Signed-off-by: zhoufeng <zhoufeng54@huawei.com>

From: @zhaozhenlong
Reviewed-by: @zhanghaibo5,@zhang_xue_tong
Signed-off-by: @zhang_xue_tong

From: @laiyongqiang
Reviewed-by: 
Signed-off-by:

From: @zhangbuxue
Reviewed-by: @ginfung,@zh_qh
Signed-off-by: @zh_qh

From: @zhouneng2
Reviewed-by: @linqingke,@liangchenghui
Signed-off-by: @linqingke

From: @shibeiji
Reviewed-by: @liangchenghui,@liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui,@liangchenghui

From: @lijiaqi0612
Reviewed-by: 
Signed-off-by:

From: @c_34
Reviewed-by: @ljl0711,@liangchenghui
Signed-off-by: @liangchenghui

From: @yeyunpeng2020
Reviewed-by: 
Signed-off-by:

From: @ling_qiao_min
Reviewed-by: 
Signed-off-by:

From: @kisnwang
Reviewed-by: @zhoufeng54,@chujinjin
Signed-off-by: @chujinjin

From: @kisnwang
Reviewed-by: 
Signed-off-by:

From: @liubuyu
Reviewed-by: @kisnwang,@zhoufeng54
Signed-off-by: @zhoufeng54

From: @hwjiaorui
Reviewed-by: 
Signed-off-by:

From: @cjh9368
Reviewed-by: @zhanghaibo5
Signed-off-by:

delete clip
unstack to base
unsqueeze to base
batchToSpace to base

From: @david-he91
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui

From: @VectorSL
Reviewed-by: @gaoxiong1,@dylangeng,@anyrenwei
Signed-off-by: @gaoxiong1

this commit reverts the modification for basic_ops_fusion.cc in 8af78cd5c,
the getitem should be fused with its all users.
(no bug. but when the network is large, it works very slowly, this's a temporary solution)

From: @gaojing22
Reviewed-by: @wuxuejian,@linqingke
Signed-off-by: @wuxuejian

From: @dangjiaqi1
Reviewed-by: @wuxuejian,@liangchenghui
Signed-off-by: @liangchenghui

1. add parameter info
2. update atomic clean inputs
3. remove somas_mem_pool.ir

change ways to get physic_logic_ids

From: @wukesong
Reviewed-by: @yingjy
Signed-off-by:

From: @cathwong
Reviewed-by: @nsyca,@robingrosman
Signed-off-by: @nsyca

From: @jonyguo
Reviewed-by: 
Signed-off-by:

From: @xiefangqi
Reviewed-by: @liucunwei,@heleiwang
Signed-off-by: @liucunwei

From: @TFbunny
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @tom__chen

port over tensor_op_fusion pass

add fusion support for prebuildOpeartion (TensorOpeartion)

From: @peilin-wang
Reviewed-by: 
Signed-off-by:

new mul node

new mul node

convert const to attr

From: @lijiaqi0612
Reviewed-by: 
Signed-off-by: