diff --git a/llvm/include/llvm/Transforms/Scalar/LoopIdiomRecognize.h b/llvm/include/llvm/Transforms/Scalar/LoopIdiomRecognize.h
--- a/llvm/include/llvm/Transforms/Scalar/LoopIdiomRecognize.h
+++ b/llvm/include/llvm/Transforms/Scalar/LoopIdiomRecognize.h
@@ -16,6 +16,7 @@
 #define LLVM_TRANSFORMS_SCALAR_LOOPIDIOMRECOGNIZE_H
 
 #include "llvm/Analysis/LoopAnalysisManager.h"
+#include "llvm/Analysis/LoopNestAnalysis.h"
 #include "llvm/IR/PassManager.h"
 
 namespace llvm {
@@ -43,6 +44,13 @@
                         LoopStandardAnalysisResults &AR, LPMUpdater &U);
 };
 
+// NFC LoopNestPass with regards to the current LoopPass-LoopIdiomRecognize
+class LoopNestIdiomRecognizePass : public PassInfoMixin<LoopNestIdiomRecognizePass> {
+public:
+  PreservedAnalyses run(LoopNest &LN, LoopAnalysisManager &LAM,
+                        LoopStandardAnalysisResults &AR, LPMUpdater &U);
+};
+
 } // end namespace llvm
 
 #endif // LLVM_TRANSFORMS_SCALAR_LOOPIDIOMRECOGNIZE_H
diff --git a/llvm/lib/Passes/PassRegistry.def b/llvm/lib/Passes/PassRegistry.def
--- a/llvm/lib/Passes/PassRegistry.def
+++ b/llvm/lib/Passes/PassRegistry.def
@@ -392,6 +392,7 @@
 LOOP_PASS("loop-idiom", LoopIdiomRecognizePass())
 LOOP_PASS("loop-instsimplify", LoopInstSimplifyPass())
 LOOP_PASS("loop-interchange", LoopInterchangePass())
+LOOP_PASS("loop-nest-idiom", LoopNestIdiomRecognizePass())
 LOOP_PASS("loop-rotate", LoopRotatePass())
 LOOP_PASS("no-op-loop", NoOpLoopPass())
 LOOP_PASS("print", PrintLoopPass(dbgs()))
diff --git a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
--- a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
@@ -148,6 +148,7 @@
 
 class LoopIdiomRecognize {
   Loop *CurLoop = nullptr;
+  LoopNest *LN;
   AliasAnalysis *AA;
   DominatorTree *DT;
   LoopInfo *LI;
@@ -161,16 +162,17 @@
 
 public:
   explicit LoopIdiomRecognize(AliasAnalysis *AA, DominatorTree *DT,
-                              LoopInfo *LI, ScalarEvolution *SE,
+                              LoopInfo *LI, LoopNest *LN, ScalarEvolution *SE,
                               TargetLibraryInfo *TLI,
                               const TargetTransformInfo *TTI, MemorySSA *MSSA,
                               const DataLayout *DL,
                               OptimizationRemarkEmitter &ORE)
-      : AA(AA), DT(DT), LI(LI), SE(SE), TLI(TLI), TTI(TTI), DL(DL), ORE(ORE) {
+      : LN(LN), AA(AA), DT(DT), LI(LI), SE(SE), TLI(TLI), TTI(TTI), DL(DL), ORE(ORE) {
     if (MSSA)
       MSSAU = std::make_unique<MemorySSAUpdater>(MSSA);
   }
 
+  bool runOnLoopNest();
   bool runOnLoop(Loop *L);
 
 private:
@@ -292,7 +294,7 @@
     // but ORE cannot be preserved (see comment before the pass definition).
     OptimizationRemarkEmitter ORE(L->getHeader()->getParent());
 
-    LoopIdiomRecognize LIR(AA, DT, LI, SE, TLI, TTI, MSSA, DL, ORE);
+    LoopIdiomRecognize LIR(AA, DT, LI, nullptr, SE, TLI, TTI, MSSA, DL, ORE);
     return LIR.runOnLoop(L);
   }
 
@@ -323,7 +325,7 @@
   // but ORE cannot be preserved (see comment before the pass definition).
   OptimizationRemarkEmitter ORE(L.getHeader()->getParent());
 
-  LoopIdiomRecognize LIR(&AR.AA, &AR.DT, &AR.LI, &AR.SE, &AR.TLI, &AR.TTI,
+  LoopIdiomRecognize LIR(&AR.AA, &AR.DT, &AR.LI, nullptr, &AR.SE, &AR.TLI, &AR.TTI,
                          AR.MSSA, DL, ORE);
   if (!LIR.runOnLoop(&L))
     return PreservedAnalyses::all();
@@ -334,6 +336,28 @@
   return PA;
 }
 
+PreservedAnalyses LoopNestIdiomRecognizePass::run(LoopNest &LN, LoopAnalysisManager &LAM,
+                                                  LoopStandardAnalysisResults &AR,
+                                                  LPMUpdater &U) {
+  if (DisableLIRP::All)
+    return PreservedAnalyses::all();
+
+  const auto *DL = &LN.getOutermostLoop().getHeader()->getModule()->getDataLayout();
+  OptimizationRemarkEmitter ORE(LN.getOutermostLoop().getHeader()->getParent());
+
+  LoopIdiomRecognize LIR(&AR.AA, &AR.DT, &AR.LI, &LN, &AR.SE, &AR.TLI, &AR.TTI,
+                         AR.MSSA, DL, ORE);
+
+  if (!LIR.runOnLoopNest())
+    return PreservedAnalyses::all();
+
+  auto PA = getLoopPassPreservedAnalyses();
+  if (AR.MSSA)
+    PA.preserve<MemorySSAAnalysis>();
+
+  return PA;
+}
+
 INITIALIZE_PASS_BEGIN(LoopIdiomRecognizeLegacyPass, "loop-idiom",
                       "Recognize loop idioms", false, false)
 INITIALIZE_PASS_DEPENDENCY(LoopPass)
@@ -355,6 +379,27 @@
 //
 //===----------------------------------------------------------------------===//
 
+bool LoopIdiomRecognize::runOnLoopNest() {
+  assert(LN != nullptr && "should not call this function is LoopNest isn't" 
+         "provided in ctor");
+
+  // Build worklist that contains all loops inside the LoopNest
+  SmallVector<Loop *, 8> WorkList;
+  for (Loop *L : LN->getLoops()) {
+    WorkList.push_back(L);
+  }
+
+  std::reverse(WorkList.begin(), WorkList.end());
+
+  // Iterate from innermost to outermost
+  bool Changed = false;
+  for (Loop *L : WorkList) {
+    Changed |= runOnLoop(L);
+  }
+
+  return Changed;
+}
+
 bool LoopIdiomRecognize::runOnLoop(Loop *L) {
   CurLoop = L;
   // If the loop could not be converted to canonical form, it must have an
diff --git a/llvm/test/Transforms/LoopIdiom/AMDGPU/popcnt.ll b/llvm/test/Transforms/LoopIdiom/AMDGPU/popcnt.ll
--- a/llvm/test/Transforms/LoopIdiom/AMDGPU/popcnt.ll
+++ b/llvm/test/Transforms/LoopIdiom/AMDGPU/popcnt.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -loop-idiom -mtriple=amdgcn-- -S < %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=amdgcn-- < %s | FileCheck %s
 
 ; Mostly copied from x86 version.
 
diff --git a/llvm/test/Transforms/LoopIdiom/ARM/ctlz.ll b/llvm/test/Transforms/LoopIdiom/ARM/ctlz.ll
--- a/llvm/test/Transforms/LoopIdiom/ARM/ctlz.ll
+++ b/llvm/test/Transforms/LoopIdiom/ARM/ctlz.ll
@@ -1,5 +1,7 @@
 ; RUN: opt -loop-idiom -mtriple=armv7a < %s -S | FileCheck -check-prefix=LZCNT --check-prefix=ALL %s
 ; RUN: opt -loop-idiom -mtriple=armv4t < %s -S | FileCheck -check-prefix=NOLZCNT --check-prefix=ALL %s
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=armv7a < %s | FileCheck %s -check-prefix=LZCNT --check-prefix=ALL
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=armv7t < %s | FileCheck %s -check-prefix=NOLZCNT --check-prefix=ALL
 
