diff --git a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
--- a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -521,6 +521,7 @@
     case Intrinsic::annotation:
     case Intrinsic::assume:
     case Intrinsic::sideeffect:
+    case Intrinsic::pseudoprobe:
     case Intrinsic::dbg_declare:
     case Intrinsic::dbg_value:
     case Intrinsic::dbg_label:
diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -1416,6 +1416,7 @@
     case Intrinsic::lifetime_start:
     case Intrinsic::lifetime_end:
     case Intrinsic::sideeffect:
+    case Intrinsic::pseudoprobe:
       return 0;
     case Intrinsic::masked_store: {
       Type *Ty = Tys[0];
diff --git a/llvm/include/llvm/IR/BasicBlock.h b/llvm/include/llvm/IR/BasicBlock.h
--- a/llvm/include/llvm/IR/BasicBlock.h
+++ b/llvm/include/llvm/IR/BasicBlock.h
@@ -180,6 +180,32 @@
         static_cast<const BasicBlock *>(this)->getFirstNonPHIOrDbgOrLifetime());
   }
 
+  /// Returns a pointer to the first instruction in this block that is not a
+  /// PHINode, a debug intrinsic, or a pseudo probe intrinsic.
+  const Instruction *getFirstNonPHIOrDbgOrPseudoProbe() const;
+  Instruction *getFirstNonPHIOrDbgOrPseudoProbe() {
+    return const_cast<Instruction *>(static_cast<const BasicBlock *>(this)
+                                         ->getFirstNonPHIOrDbgOrPseudoProbe());
+  }
+
+  /// Returns a pointer to the first instruction in this block that is not a
+  /// PHINode, a debug intrinsic, a lifetime intrinsic, or a pseudo probe
+  /// intrinsic.
+  const Instruction *getFirstNonPHIOrDbgOrLifetimeOrPseudoProbe() const;
+  Instruction *getFirstNonPHIOrDbgOrLifetimeOrPseudoProbe() {
+    return const_cast<Instruction *>(
+        static_cast<const BasicBlock *>(this)
+            ->getFirstNonPHIOrDbgOrLifetimeOrPseudoProbe());
+  }
+
+  /// Returns a pointer to the last instruction in this block that is not a
+  /// debug intrinsic, or a pseudo probe intrinsic.
+  const Instruction *getLastNonDbgOrPseudoProbe() const;
+  Instruction *getLastNonDbgOrPseudoProbe() {
+    return const_cast<Instruction *>(
+        static_cast<const BasicBlock *>(this)->getLastNonDbgOrPseudoProbe());
+  }
+
   /// Returns an iterator to the first instruction in this block that is
   /// suitable for inserting a non-PHI instruction.
   ///
diff --git a/llvm/include/llvm/IR/IntrinsicInst.h b/llvm/include/llvm/IR/IntrinsicInst.h
--- a/llvm/include/llvm/IR/IntrinsicInst.h
+++ b/llvm/include/llvm/IR/IntrinsicInst.h
@@ -967,6 +967,23 @@
   }
 };
 
+class PseudoProbeInst : public IntrinsicInst {
+public:
+  static bool classof(const IntrinsicInst *I) {
+    return I->getIntrinsicID() == Intrinsic::pseudoprobe;
+  }
+  static bool classof(const Value *V) {
+    return isa<IntrinsicInst>(V) && classof(cast<IntrinsicInst>(V));
+  }
+
+  ConstantInt *getFuncGuid() const {
+    return cast<ConstantInt>(const_cast<Value *>(getArgOperand(0)));
+  }
+
+  ConstantInt *getIndex() const {
+    return cast<ConstantInt>(const_cast<Value *>(getArgOperand(1)));
+  }
+};
 } // end namespace llvm
 
 #endif // LLVM_IR_INTRINSICINST_H
diff --git a/llvm/include/llvm/IR/Intrinsics.td b/llvm/include/llvm/IR/Intrinsics.td
--- a/llvm/include/llvm/IR/Intrinsics.td
+++ b/llvm/include/llvm/IR/Intrinsics.td
@@ -1260,6 +1260,12 @@
 // which specify that infinite loops must be preserved.
 def int_sideeffect : DefaultAttrsIntrinsic<[], [], [IntrInaccessibleMemOnly, IntrWillReturn]>;
 
