MAGMA  2.5.1
Matrix Algebra for GPU and Multicore Architectures
 All Classes Files Functions Friends Groups Pages
magmablas Directory Reference

Files

file  atomics.cuh
 
file  blas_cbatched.cpp
 
file  blas_dbatched.cpp
 
file  blas_sbatched.cpp
 
file  blas_zbatched.cpp
 
file  caxpycp.cu
 
file  cbcyclic.cpp
 
file  cgeadd.cu
 
file  cgeadd2.cu
 
file  cgeadd_batched.cu
 
file  cgemm_batched.cpp
 
file  cgemm_batched_core.cu
 
file  cgemm_batched_smallsq.cu
 
file  cgemm_fermi.cu
 
file  cgemm_fermi_kernels.h
 
file  cgemm_reduce.cu
 
file  cgemm_vbatched.cpp
 
file  cgemm_vbatched_core.cu
 
file  cgemv_batched_core.cu
 
file  cgemv_conj.cu
 
file  cgemv_fermi.cu
 
file  cgemv_vbatched.cpp
 
file  cgemv_vbatched_core.cu
 
file  cgeqr2.cpp
 
file  cgeqr2_batched.cu
 
file  cgeqr2x_gpu-v4.cu
 
file  cgeqrf_batched_smallsq.cu
 
file  cgerbt.cu
 
file  cgerbt.h
 
file  cgerbt_func_batched.cu
 
file  cgerbt_kernels.cu
 
file  cgetf2.cu
 
file  cgetf2_kernels.cu
 
file  cgetf2_native_kernel.cu
 
file  cgetf2_nopiv_kernels.cu
 
file  cgetmatrix_transpose.cpp
 
file  cgetmatrix_transpose_mgpu.cpp
 
file  cgetrf_batched_smallsq_noshfl.cu
 
file  cgetrf_batched_smallsq_shfl.cu
 
file  chemm_batched_core.cu
 
file  chemm_mgpu.cpp
 
file  chemm_vbatched.cpp
 
file  chemm_vbatched_core.cu
 
file  chemv.cu
 
file  chemv_batched_core.cu
 
file  chemv_mgpu.cu
 
file  chemv_mgpu_upper.cu
 
file  chemv_upper.cu
 
file  chemv_vbatched.cpp
 
file  chemv_vbatched_core.cu
 
file  cher2k_batched.cpp
 
file  cher2k_mgpu.cpp
 
file  cher2k_vbatched.cpp
 
file  cherk_batched.cpp
 
file  cherk_batched_core.cu
 
file  cherk_mgpu.cpp
 
file  cherk_small_reduce.cu
 
file  cherk_vbatched.cpp
 
file  cherk_vbatched_core.cu
 
file  clacpy.cu
 
file  clacpy_conj.cu
 
file  clacpy_sym_in.cu
 
file  clacpy_sym_out.cu
 
file  clag2z.cu
 
file  clange.cu
 
file  clanhe.cu
 
file  claqps2_gpu.cu
 
file  clarf.cu
 
file  clarfbx.cu
 
file  clarfg-v2.cu
 
file  clarfg.cu
 
file  clarfg_devicesfunc.cuh
 
file  clarfgx-v2.cu
 
file  clarft_kernels.cu
 
file  clarfx.cu
 
file  clascl.cu
 
file  clascl2.cu
 
file  clascl_2x2.cu
 
file  clascl_diag.cu
 
file  claset.cu
 
file  claset_band.cu
 
file  claswp.cu
 
file  claswp_batched.cu
 
file  claswp_sym.cu
 
file  clat2z.cu
 
file  commonblas_c.h
 
file  commonblas_d.h
 
file  commonblas_s.h
 
file  commonblas_z.h
 
file  cpotf2.cu
 
file  cpotf2_devicesfunc.cuh
 
file  cpotf2_kernels.cu
 
file  cpotf2_kernels_old.cu
 
file  cpotf2_kernels_var.cu
 
file  cset_pointer.cu
 
file  csetmatrix_transpose.cpp
 
file  csetmatrix_transpose_mgpu.cpp
 
file  cswap.cu
 
file  cswapblk.cu
 
file  cswapdblk.cu
 
file  csymmetrize.cu
 
file  csymmetrize_tiles.cu
 
file  csymv.cu
 
file  csymv_upper.cu
 
file  csyr2k_batched.cpp
 
file  csyr2k_vbatched.cpp
 
file  csyrk_vbatched.cpp
 