 ; Recognize CTLZ builtin pattern.
 ; Here we'll just convert loop to countable,
diff --git a/llvm/test/Transforms/LoopIdiom/RISCV/popcnt.ll b/llvm/test/Transforms/LoopIdiom/RISCV/popcnt.ll
--- a/llvm/test/Transforms/LoopIdiom/RISCV/popcnt.ll
+++ b/llvm/test/Transforms/LoopIdiom/RISCV/popcnt.ll
@@ -5,6 +5,12 @@
 ; RUN: opt -loop-idiom -mtriple=riscv64 -mattr=+experimental-b -S < %s | FileCheck %s --check-prefixes=CPOP
 ; RUN: opt -loop-idiom -mtriple=riscv32 -S < %s | FileCheck %s --check-prefixes=NOCPOP
 ; RUN: opt -loop-idiom -mtriple=riscv64 -S < %s | FileCheck %s --check-prefixes=NOCPOP
+; RUN: opt -passes="loop-nest-idiom" -mtriple=riscv32 -mattr=+experimental-zbb -S < %s | FileCheck %s --check-prefixes=CPOP
+; RUN: opt -passes="loop-nest-idiom" -mtriple=riscv64 -mattr=+experimental-zbb -S < %s | FileCheck %s --check-prefixes=CPOP
+; RUN: opt -passes="loop-nest-idiom" -mtriple=riscv32 -mattr=+experimental-b -S < %s | FileCheck %s --check-prefixes=CPOP
+; RUN: opt -passes="loop-nest-idiom" -mtriple=riscv64 -mattr=+experimental-b -S < %s | FileCheck %s --check-prefixes=CPOP
+; RUN: opt -passes="loop-nest-idiom" -mtriple=riscv32 -S < %s | FileCheck %s --check-prefixes=NOCPOP
+; RUN: opt -passes="loop-nest-idiom" -mtriple=riscv64 -S < %s | FileCheck %s --check-prefixes=NOCPOP
 
 ; Mostly copied from AMDGPU version.
 
diff --git a/llvm/test/Transforms/LoopIdiom/X86/arithmetic-right-shift-until-zero.ll b/llvm/test/Transforms/LoopIdiom/X86/arithmetic-right-shift-until-zero.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/arithmetic-right-shift-until-zero.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/arithmetic-right-shift-until-zero.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=x86_64 -mcpu=core-avx2 < %s | FileCheck %s
 
 declare void @escape_inner(i8, i8, i8, i1, i8)
 declare void @escape_outer(i8, i8, i8, i1, i8)
diff --git a/llvm/test/Transforms/LoopIdiom/X86/ctlz.ll b/llvm/test/Transforms/LoopIdiom/X86/ctlz.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/ctlz.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/ctlz.ll
@@ -1,6 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck %s -check-prefixes=ALL,LZCNT
 ; RUN: opt -loop-idiom -mtriple=x86_64 -mcpu=corei7 < %s -S | FileCheck %s -check-prefixes=ALL,NOLZCNT
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=x86_64 -mcpu=core-avx2 < %s | FileCheck %s -check-prefixes=ALL,LZCNT
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=x86_64 -mcpu=corei7 < %s | FileCheck %s -check-prefixes=ALL,NOLZCNT
 
 ; Recognize CTLZ builtin pattern.
 ; Here we'll just convert loop to countable,
diff --git a/llvm/test/Transforms/LoopIdiom/X86/cttz.ll b/llvm/test/Transforms/LoopIdiom/X86/cttz.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/cttz.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/cttz.ll
@@ -1,6 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck --check-prefix=ALL %s
 ; RUN: opt -loop-idiom -mtriple=x86_64 -mcpu=corei7 < %s -S | FileCheck --check-prefix=ALL %s
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=x86_64 -mcpu=core-avx2 < %s | FileCheck %s --check-prefix=ALL
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=x86_64 -mcpu=corei7 < %s | FileCheck %s --check-prefix=ALL
 
