[PATCH] D52195: [DAGCombiner][x86] add transform/hook to decompose integer multiply into shift/add

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

> The shakiest test diff here may be SSE4.1 code that uses 'pmulld' with a constant pool load. That can become 4 instructions like:

pmullw could be worse - that's often just 2/3cy latency


https://reviews.llvm.org/D52195