https://github.com/optimisan updated
https://github.com/llvm/llvm-project/pull/130062
>From 48ec9e7d569fa5f181188aafe31fdf23fe494c76 Mon Sep 17 00:00:00 2001
From: Akshat Oke <akshat....@amd.com>
Date: Thu, 6 Mar 2025 04:52:38 +0000
Subject: [PATCH] [AMDGPU][NPM] Port SIInsertHardClauses to NPM
---
llvm/lib/Target/AMDGPU/AMDGPU.h | 8 ++-
llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def | 2 +-
.../lib/Target/AMDGPU/AMDGPUTargetMachine.cpp | 2 +-
.../lib/Target/AMDGPU/SIInsertHardClauses.cpp | 50 +++++++++++++------
.../CodeGen/AMDGPU/hard-clauses-img-gfx10.mir | 1 +
.../CodeGen/AMDGPU/hard-clauses-img-gfx11.mir | 1 +
6 files changed, 46 insertions(+), 18 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.h b/llvm/lib/Target/AMDGPU/AMDGPU.h
index 4dcfaf9b12b5e..b434676f85581 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.h
@@ -378,6 +378,12 @@ class SIInsertWaitcntsPass : public
PassInfoMixin<SIInsertWaitcntsPass> {
static bool isRequired() { return true; }
};
+class SIInsertHardClausesPass : public PassInfoMixin<SIInsertHardClausesPass> {
+public:
+ PreservedAnalyses run(MachineFunction &MF,
+ MachineFunctionAnalysisManager &MFAM);
+};
+
FunctionPass *createAMDGPUAnnotateUniformValuesLegacy();
ModulePass *createAMDGPUPrintfRuntimeBinding();
@@ -451,7 +457,7 @@ extern char &SIModeRegisterID;
void initializeAMDGPUInsertDelayAluLegacyPass(PassRegistry &);
extern char &AMDGPUInsertDelayAluID;
-void initializeSIInsertHardClausesPass(PassRegistry &);
+void initializeSIInsertHardClausesLegacyPass(PassRegistry &);
extern char &SIInsertHardClausesID;
void initializeSIInsertWaitcntsLegacyPass(PassRegistry &);
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
b/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
index c4641cba60e53..3eabe087a8a33 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
@@ -109,6 +109,7 @@ MACHINE_FUNCTION_PASS("si-fix-vgpr-copies",
SIFixVGPRCopiesPass())
MACHINE_FUNCTION_PASS("si-fold-operands", SIFoldOperandsPass());
MACHINE_FUNCTION_PASS("si-form-memory-clauses", SIFormMemoryClausesPass())
MACHINE_FUNCTION_PASS("si-i1-copies", SILowerI1CopiesPass())
+MACHINE_FUNCTION_PASS("si-insert-hard-clauses", SIInsertHardClausesPass())
MACHINE_FUNCTION_PASS("si-insert-waitcnts", SIInsertWaitcntsPass())
MACHINE_FUNCTION_PASS("si-load-store-opt", SILoadStoreOptimizerPass())
MACHINE_FUNCTION_PASS("si-lower-control-flow", SILowerControlFlowPass())
@@ -131,7 +132,6 @@ DUMMY_MACHINE_FUNCTION_PASS("amdgpu-pre-ra-optimizations",
GCNPreRAOptimizations
DUMMY_MACHINE_FUNCTION_PASS("amdgpu-rewrite-partial-reg-uses",
GCNRewritePartialRegUsesPass())
DUMMY_MACHINE_FUNCTION_PASS("amdgpu-set-wave-priority",
AMDGPUSetWavePriorityPass())
-DUMMY_MACHINE_FUNCTION_PASS("si-insert-hard-clauses",
SIInsertHardClausesPass())
DUMMY_MACHINE_FUNCTION_PASS("si-late-branch-lowering",
SILateBranchLoweringPass())
DUMMY_MACHINE_FUNCTION_PASS("si-pre-emit-peephole", SIPreEmitPeepholePass())
// TODO: Move amdgpu-preload-kern-arg-prolog to MACHINE_FUNCTION_PASS since it
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index c3cc1dc6e495b..6c24fe5f1441a 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -534,7 +534,7 @@ extern "C" LLVM_EXTERNAL_VISIBILITY void
LLVMInitializeAMDGPUTarget() {
initializeAMDGPUUnifyMetadataPass(*PR);
initializeSIAnnotateControlFlowLegacyPass(*PR);
initializeAMDGPUInsertDelayAluLegacyPass(*PR);
- initializeSIInsertHardClausesPass(*PR);
+ initializeSIInsertHardClausesLegacyPass(*PR);
initializeSIInsertWaitcntsLegacyPass(*PR);
initializeSIModeRegisterLegacyPass(*PR);
initializeSIWholeQuadModeLegacyPass(*PR);