 ; Recognize CTTZ builtin pattern.
 ; Here it will replace the loop -
diff --git a/llvm/test/Transforms/LoopIdiom/X86/left-shift-until-bittest.ll b/llvm/test/Transforms/LoopIdiom/X86/left-shift-until-bittest.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/left-shift-until-bittest.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/left-shift-until-bittest.ll
@@ -1,6 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -debugify -loop-idiom -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck --check-prefixes=ALL,LZCNT %s
 ; RUN: opt -debugify -loop-idiom -mtriple=x86_64 -mcpu=corei7 < %s -S | FileCheck  --check-prefixes=ALL,NOLZCNT %s
+; RUN: opt -passes="loop-nest-idiom" -enable-debugify -debug-pass-manager -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck --check-prefixes=ALL,LZCNT %s
+; RUN: opt -passes="loop-nest-idiom" -enable-debugify -debug-pass-manager -mtriple=x86_64 -mcpu=corei7 < %s -S | FileCheck  --check-prefixes=ALL,NOLZCNT %s
 
 declare i32 @gen32()
 declare void @use32(i32)
diff --git a/llvm/test/Transforms/LoopIdiom/X86/left-shift-until-zero.ll b/llvm/test/Transforms/LoopIdiom/X86/left-shift-until-zero.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/left-shift-until-zero.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/left-shift-until-zero.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=x86_64 -mcpu=core-avx2 < %s | FileCheck %s
 
 declare void @escape_inner(i8, i8, i8, i1, i8)
 declare void @escape_outer(i8, i8, i8, i1, i8)
diff --git a/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero-cost.ll b/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero-cost.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero-cost.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero-cost.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom -mtriple=x86_64 -mcpu=corei7 < %s -S | FileCheck %s
-
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=x86_64 -mcpu=corei7 < %s | FileCheck %s
 declare void @escape_inner(i8, i8, i8, i1, i8)
 declare void @escape_outer(i8, i8, i8, i1, i8)
 
diff --git a/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero-debuginfo.ll b/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero-debuginfo.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero-debuginfo.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero-debuginfo.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -debugify -loop-idiom -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -enable-debugify -debug-pass-manager -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck %s
 
 declare void @escape_inner(i8, i8, i8, i1, i8)
 declare void @escape_outer(i8, i8, i8, i1, i8)
diff --git a/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero.ll b/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/logical-right-shift-until-zero.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom -mtriple=x86_64 -mcpu=core-avx2 < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=x86_64 -mcpu=core-avx2 < %s | FileCheck %s
 
 declare void @escape_inner(i8, i8, i8, i1, i8)
 declare void @escape_outer(i8, i8, i8, i1, i8)
diff --git a/llvm/test/Transforms/LoopIdiom/X86/popcnt.ll b/llvm/test/Transforms/LoopIdiom/X86/popcnt.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/popcnt.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/popcnt.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -loop-idiom < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=x86_64-apple-darwin -mcpu=corei7 < %s | FileCheck %s
 
 target triple = "x86_64-apple-macosx10.8.0"
 
diff --git a/llvm/test/Transforms/LoopIdiom/X86/unordered-atomic-memcpy.ll b/llvm/test/Transforms/LoopIdiom/X86/unordered-atomic-memcpy.ll
--- a/llvm/test/Transforms/LoopIdiom/X86/unordered-atomic-memcpy.ll
+++ b/llvm/test/Transforms/LoopIdiom/X86/unordered-atomic-memcpy.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 target triple = "x86_64-unknown-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopIdiom/basic-address-space.ll b/llvm/test/Transforms/LoopIdiom/basic-address-space.ll
--- a/llvm/test/Transforms/LoopIdiom/basic-address-space.ll
+++ b/llvm/test/Transforms/LoopIdiom/basic-address-space.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 target datalayout = "e-p:32:32:32-p1:64:64:64-p2:16:16:16-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:32-n8:16:32:64"
 target triple = "x86_64-apple-darwin10.0.0"
diff --git a/llvm/test/Transforms/LoopIdiom/basic.ll b/llvm/test/Transforms/LoopIdiom/basic.ll
--- a/llvm/test/Transforms/LoopIdiom/basic.ll
+++ b/llvm/test/Transforms/LoopIdiom/basic.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" < %s -S | FileCheck %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 ; For @test11_pattern
diff --git a/llvm/test/Transforms/LoopIdiom/crash.ll b/llvm/test/Transforms/LoopIdiom/crash.ll
--- a/llvm/test/Transforms/LoopIdiom/crash.ll
+++ b/llvm/test/Transforms/LoopIdiom/crash.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -basic-aa -loop-idiom -S < %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.8.0"
 
