mlearning: CMSIS NN: add support for the CHW tensor layout

- support float version of convolution
 - support the CHW tensor layout

following function prototypes are added:
 - arm_convolve_CHW_f32_basic_nonsquare()
 - arm_convolve_CHW_q15_basic_nonsquare()
 - arm_convolve_CHW_q7_basic_nonsquare()
 - arm_nn_CHW_mat_mult_kernel_q7_q15()

NOTE:this patch will be contributed to SMSIS and reverted later from NuttX
Signed-off-by: Alin Jerpelea <alin.jerpelea@sony.com>
This commit is contained in:
Alin Jerpelea 2022-02-18 08:50:04 +00:00 committed by Xiang Xiao
parent a6773a8412
commit 02a50ccb1f
2 changed files with 1108 additions and 0 deletions

View File

@ -24,6 +24,7 @@ cmsis.zip:
$(Q) curl -L https://github.com/ARM-software/CMSIS_5/archive/refs/tags/$(CONFIG_CMSIS_VER).zip -o cmsis.zip
$(Q) unzip -o cmsis.zip
$(Q) mv CMSIS_5-$(CONFIG_CMSIS_VER) CMSIS_5
$(Q) patch -p0 < cmsis-nn-support_nnabla.patch
context:: cmsis.zip

File diff suppressed because it is too large Load Diff