x7.cThe $8\times 7$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/8x7.cThe $8\times 7$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/8x7.cThe $8\times 7$ MBCSR implementation of sparse triangular solve
MBCSR/MatMult/8x8.cMBCSR 8x8 SpMV implementation, for all transpose options
MBCSR/MatMultAndMatTransMult/8x8.cThe $8\times 8$ MBCSR implementation of simultaneous multiplication by $A$ and $\mathrm{op}(A)$
MBCSR/MatTransMatMult/8x8.cThe $8\times 8$ MBCSR implementation of $A^TA\cdot x$ and $A^HA\cdot x$
MBCSR/MatTrisolve/8x8.cThe $8\times 8$ MBCSR implementation of sparse triangular solve
a_and_at.cImplementation of simultaneously multiplication by sparse $A$ and $\mathrm{op}(A) \in \{A, A^T, A^H=\bar{A}^T\}$
MATTYPE_TEMPLATE/a_and_at.cMATTYPE_TEMPLATE implementation of the simultaneous multiplication by sparse $A$ and $op(A) \in \{A, A^T, \bar{A}^T=A^H\}$
MBCSR/a_and_at.cMBCSR implementation of the simultaneous multiplication by sparse $A$ and $op(A) \in \{A, A^T, \bar{A}^T=A^H\}$
a_and_at.h [code]Sparse simultaneous multiplication by $A$ and $A^T$
abort_prog.h [code]Macro to abort a program on error
alloc.cTest OSKI memory allocation routines
array_util.cSome utility functions for the test suite
array_util.h [code]Some array manipulation utility functions for the test suite
src/ata.cSparse $A^TA\cdot x$ implementation
src/BCSR/ata.cBCSR implementation of the A^T*A*x kernel
src/MATTYPE_TEMPLATE/ata.cMATTYPE_TEMPLATE implementation of the sparse $A^TA\cdot x$ kernel
src/MBCSR/ata.cMBCSR implementation of the sparse $A^TA\cdot x$ kernel
tests/ata.cTest sparse matrix-vector multiply
ata.h [code]Sparse $A^TA\cdot x$ implementation
autotune.cGeneric SpMV benchmarking utility
bcsr.cTest basic kernel operations for a matrix in BCSR format
bench.cGeneric workload benchmarking utility
blas.cOSKI wrappers around the dense BLAS routines
blas.h [code]BeBOP wrappers around the dense BLAS routines
blas1.cTest BLAS 1 wrappers
blas_names.h [code]Header containing mangled F77 BLAS routine names
check.cCheck CSR properties
common.h [code]A maximal set of system-independent prototypes and definitions widely useful to all of the BeBOP library's sub-modules
config.h [code]Contains macros and definitions that depend on the specific system on which the library is being compiled
src/BCSR/convert.cConversion between CSR and SPARSITY-style BCSR (i.e., register blocking) format
src/BDIAG1/convert.cConversion between CSR and BDIAG1 format
src/CB/convert.cCSR-to-CB format conversion routines
src/MATTYPE_TEMPLATE/convert.cConversion between CSR and MATTYPE_TEMPLATE format
src/MBCSR/convert.cConversion between CSR and MBCSR format
src/VBR/convert.cConversion between CSR and VBR format
tests/convert.cTest matrix conversion
copy.cTest matrix and vector handle copying
create.cTest matrix handle creation
CSR_HermMatMult.h [code]Prototypes for subroutines that compute variations on $y \leftarrow y + \alpha \cdot op(A) \cdot x$, where $A$ is Hermitian (i.e., $A = A^H$) and $op(A) = A$
CSR_HermMatMult_v1_a1_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = 1$, x is unit-stride accessible, and y is unit-stride accessible
CSR_HermMatMult_v1_a1_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = 1$, x is unit-stride accessible, and y is general-stride accessible
CSR_HermMatMult_v1_a1_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = 1$, x is general-stride accessible, and y is unit-stride accessible
CSR_HermMatMult_v1_a1_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = 1$, x is general-stride accessible, and y is general-stride accessible
CSR_HermMatMult_v1_aN1_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = -1$, x is unit-stride accessible, and y is unit-stride accessible
CSR_HermMatMult_v1_aN1_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = -1$, x is unit-stride accessible, and y is general-stride accessible
CSR_HermMatMult_v1_aN1_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = -1$, x is general-stride accessible, and y is unit-stride accessible
CSR_HermMatMult_v1_aN1_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = -1$, x is general-stride accessible, and y is general-stride accessible
CSR_HermMatMult_v1_aX_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = $ (a general value), x is unit-stride accessible, and y is unit-stride accessible
CSR_HermMatMult_v1_aX_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = $ (a general value), x is unit-stride accessible, and y is general-stride accessible
