Reapply [InstCombine] Remove early constant fold

The reported compile-time regression has been address in
47f9109dff80a1abbe2705ee71dc0882b1d62274.

Additionally, this contains a change to immediately fold zext
with constant operand, even if it's used in a trunc. I'm not sure
if this is relevant for anything, but I noticed it as a behavioral
discrepancy when investigating this issue.

-----

InstCombine currently performs a constant folding attempt as part
of the main InstCombine loop, before visiting the instruction.
However, each visit method will also attempt to simplify the
instruction, which will in turn constant fold it. (Additionally,
we also constant fold instructions before the main InstCombine loop
and use a constant folding IR builder, so this is doubly redundant.)

There is one place where InstCombine visit methods currently don't
call into simplification, and that's casts. To be conservative,
I've added an explicit constant folding call there (though it has
no impact on tests).

This makes for a mild compile-time improvement and in particular
mitigates the compile-time regression from enabling load
simplification in be88b5814d9efce131dbc0c8e288907e2e6c89be.

Differential Revision: https://reviews.llvm.org/D144369

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
index 0b3f92d..f399810 100644 (file)
--- a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -308,6 +308,10 @@ Instruction *InstCombinerImpl::commonCastTransforms(CastInst &CI) {
   Value *Src = CI.getOperand(0);
   Type *Ty = CI.getType();
 
+  if (auto *SrcC = dyn_cast<Constant>(Src))
+    if (Constant *Res = ConstantFoldCastOperand(CI.getOpcode(), SrcC, Ty, DL))
+      return replaceInstUsesWith(CI, Res);
+
   // Try to eliminate a cast of a cast.
   if (auto *CSrc = dyn_cast<CastInst>(Src)) {   // A->B->C cast
     if (Instruction::CastOps NewOpc = isEliminableCastPair(CSrc, &CI)) {
@@ -1243,7 +1247,8 @@ static bool canEvaluateZExtd(Value *V, Type *Ty, unsigned &BitsToClear,
 Instruction *InstCombinerImpl::visitZExt(ZExtInst &Zext) {
   // If this zero extend is only used by a truncate, let the truncate be
   // eliminated before we try to optimize this zext.
-  if (Zext.hasOneUse() && isa<TruncInst>(Zext.user_back()))
+  if (Zext.hasOneUse() && isa<TruncInst>(Zext.user_back()) &&
+      !isa<Constant>(Zext.getOperand(0)))
     return nullptr;
 
   // If one of the common conversion will work, do it.

diff --git a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
index 3366eae..34d1b2b 100644 (file)
--- a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -4238,23 +4238,6 @@ bool InstCombinerImpl::run() {
     if (!DebugCounter::shouldExecute(VisitCounter))
       continue;
 
-    // Instruction isn't dead, see if we can constant propagate it.
-    if (!I->use_empty() &&
-        (I->getNumOperands() == 0 || isa<Constant>(I->getOperand(0)))) {
-      if (Constant *C = ConstantFoldInstruction(I, DL, &TLI)) {
-        LLVM_DEBUG(dbgs() << "IC: ConstFold to: " << *C << " from: " << *I
-                          << '\n');
-
-        // Add operands to the worklist.
-        replaceInstUsesWith(*I, C);
-        ++NumConstProp;
-        if (isInstructionTriviallyDead(I, &TLI))
-          eraseInstFromFunction(*I);
-        MadeIRChange = true;
-        continue;
-      }
-    }
-
     // See if we can trivially sink this instruction to its user if we can
     // prove that the successor is not executed more frequently than our block.
     // Return the UserBlock if successful.

diff --git a/llvm/test/Transforms/InstCombine/pr38677.ll b/llvm/test/Transforms/InstCombine/pr38677.ll
index bacee2c..f60c7fb 100644 (file)
--- a/llvm/test/Transforms/InstCombine/pr38677.ll
+++ b/llvm/test/Transforms/InstCombine/pr38677.ll
@@ -11,9 +11,8 @@ define i32 @foo(i1 %which, ptr %dst) {
 ; CHECK:       delay:
 ; CHECK-NEXT:    br label [[FINAL]]
 ; CHECK:       final:
-; CHECK-NEXT:    [[USE2:%.*]] = phi i32 [ 1, [[ENTRY:%.*]] ], [ select (i1 icmp eq (ptr @A, ptr @B), i32 2, i32 1), [[DELAY]] ]
 ; CHECK-NEXT:    store i1 false, ptr [[DST:%.*]], align 1
-; CHECK-NEXT:    ret i32 [[USE2]]
+; CHECK-NEXT:    ret i32 1
 ;
 entry:
   br i1 true, label %final, label %delay