diff --git a/llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp
b/llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp
index dcc60765cc203..71b937f23cc3c 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp
@@ -36,6 +36,7 @@
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachinePassManager.h"
using namespace llvm;
@@ -89,18 +90,10 @@ enum HardClauseType {
HARDCLAUSE_ILLEGAL,
};
-class SIInsertHardClauses : public MachineFunctionPass {
+class SIInsertHardClauses {
public:
- static char ID;
const GCNSubtarget *ST = nullptr;
- SIInsertHardClauses() : MachineFunctionPass(ID) {}
-
- void getAnalysisUsage(AnalysisUsage &AU) const override {
- AU.setPreservesCFG();
- MachineFunctionPass::getAnalysisUsage(AU);
- }
-
HardClauseType getHardClauseType(const MachineInstr &MI) {
if (MI.mayLoad() || (MI.mayStore() && ST->shouldClusterStores())) {
if (ST->getGeneration() == AMDGPUSubtarget::GFX10) {
@@ -189,9 +182,7 @@ class SIInsertHardClauses : public MachineFunctionPass {
return true;
}
- bool runOnMachineFunction(MachineFunction &MF) override {
- if (skipFunction(MF.getFunction()))
- return false;
+ bool run(MachineFunction &MF) {
ST = &MF.getSubtarget<GCNSubtarget>();
if (!ST->hasHardClauses())
@@ -265,11 +256,40 @@ class SIInsertHardClauses : public MachineFunctionPass {
}
};
+class SIInsertHardClausesLegacy : public MachineFunctionPass {
+public:
+ static char ID;
+ SIInsertHardClausesLegacy() : MachineFunctionPass(ID) {}
+
+ bool runOnMachineFunction(MachineFunction &MF) override {
+ if (skipFunction(MF.getFunction()))
+ return false;
+
+ return SIInsertHardClauses().run(MF);
+ }
+
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
+ AU.setPreservesCFG();
+ MachineFunctionPass::getAnalysisUsage(AU);
+ }
+};
+
} // namespace
-char SIInsertHardClauses::ID = 0;
+PreservedAnalyses
+llvm::SIInsertHardClausesPass::run(MachineFunction &MF,
+ MachineFunctionAnalysisManager &MFAM) {
+ if (!SIInsertHardClauses().run(MF))
+ return PreservedAnalyses::all();
+
+ auto PA = getMachineFunctionPassPreservedAnalyses();
+ PA.preserveSet<CFGAnalyses>();
+ return PA;
+}
+
+char SIInsertHardClausesLegacy::ID = 0;
-char &llvm::SIInsertHardClausesID = SIInsertHardClauses::ID;
+char &llvm::SIInsertHardClausesID = SIInsertHardClausesLegacy::ID;
-INITIALIZE_PASS(SIInsertHardClauses, DEBUG_TYPE, "SI Insert Hard Clauses",
+INITIALIZE_PASS(SIInsertHardClausesLegacy, DEBUG_TYPE, "SI Insert Hard
Clauses",
false, false)
diff --git a/llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx10.mir
b/llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx10.mir
index 50eea4aebd5e9..1baceeef82c92 100644
--- a/llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx10.mir
+++ b/llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx10.mir
@@ -1,5 +1,6 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass
si-insert-hard-clauses %s -o - | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs -passes
si-insert-hard-clauses %s -o - | FileCheck %s
---
name: mimg_nsa
diff --git a/llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx11.mir
b/llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx11.mir
index b22de06e68a7f..7505fde047782 100644
--- a/llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx11.mir
+++ b/llvm/test/CodeGen/AMDGPU/hard-clauses-img-gfx11.mir
@@ -1,5 +1,6 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs -run-pass
si-insert-hard-clauses %s -o - | FileCheck %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs -passes
si-insert-hard-clauses %s -o - | FileCheck %s
---
name: mimg_nsa
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