CSR_HermMatMult_v1_aX_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = $ (a general value), x is general-stride accessible, and y is unit-stride accessible
CSR_HermMatMult_v1_aX_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A$, $\alpha = $ (a general value), x is general-stride accessible, and y is general-stride accessible
CSR_HermMatTransMult.h [code]Prototypes for subroutines that compute variations on $y \leftarrow y + \alpha \cdot op(A) \cdot x$, where $A$ is Hermitian (i.e., $A = A^H$) and $op(A) = A^T$
CSR_HermMatTransMult_v1_a1_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = 1$, x is unit-stride accessible, and y is unit-stride accessible
CSR_HermMatTransMult_v1_a1_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = 1$, x is unit-stride accessible, and y is general-stride accessible
CSR_HermMatTransMult_v1_a1_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = 1$, x is general-stride accessible, and y is unit-stride accessible
CSR_HermMatTransMult_v1_a1_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = 1$, x is general-stride accessible, and y is general-stride accessible
CSR_HermMatTransMult_v1_aN1_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = -1$, x is unit-stride accessible, and y is unit-stride accessible
CSR_HermMatTransMult_v1_aN1_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = -1$, x is unit-stride accessible, and y is general-stride accessible
CSR_HermMatTransMult_v1_aN1_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = -1$, x is general-stride accessible, and y is unit-stride accessible
CSR_HermMatTransMult_v1_aN1_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = -1$, x is general-stride accessible, and y is general-stride accessible
CSR_HermMatTransMult_v1_aX_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = $ (a general value), x is unit-stride accessible, and y is unit-stride accessible
CSR_HermMatTransMult_v1_aX_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = $ (a general value), x is unit-stride accessible, and y is general-stride accessible
CSR_HermMatTransMult_v1_aX_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = $ (a general value), x is general-stride accessible, and y is unit-stride accessible
CSR_HermMatTransMult_v1_aX_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is Hermitian (i.e., $A = A^H$), $op(A) = A^T$, $\alpha = $ (a general value), x is general-stride accessible, and y is general-stride accessible
CSR_MatMult.h [code]CSR sparse matrix-vector multiply implementation in the non-symmetric/non-Hermitian case
CSR_SymmMatHermMult.h [code]Prototypes for subroutines that compute variations on $y \leftarrow y + \alpha \cdot op(A) \cdot x$, where $A$ is symmetric (i.e., $A = A^T$) and $op(A) = A^H$
CSR_SymmMatHermMult_v1_a1_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = 1$, x is unit-stride accessible, and y is unit-stride accessible
CSR_SymmMatHermMult_v1_a1_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = 1$, x is unit-stride accessible, and y is general-stride accessible
CSR_SymmMatHermMult_v1_a1_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = 1$, x is general-stride accessible, and y is unit-stride accessible
CSR_SymmMatHermMult_v1_a1_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = 1$, x is general-stride accessible, and y is general-stride accessible
CSR_SymmMatHermMult_v1_aN1_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = -1$, x is unit-stride accessible, and y is unit-stride accessible
CSR_SymmMatHermMult_v1_aN1_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = -1$, x is unit-stride accessible, and y is general-stride accessible
CSR_SymmMatHermMult_v1_aN1_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = -1$, x is general-stride accessible, and y is unit-stride accessible
CSR_SymmMatHermMult_v1_aN1_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = -1$, x is general-stride accessible, and y is general-stride accessible
CSR_SymmMatHermMult_v1_aX_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = $ (a general value), x is unit-stride accessible, and y is unit-stride accessible
CSR_SymmMatHermMult_v1_aX_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = $ (a general value), x is unit-stride accessible, and y is general-stride accessible
CSR_SymmMatHermMult_v1_aX_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = $ (a general value), x is general-stride accessible, and y is unit-stride accessible
CSR_SymmMatHermMult_v1_aX_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A^H$, $\alpha = $ (a general value), x is general-stride accessible, and y is general-stride accessible
