[llvm] [MacroFusion] Support multiple predicators (PR #72219)

[Wang Pengcheng via llvm-commits]

https://github.com/wangpc-pp updated https://github.com/llvm/llvm-project/pull/72219

>From f137309d3772b18b83e0a587c7d4065ec4f610b8 Mon Sep 17 00:00:00 2001
From: wangpc <wangpengcheng.pp at bytedance.com>
Date: Fri, 10 Nov 2023 17:58:00 +0800
Subject: [PATCH] [MacroFusion] Support multiple predicators

The user can provide multiple predicators to MacroFusion and the
DAG mutation will be applied if one of them is evalated to true.

`ShouldSchedulePredTy` is renamed to `MacroFusionPredTy`.
---
 llvm/include/llvm/CodeGen/MacroFusion.h | 20 +++++++------
 llvm/lib/CodeGen/MacroFusion.cpp        | 37 +++++++++++++++++--------
 llvm/lib/Target/AMDGPU/GCNVOPDUtils.cpp |  4 +--
 3 files changed, 38 insertions(+), 23 deletions(-)

diff --git a/llvm/include/llvm/CodeGen/MacroFusion.h b/llvm/include/llvm/CodeGen/MacroFusion.h
index ea2c7a5faae385..a359fca6042600 100644
--- a/llvm/include/llvm/CodeGen/MacroFusion.h
+++ b/llvm/include/llvm/CodeGen/MacroFusion.h
@@ -14,7 +14,7 @@
 #ifndef LLVM_CODEGEN_MACROFUSION_H
 #define LLVM_CODEGEN_MACROFUSION_H
 
-#include <functional>
+#include "llvm/ADT/ArrayRef.h"
 #include <memory>
 
 namespace llvm {
@@ -29,10 +29,10 @@ class SUnit;
 /// Check if the instr pair, FirstMI and SecondMI, should be fused
 /// together. Given SecondMI, when FirstMI is unspecified, then check if
 /// SecondMI may be part of a fused pair at all.
-using ShouldSchedulePredTy = std::function<bool(const TargetInstrInfo &TII,
-                                                const TargetSubtargetInfo &TSI,
-                                                const MachineInstr *FirstMI,
-                                                const MachineInstr &SecondMI)>;
+using MacroFusionPredTy = bool (*)(const TargetInstrInfo &TII,
+                                   const TargetSubtargetInfo &STI,
+                                   const MachineInstr *FirstMI,
+                                   const MachineInstr &SecondMI);
 
 /// Checks if the number of cluster edges between SU and its predecessors is
 /// less than FuseLimit
@@ -48,15 +48,17 @@ bool fuseInstructionPair(ScheduleDAGInstrs &DAG, SUnit &FirstSU,
 
 /// Create a DAG scheduling mutation to pair instructions back to back
 /// for instructions that benefit according to the target-specific
-/// shouldScheduleAdjacent predicate function.
+/// predicate functions. shouldScheduleAdjacent will be true if any of the
+/// provided predicates are true.
 std::unique_ptr<ScheduleDAGMutation>
-createMacroFusionDAGMutation(ShouldSchedulePredTy shouldScheduleAdjacent);
+createMacroFusionDAGMutation(ArrayRef<MacroFusionPredTy> Predicates);
 
 /// Create a DAG scheduling mutation to pair branch instructions with one
 /// of their predecessors back to back for instructions that benefit according
-/// to the target-specific shouldScheduleAdjacent predicate function.
+/// to the target-specific predicate functions. shouldScheduleAdjacent will be
+/// true if any of the provided predicates are true.
 std::unique_ptr<ScheduleDAGMutation>
-createBranchMacroFusionDAGMutation(ShouldSchedulePredTy shouldScheduleAdjacent);
+createBranchMacroFusionDAGMutation(ArrayRef<MacroFusionPredTy> Predicates);
 