+// The pseudoprobe intrinsic works as a place holder to the block it probes.
+// Like the sideeffect intrinsic defined above, this intrinsic is treated by the 
+// optimizer as having opaque side effects so that it won't be get rid of or moved 
+// out of the block it probes.
+def int_pseudoprobe : Intrinsic<[], [llvm_i64_ty, llvm_i64_ty], [IntrInaccessibleMemOnly, IntrWillReturn]>;
+
 // Intrinsics to support half precision floating point format
 let IntrProperties = [IntrNoMem, IntrWillReturn] in {
 def int_convert_to_fp16   : DefaultAttrsIntrinsic<[llvm_i16_ty], [llvm_anyfloat_ty]>;
diff --git a/llvm/lib/Analysis/AliasSetTracker.cpp b/llvm/lib/Analysis/AliasSetTracker.cpp
--- a/llvm/lib/Analysis/AliasSetTracker.cpp
+++ b/llvm/lib/Analysis/AliasSetTracker.cpp
@@ -439,6 +439,7 @@
       // FIXME: Add lifetime/invariant intrinsics (See: PR30807).
     case Intrinsic::assume:
     case Intrinsic::sideeffect:
+    case Intrinsic::pseudoprobe:
       return;
     }
   }
diff --git a/llvm/lib/Analysis/InlineCost.cpp b/llvm/lib/Analysis/InlineCost.cpp
--- a/llvm/lib/Analysis/InlineCost.cpp
+++ b/llvm/lib/Analysis/InlineCost.cpp
@@ -1911,6 +1911,10 @@
     if (isa<DbgInfoIntrinsic>(I))
       continue;
 
+    // Skip pseudo-probes.
+    if (isa<PseudoProbeInst>(I))
+      continue;
+
     // Skip ephemeral values.
     if (EphValues.count(&*I))
       continue;
diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -527,6 +527,7 @@
       // FIXME: This list is repeated from NoTTI::getIntrinsicCost.
       case Intrinsic::assume:
       case Intrinsic::sideeffect:
+      case Intrinsic::pseudoprobe:
       case Intrinsic::dbg_declare:
       case Intrinsic::dbg_value:
       case Intrinsic::dbg_label:
diff --git a/llvm/lib/Analysis/VectorUtils.cpp b/llvm/lib/Analysis/VectorUtils.cpp
--- a/llvm/lib/Analysis/VectorUtils.cpp
+++ b/llvm/lib/Analysis/VectorUtils.cpp
@@ -125,7 +125,7 @@
 
   if (isTriviallyVectorizable(ID) || ID == Intrinsic::lifetime_start ||
       ID == Intrinsic::lifetime_end || ID == Intrinsic::assume ||
-      ID == Intrinsic::sideeffect)
+      ID == Intrinsic::sideeffect || ID == Intrinsic::pseudoprobe)
     return ID;
   return Intrinsic::not_intrinsic;
 }
diff --git a/llvm/lib/CodeGen/Analysis.cpp b/llvm/lib/CodeGen/Analysis.cpp
--- a/llvm/lib/CodeGen/Analysis.cpp
+++ b/llvm/lib/CodeGen/Analysis.cpp
@@ -537,6 +537,9 @@
     // Debug info intrinsics do not get in the way of tail call optimization.
     if (isa<DbgInfoIntrinsic>(BBI))
       continue;
+    // Pseudo probe intrinsics do not block tail call optimization either.
+    if (isa<PseudoProbeInst>(BBI))
+      continue;
     // A lifetime end or assume intrinsic should not stop tail call
     // optimization.
     if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(BBI))
diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
--- a/llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ b/llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -2241,13 +2241,13 @@
     // Skip over debug and the bitcast.
     do {
       ++BI;
-    } while (isa<DbgInfoIntrinsic>(BI) || &*BI == BCI || &*BI == EVI);
+    } while (isa<DbgInfoIntrinsic>(BI) || &*BI == BCI || &*BI == EVI ||
+             isa<PseudoProbeInst>(BI));
     if (&*BI != RetI)
       return false;
   } else {
-    BasicBlock::iterator BI = BB->begin();
-    while (isa<DbgInfoIntrinsic>(BI)) ++BI;
-    if (&*BI != RetI)
+    Instruction *I = BB->getFirstNonPHIOrDbgOrPseudoProbe();
+    if (I != RetI)
       return false;
   }
 
