Esme-Yi e9fd8823ba [DAGCombiner] Add decomposition patterns for Mul-by-Imm.
Summary: This patch is derived from D87384.
In this patch we expand the existing decomposition of mul-by-constant to be more general by implementing 2 patterns:
```
  mul x, (2^N + 2^M) --> (add (shl x, N), (shl x, M))
  mul x, (2^N - 2^M) --> (sub (shl x, N), (shl x, M))
```
The conversion will be trigged if the multiplier is a big constant that the target can't use a single multiplication instruction to handle. This is controlled by the hook `decomposeMulByConstant`.
More over, the conversion benefits from an ILP improvement since the instructions are independent. A case with the sequence like following also gets benefit since a shift instruction is saved.

```
*res1 = a * 0x8800;
*res2 = a * 0x8080;
```

Reviewed By: spatel

Differential Revision: https://reviews.llvm.org/D88201
2020-10-09 08:51:40 +00:00
..
2018-09-07 07:56:05 +00:00
2020-03-19 08:34:48 -05:00
2019-03-29 17:35:56 +00:00
2017-10-10 08:46:10 +00:00
2020-07-31 22:42:57 -05:00
2020-06-01 02:30:27 +00:00