[InstCombine] reassociate loop invariant GEP chains to enable LICM

This change brings performance of zlib up by 10%. The example below is from a
hot loop in longest_match() from zlib.

do.body:
  %cur_match.addr.0 = phi i32 [ %cur_match, %entry ], [ %2, %do.cond ]
  %idx.ext = zext i32 %cur_match.addr.0 to i64
  %add.ptr = getelementptr inbounds i8, i8* %win, i64 %idx.ext
  %add.ptr2 = getelementptr inbounds i8, i8* %add.ptr, i64 %idx.ext1
  %add.ptr3 = getelementptr inbounds i8, i8* %add.ptr2, i64 -1

In this example %idx.ext1 is a loop invariant. It will be moved above the use of
loop induction variable %idx.ext such that it can be hoisted out of the loop by
LICM. The operands that have dependences carried by the loop will be sinked down
in the GEP chain. This patch will produce the following output:

do.body:
  %cur_match.addr.0 = phi i32 [ %cur_match, %entry ], [ %2, %do.cond ]
  %idx.ext = zext i32 %cur_match.addr.0 to i64
  %add.ptr = getelementptr inbounds i8, i8* %win, i64 %idx.ext1
  %add.ptr2 = getelementptr inbounds i8, i8* %add.ptr, i64 -1
  %add.ptr3 = getelementptr inbounds i8, i8* %add.ptr2, i64 %idx.ext

llvm-svn: 328539

1 files changed, 17 insertions, 0 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
index 52519acb33f..94a7a4c5030 100644
--- a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -1670,6 +1670,23 @@ Instruction *InstCombiner::visitGetElementPtrInst(GetElementPtrInst &GEP) {
     if (!shouldMergeGEPs(*cast<GEPOperator>(&GEP), *Src))
       return nullptr;
 
+    // Try to reassociate loop invariant GEP chains to enable LICM.
+    if (LI && Src->getNumOperands() == 2 && GEP.getNumOperands() == 2 &&
+        Src->hasOneUse()) {
+      if (Loop *L = LI->getLoopFor(GEP.getParent())) {
+        Value *GO1 = GEP.getOperand(1);
+        Value *SO1 = Src->getOperand(1);
+        // Reassociate the two GEPs if SO1 is variant in the loop and GO1 is
+        // invariant: this breaks the dependence between GEPs and allows LICM
+        // to hoist the invariant part out of the loop.
+        if (L->isLoopInvariant(GO1) && !L->isLoopInvariant(SO1)) {
+          Src->setOperand(1, GO1);
+          GEP.setOperand(1, SO1);
+          return &GEP;
+        }
+      }
+    }
+
     // Note that if our source is a gep chain itself then we wait for that
     // chain to be resolved before we perform this transformation.  This
     // avoids us creating a TON of code in some cases.