 } // end namespace llvm
 
diff --git a/llvm/lib/CodeGen/MacroFusion.cpp b/llvm/lib/CodeGen/MacroFusion.cpp
index fa5df68b8abcc0..30affc93d4adc0 100644
--- a/llvm/lib/CodeGen/MacroFusion.cpp
+++ b/llvm/lib/CodeGen/MacroFusion.cpp
@@ -137,19 +137,34 @@ namespace {
 /// Post-process the DAG to create cluster edges between instrs that may
 /// be fused by the processor into a single operation.
 class MacroFusion : public ScheduleDAGMutation {
-  ShouldSchedulePredTy shouldScheduleAdjacent;
+  std::vector<MacroFusionPredTy> Predicates;
   bool FuseBlock;
   bool scheduleAdjacentImpl(ScheduleDAGInstrs &DAG, SUnit &AnchorSU);
 
 public:
-  MacroFusion(ShouldSchedulePredTy shouldScheduleAdjacent, bool FuseBlock)
-    : shouldScheduleAdjacent(shouldScheduleAdjacent), FuseBlock(FuseBlock) {}
+  MacroFusion(ArrayRef<MacroFusionPredTy> Predicates, bool FuseBlock)
+      : Predicates(Predicates.begin(), Predicates.end()), FuseBlock(FuseBlock) {
+  }
 
   void apply(ScheduleDAGInstrs *DAGInstrs) override;
+
+  bool shouldScheduleAdjacent(const TargetInstrInfo &TII,
+                              const TargetSubtargetInfo &STI,
+                              const MachineInstr *FirstMI,
+                              const MachineInstr &SecondMI);
 };
 
 } // end anonymous namespace
 
+bool MacroFusion::shouldScheduleAdjacent(const TargetInstrInfo &TII,
+                                         const TargetSubtargetInfo &STI,
+                                         const MachineInstr *FirstMI,
+                                         const MachineInstr &SecondMI) {
+  return llvm::any_of(Predicates, [&](MacroFusionPredTy Predicate) {
+    return Predicate(TII, STI, FirstMI, SecondMI);
+  });
+}
+
 void MacroFusion::apply(ScheduleDAGInstrs *DAG) {
   if (FuseBlock)
     // For each of the SUnits in the scheduling block, try to fuse the instr in
@@ -197,17 +212,15 @@ bool MacroFusion::scheduleAdjacentImpl(ScheduleDAGInstrs &DAG, SUnit &AnchorSU)
 }
 
 std::unique_ptr<ScheduleDAGMutation>
-llvm::createMacroFusionDAGMutation(
-     ShouldSchedulePredTy shouldScheduleAdjacent) {
-  if(EnableMacroFusion)
-    return std::make_unique<MacroFusion>(shouldScheduleAdjacent, true);
+llvm::createMacroFusionDAGMutation(ArrayRef<MacroFusionPredTy> Predicates) {
+  if (EnableMacroFusion)
+    return std::make_unique<MacroFusion>(std::move(Predicates), true);
   return nullptr;
 }
 
-std::unique_ptr<ScheduleDAGMutation>
-llvm::createBranchMacroFusionDAGMutation(
-     ShouldSchedulePredTy shouldScheduleAdjacent) {
-  if(EnableMacroFusion)
-    return std::make_unique<MacroFusion>(shouldScheduleAdjacent, false);
+std::unique_ptr<ScheduleDAGMutation> llvm::createBranchMacroFusionDAGMutation(
+    ArrayRef<MacroFusionPredTy> Predicates) {
+  if (EnableMacroFusion)
+    return std::make_unique<MacroFusion>(std::move(Predicates), false);
   return nullptr;
 }
diff --git a/llvm/lib/Target/AMDGPU/GCNVOPDUtils.cpp b/llvm/lib/Target/AMDGPU/GCNVOPDUtils.cpp
index 29c9b9ccf27614..0bddeeef9e9b1a 100644
--- a/llvm/lib/Target/AMDGPU/GCNVOPDUtils.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNVOPDUtils.cpp
@@ -142,10 +142,10 @@ namespace {
 /// be turned into VOPD instructions
 /// Greedily pairs instruction candidates. O(n^2) algorithm.
 struct VOPDPairingMutation : ScheduleDAGMutation {
-  ShouldSchedulePredTy shouldScheduleAdjacent; // NOLINT: function pointer
+  MacroFusionPredTy shouldScheduleAdjacent; // NOLINT: function pointer
 
   VOPDPairingMutation(
-      ShouldSchedulePredTy shouldScheduleAdjacent) // NOLINT: function pointer
+      MacroFusionPredTy shouldScheduleAdjacent) // NOLINT: function pointer
       : shouldScheduleAdjacent(shouldScheduleAdjacent) {}
 
   void apply(ScheduleDAGInstrs *DAG) override {