Analyze recursive PHI nodes in BasicAA

Summary:
This patch allows phi nodes like
  %x = phi [ %incptr, ... ] [ %var, ... ]
  %incptr = getelementptr %x, 1
to be analyzed by BasicAliasAnalysis.

In aliasPHI, we can detect incoming values that are recursive GEPs with a
constant offset. Instead of trying to analyze a recursive GEP (and failing),
we now ignore it and instead set the size of the memory referenced by
the PHINode to UnknownSize. This represents all the possible memory
locations the pointer represented by the PHINode could be advanced to
by the GEP.

For now, this new behavior is turned off by default to allow debugging of
performance degradations seen with SPEC/x86 and Hexagon benchmarks.
The flag -basicaa-recphi turns it on.

Reviewers: hfinkel, sanjoy

Subscribers: tobiasvk_caf, sanjoy, llvm-commits

Differential Revision: http://reviews.llvm.org/D10368

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@242320 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Analysis/BasicAliasAnalysis.cpp b/lib/Analysis/BasicAliasAnalysis.cpp
index 68f766edb301342eedc8c2f23910bdbf6e2db8d0..06e600e8835388b465d2e29e8d02bc1159bcb001 100644 (file)
--- a/lib/Analysis/BasicAliasAnalysis.cpp
+++ b/lib/Analysis/BasicAliasAnalysis.cpp
@@ -42,6 +42,10 @@
 #include <algorithm>
 using namespace llvm;
 
+/// Enable analysis of recursive PHI nodes.
+static cl::opt<bool> EnableRecPhiAnalysis("basicaa-recphi",
+                                          cl::Hidden, cl::init(false));
+
 /// Cutoff after which to stop analysing a set of phi nodes potentially involved
 /// in a cycle. Because we are analysing 'through' phi nodes we need to be
 /// careful with value equivalence. We use reachability to make sure a value
@@ -1297,6 +1301,7 @@ AliasResult BasicAliasAnalysis::aliasPHI(const PHINode *PN, uint64_t PNSize,
 
   SmallPtrSet<Value*, 4> UniqueSrc;
   SmallVector<Value*, 4> V1Srcs;
+  bool isRecursive = false;
   for (Value *PV1 : PN->incoming_values()) {
     if (isa<PHINode>(PV1))
       // If any of the source itself is a PHI, return MayAlias conservatively
@@ -1304,12 +1309,33 @@ AliasResult BasicAliasAnalysis::aliasPHI(const PHINode *PN, uint64_t PNSize,
       // sides are PHI nodes. In which case, this is O(m x n) time where 'm'
       // and 'n' are the number of PHI sources.
       return MayAlias;
+
+    if (EnableRecPhiAnalysis)
+      if (GEPOperator *PV1GEP = dyn_cast<GEPOperator>(PV1)) {
+        // Check whether the incoming value is a GEP that advances the pointer
+        // result of this PHI node (e.g. in a loop). If this is the case, we
+        // would recurse and always get a MayAlias. Handle this case specially
+        // below.
+        if (PV1GEP->getPointerOperand() == PN && PV1GEP->getNumIndices() == 1 &&
+            isa<ConstantInt>(PV1GEP->idx_begin())) {
+          isRecursive = true;
+          continue;
+        }
+      }
+
     if (UniqueSrc.insert(PV1).second)
       V1Srcs.push_back(PV1);
   }
 
