* Improve argsort performance.

- Give 200000 data to compute argsort on v100,
can speed up ~190x
before opt cost: 0.53s
after opt cost:0.0027s

- Add fp16 support

* Refine error message
* Refine code

test=develop
Signed-off-by: Nzhaoyuchen <zhaoyuchen01@baidu.com>