1 files changed, 43 insertions, 17 deletions

diff --git a/llvm/lib/Target/AArch64/SVEIntrinsicOpts.cpp b/llvm/lib/Target/AArch64/SVEIntrinsicOpts.cpp
index 74fe0cdd1ea7..9911f33371c6 100644
--- a/llvm/lib/Target/AArch64/SVEIntrinsicOpts.cpp
+++ b/llvm/lib/Target/AArch64/SVEIntrinsicOpts.cpp
@@ -37,7 +37,7 @@
 using namespace llvm;
 using namespace llvm::PatternMatch;
 
-#define DEBUG_TYPE "sve-intrinsic-opts"
+#define DEBUG_TYPE "aarch64-sve-intrinsic-opts"
 
 namespace llvm {
 void initializeSVEIntrinsicOptsPass(PassRegistry &);
@@ -160,7 +160,7 @@ bool SVEIntrinsicOpts::optimizePTest(IntrinsicInst *I) {
     I->eraseFromParent();
     if (Op1->use_empty())
       Op1->eraseFromParent();
-    if (Op2->use_empty())
+    if (Op1 != Op2 && Op2->use_empty())
       Op2->eraseFromParent();
 
     return true;
@@ -177,22 +177,50 @@ bool SVEIntrinsicOpts::optimizeConvertFromSVBool(IntrinsicInst *I) {
   if (isa<PHINode>(I->getArgOperand(0)))
     return processPhiNode(I);
 
-  // If we have a reinterpret intrinsic I of type A which is converting from
-  // another reinterpret Y of type B, and the source type of Y is A, then we can
-  // elide away both reinterprets if there are no other users of Y.
-  auto *Y = isReinterpretToSVBool(I->getArgOperand(0));
-  if (!Y)
-    return false;
+  SmallVector<Instruction *, 32> CandidatesForRemoval;
+  Value *Cursor = I->getOperand(0), *EarliestReplacement = nullptr;
+
+  const auto *IVTy = cast<VectorType>(I->getType());
+
+  // Walk the chain of conversions.
+  while (Cursor) {
+    // If the type of the cursor has fewer lanes than the final result, zeroing
+    // must take place, which breaks the equivalence chain.
+    const auto *CursorVTy = cast<VectorType>(Cursor->getType());
+    if (CursorVTy->getElementCount().getKnownMinValue() <
+        IVTy->getElementCount().getKnownMinValue())
+      break;
+
+    // If the cursor has the same type as I, it is a viable replacement.
+    if (Cursor->getType() == IVTy)
+      EarliestReplacement = Cursor;
+
+    auto *IntrinsicCursor = dyn_cast<IntrinsicInst>(Cursor);
 
-  Value *SourceVal = Y->getArgOperand(0);
-  if (I->getType() != SourceVal->getType())
+    // If this is not an SVE conversion intrinsic, this is the end of the chain.
+    if (!IntrinsicCursor || !(IntrinsicCursor->getIntrinsicID() ==
+                                  Intrinsic::aarch64_sve_convert_to_svbool ||
+                              IntrinsicCursor->getIntrinsicID() ==
+                                  Intrinsic::aarch64_sve_convert_from_svbool))
+      break;
+
+    CandidatesForRemoval.insert(CandidatesForRemoval.begin(), IntrinsicCursor);
+    Cursor = IntrinsicCursor->getOperand(0);
+  }
+
+  // If no viable replacement in the conversion chain was found, there is
+  // nothing to do.
+  if (!EarliestReplacement)
     return false;
 
-  I->replaceAllUsesWith(SourceVal);
+  I->replaceAllUsesWith(EarliestReplacement);
   I->eraseFromParent();
-  if (Y->use_empty())
-    Y->eraseFromParent();
 
+  while (!CandidatesForRemoval.empty()) {
+    Instruction *Candidate = CandidatesForRemoval.pop_back_val();
+    if (Candidate->use_empty())
+      Candidate->eraseFromParent();
+  }
   return true;
 }
 
@@ -248,10 +276,8 @@ bool SVEIntrinsicOpts::runOnModule(Module &M) {
     case Intrinsic::aarch64_sve_ptest_any:
     case Intrinsic::aarch64_sve_ptest_first:
     case Intrinsic::aarch64_sve_ptest_last:
-      for (auto I = F.user_begin(), E = F.user_end(); I != E;) {
-        auto *Inst = dyn_cast<Instruction>(*I++);
-        Functions.insert(Inst->getFunction());
-      }
+      for (User *U : F.users())
+        Functions.insert(cast<Instruction>(U)->getFunction());
       break;
     default:
       break;