Index: lib/Transforms/Scalar/LoopInstSimplify.cpp
===================================================================
--- lib/Transforms/Scalar/LoopInstSimplify.cpp
+++ lib/Transforms/Scalar/LoopInstSimplify.cpp
@@ -22,8 +22,8 @@
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/LoopIterator.h"
 #include "llvm/Analysis/LoopPass.h"
+#include "llvm/Analysis/ScalarEvolution.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
-#include "llvm/Transforms/Utils/Local.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/CFG.h"
 #include "llvm/IR/DataLayout.h"
@@ -36,6 +36,7 @@
 #include "llvm/Pass.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Transforms/Scalar.h"
+#include "llvm/Transforms/Utils/Local.h"
 #include "llvm/Transforms/Utils/LoopUtils.h"
 #include <algorithm>
 #include <utility>
@@ -47,8 +48,8 @@
 STATISTIC(NumSimplified, "Number of redundant instructions simplified");
 
 static bool simplifyLoopInst(Loop &L, DominatorTree &DT, LoopInfo &LI,
-                             AssumptionCache &AC,
-                             const TargetLibraryInfo &TLI) {
+                             AssumptionCache &AC, const TargetLibraryInfo &TLI,
+                             ScalarEvolution *SE) {
   const DataLayout &DL = L.getHeader()->getModule()->getDataLayout();
   SimplifyQuery SQ(DL, &TLI, &DT, &AC);
 
@@ -157,6 +158,11 @@
     DeadInsts.clear();
   }
 
+  // If ScalarEvolution is around and knows anything about values in this loop,
+  // tell it to forget them, because we simplifed the in-loop instructions.
+  if (SE && Changed)
+    SE->forgetLoop(&L);
+
   return Changed;
 }
 
@@ -180,14 +186,17 @@
             *L->getHeader()->getParent());
     const TargetLibraryInfo &TLI =
         getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
+    auto *SEWP = getAnalysisIfAvailable<ScalarEvolutionWrapperPass>();
+    ScalarEvolution *SE = SEWP ? &SEWP->getSE() : nullptr;
 
-    return simplifyLoopInst(*L, DT, LI, AC, TLI);
+    return simplifyLoopInst(*L, DT, LI, AC, TLI, SE);
   }
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<AssumptionCacheTracker>();
     AU.addRequired<DominatorTreeWrapperPass>();
     AU.addRequired<TargetLibraryInfoWrapperPass>();
+    AU.addPreserved<ScalarEvolutionWrapperPass>();
     AU.setPreservesCFG();
     getLoopAnalysisUsage(AU);
   }
@@ -198,11 +207,16 @@
 PreservedAnalyses LoopInstSimplifyPass::run(Loop &L, LoopAnalysisManager &AM,
                                             LoopStandardAnalysisResults &AR,
                                             LPMUpdater &) {
-  if (!simplifyLoopInst(L, AR.DT, AR.LI, AR.AC, AR.TLI))
+  const auto &FAM =
+      AM.getResult<FunctionAnalysisManagerLoopProxy>(L, AR).getManager();
+  Function *F = L.getHeader()->getParent();
+  ScalarEvolution *SE = FAM.getCachedResult<ScalarEvolutionAnalysis>(*F);
+  if (!simplifyLoopInst(L, AR.DT, AR.LI, AR.AC, AR.TLI, SE))
     return PreservedAnalyses::all();
 
   auto PA = getLoopPassPreservedAnalyses();
   PA.preserveSet<CFGAnalyses>();
+  PA.preserve<ScalarEvolutionAnalysis>();
   return PA;
 }
 
Index: test/Other/new-pm-defaults.ll
===================================================================
--- test/Other/new-pm-defaults.ll
+++ test/Other/new-pm-defaults.ll
@@ -146,10 +146,10 @@
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Starting Loop pass manager run.
 ; CHECK-O-NEXT: Running pass: LoopInstSimplifyPass
+; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}FunctionAnalysisManager{{.*}}>
 ; CHECK-O-NEXT: Running pass: LoopSimplifyCFGPass
 ; CHECK-O-NEXT: Running pass: LoopRotatePass
 ; CHECK-O-NEXT: Running pass: LICM
-; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
 ; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
 ; CHECK-O-NEXT: Finished Loop pass manager run.
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
Index: test/Other/new-pm-thinlto-defaults.ll
===================================================================
--- test/Other/new-pm-thinlto-defaults.ll
+++ test/Other/new-pm-thinlto-defaults.ll
@@ -130,10 +130,10 @@
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Starting Loop pass manager run.
 ; CHECK-O-NEXT: Running pass: LoopInstSimplifyPass
+; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}FunctionAnalysisManager{{.*}}>
 ; CHECK-O-NEXT: Running pass: LoopSimplifyCFGPass
 ; CHECK-O-NEXT: Running pass: LoopRotatePass
 ; CHECK-O-NEXT: Running pass: LICM
-; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
 ; CHECK-O-NEXT: Running pass: SimpleLoopUnswitchPass
 ; CHECK-O-NEXT: Finished Loop pass manager run.
 ; CHECK-O-NEXT: Running pass: SimplifyCFGPass
Index: test/Transforms/LoopInstSimplify/forget-scev.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoopInstSimplify/forget-scev.ll
@@ -0,0 +1,43 @@
+; RUN: opt %s -indvars -loop-instsimplify -loop-reduce
+; We are only checking that there is no crash!
+
+; https://bugs.llvm.org/show_bug.cgi?id=37936
+
+; The problem is as follows:
+; 1. indvars marks %dec as NUW.
+; 2. loop-instsimplify runs instsimplify, which constant-folds %dec to -1
+; 3. loop-reduce tries to do some further modification, but crashes
+;    with an type assertion in cast, because %dec is no longer an Instruction,
+;    even though the SCEV data indicated it was.
+
+; If the runline is split into two, i.e. -indvars -loop-instsimplify first, that
+; stored into a file, and then -loop-reduce is run on that, there is no crash.
+; So it looks like the problem is due to -loop-instsimplify not discarding SCEV.
+
+target datalayout = "n16"
+
+@a = external global i16, align 1
+
+define void @f1() {
+entry:
+  br label %for.cond
+
+for.cond:                                         ; preds = %land.end, %entry
+  %c.0 = phi i16 [ 0, %entry ], [ %dec, %land.end ]
+  br i1 undef, label %for.body, label %for.cond.cleanup
+
+for.cond.cleanup:                                 ; preds = %for.cond
+  ret void
+
+for.body:                                         ; preds = %for.cond
+  %0 = load i16, i16* @a, align 1
+  %cmp = icmp sgt i16 %0, %c.0
+  br i1 %cmp, label %land.rhs, label %land.end
+
+land.rhs:                                         ; preds = %for.body
+  unreachable
+
+land.end:                                         ; preds = %for.body
+  %dec = add nsw i16 %c.0, -1
+  br label %for.cond
+}