[llvm] [AMDGPU] Introduce iglp_opt(2): Generalized exp/mfma interleaving for select kernels (PR #81342)

[Austin Kerbow via llvm-commits]

================
@@ -902,6 +904,921 @@ void MFMASmallGemmOpt::applyIGLPStrategy(
         SchedGroupMask::MFMA, 1, PipelineSyncID, DAG, TII);
     SG->initSchedGroup(SyncedInstrs[SG->getSyncID()]);
   }
+
+  return true;
+}
+
+class MFMAExpInterleaveOpt final : public IGLPStrategy {
+private:
+  SmallVector<SUnit *, 4> MFMAChainSeeds;
+  // Compute the heuristics for the pipeline, returning whether or not the DAG
+  // is well formatted for the mutation
+  bool analyzeDAG(const SIInstrInfo *TII);
+
+  /// Whether or not the instruction is a transitive predecessor of an MFMA
+  /// instruction
+  class IsPipeExp final : public InstructionRule {
+  public:
+    bool apply(const SUnit *SU, const ArrayRef<SUnit *> Collection,
+               SmallVectorImpl<SchedGroup> &SyncPipe) override {
+
+      auto DAG = SyncPipe[0].DAG;
+      auto TII = SyncPipe[0].TII;
+
+      if (Cache->empty()) {
+        auto I = DAG->SUnits.rbegin();
+        auto E = DAG->SUnits.rend();
+        for (; I != E; I++) {
+          if (TII->isMFMAorWMMA(*(I->getInstr())))
+            Cache->push_back(&*I);
+        }
+      }
+
+      if (Cache->empty())
+        return false;
+
+      auto Reaches = (std::any_of(
+          Cache->begin(), Cache->end(), [&SU, &DAG](SUnit *TargetSU) {
+            return DAG->IsReachable(TargetSU, const_cast<SUnit *>(SU));
+          }));
+
+      return Reaches;
+    }
+    IsPipeExp(const SIInstrInfo *TII, unsigned SGID, bool NeedsCache = false)
+        : InstructionRule(TII, SGID, NeedsCache) {}
+  };
+
+  /// Whether or not the instruction enables the exact MFMA that is the \p
+  /// Number th MFMA in the chain starting with \p ChainSeed
+  class EnablesNthMFMA final : public InstructionRule {
+  private:
+    unsigned Number = 1;
+
+  public:
+    bool apply(const SUnit *SU, const ArrayRef<SUnit *> Collection,
+               SmallVectorImpl<SchedGroup> &SyncPipe) override {
+      bool FoundTrans = false;
+      unsigned Counter = 1;
+      auto DAG = SyncPipe[0].DAG;
+
+      if (Cache->empty()) {
+        auto TII = SyncPipe[0].TII;
+        SmallVector<SUnit *, 8> Worklist;
+
+        auto I = DAG->SUnits.begin();
+        auto E = DAG->SUnits.end();
+        for (; I != E; I++) {
+          if (!FoundTrans) {
+            if (TII->isTRANS(I->getInstr()->getOpcode()))
+              FoundTrans = true;
+            continue;
+          } else {
----------------
kerbowa wrote:

Else after continue?

https://github.com/llvm/llvm-project/pull/81342