metal : add POOL2D and fix IM2COL (#9943)
* add pool_2d
Signed-off-by: Junhee Yoo <[email protected]>
* fix im2col and add unittest for N>=1024
Signed-off-by: Junhee Yoo <[email protected]>
* add tests for N % 1024 != 0
Signed-off-by: Junhee Yoo <[email protected]>
* remove trailing whitespaces
Signed-off-by: Junhee Yoo <[email protected]>
* apply suggestions
Signed-off-by: Junhee Yoo <[email protected]>
* apply more optimization
- original IM2COL kernel + _ext with MIN()
Signed-off-by: Junhee Yoo <[email protected]>
* apply review: change kernel name of pool_2d
Signed-off-by: Junhee Yoo <[email protected]>
* apply review
Signed-off-by: Junhee Yoo <[email protected]>
* fix more formatting and enhance readability
Signed-off-by: Junhee Yoo <[email protected]>
---------
Signed-off-by: Junhee Yoo <[email protected]>
