Chen Fu 1c84621020 Adding ARM64 depthwise convolution kernel for symmetric quantization (#9655) ... Adding ARM64 depthwise convolution kernel for symmetric quantization Motivation and Context Two improvements against current kernel code : 1. Signed int8 based instructions, no need to extend from 8b to 16b before multiplication. 2. Unrolled loop with manual software pipelining Co-authored-by: Chen Fu <fuchen@microsoft.com>		2021-11-15 12:18:43 -08:00
..
__init__.py
build_full_ort_and_create_ort_files.sh	Add build.py option to disable ORT format model runtime optimization (#9723)	2021-11-11 18:05:45 -08:00
build_minimal_ort_and_run_tests.sh	Bring code coverage dashboard back (#8394)	2021-08-16 20:54:39 -07:00
build_minimal_ort_android_baseline_and_report_bin_size.sh	Adding ARM64 depthwise convolution kernel for symmetric quantization (#9655)	2021-11-15 12:18:43 -08:00
check_build_binary_size.py
nnapi_minimal_build_minimal_ort_and_run_tests.sh	Build shared host protoc in iOS CI pipelines (#9087)	2021-09-16 17:16:50 -07:00
readelf_utils.py