[llvm] Add pass to align inner loops. Loops less than 32B are aggresively (PR #152356)

via llvm-commits llvm-commits at lists.llvm.org
Wed Aug 6 11:14:05 PDT 2025


https://github.com/hjagasiaAMD created https://github.com/llvm/llvm-project/pull/152356

aligned to 32B boundary. Otherwise for larger loops, check if loop starts at an offset >16B and if so align to 32B boundary. This is done to improve performance.

>From 8f5e8f0587ca47241ecf2a6c9e26d75c1956c0a8 Mon Sep 17 00:00:00 2001
From: Harsha Jagasia <harsha.jagasia at amd.com>
Date: Wed, 6 Aug 2025 10:52:55 -0500
Subject: [PATCH] Add pass to align inner loops. Loops less than 32B are
 aggresively aligned to 32B boundary. Otherwise for larger loops, check if
 loop starts at an offset >16B and if so align to 32B boundary. This is done
 to improve performance.

---
 llvm/lib/Target/AMDGPU/AMDGPU.h               |   3 +
 llvm/lib/Target/AMDGPU/AMDGPULoopAlign.cpp    | 153 ++++++++++++++++++
 llvm/lib/Target/AMDGPU/AMDGPULoopAlign.h      |  24 +++
 llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def |   1 +
 .../lib/Target/AMDGPU/AMDGPUTargetMachine.cpp |   6 +
 llvm/lib/Target/AMDGPU/CMakeLists.txt         |   1 +
 .../GlobalISel/divergence-structurizer.ll     |   2 +-
 .../GlobalISel/llvm.amdgcn.intersect_ray.ll   |   8 +-
 .../GlobalISel/llvm.amdgcn.wqm.demote.ll      |   8 +-
 .../CodeGen/AMDGPU/GlobalISel/llvm.memcpy.ll  |   4 +-
 .../CodeGen/AMDGPU/GlobalISel/llvm.memset.ll  |   4 +-
 .../AMDGPU/GlobalISel/regbankselect-mui.ll    |   4 +-
 .../AMDGPU/atomic-optimizer-strict-wqm.ll     |   2 +-
 .../atomic_optimizations_global_pointer.ll    |  52 +++---
 .../atomic_optimizations_local_pointer.ll     |  28 ++--
 llvm/test/CodeGen/AMDGPU/branch-relaxation.ll |   8 +-
 .../AMDGPU/buffer-fat-pointers-memcpy.ll      |   8 +-
 .../CodeGen/AMDGPU/cf-loop-on-constant.ll     |   4 +-
 .../AMDGPU/cgp-addressing-modes-smem.ll       |  10 +-
 .../CodeGen/AMDGPU/coalescer_distribute.ll    |   2 +-
 .../CodeGen/AMDGPU/copy-to-reg-frameindex.ll  |   2 +-
 .../test/CodeGen/AMDGPU/dynamic_stackalloc.ll |   8 +-
 ...-phi-regression-issue130646-issue130119.ll |   2 +-
 .../CodeGen/AMDGPU/flat_atomics_i32_system.ll |   6 +-
 .../CodeGen/AMDGPU/flat_atomics_i64_system.ll |   6 +-
 .../flat_atomics_i64_system_noprivate.ll      |   6 +-
 .../AMDGPU/global-load-saddr-to-vaddr.ll      |   2 +-
 .../global-saddr-atomics-min-max-system.ll    |   8 +-
 llvm/test/CodeGen/AMDGPU/global-saddr-load.ll |  16 +-
 .../AMDGPU/global_atomics_i32_system.ll       |   6 +-
 .../AMDGPU/global_atomics_i64_system.ll       |   6 +-
 .../AMDGPU/global_atomics_scan_fadd.ll        |  24 +--
 .../AMDGPU/global_atomics_scan_fmax.ll        |  24 +--
 .../AMDGPU/global_atomics_scan_fmin.ll        |  24 +--
 .../AMDGPU/global_atomics_scan_fsub.ll        |  24 +--
 llvm/test/CodeGen/AMDGPU/iglp-no-clobber.ll   |   2 +-
 .../CodeGen/AMDGPU/indirect-addressing-si.ll  |  12 +-
 .../AMDGPU/infer-addrspace-flat-atomic.ll     |   2 +-
 llvm/test/CodeGen/AMDGPU/infinite-loop.ll     |   2 +-
 .../CodeGen/AMDGPU/insert-delay-alu-bug.ll    |   4 +-
 .../test/CodeGen/AMDGPU/kill-infinite-loop.ll |   2 +-
 llvm/test/CodeGen/AMDGPU/llc-pipeline-npm.ll  |  10 +-
 llvm/test/CodeGen/AMDGPU/llc-pipeline.ll      |  16 +-
 .../llvm.amdgcn.pops.exiting.wave.id.ll       |   8 +-
 .../llvm.amdgcn.raw.atomic.buffer.load.ll     |   8 +-
 .../llvm.amdgcn.raw.ptr.atomic.buffer.load.ll |   8 +-
 .../CodeGen/AMDGPU/llvm.amdgcn.reduce.add.ll  |  24 +--
 .../CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll  |  24 +--
 .../CodeGen/AMDGPU/llvm.amdgcn.reduce.max.ll  |  24 +--
 .../CodeGen/AMDGPU/llvm.amdgcn.reduce.min.ll  |  24 +--
 .../CodeGen/AMDGPU/llvm.amdgcn.reduce.or.ll   |  24 +--
 .../CodeGen/AMDGPU/llvm.amdgcn.reduce.sub.ll  |  24 +--
 .../CodeGen/AMDGPU/llvm.amdgcn.reduce.umax.ll |  24 +--
 .../CodeGen/AMDGPU/llvm.amdgcn.reduce.umin.ll |  24 +--
 .../CodeGen/AMDGPU/llvm.amdgcn.reduce.xor.ll  |  24 +--
 .../llvm.amdgcn.struct.atomic.buffer.load.ll  |   8 +-
 ...vm.amdgcn.struct.ptr.atomic.buffer.load.ll |   8 +-
 .../CodeGen/AMDGPU/llvm.amdgcn.wqm.demote.ll  |   8 +-
 .../CodeGen/AMDGPU/local-atomicrmw-fadd.ll    |  22 +--
 .../local-stack-alloc-block-sp-reference.ll   |   4 +-
 .../test/CodeGen/AMDGPU/loop-prefetch-data.ll |   6 +-
 llvm/test/CodeGen/AMDGPU/loop-prefetch.ll     |   6 +-
 llvm/test/CodeGen/AMDGPU/loop_break.ll        |   2 +-
 ...ne-sink-temporal-divergence-swdev407790.ll |   2 +-
 .../CodeGen/AMDGPU/mdt-preserving-crash.ll    |   2 +-
 llvm/test/CodeGen/AMDGPU/mfma-loop.ll         |   6 +-
 .../CodeGen/AMDGPU/nested-loop-conditions.ll  |  20 ++-
 .../CodeGen/AMDGPU/no-dup-inst-prefetch.ll    |   4 +-
 .../CodeGen/AMDGPU/no-fold-accvgpr-mov.ll     |   4 +-
 llvm/test/CodeGen/AMDGPU/noclobber-barrier.ll |   2 +-
 .../CodeGen/AMDGPU/optimize-negated-cond.ll   |   2 +-
 .../AMDGPU/promote-constOffset-to-imm.ll      |  12 +-
 llvm/test/CodeGen/AMDGPU/select-undef.ll      |   2 +-
 .../AMDGPU/should-not-hoist-set-inactive.ll   |   2 +-
 llvm/test/CodeGen/AMDGPU/si-annotate-cf.ll    |   4 +-
 .../AMDGPU/si-annotate-cfg-loop-assert.ll     |   2 +-
 .../AMDGPU/simplifydemandedbits-recursion.ll  |   2 +-
 llvm/test/CodeGen/AMDGPU/skip-if-dead.ll      |   8 +-
 llvm/test/CodeGen/AMDGPU/srem64.ll            |   4 +-
 llvm/test/CodeGen/AMDGPU/trap-abis.ll         |  12 +-
 .../AMDGPU/undefined-subreg-liverange.ll      |   4 +-
 llvm/test/CodeGen/AMDGPU/uniform-cfg.ll       |   4 +-
 llvm/test/CodeGen/AMDGPU/valu-i1.ll           |   2 +-
 .../test/CodeGen/AMDGPU/vni8-across-blocks.ll |   2 +-
 llvm/test/CodeGen/AMDGPU/wave32.ll            |  10 +-
 85 files changed, 587 insertions(+), 375 deletions(-)
 create mode 100644 llvm/lib/Target/AMDGPU/AMDGPULoopAlign.cpp
 create mode 100644 llvm/lib/Target/AMDGPU/AMDGPULoopAlign.h

diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.h b/llvm/lib/Target/AMDGPU/AMDGPU.h
index 007b481f84960..a9270eadf1232 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.h
@@ -231,6 +231,9 @@ extern char &AMDGPUPerfHintAnalysisLegacyID;
 void initializeGCNRegPressurePrinterPass(PassRegistry &);
 extern char &GCNRegPressurePrinterID;
 