diff --git a/llvm/test/Transforms/LoopIdiom/ctpop-multiple-users-crash.ll b/llvm/test/Transforms/LoopIdiom/ctpop-multiple-users-crash.ll
--- a/llvm/test/Transforms/LoopIdiom/ctpop-multiple-users-crash.ll
+++ b/llvm/test/Transforms/LoopIdiom/ctpop-multiple-users-crash.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -loop-idiom -S < %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
 target triple = "arm64-apple-ios8.0.0"
diff --git a/llvm/test/Transforms/LoopIdiom/dbginfo-cost.ll b/llvm/test/Transforms/LoopIdiom/dbginfo-cost.ll
--- a/llvm/test/Transforms/LoopIdiom/dbginfo-cost.ll
+++ b/llvm/test/Transforms/LoopIdiom/dbginfo-cost.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -S -loop-idiom -mtriple=systemz-unknown -mcpu=z13 %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S -mtriple=systemz-unknown -mcpu=z13 < %s | FileCheck %s
 
 ; CHECK: @llvm.ctlz.i32
 
diff --git a/llvm/test/Transforms/LoopIdiom/debug-line.ll b/llvm/test/Transforms/LoopIdiom/debug-line.ll
--- a/llvm/test/Transforms/LoopIdiom/debug-line.ll
+++ b/llvm/test/Transforms/LoopIdiom/debug-line.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 target triple = "x86_64-apple-darwin10.0.0"
 
diff --git a/llvm/test/Transforms/LoopIdiom/disable-options.ll b/llvm/test/Transforms/LoopIdiom/disable-options.ll
--- a/llvm/test/Transforms/LoopIdiom/disable-options.ll
+++ b/llvm/test/Transforms/LoopIdiom/disable-options.ll
@@ -9,6 +9,11 @@
 ; RUN: opt -passes="loop-idiom" -aa-pipeline=basic-aa -disable-loop-idiom-memcpy < %s -S | FileCheck %s --check-prefix=DIS-MEMCPY
 ; RUN: opt -passes="loop-idiom" -aa-pipeline=basic-aa -disable-loop-idiom-memset < %s -S | FileCheck %s --check-prefix=DIS-MEMSET
 ; RUN: opt -passes="loop-idiom" -aa-pipeline=basic-aa -disable-loop-idiom-memset -disable-loop-idiom-memcpy < %s -S | FileCheck %s --check-prefix=DIS-ALL
+; RUN: opt -passes="loop-nest-idiom" -aa-pipeline=basic-aa                             < %s -S | FileCheck %s --check-prefix=DIS-NONE
+; RUN: opt -passes="loop-nest-idiom" -aa-pipeline=basic-aa -disable-loop-idiom-all    < %s -S | FileCheck %s --check-prefix=DIS-ALL
+; RUN: opt -passes="loop-nest-idiom" -aa-pipeline=basic-aa -disable-loop-idiom-memcpy < %s -S | FileCheck %s --check-prefix=DIS-MEMCPY
+; RUN: opt -passes="loop-nest-idiom" -aa-pipeline=basic-aa -disable-loop-idiom-memset < %s -S | FileCheck %s --check-prefix=DIS-MEMSET
+; RUN: opt -passes="loop-nest-idiom" -aa-pipeline=basic-aa -disable-loop-idiom-memset -disable-loop-idiom-memcpy < %s -S | FileCheck %s --check-prefix=DIS-ALL
 
 define void @test-memcpy(i64 %Size) nounwind ssp {
 ; DIS-NONE-LABEL: @test-memcpy(
diff --git a/llvm/test/Transforms/LoopIdiom/expander-do-not-delete-reused-values.ll b/llvm/test/Transforms/LoopIdiom/expander-do-not-delete-reused-values.ll
--- a/llvm/test/Transforms/LoopIdiom/expander-do-not-delete-reused-values.ll
+++ b/llvm/test/Transforms/LoopIdiom/expander-do-not-delete-reused-values.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom -S %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 ; Make sure we do not delete instructions not inserted during expansion, e.g.
 ; because the expande re-used existing instructions.
diff --git a/llvm/test/Transforms/LoopIdiom/int_sideeffect.ll b/llvm/test/Transforms/LoopIdiom/int_sideeffect.ll
--- a/llvm/test/Transforms/LoopIdiom/int_sideeffect.ll
+++ b/llvm/test/Transforms/LoopIdiom/int_sideeffect.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -S < %s -loop-idiom | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 declare void @llvm.sideeffect()
 
diff --git a/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll b/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll
--- a/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll
+++ b/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll
@@ -1,4 +1,5 @@
 ;  RUN: opt -basic-aa -loop-idiom -use-lir-code-size-heurs=true < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -use-lir-code-size-heurs=true -S < %s | FileCheck %s
 
