Li Peng 145eae321e pooling ocl kernel optimization ... set global size with real output size, also optimize max pooling index computation if necessary. Signed-off-by: Li Peng <peng.li@intel.com>		2018-06-29 15:22:49 +08:00
..
activations.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
batchnorm.cl	fp16 ocl support for more layers	2018-05-16 22:45:04 +08:00
col2im.cl	ocl support for Deconvolution layer	2018-01-18 23:40:22 +08:00
concat.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
conv_layer_spatial.cl	update convolution opencl kernels in dnn module (#11762)	2018-06-25 17:06:18 +03:00
conv_spatial_helper.cl
detection_output.cl	ocl fix for detection_output and prior_box layer	2018-02-13 23:09:14 +08:00
dummy.cl
eltwise.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
gemm_buffer.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
gemm_image.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
im2col.cl
lrn.cl
math.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
matvec_mul.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
mvn.cl	make ocl4dnn available to run on other platform than Intel GPU	2018-05-29 19:18:10 +09:00
ocl4dnn_lrn.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
ocl4dnn_pooling.cl	pooling ocl kernel optimization	2018-06-29 15:22:49 +08:00
permute.cl	fp16 ocl support for more layers	2018-05-16 22:45:04 +08:00
pooling.cl
prior_box.cl	fp16 ocl support for more layers	2018-05-16 22:45:04 +08:00
region.cl	region layer ocl implementation	2017-12-07 02:26:46 +08:00
reorg.cl	fp16 ocl support for more layers	2018-05-16 22:45:04 +08:00
slice.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
softmax_loss.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00
softmax.cl	fp16 ocl support for googlenet	2018-05-16 22:45:02 +08:00