Index: lib/Transforms/Scalar/EarlyCSE.cpp
===================================================================
--- lib/Transforms/Scalar/EarlyCSE.cpp
+++ lib/Transforms/Scalar/EarlyCSE.cpp
@@ -562,6 +562,14 @@
       continue;
     }
 
+    if (match(Inst, m_Intrinsic<Intrinsic::invariant_start>())) {
+      // invariant.start intrinsics read memory, but don't write any memory.
+      // Accordingly, don't update the generation but consume the last store (to
+      // avoid an incorrect DSE).
+      LastStore = nullptr;
+      continue;
+    }
+
     if (match(Inst, m_Intrinsic<Intrinsic::experimental_guard>())) {
       if (auto *CondI =
               dyn_cast<Instruction>(cast<CallInst>(Inst)->getArgOperand(0))) {
Index: test/Transforms/EarlyCSE/invariant.start.ll
===================================================================
--- /dev/null
+++ test/Transforms/EarlyCSE/invariant.start.ll
@@ -0,0 +1,53 @@
+; RUN: opt < %s -S -early-cse | FileCheck %s
+; RUN: opt < %s -S -passes=early-cse | FileCheck %s
+
+declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) nounwind readonly
+
+; Check that we do load-load forwarding over invariant.start, since it does not
+; clobber memory
+define i8 @test1(i8 *%P) {
+  ; CHECK-LABEL:@test1(
+  ; CHECK-NEXT: %V1 = load i8, i8* %P
+  ; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %P)
+  ; CHECK-NEXT: ret i8 0
+
+
+  %V1 = load i8, i8* %P
+  %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %P)
+  %V2 = load i8, i8* %P
+  %Diff = sub i8 %V1, %V2
+  ret i8 %Diff
+}
+
+
+; Trivial Store->load forwarding over invariant.start
+define i8 @test2(i8 *%P) {
+  ; CHECK-LABEL: @test2(
+  ; CHECK-NEXT: store i8 42, i8* %P
+  ; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %P)
+  ; CHECK-NEXT: ret i8 42
+
+
+  store i8 42, i8* %P
+  %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %P)
+  %V1 = load i8, i8* %P
+  ret i8 %V1
+}
+
+; Check that we do not DSE over invariant.start calls, since the first store to
+; %P is valid, and the second store is actually unreachable based on semantics
+; of invariant.start. Due to this, we treat invariant.start as _read_memory_,
+; and the first store should not be DSE'd
+define void @test3(i8* %P) {
+
+; CHECK-LABEL: @test3(
+; CHECK-NEXT:  store i8 50, i8* %P
+; CHECK-NEXT:  %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %P)
+; CHECK-NEXT:  store i8 60, i8* %P
+
+
+  store i8 50, i8* %P
+  %i = call {}* @llvm.invariant.start.p0i8(i64 1, i8* %P)
+  store i8 60, i8* %P
+  ret void
+}