[llvm] [Transforms][Utils] Add LoopSplit for iteration-space loop splitting (PR #217232)

[Florian Hahn via llvm-commits]

================
@@ -0,0 +1,590 @@
+//===- LoopSplit.cpp - Split a loop's iteration space ---------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+//
+// Splits a counted loop's iteration space into a chain of per-partition
+// sub-loops. See LoopSplit.h for the high-level usage guidelines.
+//
+// Structure produced for partitions [S0,E0], [S1,E1], ... where E is the loop's
+// last iteration and each clamped end sel_i is min(E_i, E), or max descending:
+//
+//   guard0:                            ; every S_i and sel_i is computed here
+//     if (S0 <= sel0) goto preheader0 else goto guard1
+//   loop0: ...                         ; latch iterates while i < sel0
+//   exit0 -> guard1
+//   guard1:
+//     if (S1 <= sel1) goto preheader1 else goto guard2
+//   loop1: ...                         ; latch iterates while i < sel1
+//   exit1 -> guard2
+//     ...
+//   final.exit:
+//
+// Each guard holds the "S_i <= sel_i" check and skips an empty partition by
+// falling through to the next guard. All S_i/sel_i are materialized once in
+// guard0, and the end clamp keeps the "runs at least once" iteration in the
+// right partition.
+//
+// The latch keeps iterating while the value the next iteration would use is
+// still in the partition. That is written as the strict "i < sel_i" on the
+// induction PHI rather than "i + 1 <= sel_i" on the step value; the two agree
+// because legality analysis has established that the space does not wrap, and
+// the strict form never forms i + 1, so it remains a real test even when sel_i
+// is the last value of the type, where the inclusive one would be a tautology
+// and the partition would never exit.
+//
+// A descending (step -1) loop uses the same structure mirrored: partitions run
+// high-to-low and the clamp and predicates flip (>=/>).
+//
+// Usage guidelines:
+//  - Caller bounds must not wrap the induction type. The clamp absorbs a bound
+//    past the runtime trip count, and legality analysis reserves the one step
+//    past the induction start that an empty partition needs, but a bound
+//    reaching any further wraps in the bound arithmetic and cannot be repaired
+//    here.
+//  - Bounds must be loop-invariant: they are expanded in guard0, so a bound
+//    depending on a value defined inside the loop cannot be placed.
+//  - The partitions must tile the original iteration space exactly -- same
+//    iterations, same order -- so the split preserves program behaviour.
+//
+// The transform is structural: inside a partition it only seeds the induction
+// PHI with that partition's start and replaces the latch test. It never
+// rebuilds a value that flows between partitions, so no SSA reconstruction is
+// needed.
+//
+// Not yet supported, and rejected during legality analysis: loop-carried
+// values, values that escape the loop (exit values), non-unit and non-integer
+// inductions, top-tested loops, and multiple exits. Also rejected is an
+// induction start at the extreme of the iteration direction, which leaves
+// nowhere to put a boundary. An induction *end* at that extreme is fine,
+// because the latch stays strict.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Transforms/Utils/LoopSplit.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/Analysis/LoopInfo.h"
+#include "llvm/Analysis/ScalarEvolution.h"
+#include "llvm/Analysis/ScalarEvolutionExpressions.h"
+#include "llvm/Analysis/ScalarEvolutionPatternMatch.h"
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/Dominators.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/ProfDataUtils.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Transforms/Utils/BasicBlockUtils.h"
+#include "llvm/Transforms/Utils/Cloning.h"
+#include "llvm/Transforms/Utils/LoopUtils.h"
+#include "llvm/Transforms/Utils/ScalarEvolutionExpander.h"
+#include "llvm/Transforms/Utils/ValueMapper.h"
+#include <optional>
+
+using namespace llvm;
+using namespace llvm::SCEVPatternMatch;
+
+#define DEBUG_TYPE "loop-split"
+
+//===----------------------------------------------------------------------===//
+// LoopSplit - construction, partition list, induction analysis
+//===----------------------------------------------------------------------===//
+
+/// Per-split() scratch shared by the phase helpers; lives for one split() call.
+/// Everything derived from the induction lives on LoopSplit itself, filled in
+/// by legality analysis; this holds only what the transform creates.
+struct LoopSplit::SplitState {
+  // Partition 0 reuses the original loop's preheader, exit, and entry guard;
+  // those blocks live in Partitions[0] rather than being duplicated here.
+  BasicBlock *FinalExit = nullptr; // where the partition chain converges.
+  Loop *OuterLoop = nullptr;       // parent of the new blocks, if any.
----------------
fhahn wrote:

```suggestion
  // Where the partition chain converges.
  BasicBlock *FinalExit = nullptr; 
  
  // Parent of the new blocks, if any.
  Loop *OuterLoop = nullptr; 
```

https://github.com/llvm/llvm-project/pull/217232