file  ctranspose.cu
 
file  ctranspose_conj.cu
 
file  ctranspose_conj_inplace.cu
 
file  ctranspose_inplace.cu
 
file  ctrmm_batched_core.cu
 
file  ctrmm_vbatched.cpp
 
file  ctrmm_vbatched_core.cu
 
file  ctrsm.cu
 
file  ctrsm_batched.cpp
 
file  ctrsm_batched_core.cpp
 
file  ctrsm_small_batched.cu
 
file  ctrsm_vbatched.cpp
 
file  ctrsm_vbatched_core.cu
 
file  ctrsv.cu
 
file  ctrsv_batched.cu
 
file  ctrsv_template_device.cuh
 
file  ctrtri.cuh
 
file  ctrtri_diag.cu
 
file  ctrtri_diag_batched.cu
 
file  ctrtri_diag_vbatched.cu
 
file  ctrtri_lower.cu
 
file  ctrtri_lower_batched.cu
 
file  ctrtri_lower_device.cuh
 
file  ctrtri_upper.cu
 
file  ctrtri_upper_batched.cu
 
file  ctrtri_upper_device.cuh
 
file  daxpycp.cu
 
file  dbcyclic.cpp
 
file  dgeadd.cu
 
file  dgeadd2.cu
 
file  dgeadd_batched.cu
 
file  dgemm_batched.cpp
 
file  dgemm_batched_core.cu
 
file  dgemm_batched_smallsq.cu
 
file  dgemm_fermi.cu
 
file  dgemm_fermi_kernels.h
 
file  dgemm_reduce.cu
 
file  dgemm_vbatched.cpp
 
file  dgemm_vbatched_core.cu
 
file  dgemv_batched_core.cu
 
file  dgemv_conj.cu
 
file  dgemv_fermi.cu
 
file  dgemv_vbatched.cpp
 
file  dgemv_vbatched_core.cu
 
file  dgeqr2.cpp
 
file  dgeqr2_batched.cu
 
file  dgeqr2x_gpu-v4.cu
 
file  dgeqrf_batched_smallsq.cu
 
file  dgerbt.cu
 
file  dgerbt.h
 
file  dgerbt_func_batched.cu
 
file  dgerbt_kernels.cu
 
file  dgetf2.cu
 
file  dgetf2_kernels.cu
 
file  dgetf2_native_kernel.cu
 
file  dgetf2_nopiv_kernels.cu
 
file  dgetmatrix_transpose.cpp
 
file  dgetmatrix_transpose_mgpu.cpp
 
file  dgetrf_batched_smallsq_noshfl.cu
 
file  dgetrf_batched_smallsq_shfl.cu
 
file  dlacpy.cu
 
file  dlacpy_conj.cu
 
file  dlacpy_sym_in.cu
 
file  dlacpy_sym_out.cu
 
file  dlag2s.cu
 
file  dlange.cu
 
file  dlansy.cu
 
file  dlaqps2_gpu.cu
 
file  dlarf.cu
 
file  dlarfbx.cu
 
file  dlarfg-v2.cu
 
file  dlarfg.cu
 
file  dlarfg_devicesfunc.cuh
 
file  dlarfgx-v2.cu
 
file  dlarft_kernels.cu
 
file  dlarfx.cu
 
file  dlascl.cu
 
file  dlascl2.cu
 
file  dlascl_2x2.cu
 
file  dlascl_diag.cu
 
file  dlaset.cu
 
file  dlaset_band.cu
 
file  dlaswp.cu
 
file  dlaswp_batched.cu
 
file  dlaswp_sym.cu
 
file  dlat2s.cu
 
file  dnrm2.cu
 
file  dpotf2.cu
 
file  dpotf2_devicesfunc.cuh
 
file  dpotf2_kernels.cu
 
file  dpotf2_kernels_old.cu
 
file  dpotf2_kernels_var.cu
 
file  dsaxpycp.cu
 
file  dset_pointer.cu
 
file  dsetmatrix_transpose.cpp
 
file  dsetmatrix_transpose_mgpu.cpp
 
file  dslaswp.cu
 
file  dswap.cu
 
file  dswapblk.cu
 
file  dswapdblk.cu
 
file  dsymm_batched_core.cu
 
file  dsymm_mgpu.cpp
 
file  dsymm_vbatched.cpp
 
file  dsymm_vbatched_core.cu
 
file  dsymmetrize.cu
 
file  dsymmetrize_tiles.cu
 
file  dsymv.cu
 
file  dsymv_batched_core.cu
 
file  dsymv_mgpu.cu
 
file  dsymv_mgpu_upper.cu
 
file  dsymv_upper.cu
 
