You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
zhujingxuan 28987d787d add trsm 4 years ago
..
addn_gpu_kernel.cc addn int64 support 4 years ago
addn_gpu_kernel.h addn support ND 4 years ago
assign_add_gpu_kernel.cc fix isnan isfinite isinfinite infer type 5 years ago
assign_add_gpu_kernel.h code clean of gpu-math 4 years ago
broadcast_complex_gpu_kernel.cc Add complex ops and bprop of real、conj、imag ops 4 years ago
broadcast_complex_gpu_kernel.h Add complex ops and bprop of real、conj、imag ops 4 years ago
broadcast_gpu_kernel.cc Revert "[feat] [assistant] [I3T96T] add new Dataset operator CMUARCTICDataset" 4 years ago
broadcast_gpu_kernel.h optimize the comment and log description 4 years ago
broadcast_grad_gpu_kernel.cc add float64 support for ops for end of version 1.1 5 years ago
broadcast_grad_gpu_kernel.h add validation of vector size and non-zero validation of denominator for nn gpu operators. 4 years ago
cast_all_gpu_kernel.cc gpu add combine cast fusion 5 years ago
cast_all_gpu_kernel.h Clean up the first batch of static alarms of operator group 4 years ago
cholesky_gpu_kernel.cc add cholesky && lu factorization for gpu backend 4 years ago
cholesky_gpu_kernel.h add cholesky && lu factorization for gpu backend 4 years ago
cholesky_solve_gpu_kernel.cc Add Cholesky op at GPU back-end 5 years ago
cholesky_solve_gpu_kernel.h clean up the static alarms of the second batch of operator groups 4 years ago
cholesky_trsm_solve_gpu_kernel.cc Refactor Cholesky to CholeskyTrsm 5 years ago
cholesky_trsm_solve_gpu_kernel.h Clean up the first batch of static alarms of operator group 4 years ago
cumprod_gpu_kernel.cc add gpu op cumprod, tensor_scatter_add 4 years ago
cumprod_gpu_kernel.h add vector size check, input shape check and divide by zero check for gpu operators. 4 years ago
cumsum_gpu_kernel.cc initial commit 5 years ago
cumsum_gpu_kernel.h clean up the static alarms of the second batch of operator groups 4 years ago
determinant_triangle_gpu_kernel.cc Add calculation of triangle matrix determinant op at GPU back-end 5 years ago
determinant_triangle_gpu_kernel.h clean up the static alarms of the second batch of operator groups 4 years ago
equalcount_gpu_kernel.cc mindspore path adjust 5 years ago
equalcount_gpu_kernel.h clean up the static alarms of the second batch of operator groups 4 years ago
float_status_gpu_kernel.cc change float status output type to float32 5 years ago
float_status_gpu_kernel.h Clean up the first batch of static alarms of operator group 4 years ago
identity_gpu_kernel.cc Add identity op for cpu and gpu 4 years ago
identity_gpu_kernel.h add vector size check, input shape check and divide by zero check for gpu operators. 4 years ago
index_add_gpu_kernel.cc index_add gpu op 5 years ago
index_add_gpu_kernel.h Clean up the first batch of static alarms of operator group 4 years ago
linspace.cc Initial Commit - GPU LinSpace 5 years ago
linspace.h add validation of vector size and non-zero validation of denominator for nn gpu operators. 4 years ago
logical_not_gpu_kernel.cc add some gpu ops after removing akg 4 years ago
logical_not_gpu_kernel.h add validation of vector size and non-zero validation of denominator for nn gpu operators. 4 years ago
lu_gpu_kernel.cc add cholesky && lu factorization for gpu backend 4 years ago
lu_gpu_kernel.h add cholesky && lu factorization for gpu backend 4 years ago
matmul_gpu_kernel.cc gpu matmul biasadd fusion 4 years ago
matmul_gpu_kernel.h add validation of vector size and non-zero validation of denominator for nn gpu operators. 4 years ago
matrix_inverse_gpu_kernel.cc new add matrix inverse. 5 years ago
matrix_inverse_gpu_kernel.h clean up the static alarms of the second batch of operator groups 4 years ago
multinomial_gpu_kernel.cc add multinomial backend 5 years ago
multinomial_gpu_kernel.h clean up the static alarms of the second batch of operator groups 4 years ago
nms_with_mask_gpu_kernel.cc stuff added 5 years ago
nms_with_mask_gpu_kernel.h Clean up the first batch of static alarms of operator group 4 years ago
random_op_gpu_kernel.cc substitute dropout by cudnnuniformreal and dropout 5 years ago
random_op_gpu_kernel.h some bugfix for parameter server cache 4 years ago
square_sum_all_gpu_kernel.cc support squaresumall on gpu 5 years ago
square_sum_all_gpu_kernel.h code clean of gpu-math 4 years ago
squared_difference_kernel.cc fix codex warnings 4 years ago
squared_difference_kernel.h Clean up the first batch of static alarms of operator group 4 years ago
trsm_solve_gpu_kernel.cc add trsm 4 years ago
trsm_solve_gpu_kernel.h add trsm 4 years ago
unary_op_complex_gpu_kernel.cc add gpu complex ops 4 years ago
unary_op_complex_gpu_kernel.h add gpu complex ops 4 years ago
unary_op_gpu_kernel.cc initial commit: fixed python class 4 years ago
unary_op_gpu_kernel.h add vector size check, nullptr check and clean code for gpu operators. 4 years ago
unary_op_grad_gpu_kernel.cc add float64 support to absgrad and sqrtgrad 5 years ago
unary_op_grad_gpu_kernel.h add vector size check, nullptr check and clean code for gpu operators. 4 years ago
update_thor_gradient.cc update thor gradient op 5 years ago
update_thor_gradient.h Clean up the first batch of static alarms of operator group 4 years ago