[SCEV] Avoid redundant computations when doing AddRec merge

When we calculate a product of 2 AddRecs, we end up making quite massive
computations to deduce the operands of resulting AddRec. This process can
be optimized by computing all args of intermediate sum and then calling
`getAddExpr` once rather than calling `getAddExpr` with intermediate
result every time a new argument is computed.

Differential Revision: https://reviews.llvm.org/D53189
Reviewed By: rtereshin

llvm-svn: 345813

diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 8fe500f..77f2467 100644 (file)
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -3060,7 +3060,7 @@ const SCEV *ScalarEvolution::getMulExpr(SmallVectorImpl<const SCEV *> &Ops,
       SmallVector<const SCEV*, 7> AddRecOps;
       for (int x = 0, xe = AddRec->getNumOperands() +
              OtherAddRec->getNumOperands() - 1; x != xe && !Overflow; ++x) {
-        const SCEV *Term = getZero(Ty);
+        SmallVector <const SCEV *, 7> SumOps;
         for (int y = x, ye = 2*x+1; y != ye && !Overflow; ++y) {
           uint64_t Coeff1 = Choose(x, 2*x - y, Overflow);
           for (int z = std::max(y-x, y-(int)AddRec->getNumOperands()+1),
@@ -3075,12 +3075,13 @@ const SCEV *ScalarEvolution::getMulExpr(SmallVectorImpl<const SCEV *> &Ops,
             const SCEV *CoeffTerm = getConstant(Ty, Coeff);
             const SCEV *Term1 = AddRec->getOperand(y-z);
             const SCEV *Term2 = OtherAddRec->getOperand(z);
-            Term = getAddExpr(Term, getMulExpr(CoeffTerm, Term1, Term2,
-                                               SCEV::FlagAnyWrap, Depth + 1),
-                              SCEV::FlagAnyWrap, Depth + 1);
+            SumOps.push_back(getMulExpr(CoeffTerm, Term1, Term2,
+                                        SCEV::FlagAnyWrap, Depth + 1));
           }
         }
-        AddRecOps.push_back(Term);
+        if (SumOps.empty())
+          SumOps.push_back(getZero(Ty));
+        AddRecOps.push_back(getAddExpr(SumOps, SCEV::FlagAnyWrap, Depth + 1));
       }
       if (!Overflow) {
         const SCEV *NewAddRec = getAddRecExpr(AddRecOps, AddRec->getLoop(),

diff --git a/llvm/test/Analysis/ScalarEvolution/binomial-explision.ll b/llvm/test/Analysis/ScalarEvolution/binomial-explision.ll
index 82d0bed..ff27bfc 100644 (file)
--- a/llvm/test/Analysis/ScalarEvolution/binomial-explision.ll
+++ b/llvm/test/Analysis/ScalarEvolution/binomial-explision.ll
@@ -8,7 +8,7 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128-ni:1"
 define void @test(i32 %x, i64 %y, i1 %cond) {
 
 ; CHECK: %tmp19 = mul i32 %tmp17, %tmp18
-; CHECK: ((((
+; CHECK: ((((((
 ; CHECK-NOT: (((((
 ; CHECK: %tmp20 = add i32 %tmp19, %x