 ; When compiling for codesize we avoid idiom recognition for a
 ; multi-block loop unless it is one of
diff --git a/llvm/test/Transforms/LoopIdiom/memcpy-debugify-remarks.ll b/llvm/test/Transforms/LoopIdiom/memcpy-debugify-remarks.ll
--- a/llvm/test/Transforms/LoopIdiom/memcpy-debugify-remarks.ll
+++ b/llvm/test/Transforms/LoopIdiom/memcpy-debugify-remarks.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -basic-aa -debugify -loop-idiom -pass-remarks=loop-idiom -pass-remarks-analysis=loop-idiom -verify -verify-each -verify-dom-info -verify-loop-info  < %s -S 2>&1 | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -enable-debugify -debug-pass-manager -pass-remarks=loop-idiom -pass-remarks-analysis=loop-idiom < %s -S 2>&1 | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopIdiom/memcpy-intrinsic-different-types.ll b/llvm/test/Transforms/LoopIdiom/memcpy-intrinsic-different-types.ll
--- a/llvm/test/Transforms/LoopIdiom/memcpy-intrinsic-different-types.ll
+++ b/llvm/test/Transforms/LoopIdiom/memcpy-intrinsic-different-types.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 ; #include <vector>
 ;
diff --git a/llvm/test/Transforms/LoopIdiom/memcpy-intrinsic.ll b/llvm/test/Transforms/LoopIdiom/memcpy-intrinsic.ll
--- a/llvm/test/Transforms/LoopIdiom/memcpy-intrinsic.ll
+++ b/llvm/test/Transforms/LoopIdiom/memcpy-intrinsic.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 %struct.S = type { i32, i32, i8 }
 
diff --git a/llvm/test/Transforms/LoopIdiom/memcpy-vectors.ll b/llvm/test/Transforms/LoopIdiom/memcpy-vectors.ll
--- a/llvm/test/Transforms/LoopIdiom/memcpy-vectors.ll
+++ b/llvm/test/Transforms/LoopIdiom/memcpy-vectors.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -loop-idiom -S <%s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 define void @memcpy_fixed_vec(i64* noalias %a, i64* noalias %b) local_unnamed_addr #1 {
 ; CHECK-LABEL: @memcpy_fixed_vec(
diff --git a/llvm/test/Transforms/LoopIdiom/memcpy.ll b/llvm/test/Transforms/LoopIdiom/memcpy.ll
--- a/llvm/test/Transforms/LoopIdiom/memcpy.ll
+++ b/llvm/test/Transforms/LoopIdiom/memcpy.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 define void @copy_both_noalias(float* noalias nocapture %d, float* noalias nocapture readonly %s, i64 %sz) {
 ; CHECK-LABEL: @copy_both_noalias(
diff --git a/llvm/test/Transforms/LoopIdiom/memset-debugify-remarks.ll b/llvm/test/Transforms/LoopIdiom/memset-debugify-remarks.ll
--- a/llvm/test/Transforms/LoopIdiom/memset-debugify-remarks.ll
+++ b/llvm/test/Transforms/LoopIdiom/memset-debugify-remarks.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -basic-aa -debugify -loop-idiom -pass-remarks=loop-idiom -pass-remarks-analysis=loop-idiom -verify -verify-each -verify-dom-info -verify-loop-info  < %s -S 2>&1 | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -enable-debugify -debug-pass-manager -pass-remarks=loop-idiom -pass-remarks-analysis=loop-idiom < %s -S 2>&1 | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopIdiom/memset.ll b/llvm/test/Transforms/LoopIdiom/memset.ll
--- a/llvm/test/Transforms/LoopIdiom/memset.ll
+++ b/llvm/test/Transforms/LoopIdiom/memset.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" < %s -S | FileCheck %s
 
