[PowerPC] Enable late partial unrolling on the POWER7

The P7 benefits from not have really-small loops so that we either have
multiple dispatch groups in the loop and/or the ability to form more-full
dispatch groups during scheduling. Setting the partial unrolling threshold to
44 seems good, empirically, for the P7. Compared to using no late partial
unrolling, this yields the following test-suite speedups:

SingleSource/Benchmarks/Adobe-C++/simple_types_constant_folding
	-66.3253% +/- 24.1975%
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
	-44.0169% +/- 29.4881%
SingleSource/Benchmarks/Misc/pi
	-27.8351% +/- 12.2712%
SingleSource/Benchmarks/Stanford/Bubblesort
	-30.9898% +/- 22.4647%

I've speculatively added a similar setting for the P8. Also, I've noticed that
the unroller does not quite calculate the unrolling factor correctly for really
tiny loops because it neglects to account for the fact that not every loop body
replicant contains an ending branch and counter increment. I'll fix that later.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225522 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/PowerPC/PPCScheduleP7.td

@@ -380,6 +380,9 @@ def P7Model : SchedMachineModel {
                        // Itineraries are queried instead.
   let MispredictPenalty = 16;
 
+  // Try to make sure we have at least 10-11 dispatch groups in a loop.
+  let LoopMicroOpBufferSize = 44;
+
   let Itineraries = P7Itineraries;
 }
 

lib/Target/PowerPC/PPCScheduleP8.td

@@ -389,6 +389,9 @@ def P8Model : SchedMachineModel {
                        // Itineraries are queried instead.
   let MispredictPenalty = 16;
 
+  // Try to make sure we have at least 10-11 dispatch groups in a loop.
+  let LoopMicroOpBufferSize = 66;
+
   let Itineraries = P8Itineraries;
 }
 

lib/Target/PowerPC/PPCTargetTransformInfo.cpp

@@ -277,6 +277,8 @@ void PPCTTI::getUnrollingPreferences(const Function *F, Loop *L,
     // helps expose latency-hiding opportunities to the instruction scheduler.
     UP.Partial = UP.Runtime = true;
   }
+
+  TargetTransformInfo::getUnrollingPreferences(F, L, UP);
 }
 
 unsigned PPCTTI::getNumberOfRegisters(bool Vector) const {

test/Transforms/LoopUnroll/PowerPC/p7-unrolling.ll

@@ -0,0 +1,51 @@
+; RUN: opt < %s -S -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -loop-unroll | FileCheck %s
+define void @unroll_opt_for_size() nounwind optsize {
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i32 [ 0, %entry ], [ %inc, %loop ]
+  %inc = add i32 %iv, 1
+  %exitcnd = icmp uge i32 %inc, 1024
+  br i1 %exitcnd, label %exit, label %loop
+
+exit:
+  ret void
+}
+
+; CHECK-LABEL: @unroll_opt_for_size
+; CHECK:      add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK: icmp
+
+define void @unroll_default() nounwind {
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i32 [ 0, %entry ], [ %inc, %loop ]
+  %inc = add i32 %iv, 1
+  %exitcnd = icmp uge i32 %inc, 1024
+  br i1 %exitcnd, label %exit, label %loop
+
+exit:
+  ret void
+}
+
+; CHECK-LABEL: @unroll_default
+; CHECK:      add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK: icmp
+