CSR_SymmMatMult.h [code]Prototypes for subroutines that compute variations on $y \leftarrow y + \alpha \cdot op(A) \cdot x$, where $A$ is symmetric (i.e., $A = A^T$) and $op(A) = A$
CSR_SymmMatMult_v1_a1_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = 1$, x is unit-stride accessible, and y is unit-stride accessible
CSR_SymmMatMult_v1_a1_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = 1$, x is unit-stride accessible, and y is general-stride accessible
CSR_SymmMatMult_v1_a1_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = 1$, x is general-stride accessible, and y is unit-stride accessible
CSR_SymmMatMult_v1_a1_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = 1$, x is general-stride accessible, and y is general-stride accessible
CSR_SymmMatMult_v1_aN1_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = -1$, x is unit-stride accessible, and y is unit-stride accessible
CSR_SymmMatMult_v1_aN1_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = -1$, x is unit-stride accessible, and y is general-stride accessible
CSR_SymmMatMult_v1_aN1_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = -1$, x is general-stride accessible, and y is unit-stride accessible
CSR_SymmMatMult_v1_aN1_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = -1$, x is general-stride accessible, and y is general-stride accessible
CSR_SymmMatMult_v1_aX_b1_xs1_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = $ (a general value), x is unit-stride accessible, and y is unit-stride accessible
CSR_SymmMatMult_v1_aX_b1_xs1_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = $ (a general value), x is unit-stride accessible, and y is general-stride accessible
CSR_SymmMatMult_v1_aX_b1_xsX_ys1.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = $ (a general value), x is general-stride accessible, and y is unit-stride accessible
CSR_SymmMatMult_v1_aX_b1_xsX_ysX.c$y \leftarrow y + \alpha\cdot op(A)\cdot x$, where $A$ is symmetric (i.e., $A = A^T$), $op(A) = A$, $\alpha = $ (a general value), x is general-stride accessible, and y is general-stride accessible
cycle.h [code]Cycle counter readers, taken from FFTW 3.0.1
tests/debug.cTest the rudimentary debugging/logging facility
debug.h [code]Debugging support module
err.cTest OSKI error handling facilities
error.cError-handling module
error.h [code]Error-handling module
estfill.cBCSR fill ratio estimator
estfill.h [code]BCSR fill ratio estimator
BCSR/format.h [code]Block compressed sparse row data structure
BDIAG1/format.h [code]Single block diagonal data structure
CB/format.h [code]Cache blocking data structure
CSC/format.h [code]Compressed sparse column data structure
CSR/format.h [code]Compressed sparse row data structure
DENSE/format.h [code]Generalized compressed sparse row data structure
GCSR/format.h [code]Generalized compressed sparse row data structure
MATTYPE_TEMPLATE/format.h [code]Custom matrix data structure
MBCSR/format.h [code]Modified block compressed sparse row data structure
TRIPART/format.h [code]\ Block compressed sparse row data structure
VBR/format.h [code]Generalized compressed sparse row data structure
gemv.cOSKI wrapper around the dense BLAS routine, xGEMV
getcpu.cGet the CPU architecture using a run-time probe
src/BCSR/getset.cBCSR get/set value routines
src/BDIAG1/getset.cBDIAG1 get/set value routines
src/CB/getset.cCB get/set value routines
src/CSC/getset.cCSC get/set value routines
src/CSR/getset.cCSR get/set value routines
src/DENSE/getset.cDENSE get/set value routines
src/GCSR/getset.cGCSR get/set value routines
src/getset.cGet/set value routines
src/MATTYPE_TEMPLATE/getset.cMATTYPE_TEMPLATE get/set value routines
src/MBCSR/getset.cMBCSR get/set value routines
src/VBR/getset.cVBR get/set value routines
tests/getset.cGet/set matrix values
getset.h [code]Get/set value routines
hba_and_at.cComprehensive test of the kernel for applying sparse $A$ and $\mathrm{op}(A) \in \{A, A^T, A^H=\bar{A}^T\}$ simultaneously
hbata.cComprehensive test of sparse $A^TAx$ kernel routine, oski_MatTransMatMult(), for an arbitrary data structure transformation (specified by a OSKI-Lua program), where the matrix is read from a Harwell-Boeing file
hbmatmult.cComprehensive test of matrix-vector multiply for an arbitrary data structure transformation (specified by a OSKI-Lua program), where the matrix is read from a Harwell-Boeing file
tests/heur.cTest sparse matrix-vector multiply tuning
heur.h [code]Heuristic management module
