projects / platform / core / ml / nntrainer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 9c8decb) | patch
[GPU/OpenCL] Initial version of RMSNorm Layer
authorThummalaPallavi <t.pallavi@samsung.com>
Tue, 11 Jun 2024 09:24:49 +0000 (14:54 +0530)
committerJijoong Moon <jijoong.moon@samsung.com>
Wed, 10 Jul 2024 04:36:32 +0000 (13:36 +0900)
commite0055018b1a096cafae54db513af43957a0e86ac
tree5a39d1cd874dfc15a69106ec912c86fc25528497tree | snapshot
parent9c8decb4f5af9948b253e2dd2bc685868b300118commit | diff
[GPU/OpenCL] Initial version of RMSNorm Layer

Added naive version of OpenCL implementation for RMSNorm Layer.
Incorporated kernel for ops used.
Added unit test for rmsnorm_layer_cl.

Signed-off-by: ThummalaPallavi <t.pallavi@samsung.com>
api/ccapi/include/layer.h diff | blob | history
api/nntrainer-api-common.h diff | blob | history
nntrainer/cl_context.cpp diff | blob | history
nntrainer/layers/cl_layers/meson.build diff | blob | history
nntrainer/layers/cl_layers/rmsnorm_layer_cl.cpp [new file with mode: 0644] blob
nntrainer/layers/cl_layers/rmsnorm_layer_cl.h [new file with mode: 0644] blob
nntrainer/layers/layer_context.cpp diff | blob | history
nntrainer/layers/layer_context.h diff | blob | history
test/input_gen/gen_layer_tests.py diff | blob | history
test/jni/Android.mk diff | blob | history
test/unittest/layers/unittest_layers_rmsnorm_cl.cpp [new file with mode: 0644] blob
Domain: Machine Learning / ML Framework;