@@ -2272,18 +2272,12 @@
     for (pred_iterator PI = pred_begin(BB), PE = pred_end(BB); PI != PE; ++PI) {
       if (!VisitedBBs.insert(*PI).second)
         continue;
-
-      BasicBlock::InstListType &InstList = (*PI)->getInstList();
-      BasicBlock::InstListType::reverse_iterator RI = InstList.rbegin();
-      BasicBlock::InstListType::reverse_iterator RE = InstList.rend();
-      do { ++RI; } while (RI != RE && isa<DbgInfoIntrinsic>(&*RI));
-      if (RI == RE)
-        continue;
-
-      CallInst *CI = dyn_cast<CallInst>(&*RI);
-      if (CI && CI->use_empty() && TLI->mayBeEmittedAsTailCall(CI) &&
-          attributesPermitTailCall(F, CI, RetI, *TLI))
-        TailCallBBs.push_back(*PI);
+      if (Instruction *RI = (*PI)->getLastNonDbgOrPseudoProbe()) {
+        CallInst *CI = dyn_cast<CallInst>(RI);
+        if (CI && CI->use_empty() && TLI->mayBeEmittedAsTailCall(CI) &&
+            attributesPermitTailCall(F, CI, RetI, *TLI))
+          TailCallBBs.push_back(*PI);
+      }
     }
   }
 
diff --git a/llvm/lib/IR/BasicBlock.cpp b/llvm/lib/IR/BasicBlock.cpp
--- a/llvm/lib/IR/BasicBlock.cpp
+++ b/llvm/lib/IR/BasicBlock.cpp
@@ -238,6 +238,38 @@
   return nullptr;
 }
 
+const Instruction *BasicBlock::getFirstNonPHIOrDbgOrPseudoProbe() const {
+  for (const Instruction &I : *this) {
+    if (isa<PHINode>(I) || isa<DbgInfoIntrinsic>(I) || isa<PseudoProbeInst>(I))
+      continue;
+    return &I;
+  }
+  return nullptr;
+}
+
+const Instruction *
+BasicBlock::getFirstNonPHIOrDbgOrLifetimeOrPseudoProbe() const {
+  for (const Instruction &I : *this) {
+    if (isa<PHINode>(I) || isa<DbgInfoIntrinsic>(I) || isa<PseudoProbeInst>(I))
+      continue;
+
+    if (I.isLifetimeStartOrEnd())
+      continue;
+
+    return &I;
+  }
+  return nullptr;
+}
+
+const Instruction *BasicBlock::getLastNonDbgOrPseudoProbe() const {
+  for (const Instruction &I : reverse(*this)) {
+    if (isa<DbgInfoIntrinsic>(I) || isa<PseudoProbeInst>(I))
+      continue;
+    return &I;
+  }
+  return nullptr;
+}
+
 BasicBlock::const_iterator BasicBlock::getFirstInsertionPt() const {
   const Instruction *FirstNonPHI = getFirstNonPHI();
   if (!FirstNonPHI)
diff --git a/llvm/lib/Transforms/Scalar/JumpThreading.cpp b/llvm/lib/Transforms/Scalar/JumpThreading.cpp
--- a/llvm/lib/Transforms/Scalar/JumpThreading.cpp
+++ b/llvm/lib/Transforms/Scalar/JumpThreading.cpp
@@ -538,6 +538,10 @@
     // Debugger intrinsics don't incur code size.
     if (isa<DbgInfoIntrinsic>(I)) continue;
 
+    // Pseudo-probes don't incur code size.
+    if (isa<PseudoProbeInst>(I))
+      continue;
+
     // If this is a pointer->pointer bitcast, it is free.
     if (isa<BitCastInst>(I) && I->getType()->isPointerTy())
       continue;
diff --git a/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp b/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp
--- a/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/TailRecursionElimination.cpp
@@ -240,7 +240,11 @@
         Escaped = ESCAPED;
 
       CallInst *CI = dyn_cast<CallInst>(&I);
-      if (!CI || CI->isTailCall() || isa<DbgInfoIntrinsic>(&I))
+      // A PseudoProbeInst has the IntrInaccessibleMemOnly tag hence it is
+      // considered accessing memory and will be marked as a tail call if we
+      // don't bail out here.
+      if (!CI || CI->isTailCall() || isa<DbgInfoIntrinsic>(&I) ||
+          isa<PseudoProbeInst>(&I))
         continue;
 
       bool IsNoTail = CI->isNoTailCall() || CI->hasOperandBundles();
@@ -752,7 +756,8 @@
       return false;
 
     BasicBlock *Succ = BI->getSuccessor(0);
-    ReturnInst *Ret = dyn_cast<ReturnInst>(Succ->getFirstNonPHIOrDbg());
+    ReturnInst *Ret =
+        dyn_cast<ReturnInst>(Succ->getFirstNonPHIOrDbgOrPseudoProbe());
 
     if (!Ret)
       return false;
diff --git a/llvm/lib/Transforms/Utils/Evaluator.cpp b/llvm/lib/Transforms/Utils/Evaluator.cpp
--- a/llvm/lib/Transforms/Utils/Evaluator.cpp
+++ b/llvm/lib/Transforms/Utils/Evaluator.cpp
@@ -551,6 +551,10 @@
           LLVM_DEBUG(dbgs() << "Skipping sideeffect intrinsic.\n");
           ++CurInst;
           continue;
+        } else if (II->getIntrinsicID() == Intrinsic::pseudoprobe) {
+          LLVM_DEBUG(dbgs() << "Skipping pseudoprobe intrinsic.\n");
+          ++CurInst;
+          continue;
         }
 
