Sanjay Patel 74007202a3 [LoopStrengthReduce, x86] don't add cost for a cmp that will be macro-fused (PR35681) ...

In the motivating case from PR35681 and represented by the macro-fuse-cmp test:
https://bugs.llvm.org/show_bug.cgi?id=35681
...there's a 37 -> 31 byte size win for the loop because we eliminate the big base 
address offsets.

SPEC2017 on Ryzen shows no significant perf difference.

Differential Revision: https://reviews.llvm.org/D42607



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@324289 91177308-0d34-0410-b5e6-96231b3b80d8

2018-02-05 23:43:05 +00:00

..

2008-08-14-ShadowIV.ll

[LSR] Fix Shadow IV in case of integer overflow

2017-08-29 07:32:20 +00:00

2009-11-10-LSRCrash.ll

…

2011-07-20-DoubleIV.ll

Make DataLayout Non-Optional in the Module

2015-03-04 18:43:29 +00:00

2011-11-29-postincphi.ll

…

2011-12-04-loserreg.ll

[opaque pointer type] Add textual IR support for explicit type parameter to load instruction

2015-02-27 21:17:42 +00:00

2012-01-13-phielim.ll

Fix testcases failing after r284036

2016-10-12 20:39:33 +00:00

bin_power.ll

[SCEV] Teach SCEVExpander to expand BinPow

2017-06-19 06:24:53 +00:00

canonical-2.ll

[LSR] Call canonicalize after we generate a new Formula in GenerateTruncates. Fix PR33077.

2017-05-18 17:21:22 +00:00

canonical.ll

Reapply fix PR23384 (part 3 of 3) r304824 (was reverted in r305720).

2017-08-07 19:56:34 +00:00

incorrect-offset-scaling.ll

Re-enable "[SCEV] Do not fold dominated SCEVUnknown into AddRecExpr start"

2017-05-26 06:47:04 +00:00

ivchain-stress-X86.ll

[TwoAddressInstructionPass] When looking for a 3 addr conversion after commuting, make sure regB has been updated to take into account the commute.

2015-10-06 05:39:59 +00:00

ivchain-X86.ll

[LoopStrengthReduce, x86] don't add cost for a cmp that will be macro-fused (PR35681)

2018-02-05 23:43:05 +00:00

lit.local.cfg

Reduce verbiage of lit.local.cfg files

2014-06-09 22:42:55 +00:00

lsr-expand-quadratic.ll

Reapply fix PR23384 (part 3 of 3) r304824 (was reverted in r305720).

2017-08-07 19:56:34 +00:00

lsr-filtering-scaledreg.ll

[LSR] Narrow search space by filtering non-optimal formulae with the same ScaledReg and Scale.

2017-07-06 15:52:14 +00:00

lsr-insns-1.ll

[x86] auto-generate complete checks; NFC

2018-01-26 22:06:07 +00:00

lsr-insns-2.ll

Reapply fix PR23384 (part 3 of 3) r304824 (was reverted in r305720).

2017-08-07 19:56:34 +00:00

macro-fuse-cmp.ll

[LoopStrengthReduce, x86] don't add cost for a cmp that will be macro-fused (PR35681)

2018-02-05 23:43:05 +00:00

nested-loop.ll

[LSR] Don't force bases of foldable formulae to the final type.

2018-02-01 06:38:34 +00:00

no_superflous_induction_vars.ll

[opaque pointer type] Add textual IR support for explicit type parameter to load instruction

2015-02-27 21:17:42 +00:00

pr17473.ll

[opaque pointer type] Add textual IR support for explicit type parameter to the call instruction

2015-04-16 23:24:18 +00:00

pr28719.ll

[SCEV] Update interface to handle SCEVExpander insert point motion.

2016-08-11 21:05:17 +00:00

sibling-loops.ll

[LSR] Prevent formula with SCEVAddRecExpr type of Reg from Sibling loops

2017-02-16 21:27:31 +00:00