Implement TTI getUnrollingPreferences for PowerPC

The PowerPC A2 core greatly benefits from aggressive concatenation unrolling;
use the new getUnrollingPreferences to enable this by default when targeting
the PPC A2 core.

llvm-svn: 190549

3 files changed, 61 insertions, 0 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index 2504ba70c25..8879630270e 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -77,6 +77,7 @@ public:
   /// \name Scalar TTI Implementations
   /// @{
   virtual PopcntSupportKind getPopcntSupport(unsigned TyWidth) const;
+  virtual void getUnrollingPreferences(Loop *L, UnrollingPreferences &UP) const;
 
   /// @}
 
@@ -129,6 +130,14 @@ PPCTTI::PopcntSupportKind PPCTTI::getPopcntSupport(unsigned TyWidth) const {
   return PSK_Software;
 }
 
+void PPCTTI::getUnrollingPreferences(Loop *L, UnrollingPreferences &UP) const {
+  if (ST->getDarwinDirective() == PPC::DIR_A2) {
+    // The A2 is in-order with a deep pipeline, and concatenation unrolling
+    // helps expose latency-hiding opportunities to the instruction scheduler.
+    UP.Partial = UP.Runtime = true;
+  }
+}
+
 unsigned PPCTTI::getNumberOfRegisters(bool Vector) const {
   if (Vector && !ST->hasAltivec())
     return 0;
diff --git a/llvm/test/Transforms/LoopUnroll/PowerPC/a2-unrolling.ll b/llvm/test/Transforms/LoopUnroll/PowerPC/a2-unrolling.ll
new file mode 100644
index 00000000000..17c91e5c07b
--- /dev/null
+++ b/llvm/test/Transforms/LoopUnroll/PowerPC/a2-unrolling.ll
@@ -0,0 +1,48 @@
+; RUN: opt < %s -S -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 -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: icmp
+
+define i32 @test(i32* nocapture %a, i32 %n) nounwind uwtable readonly {
+entry:
+  %cmp1 = icmp eq i32 %n, 0
+  br i1 %cmp1, label %for.end, label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %sum.02
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  ret i32 %sum.0.lcssa
+}
+
+; CHECK-LABEL: @test
+; CHECK: unr.cmp{{.*}}:
+; CHECK: for.body.unr{{.*}}:
+; CHECK: for.body:
+; CHECK: br i1 %exitcond.7, label %for.end.loopexit{{.*}}, label %for.body
+
diff --git a/llvm/test/Transforms/LoopUnroll/PowerPC/lit.local.cfg b/llvm/test/Transforms/LoopUnroll/PowerPC/lit.local.cfg
new file mode 100644
index 00000000000..2e463005586
--- /dev/null
+++ b/llvm/test/Transforms/LoopUnroll/PowerPC/lit.local.cfg
@@ -0,0 +1,4 @@
+targets = set(config.root.targets_to_build.split())
+if not 'PowerPC' in targets:
+    config.unsupported = True
+