+void initializeAMDGPULoopAlignLegacyPass(PassRegistry &);
+extern char &AMDGPULoopAlignLegacyID;
+
 void initializeAMDGPUPreloadKernArgPrologLegacyPass(PassRegistry &);
 extern char &AMDGPUPreloadKernArgPrologLegacyID;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULoopAlign.cpp b/llvm/lib/Target/AMDGPU/AMDGPULoopAlign.cpp
new file mode 100644
index 0000000000000..409b3e47bf2a8
--- /dev/null
+++ b/llvm/lib/Target/AMDGPU/AMDGPULoopAlign.cpp
@@ -0,0 +1,153 @@
+//===----- AMDGPULoopAlign.cpp - Generate loop alignment directives  -----===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+// Inspect a basic block and if certain conditions are met then align to 32
+// bytes.
+//===----------------------------------------------------------------------===//
+
+#include "AMDGPULoopAlign.h"
+#include "AMDGPU.h"
+#include "AMDGPUTargetMachine.h"
+#include "GCNSubtarget.h"
+#include "SIMachineFunctionInfo.h"
+#include "llvm/CodeGen/MachineLoopInfo.h"
+using namespace llvm;
+
+#define DEBUG_TYPE "amdgpu-loop-align"
+
+static cl::opt<bool>
+    DisableLoopAlign("disable-amdgpu-loop-align", cl::init(false), cl::Hidden,
+                     cl::desc("Disable AMDGPU loop alignment pass"));
+
+namespace {
+
+class AMDGPULoopAlign {
+private:
+  MachineLoopInfo &MLI;
+
+public:
+  AMDGPULoopAlign(MachineLoopInfo &MLI) : MLI(MLI) {}
+
+  struct BasicBlockInfo {
+    // Offset - Distance from the beginning of the function to the beginning
+    // of this basic block.
+    uint64_t Offset = 0;
+    // Size - Size of the basic block in bytes
+    uint64_t Size = 0;
+  };
+
+  void generateBlockInfo(MachineFunction &MF,
+                         SmallVectorImpl<BasicBlockInfo> &BlockInfo) {
+    BlockInfo.clear();
+    BlockInfo.resize(MF.getNumBlockIDs());
+    const SIInstrInfo *TII = MF.getSubtarget<GCNSubtarget>().getInstrInfo();
+    for (const MachineBasicBlock &MBB : MF) {
+      BlockInfo[MBB.getNumber()].Size = 0;
+      for (const MachineInstr &MI : MBB) {
+        BlockInfo[MBB.getNumber()].Size += TII->getInstSizeInBytes(MI);
+      }
+    }
+    uint64_t PrevNum = (&MF)->begin()->getNumber();
+    for (auto &MBB :
+         make_range(std::next(MachineFunction::iterator((&MF)->begin())),
+                    (&MF)->end())) {
+      uint64_t Num = MBB.getNumber();
+      BlockInfo[Num].Offset =
+          BlockInfo[PrevNum].Offset + BlockInfo[PrevNum].Size;
+      unsigned blockAlignment = MBB.getAlignment().value();
+      unsigned ParentAlign = MBB.getParent()->getAlignment().value();
+      if (blockAlignment <= ParentAlign)
+        BlockInfo[Num].Offset = alignTo(BlockInfo[Num].Offset, blockAlignment);
+      else
+        BlockInfo[Num].Offset = alignTo(BlockInfo[Num].Offset, blockAlignment) +
+                                blockAlignment - ParentAlign;
+      PrevNum = Num;
+    }
+  }
+
+  bool run(MachineFunction &MF) {
+    if (DisableLoopAlign)
+      return false;
+
+    // The starting address of all shader programs must be 256 bytes aligned.
+    // Regular functions just need the basic required instruction alignment.
+    const AMDGPUMachineFunction *MFI = MF.getInfo<AMDGPUMachineFunction>();
+    MF.setAlignment(MFI->isEntryFunction() ? Align(256) : Align(4));
+    if (MF.getAlignment().value() < 32)
+      return false;
+
+    const SIInstrInfo *TII = MF.getSubtarget<GCNSubtarget>().getInstrInfo();
+    SmallVector<BasicBlockInfo, 16> BlockInfo;
+    generateBlockInfo(MF, BlockInfo);
+
+    bool Changed = false;
+    for (MachineLoop *ML : MLI.getLoopsInPreorder()) {
+      // Check if loop is innermost
+      if (!ML->isInnermost())
+        continue;
+      MachineBasicBlock *Header = ML->getHeader();
+      // Check if loop is already evaluated for prefetch & aligned
+      if (Header->getAlignment().value() == 64 ||
+          ML->getTopBlock()->getAlignment().value() == 64)
+        continue;
+
+      // If loop is < 8-dwords, align aggressively to 0 mod 8 dword boundary.
+      // else align to 0 mod 8 dword boundary only if less than 4 dwords of
+      // instructions are available
+      unsigned loopSizeInBytes = 0;
+      for (MachineBasicBlock *MBB : ML->getBlocks())
+        for (MachineInstr &MI : *MBB)
+          loopSizeInBytes += TII->getInstSizeInBytes(MI);
+
+      if (loopSizeInBytes < 32) {
+        Header->setAlignment(llvm::Align(32));
+        generateBlockInfo(MF, BlockInfo);
+        Changed = true;
+      } else if (BlockInfo[Header->getNumber()].Offset % 32 > 16) {
+        Header->setAlignment(llvm::Align(32));
+        generateBlockInfo(MF, BlockInfo);
+        Changed = true;
+      }
+    }
+    return Changed;
+  }
+};
+
+class AMDGPULoopAlignLegacy : public MachineFunctionPass {
+public:
+  static char ID;
+
+  AMDGPULoopAlignLegacy() : MachineFunctionPass(ID) {}
+
+  bool runOnMachineFunction(MachineFunction &MF) override {
+    return AMDGPULoopAlign(getAnalysis<MachineLoopInfoWrapperPass>().getLI())
+        .run(MF);
+  }
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addRequired<MachineLoopInfoWrapperPass>();
+    MachineFunctionPass::getAnalysisUsage(AU);
+  }
+};
+
+} // namespace
+
+char AMDGPULoopAlignLegacy::ID = 0;
+
+char &llvm::AMDGPULoopAlignLegacyID = AMDGPULoopAlignLegacy::ID;
+
+INITIALIZE_PASS(AMDGPULoopAlignLegacy, DEBUG_TYPE, "AMDGPU Loop Align", false,
+                false)
+
+PreservedAnalyses
+AMDGPULoopAlignPass::run(MachineFunction &MF,
+                         MachineFunctionAnalysisManager &MFAM) {
+  auto &MLI = MFAM.getResult<MachineLoopAnalysis>(MF);
+  if (AMDGPULoopAlign(MLI).run(MF))
+    return PreservedAnalyses::none();
+  return PreservedAnalyses::all();
+}
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULoopAlign.h b/llvm/lib/Target/AMDGPU/AMDGPULoopAlign.h
new file mode 100644
index 0000000000000..12b9f13926415
--- /dev/null
+++ b/llvm/lib/Target/AMDGPU/AMDGPULoopAlign.h
@@ -0,0 +1,24 @@
+//===--- AMDGPULoopAlign.h --------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPULOOPALIGN_H
+#define LLVM_LIB_TARGET_AMDGPU_AMDGPULOOPALIGN_H
+
+#include "llvm/CodeGen/MachinePassManager.h"
+
+namespace llvm {
+
+class AMDGPULoopAlignPass : public PassInfoMixin<AMDGPULoopAlignPass> {
+public:
+  PreservedAnalyses run(MachineFunction &MF,
+                        MachineFunctionAnalysisManager &MFAM);
+};
+
+} // namespace llvm
+
+#endif // LLVM_LIB_TARGET_AMDGPU_AMDGPULOOPALIGN_H
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def b/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
index b6c6d927d0e89..35c41d1d73a59 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
@@ -117,6 +117,7 @@ MACHINE_FUNCTION_PASS("amdgpu-preload-kern-arg-prolog", AMDGPUPreloadKernArgProl
 MACHINE_FUNCTION_PASS("amdgpu-prepare-agpr-alloc", AMDGPUPrepareAGPRAllocPass())
 MACHINE_FUNCTION_PASS("amdgpu-nsa-reassign", GCNNSAReassignPass())
 MACHINE_FUNCTION_PASS("amdgpu-wait-sgpr-hazards", AMDGPUWaitSGPRHazardsPass())
+MACHINE_FUNCTION_PASS("amdgpu-loop-align", AMDGPULoopAlignPass())
 MACHINE_FUNCTION_PASS("gcn-create-vopd", GCNCreateVOPDPass())
 MACHINE_FUNCTION_PASS("gcn-dpp-combine", GCNDPPCombinePass())
 MACHINE_FUNCTION_PASS("si-fix-sgpr-copies", SIFixSGPRCopiesPass())
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index c1f17033d04a8..848968a4da88a 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -22,6 +22,7 @@
 #include "AMDGPUExportKernelRuntimeHandles.h"
 #include "AMDGPUIGroupLP.h"
 #include "AMDGPUISelDAGToDAG.h"
+#include "AMDGPULoopAlign.h"
 #include "AMDGPUMacroFusion.h"
 #include "AMDGPUPerfHintAnalysis.h"
 #include "AMDGPUPreloadKernArgProlog.h"
@@ -570,6 +571,7 @@ extern "C" LLVM_ABI LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() {
   initializeGCNRegPressurePrinterPass(*PR);
   initializeAMDGPUPreloadKernArgPrologLegacyPass(*PR);
   initializeAMDGPUWaitSGPRHazardsLegacyPass(*PR);
+  initializeAMDGPULoopAlignLegacyPass(*PR);
   initializeAMDGPUPreloadKernelArgumentsLegacyPass(*PR);
 }
 
@@ -1764,6 +1766,8 @@ void GCNPassConfig::addPreEmitPass() {
     addPass(&AMDGPUInsertDelayAluID);
 
   addPass(&BranchRelaxationPassID);
+  if (getOptLevel() > CodeGenOptLevel::Less)
+    addPass(&AMDGPULoopAlignLegacyID);
 }
 
 void GCNPassConfig::addPostBBSections() {
@@ -2352,6 +2356,8 @@ void AMDGPUCodeGenPassBuilder::addPreEmitPass(AddMachinePass &addPass) const {
   }
 
   addPass(BranchRelaxationPass());
+  if (getOptLevel() > CodeGenOptLevel::Less)
+    addPass(AMDGPULoopAlignPass());
 }
 
 bool AMDGPUCodeGenPassBuilder::isPassEnabled(const cl::opt<bool> &Opt,
diff --git a/llvm/lib/Target/AMDGPU/CMakeLists.txt b/llvm/lib/Target/AMDGPU/CMakeLists.txt
index c466f9cf0f359..482b71d910a21 100644
--- a/llvm/lib/Target/AMDGPU/CMakeLists.txt
+++ b/llvm/lib/Target/AMDGPU/CMakeLists.txt
@@ -70,6 +70,7 @@ add_llvm_target(AMDGPUCodeGen
   AMDGPULibCalls.cpp
   AMDGPUImageIntrinsicOptimizer.cpp
   AMDGPULibFunc.cpp
+  AMDGPULoopAlign.cpp
   AMDGPULowerBufferFatPointers.cpp
   AMDGPULowerKernelArguments.cpp
   AMDGPULowerKernelAttributes.cpp
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-structurizer.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-structurizer.ll
index fd08ab88990ed..1b81022a273a2 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-structurizer.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-structurizer.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 -new-reg-bank-select < %s | FileCheck -check-prefix=GFX10 %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 -new-reg-bank-select < %s | FileCheck -check-prefix=GFX10 %s
 
 ; Simples case, if - then, that requires lane mask merging,
 ; %phi lane mask will hold %val_A at %A. Lanes that are active in %B
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.intersect_ray.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.intersect_ray.ll
index 2b595b9bbecc0..5d8cd9af8a7b1 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.intersect_ray.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.intersect_ray.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx1030 < %s | FileCheck -check-prefixes=GCN,GFX10,GFX1030 %s
-; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx1013 < %s | FileCheck -check-prefixes=GCN,GFX10,GFX1013 %s
-; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GCN,GFX11 %s
-; RUN: not llc -global-isel -mtriple=amdgcn -mcpu=gfx1012 < %s -o /dev/null 2>&1 | FileCheck -check-prefix=ERR %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn -mcpu=gfx1030 < %s | FileCheck -check-prefixes=GCN,GFX10,GFX1030 %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn -mcpu=gfx1013 < %s | FileCheck -check-prefixes=GCN,GFX10,GFX1013 %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GCN,GFX11 %s
+; RUN: not llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn -mcpu=gfx1012 < %s -o /dev/null 2>&1 | FileCheck -check-prefix=ERR %s
 
 ; uint4 llvm.amdgcn.image.bvh.intersect.ray.i32.v4f32(uint node_ptr, float ray_extent, float3 ray_origin, float3 ray_dir, float3 ray_inv_dir, uint4 texture_descr)
 ; uint4 llvm.amdgcn.image.bvh.intersect.ray.i32.v4f16(uint node_ptr, float ray_extent, float3 ray_origin, half3 ray_dir, half3 ray_inv_dir, uint4 texture_descr)
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wqm.demote.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wqm.demote.ll
index 8a53c862371cf..e3842a124985b 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wqm.demote.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wqm.demote.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -global-isel -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=SI %s
-; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
-; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck -check-prefix=GFX10-32 %s
-; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefix=GFX10-64 %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=SI %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck -check-prefix=GFX10-32 %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefix=GFX10-64 %s
 
 define amdgpu_ps void @static_exact(float %arg0, float %arg1) {
 ; SI-LABEL: static_exact:
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memcpy.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memcpy.ll
index e0016b0a5a64d..ba70628ea1e0b 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memcpy.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memcpy.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -global-isel -mtriple=amdgcn-- -amdgpu-memcpy-loop-unroll=2 -mem-intrinsic-expand-size=35 %s -o - | FileCheck -check-prefix=LOOP %s
-; RUN: llc -global-isel -mtriple=amdgcn-- -amdgpu-memcpy-loop-unroll=2 -mem-intrinsic-expand-size=37 %s -o - | FileCheck -check-prefix=UNROLL %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn-- -amdgpu-memcpy-loop-unroll=2 -mem-intrinsic-expand-size=35 %s -o - | FileCheck -check-prefix=LOOP %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn-- -amdgpu-memcpy-loop-unroll=2 -mem-intrinsic-expand-size=37 %s -o - | FileCheck -check-prefix=UNROLL %s
 
 declare void @llvm.memcpy.p1.p1.i32(ptr addrspace(1), ptr addrspace(1), i32, i1 immarg)
 
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memset.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memset.ll
index 04652af147f9b..cf1da9ae2e6b7 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memset.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memset.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -global-isel -mtriple=amdgcn-- -mem-intrinsic-expand-size=3 %s -o - | FileCheck -check-prefix=LOOP %s
-; RUN: llc -global-isel -mtriple=amdgcn-- -mem-intrinsic-expand-size=5 %s -o - | FileCheck -check-prefix=UNROLL %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn-- -mem-intrinsic-expand-size=3 %s -o - | FileCheck -check-prefix=LOOP %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn-- -mem-intrinsic-expand-size=5 %s -o - | FileCheck -check-prefix=UNROLL %s
 
 declare void @llvm.memset.p1.i32(ptr addrspace(1), i8, i32, i1)
 
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui.ll
index 5240bf4f3a1d7..905b6ec81b98c 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 < %s | FileCheck -check-prefix=OLD_RBS %s
-; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 -new-reg-bank-select < %s | FileCheck -check-prefix=NEW_RBS %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 < %s | FileCheck -check-prefix=OLD_RBS %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 -new-reg-bank-select < %s | FileCheck -check-prefix=NEW_RBS %s
 
