1. 13 4月, 2022 1 次提交
  2. 07 4月, 2022 1 次提交
  3. 01 4月, 2022 1 次提交
  4. 14 3月, 2022 1 次提交
  5. 28 2月, 2022 1 次提交
    • Z
      Add sparse conv3d kernel (#39879) · bc99a76c
      zhangkaihuo 提交于
      * fix incorrect dims settings
      
      * sparse conv3d
      
      * fix out dims
      
      * test performance
      
      * test large shape success
      
      * opt scatter, double performance
      
      * test float16
      
      * remove profiling code
      
      * remove pten
      
      * opt code lines
      
      * correct boundary judgment
      
      * only cpu
      
      * test ci
      
      * test ci
      
      * remove the including paddle/fluid header; extract the conmmon function
      
      * opt code lines
      
      * use DenseTensor::data() instead of mutable_data
      
      * return rulebook for backward
      
      * specify layout
      
      * rename:conv -> sparse_conv3d
      bc99a76c
  6. 22 2月, 2022 2 次提交
  7. 20 2月, 2022 1 次提交
  8. 10 2月, 2022 1 次提交
  9. 09 2月, 2022 3 次提交
    • Z
      【Pten】Adjust the Empyt dev_api (#39143) · 9d4d0c3b
      zyfncg 提交于
      * adjust the Empyt dev_api
      
      * fix merge conflict
      
      * fix sparse_utils_kernel
      9d4d0c3b
    • Z
      Add a Sparse Op to_dense (#39335) · aca86470
      zhangkaihuo 提交于
      * implement AllocateFrom
      
      * dense_to_sparse_coo
      
      * optimize unit testing; support rocm
      
      * 1. delete fluid related header file
      2. update the copyright
      
      * fix hipMemcpy
      
      * update dense_to_sparsecoo
      
      * add namespace sparse
      
      * sparse_csr_to_dense
      
      * test to_sparse_coo: csr_to_coo
      
      * fix writing error
      
      * to_sparse_csr: dense_to_sparse_csr and sparse_coo_to_csr
      
      * fix check shape
      
      * fix unit test
      
      * to_dense: sparse_coo_to_dense, sparse_csr_to_dense
      
      * replace CUDADeviceContext by GPUContext
      aca86470
    • Z
      Add a Sparse Op: to_sparse_csr (#39333) · 76d527e1
      zhangkaihuo 提交于
      * implement AllocateFrom
      
      * dense_to_sparse_coo
      
      * optimize unit testing; support rocm
      
      * 1. delete fluid related header file
      2. update the copyright
      
      * fix hipMemcpy
      
      * update dense_to_sparsecoo
      
      * add namespace sparse
      
      * sparse_csr_to_dense
      
      * test to_sparse_coo: csr_to_coo
      
      * fix writing error
      
      * to_sparse_csr: dense_to_sparse_csr and sparse_coo_to_csr
      
      * fix check shape
      
      * fix unit test
      
      * replace CUDADeviceContext by GPUContext
      76d527e1
  10. 30 1月, 2022 2 次提交
    • Z
      Add a Sparse OP:sparse_csr_to_coo (#39266) · bafea65c
      zhangkaihuo 提交于
      * dense_to_sparse_coo
      
      * optimize unit testing; support rocm
      
      * 1. delete fluid related header file
      2. update the copyright
      
      * fix hipMemcpy
      
      * update dense_to_sparsecoo
      
      * add namespace sparse
      
      * sparse_csr_to_dense
      
      * test to_sparse_coo: csr_to_coo
      
      * fix writing error
      bafea65c
    • Z
      Add a Sparse OP : to_sparse_coo (#39264) · 78132fe1
      zhangkaihuo 提交于
      * dense_to_sparse_coo
      
      * optimize unit testing; support rocm
      
      * 1. delete fluid related header file
      2. update the copyright
      
      * fix hipMemcpy
      
      * update dense_to_sparsecoo
      
      * add namespace sparse
      78132fe1