         LLVM_DEBUG(dbgs() << "Unknown intrinsic. Can not evaluate.\n");
diff --git a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
--- a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -1987,7 +1987,10 @@
     --MaxNumInstToLookAt;
 
     // Could be calling an instruction that affects memory like free().
-    if (CurI.mayHaveSideEffects() && !isa<StoreInst>(CurI))
+    // Skip pseudo probe intrinsic calls which are not really killing any memory
+    // accesses.
+    if (CurI.mayHaveSideEffects() && !isa<StoreInst>(CurI) &&
+        !isa<PseudoProbeInst>(CurI))
       return nullptr;
 
     if (auto *SI = dyn_cast<StoreInst>(&CurI)) {
@@ -2141,6 +2144,14 @@
       continue;
     }
 
+    // Skip pseudo probes. The consequence is we lose track of the branch
+    // probability for ThenBB, which is fine since the optimization here takes
+    // place regardless of the branch probability.
+    if (isa<PseudoProbeInst>(I)) {
+      SpeculatedDbgIntrinsics.push_back(I);
+      continue;
+    }
+
     // Only speculatively execute a single instruction (not counting the
     // terminator) for now.
     ++SpeculatedInstructions;
@@ -2495,7 +2506,8 @@
   } else {
     DomBlock = *pred_begin(IfBlock1);
     for (BasicBlock::iterator I = IfBlock1->begin(); !I->isTerminator(); ++I)
-      if (!AggressiveInsts.count(&*I) && !isa<DbgInfoIntrinsic>(I)) {
+      if (!AggressiveInsts.count(&*I) && !isa<DbgInfoIntrinsic>(I) &&
+          !isa<PseudoProbeInst>(I)) {
         // This is not an aggressive instruction that we can promote.
         // Because of this, we won't be able to get rid of the control flow, so
         // the xform is not worth it.
@@ -2508,7 +2520,8 @@
   } else {
     DomBlock = *pred_begin(IfBlock2);
     for (BasicBlock::iterator I = IfBlock2->begin(); !I->isTerminator(); ++I)
-      if (!AggressiveInsts.count(&*I) && !isa<DbgInfoIntrinsic>(I)) {
+      if (!AggressiveInsts.count(&*I) && !isa<DbgInfoIntrinsic>(I) &&
+          !isa<PseudoProbeInst>(I)) {
         // This is not an aggressive instruction that we can promote.
         // Because of this, we won't be able to get rid of the control flow, so
         // the xform is not worth it.
diff --git a/llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp b/llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
--- a/llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
@@ -666,6 +666,10 @@
                cast<IntrinsicInst>(&I)->getIntrinsicID() ==
                    Intrinsic::sideeffect) {
       // Ignore llvm.sideeffect calls.
+    } else if (isa<IntrinsicInst>(&I) &&
+               cast<IntrinsicInst>(&I)->getIntrinsicID() ==
+                   Intrinsic::pseudoprobe) {
+      // Ignore llvm.pseudoprobe calls.
     } else if (IsLoadChain && (I.mayWriteToMemory() || I.mayThrow())) {
       LLVM_DEBUG(dbgs() << "LSV: Found may-write/throw operation: " << I
                         << '\n');
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7412,7 +7412,8 @@
 
   Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
   if (ID && (ID == Intrinsic::assume || ID == Intrinsic::lifetime_end ||
-             ID == Intrinsic::lifetime_start || ID == Intrinsic::sideeffect))
+             ID == Intrinsic::lifetime_start || ID == Intrinsic::sideeffect ||
+             ID == Intrinsic::pseudoprobe))
     return nullptr;
 
   auto willWiden = [&](ElementCount VF) -> bool {
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -5175,7 +5175,9 @@
 
     if (I->mayReadOrWriteMemory() &&
         (!isa<IntrinsicInst>(I) ||
-         cast<IntrinsicInst>(I)->getIntrinsicID() != Intrinsic::sideeffect)) {
+         (cast<IntrinsicInst>(I)->getIntrinsicID() != Intrinsic::sideeffect &&
+          cast<IntrinsicInst>(I)->getIntrinsicID() !=
+              Intrinsic::pseudoprobe))) {
       // Update the linked list of memory accessing instructions.
       if (CurrentLoadStore) {
         CurrentLoadStore->NextLoadStore = SD;