Improve optimizations for DNNLOWP support on MKL-DNN (pytorch#18843)

Summary:
In this PR, the fusion alogrithms are improved to support DNNLOWP.
1. Enabled conv fusions for DNNLOWP
2. Fused order switch op into following quantize op
3. Improve conv+sum fusion to parse larger scope/window
4. re-org fusion code to fix random crash issue due to changing graph
Pull Request resolved: pytorch#18843

Differential Revision: D15021030

Pulled By: yinghai

fbshipit-source-id: 88d2199d9fc69f392de9bfbe1f291e0ebf78ab08