file  dsymv_vbatched.cpp
 
file  dsymv_vbatched_core.cu
 
file  dsyr2k_batched.cpp
 
file  dsyr2k_mgpu.cpp
 
file  dsyr2k_vbatched.cpp
 
file  dsyrk_batched.cpp
 
file  dsyrk_batched_core.cu
 
file  dsyrk_mgpu.cpp
 
file  dsyrk_small_reduce.cu
 
file  dsyrk_vbatched.cpp
 
file  dsyrk_vbatched_core.cu
 
file  dtranspose.cu
 
file  dtranspose_inplace.cu
 
file  dtrmm_batched_core.cu
 
file  dtrmm_vbatched.cpp
 
file  dtrmm_vbatched_core.cu
 
file  dtrsm.cu
 
file  dtrsm_batched.cpp
 
file  dtrsm_batched_core.cpp
 
file  dtrsm_small_batched.cu
 
file  dtrsm_vbatched.cpp
 
file  dtrsm_vbatched_core.cu
 
file  dtrsv.cu
 
file  dtrsv_batched.cu
 
file  dtrsv_template_device.cuh
 
file  dtrtri.cuh
 
file  dtrtri_diag.cu
 
file  dtrtri_diag_batched.cu
 
file  dtrtri_diag_vbatched.cu
 
file  dtrtri_lower.cu
 
file  dtrtri_lower_batched.cu
 
file  dtrtri_lower_device.cuh
 
file  dtrtri_upper.cu
 
file  dtrtri_upper_batched.cu
 
file  dtrtri_upper_device.cuh
 
file  dznrm2.cu
 
file  gemm_kernel.cuh
 
file  gemm_kernel_batched.cuh
 
file  gemm_stencil.cuh
 
file  gemm_stencil_defs.h
 
file  gemm_template_device.cuh
 
file  gemm_template_device_defs.cuh
 
file  gemm_template_kernel_batched.cuh
 
file  gemm_template_kernel_vbatched.cuh
 
file  gemv_template_device.cuh
 
file  gemv_template_kernel_batched.cuh
 
file  gemv_template_kernel_vbatched.cuh
 
file  getrf_setup_pivinfo.cu
 
file  hemm_template_device.cuh
 
file  hemm_template_kernel_batched.cuh
 
file  hemm_template_kernel_vbatched.cuh
 
file  hemv_template_device.cuh
 
file  hemv_template_kernel_batched.cuh
 
file  hemv_template_kernel_vbatched.cuh
 
file  herk_kernel_batched.cuh
 
file  herk_template_kernel_batched.cuh
 
file  herk_template_kernel_vbatched.cuh
 
file  hlaconvert.cu
 
file  hlag2s.cu
 
file  hlaswp.cu
 
file  magma_templates.h
 
file  prefix_sum.cu
 
file  saxpycp.cu
 
file  sbcyclic.cpp
 
file  scnrm2.cu
 
file  set_pointer.cu
 
file  sgeadd.cu
 
file  sgeadd2.cu
 
file  sgeadd_batched.cu
 
file  sgemm_batched.cpp
 
file  sgemm_batched_core.cu
 
file  sgemm_batched_smallsq.cu
 
file  sgemm_fermi.cu
 
file  sgemm_fermi_kernels.h
 
file  sgemm_reduce.cu
 
file  sgemm_vbatched.cpp
 
file  sgemm_vbatched_core.cu
 
file  sgemv_batched_core.cu
 
file  sgemv_conj.cu
 
file  sgemv_fermi.cu
 
file  sgemv_vbatched.cpp
 
file  sgemv_vbatched_core.cu
 
file  sgeqr2.cpp
 
file  sgeqr2_batched.cu
 
file  sgeqr2x_gpu-v4.cu
 
file  sgeqrf_batched_smallsq.cu
 
file  sgerbt.cu
 
file  sgerbt.h
 
file  sgerbt_func_batched.cu
 
file  sgerbt_kernels.cu
 
file  sgetf2.cu
 
file  sgetf2_kernels.cu
 
file  sgetf2_native_kernel.cu
 
file  sgetf2_nopiv_kernels.cu
 
file  sgetmatrix_transpose.cpp
 
file  sgetmatrix_transpose_mgpu.cpp
 
file  sgetrf_batched_smallsq_noshfl.cu
 
file  sgetrf_batched_smallsq_shfl.cu
 
file  shuffle.cuh
 
file  slacpy.cu
 
