[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 11:14:59 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-globalisel
Author: None (hjagasiaAMD)
<details>
<summary>Changes</summary>
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.
---
Patch is 174.55 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/152356.diff
85 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/AMDGPU.h (+3)
- (added) llvm/lib/Target/AMDGPU/AMDGPULoopAlign.cpp (+153)
- (added) llvm/lib/Target/AMDGPU/AMDGPULoopAlign.h (+24)
- (modified) llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def (+1)
- (modified) llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp (+6)
- (modified) llvm/lib/Target/AMDGPU/CMakeLists.txt (+1)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-structurizer.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.intersect_ray.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.wqm.demote.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memcpy.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.memset.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-mui.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/atomic-optimizer-strict-wqm.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/atomic_optimizations_global_pointer.ll (+26-26)
- (modified) llvm/test/CodeGen/AMDGPU/atomic_optimizations_local_pointer.ll (+14-14)
- (modified) llvm/test/CodeGen/AMDGPU/branch-relaxation.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/buffer-fat-pointers-memcpy.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/cf-loop-on-constant.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/cgp-addressing-modes-smem.ll (+5-5)
- (modified) llvm/test/CodeGen/AMDGPU/coalescer_distribute.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/copy-to-reg-frameindex.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/dynamic_stackalloc.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/fix-sgpr-copies-phi-regression-issue130646-issue130119.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system.ll (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system_noprivate.ll (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/global-load-saddr-to-vaddr.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/global-saddr-atomics-min-max-system.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/global-saddr-load.ll (+8-8)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_i32_system.ll (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_i64_system.ll (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_scan_fadd.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmax.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmin.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_scan_fsub.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/iglp-no-clobber.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll (+6-6)
- (modified) llvm/test/CodeGen/AMDGPU/infer-addrspace-flat-atomic.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/infinite-loop.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/insert-delay-alu-bug.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/llc-pipeline-npm.ll (+5-5)
- (modified) llvm/test/CodeGen/AMDGPU/llc-pipeline.ll (+11-5)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.pops.exiting.wave.id.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.atomic.buffer.load.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.atomic.buffer.load.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.add.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.max.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.min.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.or.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.sub.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umax.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.umin.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.xor.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.atomic.buffer.load.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.atomic.buffer.load.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wqm.demote.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/local-atomicrmw-fadd.ll (+11-11)
- (modified) llvm/test/CodeGen/AMDGPU/local-stack-alloc-block-sp-reference.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/loop-prefetch-data.ll (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/loop-prefetch.ll (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/loop_break.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/machine-sink-temporal-divergence-swdev407790.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/mdt-preserving-crash.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/mfma-loop.ll (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll (+19-1)
- (modified) llvm/test/CodeGen/AMDGPU/no-dup-inst-prefetch.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/no-fold-accvgpr-mov.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/noclobber-barrier.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/optimize-negated-cond.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.ll (+6-6)
- (modified) llvm/test/CodeGen/AMDGPU/select-undef.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/si-annotate-cf.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/si-annotate-cfg-loop-assert.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/simplifydemandedbits-recursion.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/skip-if-dead.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/srem64.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/trap-abis.ll (+6-6)
- (modified) llvm/test/CodeGen/AMDGPU/undefined-subreg-liverange.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/uniform-cfg.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/valu-i1.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/vni8-across-blocks.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/wave32.ll (+5-5)
``````````diff
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=-fla...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/152356
More information about the llvm-commits
mailing list