 ; if instruction is uniform and there is available instruction, select SALU instruction
 define amdgpu_ps void @uniform_in_vgpr(float inreg %a, i32 inreg %b, ptr addrspace(1) %ptr) {
diff --git a/llvm/test/CodeGen/AMDGPU/atomic-optimizer-strict-wqm.ll b/llvm/test/CodeGen/AMDGPU/atomic-optimizer-strict-wqm.ll
index e03c9ca34b825..6dc12caf234de 100644
--- a/llvm/test/CodeGen/AMDGPU/atomic-optimizer-strict-wqm.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomic-optimizer-strict-wqm.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s -check-prefixes=GFX10
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s -check-prefixes=GFX10
 
 declare void @llvm.amdgcn.exp.f32(i32 immarg, i32 immarg, float, float, float, float, i1 immarg, i1 immarg)
 declare i32 @llvm.amdgcn.raw.ptr.buffer.atomic.and.i32(i32, ptr addrspace(8), i32, i32, i32 immarg)
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
index 4cc39d93854a0..db4ccd2fd44cb 100644
--- a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll
@@ -1,30 +1,30 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX7LESS,GFX7LESS_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX8,GFX8_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9,GFX9_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064,GFX1064_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032,GFX1032_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164-TRUE16,GFX1164_ITERATIVE,GFX1164_ITERATIVE-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164-FAKE16,GFX1164_ITERATIVE,GFX1164_ITERATIVE-FAKE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132-TRUE16,GFX1132_ITERATIVE,GFX1132_ITERATIVE-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132-FAKE16,GFX1132_ITERATIVE,GFX1132_ITERATIVE-FAKE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1264,GFX1264-TRUE16,GFX1264_ITERATIVE,GFX1264_ITERATIVE-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1264,GFX1264-FAKE16,GFX1264_ITERATIVE,GFX1264_ITERATIVE-FAKE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1232,GFX1232-TRUE16,GFX1232_ITERATIVE,GFX1232_ITERATIVE-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1232,GFX1232-FAKE16,GFX1232_ITERATIVE,GFX1232_ITERATIVE-FAKE16 %s
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX7LESS,GFX7LESS_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX8,GFX8_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9,GFX9_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064,GFX1064_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032,GFX1032_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164-TRUE16,GFX1164_DPP,GFX1164_DPP-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164-FAKE16,GFX1164_DPP,GFX1164_DPP-FAKE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132-TRUE16,GFX1132_DPP,GFX1132_DPP-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132-FAKE16,GFX1132_DPP,GFX1132_DPP-FAKE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1264,GFX1264-TRUE16,GFX1264_DPP,GFX1264_DPP-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1264,GFX1264-FAKE16,GFX1264_DPP,GFX1264_DPP-FAKE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1232,GFX1232-TRUE16,GFX1232_DPP,GFX1232_DPP-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1232,GFX1232-FAKE16,GFX1232_DPP,GFX1232_DPP-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX7LESS,GFX7LESS_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX8,GFX8_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9,GFX9_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064,GFX1064_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032,GFX1032_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164-TRUE16,GFX1164_ITERATIVE,GFX1164_ITERATIVE-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164-FAKE16,GFX1164_ITERATIVE,GFX1164_ITERATIVE-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132-TRUE16,GFX1132_ITERATIVE,GFX1132_ITERATIVE-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132-FAKE16,GFX1132_ITERATIVE,GFX1132_ITERATIVE-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1264,GFX1264-TRUE16,GFX1264_ITERATIVE,GFX1264_ITERATIVE-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1264,GFX1264-FAKE16,GFX1264_ITERATIVE,GFX1264_ITERATIVE-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1232,GFX1232-TRUE16,GFX1232_ITERATIVE,GFX1232_ITERATIVE-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1232,GFX1232-FAKE16,GFX1232_ITERATIVE,GFX1232_ITERATIVE-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX7LESS,GFX7LESS_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX8,GFX8_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9,GFX9_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064,GFX1064_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032,GFX1032_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164-TRUE16,GFX1164_DPP,GFX1164_DPP-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164-FAKE16,GFX1164_DPP,GFX1164_DPP-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132-TRUE16,GFX1132_DPP,GFX1132_DPP-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132-FAKE16,GFX1132_DPP,GFX1132_DPP-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1264,GFX1264-TRUE16,GFX1264_DPP,GFX1264_DPP-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1264,GFX1264-FAKE16,GFX1264_DPP,GFX1264_DPP-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1232,GFX1232-TRUE16,GFX1232_DPP,GFX1232_DPP-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize32 -mattr=-flat-for-global -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1232,GFX1232-FAKE16,GFX1232_DPP,GFX1232_DPP-FAKE16 %s
 
 declare i32 @llvm.amdgcn.workitem.id.x()
 
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
index 17737cccec7c4..1f846e866ba66 100644
--- a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll
@@ -1,18 +1,18 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX7LESS,GFX7LESS_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX8,GFX8_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9,GFX9_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064,GFX1064_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032,GFX1032_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132_ITERATIVE %s
-; RUN: llc -mtriple=amdgcn - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX7LESS,GFX7LESS_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX8,GFX8_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9,GFX9_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064,GFX1064_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032,GFX1032_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164_DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX7LESS,GFX7LESS_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX8,GFX8_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9,GFX9_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064,GFX1064_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032,GFX1032_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132_ITERATIVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX7LESS,GFX7LESS_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX8,GFX8_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9,GFX9_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064,GFX1064_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032,GFX1032_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164,GFX1164_DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -mattr=-flat-for-global - -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132,GFX1132_DPP %s
 
 declare i32 @llvm.amdgcn.workitem.id.x()
 
diff --git a/llvm/test/CodeGen/AMDGPU/branch-relaxation.ll b/llvm/test/CodeGen/AMDGPU/branch-relaxation.ll
index 5959f76492f3c..d1f5f705b91bb 100644
--- a/llvm/test/CodeGen/AMDGPU/branch-relaxation.ll
+++ b/llvm/test/CodeGen/AMDGPU/branch-relaxation.ll
@@ -1,12 +1,12 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=tahiti -amdgpu-s-branch-bits=4 -simplifycfg-require-and-preserve-domtree=1 -amdgpu-long-branch-factor=0 < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-s-branch-bits=5 -simplifycfg-require-and-preserve-domtree=1 -amdgpu-long-branch-factor=0 < %s | FileCheck -enable-var-scope -check-prefix=GFX11 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -amdgpu-s-branch-bits=5 -simplifycfg-require-and-preserve-domtree=1 -amdgpu-long-branch-factor=0 < %s | FileCheck -enable-var-scope -check-prefix=GFX12 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tahiti -amdgpu-s-branch-bits=4 -simplifycfg-require-and-preserve-domtree=1 -amdgpu-long-branch-factor=0 < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-s-branch-bits=5 -simplifycfg-require-and-preserve-domtree=1 -amdgpu-long-branch-factor=0 < %s | FileCheck -enable-var-scope -check-prefix=GFX11 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -amdgpu-s-branch-bits=5 -simplifycfg-require-and-preserve-domtree=1 -amdgpu-long-branch-factor=0 < %s | FileCheck -enable-var-scope -check-prefix=GFX12 %s
 
 
 ; FIXME: We should use llvm-mc for this, but we can't even parse our own output.
 ;        See PR33579.
-; RUN: llc -mtriple=amdgcn -amdgpu-s-branch-bits=4 -amdgpu-long-branch-factor=0 -o %t.o -filetype=obj -simplifycfg-require-and-preserve-domtree=1 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-s-branch-bits=4 -amdgpu-long-branch-factor=0 -o %t.o -filetype=obj -simplifycfg-require-and-preserve-domtree=1 %s
 ; RUN: llvm-readobj -r %t.o | FileCheck --check-prefix=OBJ %s
 
 ; OBJ:       Relocations [
diff --git a/llvm/test/CodeGen/AMDGPU/buffer-fat-pointers-memcpy.ll b/llvm/test/CodeGen/AMDGPU/buffer-fat-pointers-memcpy.ll
index 3c991cfb7a1aa..da9524e242ede 100644
--- a/llvm/test/CodeGen/AMDGPU/buffer-fat-pointers-memcpy.ll
+++ b/llvm/test/CodeGen/AMDGPU/buffer-fat-pointers-memcpy.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck -check-prefix=SDAG-GFX942 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck -check-prefix=SDAG-GFX1100 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx942 -global-isel=1 -global-isel-abort=2 < %s | FileCheck -check-prefix=GISEL-GFX942 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -global-isel-abort=2 < %s | FileCheck -check-prefix=GISEL-GFX1100 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck -check-prefix=SDAG-GFX942 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck -check-prefix=SDAG-GFX1100 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx942 -global-isel=1 -global-isel-abort=2 < %s | FileCheck -check-prefix=GISEL-GFX942 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -global-isel-abort=2 < %s | FileCheck -check-prefix=GISEL-GFX1100 %s
 
 ; Note: if you're adding tests here, also add them to
 ; lower-buffer-fat-pointers-mem-transfer.ll to verify the IR produced by
diff --git a/llvm/test/CodeGen/AMDGPU/cf-loop-on-constant.ll b/llvm/test/CodeGen/AMDGPU/cf-loop-on-constant.ll
index b5352bef50b1e..14bb4e4e618a6 100644
--- a/llvm/test/CodeGen/AMDGPU/cf-loop-on-constant.ll
+++ b/llvm/test/CodeGen/AMDGPU/cf-loop-on-constant.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=GCN %s
-; RUN: llc -mtriple=amdgcn -O0 < %s | FileCheck -check-prefix=GCN_DBG %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -O0 < %s | FileCheck -check-prefix=GCN_DBG %s
 
 define amdgpu_kernel void @test_loop(ptr addrspace(3) %ptr, i32 %n) nounwind {
 ; GCN-LABEL: test_loop:
diff --git a/llvm/test/CodeGen/AMDGPU/cgp-addressing-modes-smem.ll b/llvm/test/CodeGen/AMDGPU/cgp-addressing-modes-smem.ll
index c7f7f30a5e6bd..09309704b35e2 100644
--- a/llvm/test/CodeGen/AMDGPU/cgp-addressing-modes-smem.ll
+++ b/llvm/test/CodeGen/AMDGPU/cgp-addressing-modes-smem.ll
@@ -1,9 +1,9 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
-; RUN: llc -mtriple=amdgcn -mcpu=gfx600 < %s | FileCheck %s -check-prefixes=GFX6789,GFX678,GFX689,GFX67,GFX6
-; RUN: llc -mtriple=amdgcn -mcpu=gfx700 < %s | FileCheck %s -check-prefixes=GFX6789,GFX678,GFX67,GFX7
-; RUN: llc -mtriple=amdgcn -mcpu=gfx801 < %s | FileCheck %s -check-prefixes=GFX6789,GFX678,GFX689,GFX89
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefixes=GFX6789,GFX689,GFX89,GFX9
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck %s -check-prefixes=GFX12
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx600 < %s | FileCheck %s -check-prefixes=GFX6789,GFX678,GFX689,GFX67,GFX6
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx700 < %s | FileCheck %s -check-prefixes=GFX6789,GFX678,GFX67,GFX7
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx801 < %s | FileCheck %s -check-prefixes=GFX6789,GFX678,GFX689,GFX89
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefixes=GFX6789,GFX689,GFX89,GFX9
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck %s -check-prefixes=GFX12
 
 define amdgpu_cs void @test_sink_smem_offset_400(ptr addrspace(4) inreg %ptr, i32 inreg %val) {
 ; GFX67-LABEL: test_sink_smem_offset_400:
diff --git a/llvm/test/CodeGen/AMDGPU/coalescer_distribute.ll b/llvm/test/CodeGen/AMDGPU/coalescer_distribute.ll
index d07cc84865bea..a4fff60f2e2a9 100644
--- a/llvm/test/CodeGen/AMDGPU/coalescer_distribute.ll
+++ b/llvm/test/CodeGen/AMDGPU/coalescer_distribute.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn-- -mcpu=tahiti < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-- -mcpu=tahiti < %s | FileCheck %s
 
 ; This testcase produces a situation with unused value numbers in subregister
 ; liveranges that get distributed by ConnectedVNInfoEqClasses.
diff --git a/llvm/test/CodeGen/AMDGPU/copy-to-reg-frameindex.ll b/llvm/test/CodeGen/AMDGPU/copy-to-reg-frameindex.ll
index a13f3513c660e..4fb7c1e882e9d 100644
--- a/llvm/test/CodeGen/AMDGPU/copy-to-reg-frameindex.ll
+++ b/llvm/test/CodeGen/AMDGPU/copy-to-reg-frameindex.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx90a | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=gfx90a | FileCheck %s
 
 define amdgpu_kernel void @copy_to_reg_frameindex(ptr addrspace(1) %out, i32 %a, i32 %b, i32 %c) {
 ; CHECK-LABEL: copy_to_reg_frameindex:
diff --git a/llvm/test/CodeGen/AMDGPU/dynamic_stackalloc.ll b/llvm/test/CodeGen/AMDGPU/dynamic_stackalloc.ll
index b0439b1f7968f..b83c457fd608c 100644
--- a/llvm/test/CodeGen/AMDGPU/dynamic_stackalloc.ll
+++ b/llvm/test/CodeGen/AMDGPU/dynamic_stackalloc.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9-SDAG %s
-; RUN: llc -global-isel=1 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9-GISEL %s
-; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 < %s | FileCheck -check-prefix=GFX11-SDAG %s
-; RUN: llc -global-isel=1 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 < %s | FileCheck -check-prefix=GFX11-GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9-SDAG %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=1 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9-GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 < %s | FileCheck -check-prefix=GFX11-SDAG %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=1 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 < %s | FileCheck -check-prefix=GFX11-GISEL %s
 
 define amdgpu_kernel void @test_dynamic_stackalloc_kernel_uniform(i32 %n) {
 ; GFX9-SDAG-LABEL: test_dynamic_stackalloc_kernel_uniform:
diff --git a/llvm/test/CodeGen/AMDGPU/fix-sgpr-copies-phi-regression-issue130646-issue130119.ll b/llvm/test/CodeGen/AMDGPU/fix-sgpr-copies-phi-regression-issue130646-issue130119.ll
index d03d53a8cbbaa..0ddc2119dcdd1 100644
--- a/llvm/test/CodeGen/AMDGPU/fix-sgpr-copies-phi-regression-issue130646-issue130119.ll
+++ b/llvm/test/CodeGen/AMDGPU/fix-sgpr-copies-phi-regression-issue130646-issue130119.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 < %s | FileCheck %s
 
