Merge branch 'fix_apu' into 'master'

fix: fix so file selection error and op type selection errors on apu runtime

See merge request applied-machine-learning/sysml/mace!1341

Merge branch 'buffer_transform' into 'master'

fix: fix the GPU buffer transform error

See merge request applied-machine-learning/sysml/mace!1335

Merge branch 'fp16' into 'master'

Fix fp16 delegator register

See merge request applied-machine-learning/sysml/mace!1318

Merge branch 'armhf' into 'master'

fix: change the armlinux abi from armeabi-v7a to armhf

See merge request deep-computing/mace!1260

Merge branch 'lp_normalization' into 'master'

add lpnorm、mvnorm op for caffe, enhance biasadd、reshape op

See merge request !1224

1. Remove unimplemented gpu matmul.

2. Fix the length of abbreviated commit id in MACE version.
3. Fix some bugs.