file  slacpy_conj.cu
 
file  slacpy_sym_in.cu
 
file  slacpy_sym_out.cu
 
file  slag2d.cu
 
file  slag2h.cu
 
file  slange.cu
 
file  slansy.cu
 
file  slaqps2_gpu.cu
 
file  slarf.cu
 
file  slarfbx.cu
 
file  slarfg-v2.cu
 
file  slarfg.cu
 
file  slarfg_devicesfunc.cuh
 
file  slarfgx-v2.cu
 
file  slarft_kernels.cu
 
file  slarfx.cu
 
file  slascl.cu
 
file  slascl2.cu
 
file  slascl_2x2.cu
 
file  slascl_diag.cu
 
file  slaset.cu
 
file  slaset_band.cu
 
file  slaswp.cu
 
file  slaswp_batched.cu
 
file  slaswp_sym.cu
 
file  slat2d.cu
 
file  snrm2.cu
 
file  spotf2.cu
 
file  spotf2_devicesfunc.cuh
 
file  spotf2_kernels.cu
 
file  spotf2_kernels_old.cu
 
file  spotf2_kernels_var.cu
 
file  sset_pointer.cu
 
file  ssetmatrix_transpose.cpp
 
file  ssetmatrix_transpose_mgpu.cpp
 
file  sswap.cu
 
file  sswapblk.cu
 
file  sswapdblk.cu
 
file  ssymm_batched_core.cu
 
file  ssymm_mgpu.cpp
 
file  ssymm_vbatched.cpp
 
file  ssymm_vbatched_core.cu
 
file  ssymmetrize.cu
 
file  ssymmetrize_tiles.cu
 
file  ssymv.cu
 
file  ssymv_batched_core.cu
 
file  ssymv_mgpu.cu
 
file  ssymv_mgpu_upper.cu
 
file  ssymv_upper.cu
 
file  ssymv_vbatched.cpp
 
file  ssymv_vbatched_core.cu
 
file  ssyr2k_batched.cpp
 
file  ssyr2k_mgpu.cpp
 
file  ssyr2k_vbatched.cpp
 
file  ssyrk_batched.cpp
 
file  ssyrk_batched_core.cu
 
file  ssyrk_mgpu.cpp
 
file  ssyrk_small_reduce.cu
 
file  ssyrk_vbatched.cpp
 
file  ssyrk_vbatched_core.cu
 
file  stranspose.cu
 
file  stranspose_inplace.cu
 
file  strmm_batched_core.cu
 
file  strmm_vbatched.cpp
 
file  strmm_vbatched_core.cu
 
file  strsm.cu
 
file  strsm_batched.cpp
 
file  strsm_batched_core.cpp
 
file  strsm_small_batched.cu
 
file  strsm_vbatched.cpp
 
file  strsm_vbatched_core.cu
 
file  strsv.cu
 
file  strsv_batched.cu
 
file  strsv_template_device.cuh
 
file  strtri.cuh
 
file  strtri_diag.cu
 
file  strtri_diag_batched.cu
 
file  strtri_diag_vbatched.cu
 
file  strtri_lower.cu
 
file  strtri_lower_batched.cu
 
file  strtri_lower_device.cuh
 
file  strtri_upper.cu
 
file  strtri_upper_batched.cu
 
file  strtri_upper_device.cuh
 
file  sync.cuh
 
file  trmm_template_device.cuh
 
file  trmm_template_kernel_batched.cuh
 
file  trmm_template_kernel_vbatched.cuh
 
file  trsm_template_device.cuh
 
file  trsm_template_kernel_batched.cuh
 
file  vbatched_aux.cu
 
file  vbatched_check.cu
 
file  zaxpycp.cu
 
file  zbcyclic.cpp
 
file  zcaxpycp.cu
 
file  zclaswp.cu
 
file  zgeadd.cu
 
file  zgeadd2.cu
 
file  zgeadd_batched.cu
 
file  zgemm_batched.cpp
 
file  zgemm_batched_core.cu
 
file  zgemm_batched_smallsq.cu
 
file  zgemm_fermi.cu
 
file  zgemm_fermi_kernels.h
 
file  zgemm_reduce.cu
 
file  zgemm_vbatched.cpp
 
file  zgemm_vbatched_core.cu
 
file  zgemv_batched_core.cu
 
file  zgemv_conj.cu
 
file  zgemv_fermi.cu
 
file  zgemv_vbatched.cpp
 