+  // If this PHI node is recursive, set the size of the accessed memory to
+  // unknown to represent all the possible values the GEP could advance the
+  // pointer to.
+  if (isRecursive)
+    PNSize = MemoryLocation::UnknownSize;
+
   AliasResult Alias = aliasCheck(V2, V2Size, V2AAInfo,
                                  V1Srcs[0], PNSize, PNAAInfo);
+
   // Early exit if the check of the first PHI source against V2 is MayAlias.
   // Other results are not possible.
   if (Alias == MayAlias)

diff --git a/test/Analysis/BasicAA/phi-loop.ll b/test/Analysis/BasicAA/phi-loop.ll
new file mode 100644 (file)
index 0000000..6337bfb
--- /dev/null
+++ b/test/Analysis/BasicAA/phi-loop.ll
@@ -0,0 +1,75 @@
+; RUN: opt < %s -basicaa -basicaa-recphi=1 -gvn -S | FileCheck %s
+;
+; Check that section->word_ofs doesn't get reloaded in every iteration of the
+; for loop.
+;
+; Code:
+;
+; typedef struct {
+;   unsigned num_words;
+;   unsigned word_ofs;
+;   const unsigned *data;
+; } section_t;
+; 
+; 
+; void test2(const section_t * restrict section, unsigned * restrict dst) {;
+;   while (section->data != NULL) {
+;     const unsigned *src = section->data;
+;     for (unsigned i=0; i < section->num_words; ++i) {
+;       dst[section->word_ofs + i] = src[i];
+;     }   
+; 
+;     ++section;
+;   }
+; }
+; 
+
+; CHECK-LABEL: for.body:
+; CHECK-NOT: load i32, i32* %word_ofs
+
+%struct.section_t = type { i32, i32, i32* }
+
+define void @test2(%struct.section_t* noalias nocapture readonly %section, i32* noalias nocapture %dst) {
+entry:
+  %data13 = getelementptr inbounds %struct.section_t, %struct.section_t* %section, i32 0, i32 2
+  %0 = load i32*, i32** %data13, align 4
+  %cmp14 = icmp eq i32* %0, null
+  br i1 %cmp14, label %while.end, label %for.cond.preheader
+
+for.cond.preheader:                               ; preds = %entry, %for.end
+  %1 = phi i32* [ %6, %for.end ], [ %0, %entry ]
+  %section.addr.015 = phi %struct.section_t* [ %incdec.ptr, %for.end ], [ %section, %entry ]
+  %num_words = getelementptr inbounds %struct.section_t, %struct.section_t* %section.addr.015, i32 0, i32 0
+  %2 = load i32, i32* %num_words, align 4
+  %cmp211 = icmp eq i32 %2, 0
+  br i1 %cmp211, label %for.end, label %for.body.lr.ph
+
+for.body.lr.ph:                                   ; preds = %for.cond.preheader
+  %word_ofs = getelementptr inbounds %struct.section_t, %struct.section_t* %section.addr.015, i32 0, i32 1
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.body
+  %arrayidx.phi = phi i32* [ %1, %for.body.lr.ph ], [ %arrayidx.inc, %for.body ]
+  %i.012 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
+  %3 = load i32, i32* %arrayidx.phi, align 4
+  %4 = load i32, i32* %word_ofs, align 4
+  %add = add i32 %4, %i.012
+  %arrayidx3 = getelementptr inbounds i32, i32* %dst, i32 %add
+  store i32 %3, i32* %arrayidx3, align 4
+  %inc = add i32 %i.012, 1
+  %5 = load i32, i32* %num_words, align 4
+  %cmp2 = icmp ult i32 %inc, %5
+  %arrayidx.inc = getelementptr i32, i32* %arrayidx.phi, i32 1
+  br i1 %cmp2, label %for.body, label %for.end
+
+for.end:                                          ; preds = %for.body, %for.cond.preheader
+  %incdec.ptr = getelementptr inbounds %struct.section_t, %struct.section_t* %section.addr.015, i32 1
+  %data = getelementptr inbounds %struct.section_t, %struct.section_t* %section.addr.015, i32 1, i32 2
+  %6 = load i32*, i32** %data, align 4
+  %cmp = icmp eq i32* %6, null
+  br i1 %cmp, label %while.end, label %for.cond.preheader
+
+while.end:                                        ; preds = %for.end, %entry
+  ret void
+}
+