Todo List

Global blas_sparse::cuscr_begin (m, n, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::cuscr_block_begin (Mb, Nb, k, l, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::cuscr_variable_block_begin (Mb, Nb, K, L, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::duscr_begin (m, n, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::duscr_block_begin (Mb, Nb, k, l, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::duscr_variable_block_begin (Mb, Nb, K, L, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::suscr_begin (m, n, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::suscr_block_begin (Mb, Nb, k, l, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::suscr_variable_block_begin (Mb, Nb, K, L, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::zuscr_begin (m, n, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::zuscr_block_begin (Mb, Nb, k, l, A, istat)

Shall make A intent(inout) as well.

Global blas_sparse::zuscr_variable_block_begin (Mb, Nb, K, L, A, istat)

Shall make A intent(inout) as well.

Global rsb_tune_spmm (struct rsb_mtx_t **mtxOpp, rsb_real_t *sfp, rsb_int_t *tnp, rsb_int_t maxr, rsb_time_t maxt, rsb_trans_t transA, const void *alphap, const struct rsb_mtx_t *mtxAp, rsb_coo_idx_t nrhs, rsb_flags_t order, const void *Bp, rsb_nnz_idx_t ldB, const void *betap, void *Cp, rsb_nnz_idx_t ldC)

In the future, autotuning functionality shall improve considerably. Need support for lightweight, threads-only optimization. May support strided vectors in the future.

Global rsb_tune_spsm (struct rsb_mtx_t **mtxOpp, rsb_real_t *sfp, rsb_int_t *tnp, rsb_int_t maxr, rsb_time_t maxt, rsb_trans_t transA, const void *alphap, const struct rsb_mtx_t *mtxAp, rsb_coo_idx_t nrhs, rsb_flags_t order, const void *Bp, rsb_nnz_idx_t ldB, const void *betap, void *Cp, rsb_nnz_idx_t ldC)

In the future, autotuning functionality shall improve considerably. Need support for lightweight, threads-only optimization. May support strided vectors in the future.