heur2.cAdditional testing of the heuristic
heur_internal.h [code]Heuristic management module
heur_typedep.cMatrix type-dependent part of the heuristic module
heur_typedep.h [code]Matrix type-dependent part of the heuristic module
heurexport.h [code]Matrix type-dependent part of the heuristic management module
hint.cImplementation of hint tracking for the tuning module
hint.h [code]Set-hint routines
info.cTest scalar/kernel info lookup routines
src/init.cInitialize the OSKI library
tests/init.cTest the matrix type management module
init.h [code]BeBOP library initialization
inmatprop.cInput matrix properties collection and inspection
inmatprop.h [code]Input matrix properties collection and inspection
kerinfo.h [code]Define the kernels available to the library
keropts.cProcess kernel-specific command-line options
keropts.h [code]Process kernel-specific command-line options
lower_conj.cConjugate sparse triangular solve implementation when the matrix is lower triangular and stored in CSR format
lower_conjtrans.cConjugate-transposed sparse triangular solve implementation when the matrix is lower triangular and stored in CSR format
lower_normal.cNon-transposed sparse triangular solve implementation when the matrix is lower triangular and stored in CSR format
lower_trans.cTransposed sparse triangular solve implementation when the matrix is lower triangular and stored in CSR format
ltdlstub.cStub file to define lt_preloaded_symbols in the case when we do not link using libtool
lua.cOSKI-Lua stack support
lua.h [code]Basic OSKI-Lua support routines
malloc.h [code]Customized memory allocation macros that provide diagnostic information when out-of-memory errors occur
mangle.h [code]Some macros to mangle index/value type-specific names
matcommon.cSupport routines for the data structure containing common matrix properties
matcommon.h [code]Define properties common to all matrix types
matcreate.cMatrix creation routines
matcreate.h [code]Matrix creation routines
matmodexport.h [code]Declares prototypes for the 'standard' set of dynamically exportable methods stored in matrix type modules
src/BCSR/matmult.cBCSR implementation of SpMV
src/BDIAG1/matmult.cBDIAG1 implementation of SpMV
src/CB/matmult.cSparse matrix-vector multiply implementation for a compressed sparse row (CB) matrix
src/CSC/matmult.cCSC SpMV implementation
src/CSR/matmult.cSparse matrix-vector multiply implementation for a compressed sparse row (CSR) matrix
src/DENSE/matmult.cCalls xGEMV / xGEMM
src/GCSR/matmult.cSparse matrix-vector multiply implementation for a compressed sparse row (GCSR) matrix
src/matmult.cSparse matrix-vector multiply implementation
src/MATTYPE_TEMPLATE/matmult.cMATTYPE_TEMPLATE implementation of SpMV
src/MBCSR/matmult.cMBCSR implementation of SpMV
src/VBR/matmult.cVBR implementation of SpMV
tests/matmult.cTest sparse matrix-vector multiply
matmult.h [code]Sparse matrix-vector multiply implementation
matopts.c
matopts.h [code]Matrix options processing and generation
matpow.cSparse matrix-power-vector multiply implementation
matpow.h [code]Sparse $A^k\cdot x$ implementation
matrix.cMatrix handle implementation
matrix.h [code]Matrix handle
tests/mattypes.cTest the matrix type management module
mattypes.h [code]Matrix type management routines
mattypes_internal.h [code]Defines a matrix type record
memcpy.h [code]Macros for typed block memory copy operations
methodtypes.h [code]Defines a set of function pointer types for "standard" matrix type module methods
modcommon.h [code]Definitions and structures common to dynamically shared modules
modloader.h [code]Shared library module loader
BCSR/module.cBlock compressed sparse row (BCSR) module
BDIAG1/module.cSingle block diagonal (BDIAG1) module
CB/module.cGeneralized compressed sparse row (CB) implementation
CSC/module.cCompressed sparse column (CSC) implementation
CSR/module.cCompressed sparse row (CSR) module
DENSE/module.cGeneralized compressed sparse row (DENSE) implementation
GCSR/module.cGeneralized compressed sparse row (GCSR) implementation
MATTYPE_TEMPLATE/module.cModified block compressed sparse row (MATTYPE_TEMPLATE) module
MBCSR/module.cModified block compressed sparse row (MBCSR) module
VBR/module.cVariable block row (VBR) implementation
BCSR/module.h [code]Block compressed sparse row (BCSR) implementation
BDIAG1/module.h [code]Block compressed sparse row (BDIAG1) implementation
CB/module.h [code]
CSC/module.h [code]Compressed sparse column implementation
CSR/module.h [code]Compressed sparse row implementation
