[all-commits] [llvm/llvm-project] 765348: [CostModel] Update default cost model for sadd/ssu...

[Craig Topper via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 765348298c52bcff7c33d766cda954c3371a700f
      https://github.com/llvm/llvm-project/commit/765348298c52bcff7c33d766cda954c3371a700f
  Author: Craig Topper <craig.topper at sifive.com>
  Date:   2021-09-30 (Thu, 30 Sep 2021)

  Changed paths:
    M llvm/include/llvm/CodeGen/BasicTTIImpl.h
    M llvm/test/Analysis/CostModel/AArch64/arith-ssat.ll
    M llvm/test/Analysis/CostModel/ARM/arith-overflow.ll
    M llvm/test/Analysis/CostModel/ARM/arith-ssat.ll
    M llvm/test/Analysis/CostModel/X86/arith-overflow.ll
    M llvm/test/Analysis/CostModel/X86/arith-ssat.ll
    M llvm/test/Transforms/LoopVectorize/AArch64/intrinsiccost.ll
    M llvm/test/Transforms/LoopVectorize/ARM/mve-saddsatcost.ll

  Log Message:
  -----------
  [CostModel] Update default cost model for sadd/ssub overflow to match TargetLowering

The expansion for these was updated in https://reviews.llvm.org/D47927 but the cost model was not adjusted.

I believe the cost model was also incorrect for the old expansion.
The expansion prior to D47927 used 3 icmps using LHS, RHS, and Result
to calculate theirs signs. Then 2 icmps to compare the signs. Followed
by an And. The previous cost model was using 3 icmps and 2 selects.
Digging back through git blame, those 2 selects in the cost model used to
be 2 icmps, but were changed in https://reviews.llvm.org/D90681

Differential Revision: https://reviews.llvm.org/D110739