 ; SGPR phi ends up with VGPR inputs. Make sure we do not try to
 ; process a copy which has already been erased (which was already
diff --git a/llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll b/llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll
index 1311560715ddd..038364aa5ba01 100644
--- a/llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll
+++ b/llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefixes=GCN1 %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefixes=GCN2 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN3 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefixes=GCN1 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefixes=GCN2 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN3 %s
 
 ; ---------------------------------------------------------------------
 ; atomicrmw xchg
diff --git a/llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system.ll b/llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system.ll
index 23dfe2f70fa7e..9c922a78a10d1 100644
--- a/llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system.ll
+++ b/llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=GCN1 %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=GCN2 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN3 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=GCN1 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=GCN2 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN3 %s
 
 ; ---------------------------------------------------------------------
 ; atomicrmw xchg
diff --git a/llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system_noprivate.ll b/llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system_noprivate.ll
index fe47461ebf956..f2a90eea9ecd3 100644
--- a/llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system_noprivate.ll
+++ b/llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system_noprivate.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=GFX7 %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=GFX8 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=GFX7 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=GFX8 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9 %s
 
 ; ---------------------------------------------------------------------
 ; atomicrmw xchg
diff --git a/llvm/test/CodeGen/AMDGPU/global-load-saddr-to-vaddr.ll b/llvm/test/CodeGen/AMDGPU/global-load-saddr-to-vaddr.ll
index 6fe9e1d5561de..87e5d81775298 100644
--- a/llvm/test/CodeGen/AMDGPU/global-load-saddr-to-vaddr.ll
+++ b/llvm/test/CodeGen/AMDGPU/global-load-saddr-to-vaddr.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN %s
 
 ; The first load produces address in a VGPR which is used in address calculation
 ; of the second load (one inside the loop). The value is uniform and the inner
diff --git a/llvm/test/CodeGen/AMDGPU/global-saddr-atomics-min-max-system.ll b/llvm/test/CodeGen/AMDGPU/global-saddr-atomics-min-max-system.ll
index b7ee9f70f6014..c59cd50e753dd 100644
--- a/llvm/test/CodeGen/AMDGPU/global-saddr-atomics-min-max-system.ll
+++ b/llvm/test/CodeGen/AMDGPU/global-saddr-atomics-min-max-system.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9 %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10 %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1100 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11 %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1100 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12 %s
 
 ; Test using saddr addressing mode of global_* flat atomic instructions.
 
diff --git a/llvm/test/CodeGen/AMDGPU/global-saddr-load.ll b/llvm/test/CodeGen/AMDGPU/global-saddr-load.ll
index 1602e31d6147c..125f8c5cb5363 100644
--- a/llvm/test/CodeGen/AMDGPU/global-saddr-load.ll
+++ b/llvm/test/CodeGen/AMDGPU/global-saddr-load.ll
@@ -1,12 +1,12 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,GFX9 %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GCN,GFX10 %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11,GFX11-TRUE16 %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11,GFX11-FAKE16 %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12,GFX12-SDAG,GFX12-SDAG-TRUE16 %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12,GFX12-SDAG,GFX12-SDAG-FAKE16 %s
-; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12,GFX12-GISEL,GFX12-GISEL-TRUE16 %s
-; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12,GFX12-GISEL,GFX12-GISEL-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GCN,GFX10 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1100 -mattr=+real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11,GFX11-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1100 -mattr=-real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11,GFX11-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12,GFX12-SDAG,GFX12-SDAG-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12,GFX12-SDAG,GFX12-SDAG-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=+real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12,GFX12-GISEL,GFX12-GISEL-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -mattr=-real-true16 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX12,GFX12-GISEL,GFX12-GISEL-FAKE16 %s
 
 ; Test using saddr addressing mode of global_*load_* flat instructions.
 
diff --git a/llvm/test/CodeGen/AMDGPU/global_atomics_i32_system.ll b/llvm/test/CodeGen/AMDGPU/global_atomics_i32_system.ll
index a867c6c1affb8..dc1e67c2134d8 100644
--- a/llvm/test/CodeGen/AMDGPU/global_atomics_i32_system.ll
+++ b/llvm/test/CodeGen/AMDGPU/global_atomics_i32_system.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=SI %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=VI %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=SI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=VI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
 
 ; ---------------------------------------------------------------------
 ; atomicrmw xchg
diff --git a/llvm/test/CodeGen/AMDGPU/global_atomics_i64_system.ll b/llvm/test/CodeGen/AMDGPU/global_atomics_i64_system.ll
index a7f16449f058e..f11532633426a 100644
--- a/llvm/test/CodeGen/AMDGPU/global_atomics_i64_system.ll
+++ b/llvm/test/CodeGen/AMDGPU/global_atomics_i64_system.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=SI %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=VI %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=SI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=VI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
 
 ; ---------------------------------------------------------------------
 ; atomicrmw xchg
diff --git a/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fadd.ll b/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fadd.ll
index 37756d15861be..bf17f1cb9ab38 100644
--- a/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fadd.ll
+++ b/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fadd.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132 %s
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132-DPP %s
 
 declare float @div.float.value()
 declare double @div.double.value()
diff --git a/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmax.ll b/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmax.ll
index 6351bb39e97f5..b7b19fa85fb89 100644
--- a/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmax.ll
+++ b/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmax.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32, -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132 %s
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32, -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132-DPP %s
 
 declare float @div.float.value()
 declare float @div.double.value()
diff --git a/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmin.ll b/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmin.ll
index a9ac00863cd17..4bc5e838bc9f7 100644
--- a/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmin.ll
+++ b/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmin.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132 %s
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132-DPP %s
 
 declare float @div.float.value()
 declare float @div.double.value()
diff --git a/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fsub.ll b/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fsub.ll
index 6311143f57260..577b7d0e88ffe 100644
--- a/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fsub.ll
+++ b/llvm/test/CodeGen/AMDGPU/global_atomics_scan_fsub.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132 %s
-; RUN: llc -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164-DPP %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=Iterative < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefix=GFX7LESS-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX9-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1064-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1032-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1164-DPP %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32 -amdgpu-atomic-optimizer-strategy=DPP < %s | FileCheck -enable-var-scope -check-prefixes=GFX1132-DPP %s
 
 declare float @div.float.value()
 declare double @div.double.value()
diff --git a/llvm/test/CodeGen/AMDGPU/iglp-no-clobber.ll b/llvm/test/CodeGen/AMDGPU/iglp-no-clobber.ll
index f582f984a3924..564f88dbe0666 100644
--- a/llvm/test/CodeGen/AMDGPU/iglp-no-clobber.ll
+++ b/llvm/test/CodeGen/AMDGPU/iglp-no-clobber.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 < %s | FileCheck %s
 
 ; iglp.opt should not be flagged as clobbering the memory operand for the global_load, and we should be able to
 ; lower into the scalar version (i.e. should not need to lower into vector version with waterfall loop)
diff --git a/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll b/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
index 17a5f520ff41e..975b0ed306547 100644
--- a/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
+++ b/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
@@ -1,10 +1,10 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=GENERIC %s
-; RUN: llc -mtriple=amdgcn -mcpu=tahiti -O0 < %s | FileCheck -check-prefix=NOOPT %s
-; RUN: llc -mtriple=amdgcn -mcpu=tahiti < %s | FileCheck -check-prefix=SI-MOVREL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefixes=VI,VI-MOVREL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -amdgpu-vgpr-index-mode < %s | FileCheck -check-prefixes=VI,VI-IDXMODE %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9-IDXMODE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn < %s | FileCheck -check-prefix=GENERIC %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tahiti -O0 < %s | FileCheck -check-prefix=NOOPT %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tahiti < %s | FileCheck -check-prefix=SI-MOVREL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefixes=VI,VI-MOVREL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -amdgpu-vgpr-index-mode < %s | FileCheck -check-prefixes=VI,VI-IDXMODE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9-IDXMODE %s
 
 ; Tests for indirect addressing on SI, which is implemented using dynamic
 ; indexing of vectors.
diff --git a/llvm/test/CodeGen/AMDGPU/infer-addrspace-flat-atomic.ll b/llvm/test/CodeGen/AMDGPU/infer-addrspace-flat-atomic.ll
index 0a493e5188ad5..15ea838e22fec 100644
--- a/llvm/test/CodeGen/AMDGPU/infer-addrspace-flat-atomic.ll
+++ b/llvm/test/CodeGen/AMDGPU/infer-addrspace-flat-atomic.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck %s
 
 define protected amdgpu_kernel void @InferNothing(i32 %a, ptr %b, double %c) {
 ; CHECK-LABEL: InferNothing:
diff --git a/llvm/test/CodeGen/AMDGPU/infinite-loop.ll b/llvm/test/CodeGen/AMDGPU/infinite-loop.ll
index 3e2e43faca5aa..98b784804022d 100644
--- a/llvm/test/CodeGen/AMDGPU/infinite-loop.ll
+++ b/llvm/test/CodeGen/AMDGPU/infinite-loop.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: llc -mtriple=amdgcn -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefix=SI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefix=SI %s
 ; RUN: opt -mtriple=amdgcn-- -S -amdgpu-unify-divergent-exit-nodes -verify -simplifycfg-require-and-preserve-domtree=1 %s | FileCheck -check-prefix=IR %s
 
 define amdgpu_kernel void @infinite_loop(ptr addrspace(1) %out) {
diff --git a/llvm/test/CodeGen/AMDGPU/insert-delay-alu-bug.ll b/llvm/test/CodeGen/AMDGPU/insert-delay-alu-bug.ll
index eb5c5ef15ed56..6d5c18bf8217e 100644
--- a/llvm/test/CodeGen/AMDGPU/insert-delay-alu-bug.ll
+++ b/llvm/test/CodeGen/AMDGPU/insert-delay-alu-bug.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 %s -o - | FileCheck %s -check-prefixes=GFX11
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 %s -o - | FileCheck %s -check-prefixes=GFX11
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 %s -o - | FileCheck %s -check-prefixes=GFX11
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 %s -o - | FileCheck %s -check-prefixes=GFX11
 
 declare i32 @llvm.amdgcn.workitem.id.x()
 
diff --git a/llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll b/llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll
index 684e3257a1290..3b583066d2c18 100644
--- a/llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll
+++ b/llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -enable-var-scope %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -enable-var-scope %s
 
 ; Although it's modeled without any control flow in order to get better code
 ; out of the structurizer, @llvm.amdgcn.kill actually ends the thread that calls
diff --git a/llvm/test/CodeGen/AMDGPU/llc-pipeline-npm.ll b/llvm/test/CodeGen/AMDGPU/llc-pipeline-npm.ll
index ceed41f3ed7c5..897544c9386d5 100644
--- a/llvm/test/CodeGen/AMDGPU/llc-pipeline-npm.ll
+++ b/llvm/test/CodeGen/AMDGPU/llc-pipeline-npm.ll
@@ -1,18 +1,18 @@
-; RUN: llc -enable-new-pm -mtriple=amdgcn--amdhsa -O0 -print-pipeline-passes < %s 2>&1 \
+; RUN: llc -disable-amdgpu-loop-align=true -enable-new-pm -mtriple=amdgcn--amdhsa -O0 -print-pipeline-passes < %s 2>&1 \
 ; RUN:   | FileCheck -check-prefix=GCN-O0 %s
 
-; RUN: llc -enable-new-pm -mtriple=amdgcn--amdhsa -print-pipeline-passes < %s 2>&1 \
+; RUN: llc -disable-amdgpu-loop-align=true -enable-new-pm -mtriple=amdgcn--amdhsa -print-pipeline-passes < %s 2>&1 \
 ; RUN:   | FileCheck -check-prefix=GCN-O2 %s
 
-; RUN: llc -O3 -enable-new-pm -mtriple=amdgcn--amdhsa -print-pipeline-passes < %s 2>&1 \
+; RUN: llc -disable-amdgpu-loop-align=true -O3 -enable-new-pm -mtriple=amdgcn--amdhsa -print-pipeline-passes < %s 2>&1 \
 ; RUN:   | FileCheck -check-prefix=GCN-O3 %s
 
 
 ; GCN-O0: require<MachineModuleAnalysis>,require<profile-summary>,require<collector-metadata>,pre-isel-intrinsic-lowering,function(expand-large-div-rem,expand-fp),amdgpu-remove-incompatible-functions,amdgpu-printf-runtime-binding,amdgpu-lower-ctor-dtor,expand-variadics,amdgpu-always-inline,always-inline,amdgpu-export-kernel-runtime-handles,amdgpu-sw-lower-lds,amdgpu-lower-module-lds,function(atomic-expand,verify,gc-lowering,lower-constant-intrinsics,unreachableblockelim,ee-instrument<post-inline>,scalarize-masked-mem-intrin,expand-reductions,amdgpu-lower-kernel-arguments),amdgpu-lower-buffer-fat-pointers,cgscc(function(lower-switch,lower-invoke,unreachableblockelim,amdgpu-unify-divergent-exit-nodes,fix-irreducible,unify-loop-exits,StructurizeCFGPass,amdgpu-annotate-uniform,si-annotate-control-flow,amdgpu-rewrite-undef-for-phi,lcssa,require<uniformity>,callbr-prepare,safe-stack,stack-protector,verify)),cgscc(function(machine-function(amdgpu-isel,si-fix-sgpr-copies,si-i1-copies,finalize-isel,localstackalloc))),require<reg-usage>,cgscc(function(machine-function(reg-usage-propagation,phi-node-elimination,two-address-instruction,regallocfast,si-fix-vgpr-copies,remove-redundant-debug-values,fixup-statepoint-caller-saved,prolog-epilog,post-ra-pseudos,si-post-ra-bundler,fentry-insert,xray-instrumentation,patchable-function,si-memory-legalizer,si-insert-waitcnts,si-late-branch-lowering,post-RA-hazard-rec,amdgpu-wait-sgpr-hazards,branch-relaxation,reg-usage-collector,remove-loads-into-fake-uses,live-debug-values,machine-sanmd,stack-frame-layout,verify),free-machine-function))
 
