[FuncSpec] Relax restrictions on candidates for specialisation

Allow a function to be specialised even if it has its address taken or
it's global. For such functions, consider all of the arguments as
overdefined. Don't delete the functions even if all the apparent calls
were redirected to specialised instances.

Reviewed By: labrinea, ChuanqiXu

Differential Revision: https://reviews.llvm.org/D148345

llvm/lib/Transforms/IPO/FunctionSpecialization.cpp

@@ -498,15 +498,12 @@ bool FunctionSpecializer::findSpecializations(Function *F, InstructionCost Cost,
 }
 
 bool FunctionSpecializer::isCandidateFunction(Function *F) {
-  if (F->isDeclaration())
+  if (F->isDeclaration() || F->arg_empty())
     return false;
 
   if (F->hasFnAttribute(Attribute::NoDuplicate))
     return false;
 
-  if (!Solver.isArgumentTrackedFunction(F))
-    return false;
-
   // Do not specialize the cloned function again.
   if (Specializations.contains(F))
     return false;
@@ -533,6 +530,10 @@ bool FunctionSpecializer::isCandidateFunction(Function *F) {
 Function *FunctionSpecializer::createSpecialization(Function *F, const SpecSig &S) {
   Function *Clone = cloneCandidateFunction(F);
 
+  // The original function does not neccessarily have internal linkage, but the
+  // clone must.
+  Clone->setLinkage(GlobalValue::InternalLinkage);
+
   // Initialize the lattice state of the arguments of the function clone,
   // marking the argument on which we specialized the function constant
   // with the given value.
@@ -676,6 +677,10 @@ bool FunctionSpecializer::isArgumentInteresting(Argument *A) {
   if (A->hasByValAttr() && !A->getParent()->onlyReadsMemory())
     return false;
 
+  // For non-argument-tracked functions every argument is overdefined.
+  if (!Solver.isArgumentTrackedFunction(A->getParent()))
+    return true;
+
   // Check the lattice value and decide if we should attemt to specialize,
   // based on this argument. No point in specialization, if the lattice value
   // is already a constant.
@@ -761,7 +766,7 @@ void FunctionSpecializer::updateCallSites(Function *F, const Spec *Begin,
 
   // If the function has been completely specialized, the original function
   // is no longer needed. Mark it unreachable.
-  if (NCallsLeft == 0) {
+  if (NCallsLeft == 0 && Solver.isArgumentTrackedFunction(F)) {
     Solver.markFunctionUnreachable(F);
     FullySpecialized.insert(F);
   }

llvm/test/Transforms/FunctionSpecialization/non-argument-tracked.ll

@@ -0,0 +1,64 @@
+; RUN: opt -S --passes=ipsccp,deadargelim -funcspec-for-literal-constant --force-specialization < %s | FileCheck %s
+
+; Test that all of `f0`, `f1`, and `f2` are specialised, even though `f0` has its address taken
+; and `f1` is with external linkage (`f2` was specialised anyway).
+
+@p = global ptr @f0
+
+; `f0` is kept even though all apparent calls are specialized
+; CHECK-LABEL: define internal i32 @f0(
+define internal i32 @f0(i32 %i) {
+  %v = add i32 %i, 1
+  ret i32 %v
+}
+
+; Likewise, `f1` is kept, because of the external linkage
+; CHECK-LABEL: define i32 @f1(
+define i32 @f1(i32 %i) {
+  %v = add i32 %i, 1
+  ret i32 %v
+}
+
+; `f2` is fully specialised.
+; CHECK-NOT: defined internal i32 @f2()
+define internal i32 @f2(i32 %i) {
+  %v = add i32 %i, 1
+  ret i32 %v
+}
+
+;; All calls are to specilisation instances.
+
+; CHECK-LABEL: define i32 @g0
+; CHECK:         [[U0:%.*]] = call i32 @f0.[[#A:]]()
+; CHECK-NEXT:    [[U1:%.*]] = call i32 @f1.[[#B:]]()
+; CHECK-NEXT:    [[U2:%.*]] = call i32 @f2.[[#C:]]()
+define i32 @g0(i32 %i) {
+  %u0 = call i32 @f0(i32 1)
+  %u1 = call i32 @f1(i32 2)
+  %u2 = call i32 @f2(i32 3)
+  %v0 = add i32 %u0, %u1
+  %v = add i32 %v0, %u2
+  ret i32 %v
+}
+
+; CHECK-LABEL: define i32 @g1
+; CHECK:         [[U0:%.*]] = call i32 @f0.[[#D:]]()
+; CHECK-NEXT:    [[U1:%.*]] = call i32 @f1.[[#E:]]()
+; CHECK-NEXT:    [[U2:%.*]] = call i32 @f2.[[#F:]]()
+define i32 @g1(i32 %i) {
+  %u0 = call i32 @f0(i32 2)
+  %u1 = call i32 @f1(i32 3)
+  %u2 = call i32 @f2(i32 4)
+  %v0 = add i32 %u0, %u1
+  %v = add i32 %v0, %u2
+  ret i32 %v
+}
+
+; All of the function are specialized and all clones are with internal linkage.
+
+; CHECK-DAG: define internal i32 @f0.[[#A]]() {
+; CHECK-DAG: define internal i32 @f1.[[#B]]() {
+; CHECK-DAG: define internal i32 @f2.[[#C]]() {
+; CHECK-DAG: define internal i32 @f0.[[#D]]() {
+; CHECK-DAG: define internal i32 @f1.[[#E]]() {
+; CHECK-DAG: define internal i32 @f2.[[#F]]() {