DENSE/module.h [code]Dense column major format
GCSR/module.h [code]Compressed sparse column implementation
MATTYPE_TEMPLATE/module.h [code]Custom matrix module
MBCSR/module.h [code]Modified block compressed sparse row (MBCSR) implementation
VBR/module.h [code]Variable block row implementation
mregblock.h [code]Implementation of the register blocking heuristic based on modified block compressed sparse row (MBCSR) format
multimalloc.cTest OSKI multiple-malloc routine
oski_Tic.h [code]Maps the default OSKI interface names to (int, complex_float)
oski_Tid.h [code]Maps the default OSKI interface names to (int, double)
oski_Tis.h [code]Maps the default OSKI interface names to (int, float)
oski_Tiz.h [code]Maps the default OSKI interface names to (int, complex_double)
oski_Tlc.h [code]
oski_Tld.h [code]
oski_Tls.h [code]
oski_Tlz.h [code]
parse_opts.cParse command-line options
parse_opts.h [code]Parse command-line options
perm.cPermutations
perm.h [code]Permutations
rand_util.cWrappers around the available random number generators
rand_util.h [code]Wrappers around the available random number generators
readhbpat.cRoutine to read the pattern of a file stored in Harwell-Boeing format
readhbpat.h [code]Defines utility routine to read a matrix pattern from a Harwell-Boeing formatted file
regblock.h [code]Implementation of the basic register blocking heuristic for sparse matrix-vector multiply (as described in the Sparsity SC'02 and IJHPCA'04 papers), based on block compressed sparse row format
regprofheur.h [code]Register blocking heuristic for general workloads
regprofmgr.h [code]
regprofquery.h [code]Workload query interface for register blocking heuristic
scalinfo.h [code]Define the scalar types available to the library
simplelist.h [code]Simple read-only, lockable, append-only list implementation
spmv_gencb.h [code]
spmv_rsegdiag.h [code]
spmv_tile_graph.h [code]
spmv_tiled_bcsr.h [code]Tiled BCSR format
spmv_ubcsr.h [code]
spmv_vbr.h [code]
sprintf.h [code]Macros for typed block memory copy operations
stat.cImplements some simple statistics gathering utilities
stat.h [code]Provides some simple statistical utilities
structhint.cImplementation of structural tuning hint data structure
structhint.h [code]Structural hint implementation
symmrb.h [code]Implementation of the register blocking heuristic for symmetric matrices, as described in the paper by Lee, et al., in ICPP'04, but extended to the Symmetric or Hermitian cases and based on MBCSR format
testvec.cCode to generate vectors and vector views for testing and off-line benchmarking
testvec.h [code]Test vector generation and checking
src/timer/timer.cTiming module implementation
tests/timer.cTests timer module
timer.h [code]Timing module
timing.h [code]Timing wrapper macros
trace.h [code]Implements a database for keeping track of kernel calls
trace_query.cImplements a database system for tracking kernel calls
transpose.cImplements a routine to transpose a CSR matrix
src/CSC/trisolve.cCSC sparse triangular solve implementation
src/DENSE/trisolve.cCalls xTRSV / xTRSM
src/trisolve.cSparse triangular solve implementation
tests/trisolve.cBasic test of the CSR/CSC sparse triangular solve
trisolve.h [code]Sparse triangular solve implementation
trsv.cOSKI wrapper around the dense BLAS routine, xTRSV
tune.cTuning module implementation
tune.h [code]Tuning interface
upper_conj.cConjugate sparse triangular solve implementation when the matrix is upper triangular
upper_conjtrans.cConjugate transposed sparse triangular solve implementation when the matrix is upper triangular and stored in CSR format
upper_normal.cNon-transposed sparse triangular solve implementation when the matrix is upper triangular
upper_trans.cTransposed sparse triangular solve implementation when the matrix is upper triangular and stored in CSR format
userconst.h [code]Defines the constants available to the user in the official interface
vector.h [code]Multivector view implementation
src/vecview.cMultivector view implementation
tests/vecview.cTest matrix handle creation
vecview.h [code]Multivector view module
workload.cRoutines for simulating an arbitrary workload
workload.h [code]Routines for simulating an arbitrary workload
xforms.cSave/restore tuning transformations
xforms.h [code]OSKI-Lua transformation module
xforms_internal.h [code]This header file isolates the Lua-dependent aspects of the tuning transform implementation from the core OSKI code

Generated on Wed Sep 19 16:41:18 2007 for BeBOP Optimized Sparse Kernel Interface Library by  doxygen 1.4.6