-; GCN-O2: require<MachineModuleAnalysis>,require<profile-summary>,require<collector-metadata>,pre-isel-intrinsic-lowering,function(expand-large-div-rem,expand-fp),amdgpu-remove-incompatible-functions,amdgpu-printf-runtime-binding,amdgpu-lower-ctor-dtor,function(amdgpu-image-intrinsic-opt),expand-variadics,amdgpu-always-inline,always-inline,amdgpu-export-kernel-runtime-handles,amdgpu-sw-lower-lds,amdgpu-lower-module-lds,function(amdgpu-atomic-optimizer,atomic-expand,amdgpu-promote-alloca,separate-const-offset-from-gep<>,slsr,early-cse<>,nary-reassociate,early-cse<>,amdgpu-codegenprepare,loop-mssa(licm<allowspeculation>),verify,loop-mssa(canon-freeze,loop-reduce),mergeicmps,expand-memcmp,gc-lowering,lower-constant-intrinsics,unreachableblockelim,consthoist,replace-with-veclib,partially-inline-libcalls,ee-instrument<post-inline>,scalarize-masked-mem-intrin,expand-reductions,early-cse<>),amdgpu-preload-kernel-arguments,function(amdgpu-lower-kernel-arguments),amdgpu-lower-buffer-fat-pointers,cgscc(function(codegenprepare,load-store-vectorizer,lower-switch,lower-invoke,unreachableblockelim,flatten-cfg,sink,amdgpu-late-codegenprepare,amdgpu-unify-divergent-exit-nodes,fix-irreducible,unify-loop-exits,StructurizeCFGPass,amdgpu-annotate-uniform,si-annotate-control-flow,amdgpu-rewrite-undef-for-phi,lcssa)),amdgpu-perf-hint,cgscc(function(require<uniformity>,objc-arc-contract,callbr-prepare,safe-stack,stack-protector,verify)),cgscc(function(machine-function(amdgpu-isel,si-fix-sgpr-copies,si-i1-copies,finalize-isel,early-tailduplication,opt-phis,stack-coloring,localstackalloc,dead-mi-elimination,early-machinelicm,machine-cse,machine-sink,peephole-opt,dead-mi-elimination,si-fold-operands,gcn-dpp-combine,si-load-store-opt,si-peephole-sdwa,early-machinelicm,machine-cse,si-fold-operands,dead-mi-elimination,si-shrink-instructions))),require<reg-usage>,cgscc(function(machine-function(reg-usage-propagation,amdgpu-prepare-agpr-alloc,detect-dead-lanes,dead-mi-elimination,init-undef,process-imp-defs,unreachable-mbb-elimination,require<live-vars>,si-opt-vgpr-liverange,require<machine-loops>,phi-node-elimination,si-lower-control-flow,two-address-instruction,register-coalescer,rename-independent-subregs,amdgpu-rewrite-partial-reg-uses,machine-scheduler,amdgpu-pre-ra-optimizations,si-wqm,si-optimize-exec-masking-pre-ra,si-form-memory-clauses,amdgpu-pre-ra-long-branch-reg,greedy<sgpr>,virt-reg-rewriter<no-clear-vregs>,stack-slot-coloring,si-lower-sgpr-spills,si-pre-allocate-wwm-regs,greedy<wwm>,si-lower-wwm-copies,virt-reg-rewriter<no-clear-vregs>,amdgpu-reserve-wwm-regs,greedy<vgpr>,amdgpu-nsa-reassign,virt-reg-rewriter,amdgpu-mark-last-scratch-load,machine-cp,machinelicm,si-fix-vgpr-copies,si-optimize-exec-masking,remove-redundant-debug-values,fixup-statepoint-caller-saved,postra-machine-sink,shrink-wrap,prolog-epilog,branch-folder,tailduplication,machine-latecleanup,machine-cp,post-ra-pseudos,si-shrink-instructions,si-post-ra-bundler,postmisched,block-placement,fentry-insert,xray-instrumentation,patchable-function,gcn-create-vopd,si-memory-legalizer,si-insert-waitcnts,si-late-branch-lowering,si-pre-emit-peephole,post-RA-hazard-rec,amdgpu-wait-sgpr-hazards,amdgpu-insert-delay-alu,branch-relaxation,reg-usage-collector,remove-loads-into-fake-uses,live-debug-values,machine-sanmd,stack-frame-layout,verify),free-machine-function))
+; GCN-O2: require<MachineModuleAnalysis>,require<profile-summary>,require<collector-metadata>,pre-isel-intrinsic-lowering,function(expand-large-div-rem,expand-fp),amdgpu-remove-incompatible-functions,amdgpu-printf-runtime-binding,amdgpu-lower-ctor-dtor,function(amdgpu-image-intrinsic-opt),expand-variadics,amdgpu-always-inline,always-inline,amdgpu-export-kernel-runtime-handles,amdgpu-sw-lower-lds,amdgpu-lower-module-lds,function(amdgpu-atomic-optimizer,atomic-expand,amdgpu-promote-alloca,separate-const-offset-from-gep<>,slsr,early-cse<>,nary-reassociate,early-cse<>,amdgpu-codegenprepare,loop-mssa(licm<allowspeculation>),verify,loop-mssa(canon-freeze,loop-reduce),mergeicmps,expand-memcmp,gc-lowering,lower-constant-intrinsics,unreachableblockelim,consthoist,replace-with-veclib,partially-inline-libcalls,ee-instrument<post-inline>,scalarize-masked-mem-intrin,expand-reductions,early-cse<>),amdgpu-preload-kernel-arguments,function(amdgpu-lower-kernel-arguments),amdgpu-lower-buffer-fat-pointers,cgscc(function(codegenprepare,load-store-vectorizer,lower-switch,lower-invoke,unreachableblockelim,flatten-cfg,sink,amdgpu-late-codegenprepare,amdgpu-unify-divergent-exit-nodes,fix-irreducible,unify-loop-exits,StructurizeCFGPass,amdgpu-annotate-uniform,si-annotate-control-flow,amdgpu-rewrite-undef-for-phi,lcssa)),amdgpu-perf-hint,cgscc(function(require<uniformity>,objc-arc-contract,callbr-prepare,safe-stack,stack-protector,verify)),cgscc(function(machine-function(amdgpu-isel,si-fix-sgpr-copies,si-i1-copies,finalize-isel,early-tailduplication,opt-phis,stack-coloring,localstackalloc,dead-mi-elimination,early-machinelicm,machine-cse,machine-sink,peephole-opt,dead-mi-elimination,si-fold-operands,gcn-dpp-combine,si-load-store-opt,si-peephole-sdwa,early-machinelicm,machine-cse,si-fold-operands,dead-mi-elimination,si-shrink-instructions))),require<reg-usage>,cgscc(function(machine-function(reg-usage-propagation,amdgpu-prepare-agpr-alloc,detect-dead-lanes,dead-mi-elimination,init-undef,process-imp-defs,unreachable-mbb-elimination,require<live-vars>,si-opt-vgpr-liverange,require<machine-loops>,phi-node-elimination,si-lower-control-flow,two-address-instruction,register-coalescer,rename-independent-subregs,amdgpu-rewrite-partial-reg-uses,machine-scheduler,amdgpu-pre-ra-optimizations,si-wqm,si-optimize-exec-masking-pre-ra,si-form-memory-clauses,amdgpu-pre-ra-long-branch-reg,greedy<sgpr>,virt-reg-rewriter<no-clear-vregs>,stack-slot-coloring,si-lower-sgpr-spills,si-pre-allocate-wwm-regs,greedy<wwm>,si-lower-wwm-copies,virt-reg-rewriter<no-clear-vregs>,amdgpu-reserve-wwm-regs,greedy<vgpr>,amdgpu-nsa-reassign,virt-reg-rewriter,amdgpu-mark-last-scratch-load,machine-cp,machinelicm,si-fix-vgpr-copies,si-optimize-exec-masking,remove-redundant-debug-values,fixup-statepoint-caller-saved,postra-machine-sink,shrink-wrap,prolog-epilog,branch-folder,tailduplication,machine-latecleanup,machine-cp,post-ra-pseudos,si-shrink-instructions,si-post-ra-bundler,postmisched,block-placement,fentry-insert,xray-instrumentation,patchable-function,gcn-create-vopd,si-memory-legalizer,si-insert-waitcnts,si-late-branch-lowering,si-pre-emit-peephole,post-RA-hazard-rec,amdgpu-wait-sgpr-hazards,amdgpu-insert-delay-alu,branch-relaxation,amdgpu-loop-align,reg-usage-collector,remove-loads-into-fake-uses,live-debug-values,machine-sanmd,stack-frame-layout,verify),free-machine-function))
 