file  zgemv_vbatched_core.cu
 
file  zgeqr2.cpp
 
file  zgeqr2_batched.cu
 
file  zgeqr2_kernels.cu
 
file  zgeqr2x_gpu-v4.cu
 
file  zgeqrf_batched_smallsq.cu
 
file  zgerbt.cu
 
file  zgerbt.h
 
file  zgerbt_func_batched.cu
 
file  zgerbt_kernels.cu
 
file  zgetf2.cu
 
file  zgetf2_kernels.cu
 
file  zgetf2_native_kernel.cu
 
file  zgetf2_nopiv_kernels.cu
 
file  zgetmatrix_transpose.cpp
 
file  zgetmatrix_transpose_mgpu.cpp
 
file  zgetrf_batched_smallsq_noshfl.cu
 
file  zgetrf_batched_smallsq_shfl.cu
 
file  zhemm_batched_core.cu
 
file  zhemm_mgpu.cpp
 
file  zhemm_vbatched.cpp
 
file  zhemm_vbatched_core.cu
 
file  zhemv.cu
 
file  zhemv_batched_core.cu
 
file  zhemv_mgpu.cu
 
file  zhemv_mgpu_upper.cu
 
file  zhemv_upper.cu
 
file  zhemv_vbatched.cpp
 
file  zhemv_vbatched_core.cu
 
file  zher2k_batched.cpp
 
file  zher2k_mgpu.cpp
 
file  zher2k_vbatched.cpp
 
file  zherk_batched.cpp
 
file  zherk_batched_core.cu
 
file  zherk_gpu.cpp
 
file  zherk_mgpu.cpp
 
file  zherk_small_reduce.cu
 
file  zherk_vbatched.cpp
 
file  zherk_vbatched_core.cu
 
file  zlacpy.cu
 
file  zlacpy_conj.cu
 
file  zlacpy_sym_in.cu
 
file  zlacpy_sym_out.cu
 
file  zlag2c.cu
 
file  zlange.cu
 
file  zlanhe.cu
 
file  zlaqps2_gpu.cu
 
file  zlarf.cu
 
file  zlarfbx.cu
 
file  zlarfg-v2.cu
 
file  zlarfg.cu
 
file  zlarfg_devicesfunc.cuh
 
file  zlarfgx-v2.cu
 
file  zlarft_kernels.cu
 
file  zlarfx.cu
 
file  zlascl.cu
 
file  zlascl2.cu
 
file  zlascl_2x2.cu
 
file  zlascl_diag.cu
 
file  zlaset.cu
 
file  zlaset_band.cu
 
file  zlaswp.cu
 
file  zlaswp_batched.cu
 
file  zlaswp_sym.cu
 
file  zlat2c.cu
 
file  zpotf2.cu
 
file  zpotf2_devicesfunc.cuh
 
file  zpotf2_kernels.cu
 
file  zpotf2_kernels_old.cu
 
file  zpotf2_kernels_var.cu
 
file  zset_pointer.cu
 
file  zsetmatrix_transpose.cpp
 
file  zsetmatrix_transpose_mgpu.cpp
 
file  zswap.cu
 
file  zswapblk.cu
 
file  zswapdblk.cu
 
file  zswapdblk_batched.cu
 
file  zsymmetrize.cu
 
file  zsymmetrize_tiles.cu
 
file  zsymv.cu
 
file  zsymv_upper.cu
 
file  zsyr2k_batched.cpp
 
file  zsyr2k_vbatched.cpp
 
file  zsyrk_vbatched.cpp
 
file  ztranspose.cu
 
file  ztranspose_conj.cu
 
file  ztranspose_conj_inplace.cu
 
file  ztranspose_inplace.cu
 
file  ztrmm_batched_core.cu
 
file  ztrmm_vbatched.cpp
 
file  ztrmm_vbatched_core.cu
 
file  ztrsm.cu
 
file  ztrsm_batched.cpp
 
file  ztrsm_batched_core.cpp
 
file  ztrsm_small_batched.cu
 
file  ztrsm_vbatched.cpp
 
file  ztrsm_vbatched_core.cu
 
file  ztrsv.cu
 
file  ztrsv_batched.cu
 
file  ztrsv_template_device.cuh
 
file  ztrtri.cuh
 
file  ztrtri_diag.cu
 
file  ztrtri_diag_batched.cu
 
file  ztrtri_diag_vbatched.cu
 
file  ztrtri_lower.cu
 
file  ztrtri_lower_batched.cu
 
file  ztrtri_lower_device.cuh
 
file  ztrtri_upper.cu
 
file  ztrtri_upper_batched.cu
 
file  ztrtri_upper_device.cuh