Disable hoisting MI to hotter basic blocks when using pgo

[NeHuang]

Summary

This is a follow up patch for https://reviews.llvm.org/D63676. With the feature enabled for pgo, we confirmed performance gain for SPEC benchmarks on PPC.

[NeHuang]

Ping.

[davidxl]

Can you share the performance data ?

[NeHuang]

@davidxl We found SPEC2017 performance gain for PPC. Some experiments results available at https://reviews.llvm.org/D63676

[davidxl]

lgtm

llvm/lib/CodeGen/MachineLICM.cpp

BlockFrequencyRatioThreshold("block-freq-ratio-threshold",
                              cl::init(100), cl::Hidden);
 
 enum class UseBFI { None, PGO, All };
 
 static cl::opt<UseBFI>
 DisableHoistingToHotterBlocks("disable-hoisting-to-hotter-blocks",
                               cl::desc("Disable hoisting instructions to"
                               " hotter blocks"),
-                              cl::init(UseBFI::None), cl::Hidden,
+                              cl::init(UseBFI::PGO), cl::Hidden,
                               cl::values(clEnumValN(UseBFI::None, "none",
                               "disable the feature"),
                               clEnumValN(UseBFI::PGO, "pgo",
                               "enable the feature when using profile data"),
                               clEnumValN(UseBFI::All, "all",
                               "enable the feature with/wo profile data")));
 
 STATISTIC(NumHoisted,

llvm/test/CodeGen/AArch64/O3-pipeline.ll

 ; CHECK-NEXT:       AArch64 Conditional Branch Tuning
 ; CHECK-NEXT:       Machine Trace Metrics
 ; CHECK-NEXT:       Early If-Conversion
 ; CHECK-NEXT:       AArch64 Store Pair Suppression
 ; CHECK-NEXT:       AArch64 SIMD instructions optimization pass
 ; CHECK-NEXT:       AArch64 Stack Tagging PreRA
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Natural Loop Construction
+; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       Early Machine Loop Invariant Code Motion
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Common Subexpression Elimination
 ; CHECK-NEXT:       MachinePostDominator Tree Construction
 ; CHECK-NEXT:       Machine code sinking
 ; CHECK-NEXT:       Peephole Optimizations
 ; CHECK-NEXT:       Remove dead machine instructions

llvm/test/CodeGen/ARM/O3-pipeline.ll

 ; CHECK-NEXT:      Early Tail Duplication
 ; CHECK-NEXT:      Optimize machine instruction PHIs
 ; CHECK-NEXT:      Slot index numbering
 ; CHECK-NEXT:      Merge disjoint stack slots
 ; CHECK-NEXT:      Local Stack Slot Allocation
 ; CHECK-NEXT:      Remove dead machine instructions
 ; CHECK-NEXT:      MachineDominator Tree Construction
 ; CHECK-NEXT:      Machine Natural Loop Construction
+; CHECK-NEXT:      Machine Block Frequency Analysis
 ; CHECK-NEXT:      Early Machine Loop Invariant Code Motion
 ; CHECK-NEXT:      MachineDominator Tree Construction
 ; CHECK-NEXT:      Machine Block Frequency Analysis
 ; CHECK-NEXT:      Machine Common Subexpression Elimination
 ; CHECK-NEXT:      MachinePostDominator Tree Construction
 ; CHECK-NEXT:      Machine code sinking
 ; CHECK-NEXT:      Peephole Optimizations
 ; CHECK-NEXT:      Remove dead machine instructions

llvm/test/CodeGen/X86/opt-pipeline.ll

 ; CHECK-NEXT:       Machine Natural Loop Construction
 ; CHECK-NEXT:       Machine Trace Metrics
 ; CHECK-NEXT:       Early If-Conversion
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine InstCombiner
 ; CHECK-NEXT:       X86 cmov Conversion
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Natural Loop Construction
+; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       Early Machine Loop Invariant Code Motion
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Common Subexpression Elimination
 ; CHECK-NEXT:       MachinePostDominator Tree Construction
 ; CHECK-NEXT:       Machine code sinking
 ; CHECK-NEXT:       Peephole Optimizations
 ; CHECK-NEXT:       Remove dead machine instructions