-; GCN-O3: require<MachineModuleAnalysis>,require<profile-summary>,require<collector-metadata>,pre-isel-intrinsic-lowering,function(expand-large-div-rem,expand-fp),amdgpu-remove-incompatible-functions,amdgpu-printf-runtime-binding,amdgpu-lower-ctor-dtor,function(amdgpu-image-intrinsic-opt),expand-variadics,amdgpu-always-inline,always-inline,amdgpu-export-kernel-runtime-handles,amdgpu-sw-lower-lds,amdgpu-lower-module-lds,function(amdgpu-atomic-optimizer,atomic-expand,amdgpu-promote-alloca,separate-const-offset-from-gep<>,slsr,gvn<>,nary-reassociate,early-cse<>,amdgpu-codegenprepare,loop-mssa(licm<allowspeculation>),verify,loop-mssa(canon-freeze,loop-reduce),mergeicmps,expand-memcmp,gc-lowering,lower-constant-intrinsics,unreachableblockelim,consthoist,replace-with-veclib,partially-inline-libcalls,ee-instrument<post-inline>,scalarize-masked-mem-intrin,expand-reductions,gvn<>),amdgpu-preload-kernel-arguments,function(amdgpu-lower-kernel-arguments),amdgpu-lower-buffer-fat-pointers,cgscc(function(codegenprepare,load-store-vectorizer,lower-switch,lower-invoke,unreachableblockelim,flatten-cfg,sink,amdgpu-late-codegenprepare,amdgpu-unify-divergent-exit-nodes,fix-irreducible,unify-loop-exits,StructurizeCFGPass,amdgpu-annotate-uniform,si-annotate-control-flow,amdgpu-rewrite-undef-for-phi,lcssa)),amdgpu-perf-hint,cgscc(function(require<uniformity>,objc-arc-contract,callbr-prepare,safe-stack,stack-protector,verify)),cgscc(function(machine-function(amdgpu-isel,si-fix-sgpr-copies,si-i1-copies,finalize-isel,early-tailduplication,opt-phis,stack-coloring,localstackalloc,dead-mi-elimination,early-machinelicm,machine-cse,machine-sink,peephole-opt,dead-mi-elimination,si-fold-operands,gcn-dpp-combine,si-load-store-opt,si-peephole-sdwa,early-machinelicm,machine-cse,si-fold-operands,dead-mi-elimination,si-shrink-instructions))),require<reg-usage>,cgscc(function(machine-function(reg-usage-propagation,amdgpu-prepare-agpr-alloc,detect-dead-lanes,dead-mi-elimination,init-undef,process-imp-defs,unreachable-mbb-elimination,require<live-vars>,si-opt-vgpr-liverange,require<machine-loops>,phi-node-elimination,si-lower-control-flow,two-address-instruction,register-coalescer,rename-independent-subregs,amdgpu-rewrite-partial-reg-uses,machine-scheduler,amdgpu-pre-ra-optimizations,si-wqm,si-optimize-exec-masking-pre-ra,si-form-memory-clauses,amdgpu-pre-ra-long-branch-reg,greedy<sgpr>,virt-reg-rewriter<no-clear-vregs>,stack-slot-coloring,si-lower-sgpr-spills,si-pre-allocate-wwm-regs,greedy<wwm>,si-lower-wwm-copies,virt-reg-rewriter<no-clear-vregs>,amdgpu-reserve-wwm-regs,greedy<vgpr>,amdgpu-nsa-reassign,virt-reg-rewriter,amdgpu-mark-last-scratch-load,machine-cp,machinelicm,si-fix-vgpr-copies,si-optimize-exec-masking,remove-redundant-debug-values,fixup-statepoint-caller-saved,postra-machine-sink,shrink-wrap,prolog-epilog,branch-folder,tailduplication,machine-latecleanup,machine-cp,post-ra-pseudos,si-shrink-instructions,si-post-ra-bundler,postmisched,block-placement,fentry-insert,xray-instrumentation,patchable-function,gcn-create-vopd,si-memory-legalizer,si-insert-waitcnts,si-late-branch-lowering,si-pre-emit-peephole,post-RA-hazard-rec,amdgpu-wait-sgpr-hazards,amdgpu-insert-delay-alu,branch-relaxation,reg-usage-collector,remove-loads-into-fake-uses,live-debug-values,machine-sanmd,stack-frame-layout,verify),free-machine-function))
+; GCN-O3: require<MachineModuleAnalysis>,require<profile-summary>,require<collector-metadata>,pre-isel-intrinsic-lowering,function(expand-large-div-rem,expand-fp),amdgpu-remove-incompatible-functions,amdgpu-printf-runtime-binding,amdgpu-lower-ctor-dtor,function(amdgpu-image-intrinsic-opt),expand-variadics,amdgpu-always-inline,always-inline,amdgpu-export-kernel-runtime-handles,amdgpu-sw-lower-lds,amdgpu-lower-module-lds,function(amdgpu-atomic-optimizer,atomic-expand,amdgpu-promote-alloca,separate-const-offset-from-gep<>,slsr,gvn<>,nary-reassociate,early-cse<>,amdgpu-codegenprepare,loop-mssa(licm<allowspeculation>),verify,loop-mssa(canon-freeze,loop-reduce),mergeicmps,expand-memcmp,gc-lowering,lower-constant-intrinsics,unreachableblockelim,consthoist,replace-with-veclib,partially-inline-libcalls,ee-instrument<post-inline>,scalarize-masked-mem-intrin,expand-reductions,gvn<>),amdgpu-preload-kernel-arguments,function(amdgpu-lower-kernel-arguments),amdgpu-lower-buffer-fat-pointers,cgscc(function(codegenprepare,load-store-vectorizer,lower-switch,lower-invoke,unreachableblockelim,flatten-cfg,sink,amdgpu-late-codegenprepare,amdgpu-unify-divergent-exit-nodes,fix-irreducible,unify-loop-exits,StructurizeCFGPass,amdgpu-annotate-uniform,si-annotate-control-flow,amdgpu-rewrite-undef-for-phi,lcssa)),amdgpu-perf-hint,cgscc(function(require<uniformity>,objc-arc-contract,callbr-prepare,safe-stack,stack-protector,verify)),cgscc(function(machine-function(amdgpu-isel,si-fix-sgpr-copies,si-i1-copies,finalize-isel,early-tailduplication,opt-phis,stack-coloring,localstackalloc,dead-mi-elimination,early-machinelicm,machine-cse,machine-sink,peephole-opt,dead-mi-elimination,si-fold-operands,gcn-dpp-combine,si-load-store-opt,si-peephole-sdwa,early-machinelicm,machine-cse,si-fold-operands,dead-mi-elimination,si-shrink-instructions))),require<reg-usage>,cgscc(function(machine-function(reg-usage-propagation,amdgpu-prepare-agpr-alloc,detect-dead-lanes,dead-mi-elimination,init-undef,process-imp-defs,unreachable-mbb-elimination,require<live-vars>,si-opt-vgpr-liverange,require<machine-loops>,phi-node-elimination,si-lower-control-flow,two-address-instruction,register-coalescer,rename-independent-subregs,amdgpu-rewrite-partial-reg-uses,machine-scheduler,amdgpu-pre-ra-optimizations,si-wqm,si-optimize-exec-masking-pre-ra,si-form-memory-clauses,amdgpu-pre-ra-long-branch-reg,greedy<sgpr>,virt-reg-rewriter<no-clear-vregs>,stack-slot-coloring,si-lower-sgpr-spills,si-pre-allocate-wwm-regs,greedy<wwm>,si-lower-wwm-copies,virt-reg-rewriter<no-clear-vregs>,amdgpu-reserve-wwm-regs,greedy<vgpr>,amdgpu-nsa-reassign,virt-reg-rewriter,amdgpu-mark-last-scratch-load,machine-cp,machinelicm,si-fix-vgpr-copies,si-optimize-exec-masking,remove-redundant-debug-values,fixup-statepoint-caller-saved,postra-machine-sink,shrink-wrap,prolog-epilog,branch-folder,tailduplication,machine-latecleanup,machine-cp,post-ra-pseudos,si-shrink-instructions,si-post-ra-bundler,postmisched,block-placement,fentry-insert,xray-instrumentation,patchable-function,gcn-create-vopd,si-memory-legalizer,si-insert-waitcnts,si-late-branch-lowering,si-pre-emit-peephole,post-RA-hazard-rec,amdgpu-wait-sgpr-hazards,amdgpu-insert-delay-alu,branch-relaxation,amdgpu-loop-align,reg-usage-collector,remove-loads-into-fake-uses,live-debug-values,machine-sanmd,stack-frame-layout,verify),free-machine-function))
 
 define void @empty() {
   ret void
diff --git a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
index 2a5c65278f7dc..4e35f27529303 100644
--- a/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
+++ b/llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
@@ -1,14 +1,14 @@
 ; UNSUPPORTED: expensive_checks
-; RUN: llc -O0 -mtriple=amdgcn--amdhsa -disable-verify -debug-pass=Structure < %s 2>&1 \
+; RUN: llc -disable-amdgpu-loop-align=true -O0 -mtriple=amdgcn--amdhsa -disable-verify -debug-pass=Structure < %s 2>&1 \
 ; RUN:   | FileCheck -match-full-lines -strict-whitespace -check-prefix=GCN-O0 %s
-; RUN: llc -O1 -mtriple=amdgcn--amdhsa -disable-verify -debug-pass=Structure < %s 2>&1 \
+; RUN: llc -disable-amdgpu-loop-align=true -O1 -mtriple=amdgcn--amdhsa -disable-verify -debug-pass=Structure < %s 2>&1 \
 ; RUN:   | FileCheck -match-full-lines -strict-whitespace -check-prefix=GCN-O1 %s
-; RUN: llc -O1 -mtriple=amdgcn--amdhsa -disable-verify -amdgpu-scalar-ir-passes -amdgpu-sdwa-peephole \
+; RUN: llc -disable-amdgpu-loop-align=true -O1 -mtriple=amdgcn--amdhsa -disable-verify -amdgpu-scalar-ir-passes -amdgpu-sdwa-peephole \
 ; RUN:   -amdgpu-load-store-vectorizer -amdgpu-enable-pre-ra-optimizations -amdgpu-loop-prefetch -debug-pass=Structure < %s 2>&1 \
 ; RUN:   | FileCheck -match-full-lines -strict-whitespace -check-prefix=GCN-O1-OPTS %s
-; RUN: llc -O2 -mtriple=amdgcn--amdhsa -disable-verify -debug-pass=Structure < %s 2>&1 \
+; RUN: llc -disable-amdgpu-loop-align=true -O2 -mtriple=amdgcn--amdhsa -disable-verify -debug-pass=Structure < %s 2>&1 \
 ; RUN:   | FileCheck -match-full-lines -strict-whitespace -check-prefix=GCN-O2 %s
-; RUN: llc -O3 -mtriple=amdgcn--amdhsa -disable-verify -debug-pass=Structure < %s 2>&1 \
+; RUN: llc -disable-amdgpu-loop-align=true -O3 -mtriple=amdgcn--amdhsa -disable-verify -debug-pass=Structure < %s 2>&1 \
 ; RUN:   | FileCheck -match-full-lines -strict-whitespace -check-prefix=GCN-O3 %s
 
 ; REQUIRES: asserts
@@ -1055,6 +1055,9 @@
 ; GCN-O2-NEXT:        AMDGPU Insert waits for SGPR read hazards
 ; GCN-O2-NEXT:        AMDGPU Insert Delay ALU
 ; GCN-O2-NEXT:        Branch relaxation pass
+; GCN-O2-NEXT:        MachineDominator Tree Construction
+; GCN-O2-NEXT:        Machine Natural Loop Construction
+; GCN-O2-NEXT:        AMDGPU Loop Align
 ; GCN-O2-NEXT:        Register Usage Information Collector Pass
 ; GCN-O2-NEXT:        Remove Loads Into Fake Uses
 ; GCN-O2-NEXT:        Live DEBUG_VALUE analysis
@@ -1386,6 +1389,9 @@
 ; GCN-O3-NEXT:        AMDGPU Insert waits for SGPR read hazards
 ; GCN-O3-NEXT:        AMDGPU Insert Delay ALU
 ; GCN-O3-NEXT:        Branch relaxation pass
+; GCN-O3-NEXT:        MachineDominator Tree Construction
+; GCN-O3-NEXT:        Machine Natural Loop Construction
+; GCN-O3-NEXT:        AMDGPU Loop Align
 ; GCN-O3-NEXT:        Register Usage Information Collector Pass
 ; GCN-O3-NEXT:        Remove Loads Into Fake Uses
 ; GCN-O3-NEXT:        Live DEBUG_VALUE analysis
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.pops.exiting.wave.id.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.pops.exiting.wave.id.ll
index dbe95a8091932..9149ef06c3e48 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.pops.exiting.wave.id.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.pops.exiting.wave.id.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
-; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefixes=GFX9,SDAG,GFX9-SDAG
-; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefixes=GFX9,GFX9-GISEL
-; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s -check-prefixes=GFX10,SDAG,GFX10-SDAG
-; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s -check-prefixes=GFX10,GFX10-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=0 -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefixes=GFX9,SDAG,GFX9-SDAG
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=1 -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefixes=GFX9,GFX9-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=0 -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s -check-prefixes=GFX10,SDAG,GFX10-SDAG
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=1 -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s -check-prefixes=GFX10,GFX10-GISEL
 
 declare void @foo(i32)
 
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.atomic.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.atomic.buffer.load.ll
index 7a20b5c9c51ae..612f111fd6910 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.atomic.buffer.load.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.atomic.buffer.load.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-SDAG-TRUE16
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=1 -new-reg-bank-select | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=1 -new-reg-bank-select | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-SDAG-TRUE16
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=1 -new-reg-bank-select | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=1 -new-reg-bank-select | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
 
 define amdgpu_kernel void @raw_atomic_buffer_load_i32(<4 x i32> %addr) {
 ; CHECK-LABEL: raw_atomic_buffer_load_i32:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.atomic.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.atomic.buffer.load.ll
index 561ec7de94bc6..ab369d5b8c9dc 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.atomic.buffer.load.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.atomic.buffer.load.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-SDAG-TRUE16
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=1 -new-reg-bank-select | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=1 -new-reg-bank-select | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-SDAG-TRUE16
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=0 | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -global-isel=1 -new-reg-bank-select | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -global-isel=1 -new-reg-bank-select | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
 
 define amdgpu_kernel void @raw_ptr_atomic_buffer_ptr_load_i32(ptr addrspace(8) %ptr) {
 ; CHECK-LABEL: raw_ptr_atomic_buffer_ptr_load_i32:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.add.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.add.ll
index d2ca1d8136043..0c063d263e78e 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.add.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.add.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) %out, i32 %in) {
 ; GFX8DAGISEL-LABEL: uniform_value:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll
index 356b0e73b39e7..4d9bd0deb2731 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) %out, i32 %in) {
 ; GFX8DAGISEL-LABEL: uniform_value:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.max.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.max.ll
index 7dc0cb05b0abe..cc00fa558553b 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.max.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.max.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) %out, i32 %in) {
 ; GFX8DAGISEL-LABEL: uniform_value:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.min.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.min.ll
index 7cb0e6533c722..a6e28b6447ca6 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.min.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.min.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) %out, i32 %in) {
 ; GFX8DAGISEL-LABEL: uniform_value:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.or.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.or.ll
index e08787e6ba70a..0e0d30e116ad4 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.or.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.or.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) %out, i32 %in) {
 ; GFX8DAGISEL-LABEL: uniform_value:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.sub.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.sub.ll
index edb888a21f735..d29c46c21b91e 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.sub.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.sub.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) %out, i32 %in) {
 ; GFX8DAGISEL-LABEL: uniform_value:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umax.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umax.ll
index ba7a816184cd8..e0a290dcf1e56 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umax.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umax.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
 
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) %out, i32 %in) {
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umin.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umin.ll
index 3eaa89c957474..eeedf9642ea42 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umin.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umin.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
 