 
 define dso_local void @double_memset(i8* nocapture %p, i8* noalias nocapture %q, i32 %n) {
diff --git a/llvm/test/Transforms/LoopIdiom/memset_noidiom.ll b/llvm/test/Transforms/LoopIdiom/memset_noidiom.ll
--- a/llvm/test/Transforms/LoopIdiom/memset_noidiom.ll
+++ b/llvm/test/Transforms/LoopIdiom/memset_noidiom.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 target triple = "x86_64-apple-darwin10.0.0"
 
diff --git a/llvm/test/Transforms/LoopIdiom/non-canonical-loop.ll b/llvm/test/Transforms/LoopIdiom/non-canonical-loop.ll
--- a/llvm/test/Transforms/LoopIdiom/non-canonical-loop.ll
+++ b/llvm/test/Transforms/LoopIdiom/non-canonical-loop.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -S -loop-idiom < %s
+; RUN: opt -S --passes="loop-nest-idiom" < %s
 ; Don't crash
 ; PR13892
 
diff --git a/llvm/test/Transforms/LoopIdiom/non-integral-pointers.ll b/llvm/test/Transforms/LoopIdiom/non-integral-pointers.ll
--- a/llvm/test/Transforms/LoopIdiom/non-integral-pointers.ll
+++ b/llvm/test/Transforms/LoopIdiom/non-integral-pointers.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -S -basic-aa -loop-idiom < %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128-ni:4"
 target triple = "x86_64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopIdiom/nontemporal_store.ll b/llvm/test/Transforms/LoopIdiom/nontemporal_store.ll
--- a/llvm/test/Transforms/LoopIdiom/nontemporal_store.ll
+++ b/llvm/test/Transforms/LoopIdiom/nontemporal_store.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 ; RUN: opt -aa-pipeline=basic-aa -passes='require<aa>,require<targetir>,require<scalar-evolution>,require<opt-remark-emit>,loop(loop-idiom)' < %s -S | FileCheck %s
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopIdiom/phi-insertion.ll b/llvm/test/Transforms/LoopIdiom/phi-insertion.ll
--- a/llvm/test/Transforms/LoopIdiom/phi-insertion.ll
+++ b/llvm/test/Transforms/LoopIdiom/phi-insertion.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom -S %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 define void @phi_insertion(i1 %c, i32* %ptr.start, i32* %ptr.end, i64 %offset) {
 ; CHECK-LABEL: @phi_insertion(
diff --git a/llvm/test/Transforms/LoopIdiom/pr28196.ll b/llvm/test/Transforms/LoopIdiom/pr28196.ll
--- a/llvm/test/Transforms/LoopIdiom/pr28196.ll
+++ b/llvm/test/Transforms/LoopIdiom/pr28196.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -loop-idiom -S < %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopIdiom/pr33114.ll b/llvm/test/Transforms/LoopIdiom/pr33114.ll
--- a/llvm/test/Transforms/LoopIdiom/pr33114.ll
+++ b/llvm/test/Transforms/LoopIdiom/pr33114.ll
@@ -1,6 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; Check that we're not crashing while looking at the recurrence variable.
 ; RUN: opt -S -loop-idiom %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 define void @tinkywinky() {
 ; CHECK-LABEL: @tinkywinky(
diff --git a/llvm/test/Transforms/LoopIdiom/reuse-cast.ll b/llvm/test/Transforms/LoopIdiom/reuse-cast.ll
--- a/llvm/test/Transforms/LoopIdiom/reuse-cast.ll
+++ b/llvm/test/Transforms/LoopIdiom/reuse-cast.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -loop-idiom -S %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 define void @reuse_cast_1(float** %ptr, i1 %c) {
 ; CHECK-LABEL: @reuse_cast_1(
diff --git a/llvm/test/Transforms/LoopIdiom/scev-invalidation.ll b/llvm/test/Transforms/LoopIdiom/scev-invalidation.ll
--- a/llvm/test/Transforms/LoopIdiom/scev-invalidation.ll
+++ b/llvm/test/Transforms/LoopIdiom/scev-invalidation.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -S -indvars -loop-idiom < %s
+; RUN: opt -passes="loop-nest-idiom,indvars" -S < %s
 ; PR14214
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopIdiom/scev-invalidation_topmostloop.ll b/llvm/test/Transforms/LoopIdiom/scev-invalidation_topmostloop.ll
--- a/llvm/test/Transforms/LoopIdiom/scev-invalidation_topmostloop.ll
+++ b/llvm/test/Transforms/LoopIdiom/scev-invalidation_topmostloop.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -S -indvars -loop-idiom -verify -loop-simplifycfg -simplifycfg-require-and-preserve-domtree=1 -loop-idiom < %s | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 
 target triple = "x86_64-unknown-linux-gnu"
 
