Commits · 3890c2903f83f0157a4dcf9899d4edcdd6163b9d · Kaushik Kulkarni / viennacl-dev · GitLab

Jul 26, 2013
- Fixed erroneous assert()-statement. · 3890c290
  Karl Rupp authored Jul 26, 2013
  
  3890c290
- Fixed copy&paste error in comments within scheduler tutorial · aed5c3f7
  Karl Rupp authored Jul 26, 2013
  
  aed5c3f7
- Fixed matrix element-wise kernel processing. · 8fe2dd56
  Karl Rupp authored Jul 26, 2013
  8fe2dd56
- fixed regression test script: building in serial mode now · c36d5e32
  Josef Weinbub authored Jul 26, 2013
  
  c36d5e32
- Fixed sparse matrix-vector product with strided vectors for ELL, HYB for CUDA. · 5169bf97
  Karl Rupp authored Jul 25, 2013
  5169bf97
Jul 25, 2013
- Fixed sparse matrix-vector product with strided vectors for COO, ELL, HYB for OpenMP. · 0f192210
  Karl Rupp authored Jul 25, 2013
  0f192210
- Fixed sparse matrix-vector product with strided vectors for COO, ELL, HYB for OpenCL. · da83a09a
  Karl Rupp authored Jul 25, 2013
  da83a09a
- Fixed scheduler-related pedantic warnings on GCC 4.6. · 1b158ce7
  Karl Rupp authored Jul 25, 2013
  
  1b158ce7
- Merge pull request #37 from albertzaharovits/master · af257ca9
  Karl Rupp authored Jul 25, 2013
  af257ca9
- Scheduler: Removed trailing underscores from struct and union members. · 717b9c5c
  Karl Rupp authored Jul 24, 2013
  
  717b9c5c
Jul 24, 2013
- Refined test for compressed_matrix-vector product using ranges and slices for vector. · 626eb4ba
  Karl Rupp authored Jul 24, 2013
  
  626eb4ba
- Removed incorrect CPU fallback for SpMV on CPUs using OpenCL. · 61774da5
  Karl Rupp authored Jul 24, 2013
  
  61774da5
Jul 23, 2013
- Scheduler: Replaced const-char exceptions with std::exception-compliant mechanism. · 94030632
  Karl Rupp authored Jul 23, 2013
  
  94030632
- Merge pull request #38 from bollig/master · ba2d6937
  Karl Rupp authored Jul 23, 2013
  ba2d6937
- Updated code comments · 813770c0
  Evan Bollig authored Jul 23, 2013
  
  813770c0
- Added support for switching queues · 28d5a0d5
  Evan Bollig authored Jul 23, 2013
  
  28d5a0d5
- Merge remote-tracking branch 'upstream/master' · af99e3df
  Albert authored Jul 23, 2013
  
  af99e3df
- Merge remote-tracking branch 'upstream/master' · 81c8694e
  Albert authored Jul 19, 2013
  81c8694e
Jul 22, 2013
- Fixed compilation problems on GCC 4.4. · 93cb8c76
  Karl Rupp authored Jul 22, 2013
  93cb8c76
- Added support for sparse matrix-vector problem using vector ranges and slices. · 7e688608
  Karl Rupp authored Jul 22, 2013
  
  7e688608
- Fixed missing braces around block for OpenCL vector norm kernels. · ca77e0e1
  Karl Rupp authored Jul 22, 2013
  
  ca77e0e1
Jul 19, 2013
- Now using op_mat_mat_prod instead of op_prod for matrix-matrix products. · 35242d15
  Karl Rupp authored Jul 19, 2013
  35242d15
- Sparse Matrix(compressed) * Dense Matrix product · cb9c047c
  Albert authored Jul 18, 2013
  cb9c047c
Jul 18, 2013
- Added support for integer vectors using the CUDA backend. · 9b5a3619
  Karl Rupp authored Jul 18, 2013
  
  9b5a3619
- Added support for vector<int> and vector<long> when using OpenCL. · 7d4ffeb7
  Karl Rupp authored Jul 18, 2013
  7d4ffeb7
- Added first support for integer vectors using the CPU backend. · 33863f0f
  Karl Rupp authored Jul 18, 2013
  33863f0f
Jul 17, 2013
- Added support for simple vector reduction operations (inner_prod, norm_1,... · d1d66753
  Karl Rupp authored Jul 17, 2013
  d1d66753
- Sparse Matrix(compressed) * Dense Matrix product · 10944cf7
  Albert authored Jul 17, 2013
  10944cf7
Jul 16, 2013
- Added front-end and tests for multiple inner products. Implementation now complete. · 0a1e5c99
  Karl Rupp authored Jul 16, 2013
  
  0a1e5c99
- Fixed wrong handling of a single inner product inside multiple inner products for OpenCL · 28390bb2
  Karl Rupp authored Jul 16, 2013
  
  28390bb2
- Fixed wrong use of vector_tuple and result assignment for multiple inner products on host · aa18ef2b
  Karl Rupp authored Jul 16, 2013
  
  aa18ef2b
- Fixed minor errors in CUDA implementation of multiple inner products · 6e261b1d
  Karl Rupp authored Jul 16, 2013
  
  6e261b1d
- Added additional overloads for viennacl::tie() and viennacl::vector_tuple CTOR. · e2ffb7e6
  Karl Rupp authored Jul 16, 2013
  e2ffb7e6
- Added additional barriers in sum and inner product OpenCL kernels. · 1992bff0
  Karl Rupp authored Jul 16, 2013
  1992bff0
- Fixed uninitalized context ptr in scalar_vector when using OpenCL. · 446dd945
  Karl Rupp authored Jul 16, 2013
  
  446dd945
- Added CUDA version of multiple inner products. · c597b4d1
  Karl Rupp authored Jul 16, 2013
  
  c597b4d1
- Fixed placement of barriers in sum kernels · bba96737
  Karl Rupp authored Jul 16, 2013
  
  bba96737
- Added multiple inner_prod() with same vector for CPU backend. · d0ddcfcb
  Karl Rupp authored Jul 16, 2013
  
  d0ddcfcb
- Adjusted vector_tuple to return references rather than pointers. · ecbc638b
  Karl Rupp authored Jul 16, 2013
  
  ecbc638b
- Fixed problematic use of viennacl::traits::size1() on object of integral type. · defc54c1
  Karl Rupp authored Jul 16, 2013
  defc54c1