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) %out, i32 %in) {
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.xor.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.xor.ll
index 5b21d5c3aaeb6..6ceb84a511cf6 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.xor.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.xor.ll
@@ -1,16 +1,16 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=0 < %s | FileCheck  -check-prefixes=GFX8DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -global-isel=1 < %s | FileCheck  -check-prefixes=GFX8GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=0 < %s | FileCheck  -check-prefixes=GFX9DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -global-isel=1 < %s | FileCheck  -check-prefixes=GFX9GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1064DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1064GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=0 < %s | FileCheck -check-prefixes=GFX10DAGISEL,GFX1032DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -global-isel=1 < %s | FileCheck -check-prefixes=GFX10GISEL,GFX1032GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1164DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1164GISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=0 < %s | FileCheck -check-prefixes=GFX11DAGISEL,GFX1132DAGISEL %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -global-isel=1 < %s | FileCheck -check-prefixes=GFX11GISEL,GFX1132GISEL %s
 
 define amdgpu_kernel void @uniform_value(ptr addrspace(1) %out, i32 %in) {
 ; GFX8DAGISEL-LABEL: uniform_value:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.atomic.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.atomic.buffer.load.ll
index f6f614e6e41b5..6e3b243fdb8b3 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.atomic.buffer.load.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.atomic.buffer.load.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-SDAG-TRUE16
-; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
-; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
-; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-SDAG-TRUE16
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
 
 define amdgpu_kernel void @struct_atomic_buffer_load_i32(<4 x i32> %addr, i32 %index) {
 ; CHECK-LABEL: struct_atomic_buffer_load_i32:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.atomic.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.atomic.buffer.load.ll
index 8f33dd6e3a69a..2a28d94fd8135 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.atomic.buffer.load.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.atomic.buffer.load.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-SDAG-TRUE16
-; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
-; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
-; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-SDAG-TRUE16
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-FAKE16
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
+; RUN: llc -disable-amdgpu-loop-align=true -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-GISEL
 
 define amdgpu_kernel void @struct_ptr_atomic_buffer_load_i32(ptr addrspace(8) %ptr, i32 %index) {
 ; CHECK-LABEL: struct_ptr_atomic_buffer_load_i32:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wqm.demote.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wqm.demote.ll
index 7d3b316915923..d018203622417 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wqm.demote.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wqm.demote.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=SI %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 < %s | FileCheck -check-prefixes=GFX10-32 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10-64 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=SI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 < %s | FileCheck -check-prefixes=GFX10-32 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 < %s | FileCheck -check-prefixes=GFX10-64 %s
 
 define amdgpu_ps void @static_exact(float %arg0, float %arg1) {
 ; SI-LABEL: static_exact:
diff --git a/llvm/test/CodeGen/AMDGPU/local-atomicrmw-fadd.ll b/llvm/test/CodeGen/AMDGPU/local-atomicrmw-fadd.ll
index a42c71c4849bd..1da46b83076e7 100644
--- a/llvm/test/CodeGen/AMDGPU/local-atomicrmw-fadd.ll
+++ b/llvm/test/CodeGen/AMDGPU/local-atomicrmw-fadd.ll
@@ -1,15 +1,15 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX12,GFX12-TRUE16 %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX12,GFX12-FAKE16 %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx942 < %s | FileCheck -check-prefix=GFX942 %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-TRUE16 %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-FAKE16 %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 < %s | FileCheck -check-prefix=GFX10 %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx90a < %s | FileCheck -check-prefix=GFX90A %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx908 < %s | FileCheck -check-prefix=GFX908 %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=tonga < %s | FileCheck -check-prefix=GFX8 %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=hawaii < %s | FileCheck -check-prefix=GFX7 %s
-; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=tahiti < %s | FileCheck -check-prefix=GFX6 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX12,GFX12-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX12,GFX12-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=gfx942 < %s | FileCheck -check-prefix=GFX942 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 < %s | FileCheck -check-prefix=GFX10 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=gfx90a < %s | FileCheck -check-prefix=GFX90A %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=gfx908 < %s | FileCheck -check-prefix=GFX908 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=tonga < %s | FileCheck -check-prefix=GFX8 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=hawaii < %s | FileCheck -check-prefix=GFX7 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdpal -mcpu=tahiti < %s | FileCheck -check-prefix=GFX6 %s
 
 ; --------------------------------------------------------------------
 ; float
diff --git a/llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll b/llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll
index a3ebaec4811a9..2747be57d2e81 100644
--- a/llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll
+++ b/llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 < %s | FileCheck --check-prefix=MUBUF %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 --mattr=+enable-flat-scratch < %s | FileCheck --check-prefix=FLATSCR %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 < %s | FileCheck --check-prefix=MUBUF %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdhsa -mcpu=gfx906 --mattr=+enable-flat-scratch < %s | FileCheck --check-prefix=FLATSCR %s
 
 ; Make sure we use the correct frame offset is used with the local
 ; frame area.
diff --git a/llvm/test/CodeGen/AMDGPU/loop-prefetch-data.ll b/llvm/test/CodeGen/AMDGPU/loop-prefetch-data.ll
index 702a69f776de3..7678d14dbc025 100644
--- a/llvm/test/CodeGen/AMDGPU/loop-prefetch-data.ll
+++ b/llvm/test/CodeGen/AMDGPU/loop-prefetch-data.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -amdgpu-loop-prefetch < %s | FileCheck --check-prefix=GFX12 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -amdgpu-loop-prefetch -mattr=+safe-smem-prefetch < %s | FileCheck --check-prefix=GFX12-SPREFETCH %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1250 -amdgpu-loop-prefetch < %s | FileCheck --check-prefix=GFX1250 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -amdgpu-loop-prefetch < %s | FileCheck --check-prefix=GFX12 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 -amdgpu-loop-prefetch -mattr=+safe-smem-prefetch < %s | FileCheck --check-prefix=GFX12-SPREFETCH %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1250 -amdgpu-loop-prefetch < %s | FileCheck --check-prefix=GFX1250 %s
 
 define amdgpu_kernel void @copy_flat(ptr nocapture %d, ptr nocapture readonly %s, i32 %n) {
 ; GFX12-LABEL: copy_flat:
diff --git a/llvm/test/CodeGen/AMDGPU/loop-prefetch.ll b/llvm/test/CodeGen/AMDGPU/loop-prefetch.ll
index 595a78ca0c08c..a421195ed3b4d 100644
--- a/llvm/test/CodeGen/AMDGPU/loop-prefetch.ll
+++ b/llvm/test/CodeGen/AMDGPU/loop-prefetch.ll
@@ -1,6 +1,6 @@
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1030 -asm-verbose=0 < %s | FileCheck --check-prefixes=GCN,GFX10,GFX10-ASM %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1030 < %s -filetype=obj | llvm-objdump -d --arch-name=amdgcn --mcpu=gfx1030 --symbolize-operands - | FileCheck --check-prefixes=GCN,GFX10,GFX10-DIS %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga < %s | FileCheck --check-prefix=GFX8 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1030 -asm-verbose=0 < %s | FileCheck --check-prefixes=GCN,GFX10,GFX10-ASM %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1030 < %s -filetype=obj | llvm-objdump -d --arch-name=amdgcn --mcpu=gfx1030 --symbolize-operands - | FileCheck --check-prefixes=GCN,GFX10,GFX10-DIS %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga < %s | FileCheck --check-prefix=GFX8 %s
 
 ; GFX8-NOT: s_inst_prefetch
 ; GFX8-NOT: .palign 6
diff --git a/llvm/test/CodeGen/AMDGPU/loop_break.ll b/llvm/test/CodeGen/AMDGPU/loop_break.ll
index 3af1341e12c51..faad3138d24c6 100644
--- a/llvm/test/CodeGen/AMDGPU/loop_break.ll
+++ b/llvm/test/CodeGen/AMDGPU/loop_break.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: opt -mtriple=amdgcn-- -S -structurizecfg -si-annotate-control-flow %s | FileCheck -check-prefix=OPT %s
-; RUN: llc -mtriple=amdgcn -disable-block-placement < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -disable-block-placement < %s | FileCheck -check-prefix=GCN %s
 
 ; Uses llvm.amdgcn.break
 
diff --git a/llvm/test/CodeGen/AMDGPU/machine-sink-temporal-divergence-swdev407790.ll b/llvm/test/CodeGen/AMDGPU/machine-sink-temporal-divergence-swdev407790.ll
index 553d7e09390fd..f3f362eab54c1 100644
--- a/llvm/test/CodeGen/AMDGPU/machine-sink-temporal-divergence-swdev407790.ll
+++ b/llvm/test/CodeGen/AMDGPU/machine-sink-temporal-divergence-swdev407790.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1031 < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1031 < %s | FileCheck %s
 
 ; ModuleID = 'kernel_round1_passing.bc'
 source_filename = "/tmp/comgr-295d04/input/CompileSource"
diff --git a/llvm/test/CodeGen/AMDGPU/mdt-preserving-crash.ll b/llvm/test/CodeGen/AMDGPU/mdt-preserving-crash.ll
index 4c2967a52fe93..88ca576369c4e 100644
--- a/llvm/test/CodeGen/AMDGPU/mdt-preserving-crash.ll
+++ b/llvm/test/CodeGen/AMDGPU/mdt-preserving-crash.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck %s
 
 @_RSENC_gDcd_______________________________ = external protected addrspace(1) externally_initialized global [4096 x i8], align 16
 
diff --git a/llvm/test/CodeGen/AMDGPU/mfma-loop.ll b/llvm/test/CodeGen/AMDGPU/mfma-loop.ll
index 6110b3101020a..1821c06b9c820 100644
--- a/llvm/test/CodeGen/AMDGPU/mfma-loop.ll
+++ b/llvm/test/CodeGen/AMDGPU/mfma-loop.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn -mcpu=gfx908 < %s | FileCheck -enable-var-scope -check-prefixes=GFX908 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck -enable-var-scope -check-prefixes=GFX90A %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck -enable-var-scope -check-prefixes=GFX942 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx908 < %s | FileCheck -enable-var-scope -check-prefixes=GFX908 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck -enable-var-scope -check-prefixes=GFX90A %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck -enable-var-scope -check-prefixes=GFX942 %s
 
 
 ; Check that we do not copy agprs to vgprs and back inside the loop.
diff --git a/llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll b/llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll
index 5ce30cbc8c015..28cf8f57a9da0 100644
--- a/llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll
+++ b/llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll
@@ -1,6 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 ; RUN: opt -mtriple=amdgcn-- -S -structurizecfg -si-annotate-control-flow %s | FileCheck -check-prefix=IR %s
-; RUN: llc -mtriple=amdgcn -mcpu=hawaii < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=hawaii < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn -mcpu=hawaii < %s | FileCheck -check-prefix=GCN-LOOPALIGN %s
 
 ; After structurizing, there are 3 levels of loops. The i1 phi
 ; conditions mutually depend on each other, so it isn't safe to delete
@@ -145,6 +146,23 @@ bb23:                                             ; preds = %bb10
 ; Earlier version of above, before a run of the structurizer.
 
 define amdgpu_kernel void @nested_loop_conditions(ptr addrspace(1) captures(none) %arg) #0 {
+; GCN-LOOPALIGN-LABEL: nested_loop_conditions:
+; GCN-LOOPALIGN:  .LBB1_3: ; %bb14
+; GCN-LOOPALIGN-NEXT:    ; =>This Loop Header: Depth=1
+; GCN-LOOPALIGN-NEXT:    ; Child Loop BB1_4 Depth 2
+; GCN-LOOPALIGN-NEXT:    s_waitcnt lgkmcnt(0)
+; GCN-LOOPALIGN-NEXT:    s_cmp_lg_u32 s4, 1
+; GCN-LOOPALIGN-NEXT:    s_mov_b64 s[0:1], -1
+; GCN-LOOPALIGN-NEXT:    ; implicit-def: $sgpr4
+; GCN-LOOPALIGN-NEXT:    s_cbranch_scc1 .LBB1_2
+; GCN-LOOPALIGN-NEXT:   .p2align 5
+; GCN-LOOPALIGN-NEXT:  .LBB1_4: ; %bb18
+; GCN-LOOPALIGN-NEXT:    ; Parent Loop BB1_3 Depth=1
+; GCN-LOOPALIGN-NEXT:    ; => This Inner Loop Header: Depth=2
+; GCN-LOOPALIGN-NEXT:    buffer_load_dword v0, off, s[0:3], 0 glc
+; GCN-LOOPALIGN-NEXT:    s_waitcnt vmcnt(0)
+; GCN-LOOPALIGN-NEXT:    v_cmp_lt_i32_e32 vcc, 8, v0
+; GCN-LOOPALIGN-NEXT:    s_cbranch_vccnz .LBB1_4
 ; GCN-LABEL: nested_loop_conditions:
 ; GCN:       ; %bb.0: ; %bb
 ; GCN-NEXT:    s_mov_b32 s3, 0xf000
diff --git a/llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll b/llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll
index 306703bd61806..6b870127a6c22 100644
--- a/llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll
+++ b/llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1030 < %s | FileCheck --check-prefix=GFX10 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck --check-prefix=GFX12 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1030 < %s | FileCheck --check-prefix=GFX10 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck --check-prefix=GFX12 %s
 
 define amdgpu_cs void @_amdgpu_cs_main(float %0, i32 %1) {
 ; GFX10-LABEL: _amdgpu_cs_main:
diff --git a/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-mov.ll b/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-mov.ll
index cf244f0b1f884..7b470fbc43ae7 100644
--- a/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-mov.ll
+++ b/llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-mov.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx942 %s -o - | FileCheck %s --check-prefixes=GFX942
-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx908 %s -o - | FileCheck %s --check-prefixes=GFX908
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn--amdhsa -mcpu=gfx942 %s -o - | FileCheck %s --check-prefixes=GFX942
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn--amdhsa -mcpu=gfx908 %s -o - | FileCheck %s --check-prefixes=GFX908
 
 define amdgpu_kernel void @matmul_kernel(i32 %a0, i32 %a1) {
 ; GFX942-LABEL: matmul_kernel:
diff --git a/llvm/test/CodeGen/AMDGPU/noclobber-barrier.ll b/llvm/test/CodeGen/AMDGPU/noclobber-barrier.ll
index 88cc06d8b3832..54647ee1ee7ee 100644
--- a/llvm/test/CodeGen/AMDGPU/noclobber-barrier.ll
+++ b/llvm/test/CodeGen/AMDGPU/noclobber-barrier.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 ; RUN: opt -mtriple=amdgcn -mcpu=gfx900 -amdgpu-aa -amdgpu-aa-wrapper -amdgpu-annotate-uniform -S < %s | FileCheck %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck -check-prefix=GCN %s
 
