[Mlir-commits] [mlir] [mlir][scf] Expose mlir::generateUnrolledLoop() (PR #163806)

[llvmlistbot at llvm.org]

https://github.com/fabrizio-indirli updated https://github.com/llvm/llvm-project/pull/163806

>From 6beb0389dae60cc4be7d3aab29fcd6c305019125 Mon Sep 17 00:00:00 2001
From: Fabrizio Indirli <Fabrizio.Indirli at arm.com>
Date: Thu, 16 Oct 2025 16:22:10 +0100
Subject: [PATCH] [mlir][scf] Expose mlir::generateUnrolledLoop()

Define mlir::generateUnrolledLoop() in the
mlir/Dialect/SCF/Utils/Utils.h header to make it available
to other passes, and calrify that it can be applied
also to other types of scf loops.

Signed-off-by: Fabrizio Indirli <Fabrizio.Indirli at arm.com>
---
 mlir/include/mlir/Dialect/SCF/Utils/Utils.h | 14 ++++++
 mlir/lib/Dialect/SCF/Utils/Utils.cpp        | 48 +++++++++++++--------
 2 files changed, 45 insertions(+), 17 deletions(-)

diff --git a/mlir/include/mlir/Dialect/SCF/Utils/Utils.h b/mlir/include/mlir/Dialect/SCF/Utils/Utils.h
index ecd829ed14add..7f1e8e9592a53 100644
--- a/mlir/include/mlir/Dialect/SCF/Utils/Utils.h
+++ b/mlir/include/mlir/Dialect/SCF/Utils/Utils.h
@@ -221,6 +221,20 @@ FailureOr<scf::ForallOp> normalizeForallOp(RewriterBase &rewriter,
 /// 4. Each region iter arg and result has exactly one use
 bool isPerfectlyNestedForLoops(MutableArrayRef<LoopLikeOpInterface> loops);
 
+/// Generate unrolled copies of an scf loop's 'loopBodyBlock', with 'iterArgs'
+/// and 'yieldedValues' as the block arguments and yielded values of the loop.
+/// The content of the loop body is replicated 'unrollFactor' times, calling
+/// 'ivRemapFn' to remap 'iv' for each unrolled body. If specified, annotates
+/// the Ops in each unrolled iteration using annotateFn. If provided,
+/// 'clonedToSrcOpsMap' is populated with the mappings from the cloned ops to
+/// the original op.
+void generateUnrolledLoop(
+    Block *loopBodyBlock, Value iv, uint64_t unrollFactor,
+    function_ref<Value(unsigned, Value, OpBuilder)> ivRemapFn,
+    function_ref<void(unsigned, Operation *, OpBuilder)> annotateFn,
+    ValueRange iterArgs, ValueRange yieldedValues,
+    IRMapping *clonedToSrcOpsMap = nullptr);
+
 } // namespace mlir
 
 #endif // MLIR_DIALECT_SCF_UTILS_UTILS_H_
diff --git a/mlir/lib/Dialect/SCF/Utils/Utils.cpp b/mlir/lib/Dialect/SCF/Utils/Utils.cpp
index 10eae8906ce31..af7aba26b1d34 100644
--- a/mlir/lib/Dialect/SCF/Utils/Utils.cpp
+++ b/mlir/lib/Dialect/SCF/Utils/Utils.cpp
@@ -291,47 +291,61 @@ static Value ceilDivPositive(OpBuilder &builder, Location loc, Value dividend,
   return arith::DivUIOp::create(builder, loc, sum, divisor);
 }
 
-/// Generates unrolled copies of scf::ForOp 'loopBodyBlock', with
-/// associated 'forOpIV' by 'unrollFactor', calling 'ivRemapFn' to remap
-/// 'forOpIV' for each unrolled body. If specified, annotates the Ops in each
-/// unrolled iteration using annotateFn.
-static void generateUnrolledLoop(
-    Block *loopBodyBlock, Value forOpIV, uint64_t unrollFactor,
+void mlir::generateUnrolledLoop(
+    Block *loopBodyBlock, Value iv, uint64_t unrollFactor,
     function_ref<Value(unsigned, Value, OpBuilder)> ivRemapFn,
     function_ref<void(unsigned, Operation *, OpBuilder)> annotateFn,
-    ValueRange iterArgs, ValueRange yieldedValues) {
+    ValueRange iterArgs, ValueRange yieldedValues,
+    IRMapping *clonedToSrcOpsMap) {
+
+  // check if the op was cloned from another source op, and return it if found
+  // (or the same op if not found)
+  auto findOriginalSrcOp =
+      [](Operation *op, const IRMapping &clonedToSrcOpsMap) -> Operation * {
+    Operation *srcOp = op;
+    // if the source op derives from another op: traverse the chain to find the
+    // original source op
+    while (srcOp && clonedToSrcOpsMap.contains(srcOp))
+      srcOp = clonedToSrcOpsMap.lookup(srcOp);
+    return srcOp;
+  };
+
   // Builder to insert unrolled bodies just before the terminator of the body of
-  // 'forOp'.
+  // the loop.
   auto builder = OpBuilder::atBlockTerminator(loopBodyBlock);
 
-  constexpr auto defaultAnnotateFn = [](unsigned, Operation *, OpBuilder) {};
+  static const auto noopAnnotateFn = [](unsigned, Operation *, OpBuilder) {};
   if (!annotateFn)
-    annotateFn = defaultAnnotateFn;
+    annotateFn = noopAnnotateFn;
 
   // Keep a pointer to the last non-terminator operation in the original block
   // so that we know what to clone (since we are doing this in-place).
   Block::iterator srcBlockEnd = std::prev(loopBodyBlock->end(), 2);
 
-  // Unroll the contents of 'forOp' (append unrollFactor - 1 additional copies).
+  // Unroll the contents of the loop body (append unrollFactor - 1 additional
+  // copies).
   SmallVector<Value, 4> lastYielded(yieldedValues);
 
   for (unsigned i = 1; i < unrollFactor; i++) {
-    IRMapping operandMap;
-
     // Prepare operand map.
+    IRMapping operandMap;
     operandMap.map(iterArgs, lastYielded);
 
     // If the induction variable is used, create a remapping to the value for
     // this unrolled instance.
-    if (!forOpIV.use_empty()) {
-      Value ivUnroll = ivRemapFn(i, forOpIV, builder);
-      operandMap.map(forOpIV, ivUnroll);
+    if (!iv.use_empty()) {
+      Value ivUnroll = ivRemapFn(i, iv, builder);
+      operandMap.map(iv, ivUnroll);
     }
 
     // Clone the original body of 'forOp'.
     for (auto it = loopBodyBlock->begin(); it != std::next(srcBlockEnd); it++) {
-      Operation *clonedOp = builder.clone(*it, operandMap);
+      Operation *srcOp = &(*it);
+      Operation *clonedOp = builder.clone(*srcOp, operandMap);
       annotateFn(i, clonedOp, builder);
+      if (clonedToSrcOpsMap)
+        clonedToSrcOpsMap->map(clonedOp,
+                               findOriginalSrcOp(srcOp, *clonedToSrcOpsMap));
     }
 
     // Update yielded values.