Brutex
/
cavis
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
cavis/libnd4j/include/ops/declarable/helpers/cuda
History
shugeo 0eca33ad94
Shugeo cuda solver fix (#383) 
* Refactored cuSolver handle usage to handle LaunchContext instance properly.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored svd solver usage with LaunchContext instance singleton.

Signed-off-by: shugeo <sgazeos@gmail.com>

* add device locks for cuSolver uses

Signed-off-by: raver119 <raver119@gmail.com>

Co-authored-by: raver119 <raver119@gmail.com>
 		2020-04-17 16:52:08 +03:00
..
legacy libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
BarnesHutTsne.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
README.md Merge master to upstream (#7945) 2019-06-27 18:37:04 +03:00
activations.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
addBias.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
adjust_hue.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
adjust_saturation.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
axis.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
batched_gemm.cu Nullify (#304) 2020-03-20 08:49:28 +03:00
batchnorm.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
betaInc.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
col2im.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
compare_elem.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
concat.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
confusion.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
convolutions_col2vol.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_conv2d.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_conv2dBP.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_depthwiseConv2d.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_depthwiseConv2dBP.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_pooling2d.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_pooling2dBP.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_pooling3d.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_pooling3dBP.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_sconv2d.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_upsampling2d.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_upsampling2dBP.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_upsampling3d.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_upsampling3dBP.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
convolutions_vol2col.cu Split convolutions implementations for compilation speed up (#339) 2020-03-23 07:30:26 +03:00
cross.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
d_t_s.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
diGamma.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
diag.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
dilation2d.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
dropout.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
dynamic.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
extract_patches.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
fake_quantization.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
flatten.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
gather.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
gather_nd.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
gradient.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
hamming.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
hashcode.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
histogram.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
histogramFixedWidth.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
im2col.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
image_draw_bounding_boxes.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
image_resize.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
image_suppression.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
imagesHelpers.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
ismax.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
legacy_helper.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
lgamma.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
lrn.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
lstm.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
lstsq.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
lup.cu Shugeo cuda solver fix (#383) 2020-04-17 16:52:08 +03:00
matrixSetDiag.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
matrix_band.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
matrix_diag_part.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
max_pooling.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
maximum.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
merge.cu Backpropagation implementation of mergemax, mergeadd and mergeavg ops (#343) 2020-03-25 08:40:30 +03:00
meshgrid.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
minimum.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
nth_element.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
one_hot.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
pad.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
percentile.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
polyGamma.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
prefix.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
print_variable.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
qr.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
random.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
random_crop.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
range.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
reverse.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
roll.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
s_t_b.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
s_t_d.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
scatter.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
scatter_simple.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
scatter_update.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
segment.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
segment_max.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
segment_mean.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
segment_min.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
segment_prod.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
segment_sqrtn.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
segment_sum.cu libnd4j fixes for context sync in operation execution (#350) 2020-03-30 16:33:51 +03:00
sequence_mask.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
sg_cb.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
shift.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
solve.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
split.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
sru.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
stack.cu profiling of stack and unstack ops (#261) 2020-03-03 07:32:37 +03:00
svd.cu Shugeo cuda solver fix (#383) 2020-04-17 16:52:08 +03:00
toggle_bits.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
top_k.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
transforms.cu [WIP] Shyrma coords (#305) 2020-03-11 16:21:59 +03:00
triangular_solve.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
updaterAdaDelta.cu Learning updaters for gradient (#335) 2020-03-23 07:28:31 +03:00
updaterAdaGrad.cu Learning updaters for gradient (#335) 2020-03-23 07:28:31 +03:00
updaterAdaMax.cu Learning updaters for gradient (#335) 2020-03-23 07:28:31 +03:00
updaterAdam.cu Learning updaters for gradient (#335) 2020-03-23 07:28:31 +03:00
updaterAmsGrad.cu Learning updaters for gradient (#335) 2020-03-23 07:28:31 +03:00
updaterNadam.cu Learning updaters for gradient (#335) 2020-03-23 07:28:31 +03:00
updaterNesterovs.cu Learning updaters for gradient (#335) 2020-03-23 07:28:31 +03:00
updaterRmsProp.cu Learning updaters for gradient (#335) 2020-03-23 07:28:31 +03:00
weights.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
zeta.cu libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00

README.md

This folder contains CUDA-specific implementations for operations.