 ; Check that barrier or fence in between of loads is not considered a clobber
 ; for the purpose of converting vector loads into scalar.
diff --git a/llvm/test/CodeGen/AMDGPU/optimize-negated-cond.ll b/llvm/test/CodeGen/AMDGPU/optimize-negated-cond.ll
index 0887f41b7db97..f54a9144389a5 100644
--- a/llvm/test/CodeGen/AMDGPU/optimize-negated-cond.ll
+++ b/llvm/test/CodeGen/AMDGPU/optimize-negated-cond.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn < %s | FileCheck -check-prefix=GCN %s
 
 define amdgpu_kernel void @negated_cond(ptr addrspace(1) %arg1) {
 ; GCN-LABEL: negated_cond:
diff --git a/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.ll b/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.ll
index b1e05158b6212..5571e2d483677 100644
--- a/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.ll
+++ b/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.ll
@@ -1,10 +1,10 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=gfx803 < %s | FileCheck -check-prefixes=GFX8 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9,GFX900 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck -check-prefixes=GFX10 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck -check-prefixes=GFX9,GFX90A %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-FAKE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx803 < %s | FileCheck -check-prefixes=GFX8 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9,GFX900 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck -check-prefixes=GFX10 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck -check-prefixes=GFX9,GFX90A %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-TRUE16 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-FAKE16 %s
 
 declare i64 @_Z13get_global_idj(i32) #0
 
diff --git a/llvm/test/CodeGen/AMDGPU/select-undef.ll b/llvm/test/CodeGen/AMDGPU/select-undef.ll
index f497752994852..875fcc291f6e8 100644
--- a/llvm/test/CodeGen/AMDGPU/select-undef.ll
+++ b/llvm/test/CodeGen/AMDGPU/select-undef.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -amdgpu-scalar-ir-passes=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -disable-amdgpu-loop-align=true -amdgpu-scalar-ir-passes=0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
 
 define float @select_undef_lhs(float %val, i1 %cond) {
 ; GCN-LABEL: select_undef_lhs:
diff --git a/llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll b/llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
index 98c4868e213db..8adeb409d6c30 100644
--- a/llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
+++ b/llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck %s -check-prefix=GCN
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -amdgpu-atomic-optimizer-strategy=None < %s | FileCheck %s -check-prefix=GCN
 
 define amdgpu_cs void @should_not_hoist_set_inactive(<4 x i32> inreg %i14, i32 inreg %v, i32 %lane, i32 %f, i32 %f2) #0 {
 ; GCN-LABEL: should_not_hoist_set_inactive:
diff --git a/llvm/test/CodeGen/AMDGPU/si-annotate-cf.ll b/llvm/test/CodeGen/AMDGPU/si-annotate-cf.ll
index e8da10c32f5d4..71c487bc680e9 100644
--- a/llvm/test/CodeGen/AMDGPU/si-annotate-cf.ll
+++ b/llvm/test/CodeGen/AMDGPU/si-annotate-cf.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=amdgcn -mcpu=verde | FileCheck --check-prefix=SI %s
-; RUN: llc < %s -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global | FileCheck --check-prefix=FLAT %s
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=verde | FileCheck --check-prefix=SI %s
+; RUN: llc -disable-amdgpu-loop-align=true < %s -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global | FileCheck --check-prefix=FLAT %s
 
 define amdgpu_kernel void @break_inserted_outside_of_loop(ptr addrspace(1) %out, i32 %a) {
 ; SI-LABEL: break_inserted_outside_of_loop:
diff --git a/llvm/test/CodeGen/AMDGPU/si-annotate-cfg-loop-assert.ll b/llvm/test/CodeGen/AMDGPU/si-annotate-cfg-loop-assert.ll
index 5d5e35f86890c..40df1e88d8a0d 100644
--- a/llvm/test/CodeGen/AMDGPU/si-annotate-cfg-loop-assert.ll
+++ b/llvm/test/CodeGen/AMDGPU/si-annotate-cfg-loop-assert.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=kaveri < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=kaveri < %s | FileCheck %s
 
 define amdgpu_kernel void @test(i32 %arg, i32 %arg1) {
 ; CHECK-LABEL: test:
diff --git a/llvm/test/CodeGen/AMDGPU/simplifydemandedbits-recursion.ll b/llvm/test/CodeGen/AMDGPU/simplifydemandedbits-recursion.ll
index a5299ea36958d..4dfb49bfb1b30 100644
--- a/llvm/test/CodeGen/AMDGPU/simplifydemandedbits-recursion.ll
+++ b/llvm/test/CodeGen/AMDGPU/simplifydemandedbits-recursion.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn < %s | FileCheck %s
 
 ; Check we can compile this bugpoint-reduced test without an
 ; infinite loop in TLI.SimplifyDemandedBits() due to failure
diff --git a/llvm/test/CodeGen/AMDGPU/skip-if-dead.ll b/llvm/test/CodeGen/AMDGPU/skip-if-dead.ll
index b21c781f6223a..b2cffb7ab5752 100644
--- a/llvm/test/CodeGen/AMDGPU/skip-if-dead.ll
+++ b/llvm/test/CodeGen/AMDGPU/skip-if-dead.ll
@@ -1,8 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=tahiti -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,WAVE64,SI %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,WAVE64,GFX10-WAVE64 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX10-WAVE32 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX11 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tahiti -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,WAVE64,SI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,WAVE64,GFX10-WAVE64 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX10-WAVE32 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX11 %s
 
 define amdgpu_ps void @test_kill_depth_0_imm_pos() #0 {
 ; GCN-LABEL: test_kill_depth_0_imm_pos:
diff --git a/llvm/test/CodeGen/AMDGPU/srem64.ll b/llvm/test/CodeGen/AMDGPU/srem64.ll
index e64e3def98c26..e7d869f704489 100644
--- a/llvm/test/CodeGen/AMDGPU/srem64.ll
+++ b/llvm/test/CodeGen/AMDGPU/srem64.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=gfx600 -amdgpu-bypass-slow-div=0 < %s | FileCheck -check-prefix=GCN %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx600 -amdgpu-bypass-slow-div=0 -amdgpu-codegenprepare-expand-div64 < %s | FileCheck -check-prefix=GCN-IR %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx600 -amdgpu-bypass-slow-div=0 < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx600 -amdgpu-bypass-slow-div=0 -amdgpu-codegenprepare-expand-div64 < %s | FileCheck -check-prefix=GCN-IR %s
 
 define amdgpu_kernel void @s_test_srem(ptr addrspace(1) %out, i64 %x, i64 %y) {
 ; GCN-LABEL: s_test_srem:
diff --git a/llvm/test/CodeGen/AMDGPU/trap-abis.ll b/llvm/test/CodeGen/AMDGPU/trap-abis.ll
index 469ea24634f62..014ed41813d09 100644
--- a/llvm/test/CodeGen/AMDGPU/trap-abis.ll
+++ b/llvm/test/CodeGen/AMDGPU/trap-abis.ll
@@ -1,10 +1,10 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc %s -o - -mtriple=amdgcn -mcpu=gfx900 | FileCheck --check-prefix=NOHSA-TRAP-GFX900 %s
-; RUN: llc %s -o - -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 | FileCheck --check-prefix=HSA-TRAP-GFX803 %s
-; RUN: llc %s -o - -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 | FileCheck --check-prefix=HSA-TRAP-GFX900 %s
-; RUN: llc %s -o - -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-trap-handler | FileCheck --check-prefix=HSA-NOTRAP-GFX900 %s
-; RUN: llc %s -o - -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 | FileCheck --check-prefix=HSA-TRAP-GFX1100 %s
-; RUN: llc %s -o - -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 | FileCheck --check-prefix=HSA-TRAP-GFX1100-O0 %s
+; RUN: llc -disable-amdgpu-loop-align=true %s -o - -mtriple=amdgcn -mcpu=gfx900 | FileCheck --check-prefix=NOHSA-TRAP-GFX900 %s
+; RUN: llc -disable-amdgpu-loop-align=true %s -o - -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 | FileCheck --check-prefix=HSA-TRAP-GFX803 %s
+; RUN: llc -disable-amdgpu-loop-align=true %s -o - -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 | FileCheck --check-prefix=HSA-TRAP-GFX900 %s
+; RUN: llc -disable-amdgpu-loop-align=true %s -o - -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-trap-handler | FileCheck --check-prefix=HSA-NOTRAP-GFX900 %s
+; RUN: llc -disable-amdgpu-loop-align=true %s -o - -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 | FileCheck --check-prefix=HSA-TRAP-GFX1100 %s
+; RUN: llc -disable-amdgpu-loop-align=true %s -o - -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 | FileCheck --check-prefix=HSA-TRAP-GFX1100-O0 %s
 
 declare void @llvm.trap() #0
 declare void @llvm.debugtrap() #1
diff --git a/llvm/test/CodeGen/AMDGPU/undefined-subreg-liverange.ll b/llvm/test/CodeGen/AMDGPU/undefined-subreg-liverange.ll
index 31708a9b738db..819279abb8f31 100644
--- a/llvm/test/CodeGen/AMDGPU/undefined-subreg-liverange.ll
+++ b/llvm/test/CodeGen/AMDGPU/undefined-subreg-liverange.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn < %s | FileCheck %s
-; RUN: llc -mtriple=amdgcn -early-live-intervals < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn < %s | FileCheck %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -early-live-intervals < %s | FileCheck %s
 
 ; We may have subregister live ranges that are undefined on some paths. The
 ; verifier should not complain about this.
diff --git a/llvm/test/CodeGen/AMDGPU/uniform-cfg.ll b/llvm/test/CodeGen/AMDGPU/uniform-cfg.ll
index 5108159e7a847..d6fb222b119dd 100644
--- a/llvm/test/CodeGen/AMDGPU/uniform-cfg.ll
+++ b/llvm/test/CodeGen/AMDGPU/uniform-cfg.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn -mcpu=verde -amdgpu-early-ifcvt=0 -machine-sink-split-probability-threshold=0 -structurizecfg-skip-uniform-regions < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-early-ifcvt=0 -machine-sink-split-probability-threshold=0 -structurizecfg-skip-uniform-regions < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=verde -amdgpu-early-ifcvt=0 -machine-sink-split-probability-threshold=0 -structurizecfg-skip-uniform-regions < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -amdgpu-early-ifcvt=0 -machine-sink-split-probability-threshold=0 -structurizecfg-skip-uniform-regions < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI %s
 
 define amdgpu_kernel void @uniform_if_scc(i32 %cond, ptr addrspace(1) %out) {
 ; SI-LABEL: uniform_if_scc:
diff --git a/llvm/test/CodeGen/AMDGPU/valu-i1.ll b/llvm/test/CodeGen/AMDGPU/valu-i1.ll
index 0f368ffd33b9d..94628f60ebd0e 100644
--- a/llvm/test/CodeGen/AMDGPU/valu-i1.ll
+++ b/llvm/test/CodeGen/AMDGPU/valu-i1.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn -enable-misched -asm-verbose -disable-block-placement -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefix=SI %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -enable-misched -asm-verbose -disable-block-placement -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefix=SI %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
 
diff --git a/llvm/test/CodeGen/AMDGPU/vni8-across-blocks.ll b/llvm/test/CodeGen/AMDGPU/vni8-across-blocks.ll
index d8264b5a091e1..5870bdc3a441e 100644
--- a/llvm/test/CodeGen/AMDGPU/vni8-across-blocks.ll
+++ b/llvm/test/CodeGen/AMDGPU/vni8-across-blocks.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
-; RUN: llc -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck --check-prefix=GFX942 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck --check-prefix=GFX942 %s
 
 define amdgpu_kernel void @v3i8_liveout(ptr addrspace(1) %src1, ptr addrspace(1) %src2, ptr addrspace(1) nocapture %dst) {
 ; GFX942-LABEL: v3i8_liveout:
diff --git a/llvm/test/CodeGen/AMDGPU/wave32.ll b/llvm/test/CodeGen/AMDGPU/wave32.ll
index 097154ed23ede..9912b4c7c3651 100644
--- a/llvm/test/CodeGen/AMDGPU/wave32.ll
+++ b/llvm/test/CodeGen/AMDGPU/wave32.ll
@@ -1,9 +1,9 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1032 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1064 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -amdgpu-early-ifcvt=1 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1032 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -amdgpu-early-ifcvt=1 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1064 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1032,GFX10DEFWAVE %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1032 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1064 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -amdgpu-early-ifcvt=1 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1032 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -amdgpu-early-ifcvt=1 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1064 %s
+; RUN: llc -disable-amdgpu-loop-align=true -mtriple=amdgcn -mcpu=gfx1010 -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefixes=GCN,GFX1032,GFX10DEFWAVE %s
 
 define amdgpu_kernel void @test_vopc_i32(ptr addrspace(1) %arg) {
 ; GFX1032-LABEL: test_vopc_i32:



More information about the llvm-commits mailing list