diff --git a/llvm/test/Transforms/LoopIdiom/struct-custom-dl.ll b/llvm/test/Transforms/LoopIdiom/struct-custom-dl.ll
--- a/llvm/test/Transforms/LoopIdiom/struct-custom-dl.ll
+++ b/llvm/test/Transforms/LoopIdiom/struct-custom-dl.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-p:40:64:64:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 %struct.foo = type { i32, i32 }
diff --git a/llvm/test/Transforms/LoopIdiom/struct.ll b/llvm/test/Transforms/LoopIdiom/struct.ll
--- a/llvm/test/Transforms/LoopIdiom/struct.ll
+++ b/llvm/test/Transforms/LoopIdiom/struct.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 target triple = "x86_64-apple-darwin10.0.0"
diff --git a/llvm/test/Transforms/LoopIdiom/struct_pattern.ll b/llvm/test/Transforms/LoopIdiom/struct_pattern.ll
--- a/llvm/test/Transforms/LoopIdiom/struct_pattern.ll
+++ b/llvm/test/Transforms/LoopIdiom/struct_pattern.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 ; CHECK: @.memset_pattern = private unnamed_addr constant [4 x i32] [i32 2, i32 2, i32 2, i32 2], align 16
diff --git a/llvm/test/Transforms/LoopIdiom/unordered-atomic-memcpy-noarch.ll b/llvm/test/Transforms/LoopIdiom/unordered-atomic-memcpy-noarch.ll
--- a/llvm/test/Transforms/LoopIdiom/unordered-atomic-memcpy-noarch.ll
+++ b/llvm/test/Transforms/LoopIdiom/unordered-atomic-memcpy-noarch.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 ;; memcpy.atomic formation (atomic load & store) -- element size 2
diff --git a/llvm/test/Transforms/LoopIdiom/unroll-custom-dl.ll b/llvm/test/Transforms/LoopIdiom/unroll-custom-dl.ll
--- a/llvm/test/Transforms/LoopIdiom/unroll-custom-dl.ll
+++ b/llvm/test/Transforms/LoopIdiom/unroll-custom-dl.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-p:64:64:64:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 ; CHECK: @.memset_pattern = private unnamed_addr constant [4 x i32] [i32 2, i32 2, i32 2, i32 2], align 16
diff --git a/llvm/test/Transforms/LoopIdiom/unroll.ll b/llvm/test/Transforms/LoopIdiom/unroll.ll
--- a/llvm/test/Transforms/LoopIdiom/unroll.ll
+++ b/llvm/test/Transforms/LoopIdiom/unroll.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -basic-aa -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 
 ; CHECK: @.memset_pattern = private unnamed_addr constant [4 x i32] [i32 2, i32 2, i32 2, i32 2], align 16
diff --git a/llvm/test/Transforms/LoopIdiom/unsafe.ll b/llvm/test/Transforms/LoopIdiom/unsafe.ll
--- a/llvm/test/Transforms/LoopIdiom/unsafe.ll
+++ b/llvm/test/Transforms/LoopIdiom/unsafe.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -S < %s -loop-idiom | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 ; CHECK-NOT: memset
 ; check that memset is not generated (for stores) because that will result
 ; in udiv hoisted out of the loop by the SCEV Expander
diff --git a/llvm/test/Transforms/LoopIdiom/unwind.ll b/llvm/test/Transforms/LoopIdiom/unwind.ll
--- a/llvm/test/Transforms/LoopIdiom/unwind.ll
+++ b/llvm/test/Transforms/LoopIdiom/unwind.ll
@@ -1,4 +1,5 @@
 ; RUN: opt -loop-idiom < %s -S | FileCheck %s
+; RUN: opt -passes="loop-nest-idiom" -S < %s | FileCheck %s
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"