[Mlir-commits] [mlir] [MLIR][SCF] Canonicalize redundant scf.if from scf.while before region into after region (PR #169892)

[Ming Yan]

================
@@ -3687,6 +3688,127 @@ LogicalResult scf::WhileOp::verify() {
 }
 
 namespace {
+/// Move a scf.if op that is directly before the scf.condition op in the while
+/// before region, and whose condition matches the condition of the
+/// scf.condition op, down into the while after region.
+///
+/// scf.while (..) : (...) -> ... {
+///  %additional_used_values = ...
+///  %cond = ...
+///  ...
+///  %res = scf.if %cond -> (...) {
+///    use(%additional_used_values)
+///    ... // then block
+///    scf.yield %then_value
+///  } else {
+///    scf.yield %else_value
+///  }
+///  scf.condition(%cond) %res, ...
+/// } do {
+/// ^bb0(%res_arg, ...):
+///    use(%res_arg)
+///    ...
+///
+/// becomes
+/// scf.while (..) : (...) -> ... {
+///  %additional_used_values = ...
+///  %cond = ...
+///  ...
+///  scf.condition(%cond) %else_value, ..., %additional_used_values
+/// } do {
+/// ^bb0(%res_arg ..., %additional_args): :
+///    use(%additional_args)
+///    ... // if then block
+///    use(%then_value)
+///    ...
+struct WhileMoveIfDown : public OpRewritePattern<scf::WhileOp> {
+  using OpRewritePattern<scf::WhileOp>::OpRewritePattern;
+
+  LogicalResult matchAndRewrite(scf::WhileOp op,
+                                PatternRewriter &rewriter) const override {
+    auto conditionOp =
+        cast<scf::ConditionOp>(op.getBeforeBody()->getTerminator());
+    auto ifOp = dyn_cast_or_null<scf::IfOp>(conditionOp->getPrevNode());
+
+    // Check that the ifOp is directly before the conditionOp and that it
+    // matches the condition of the conditionOp. Also ensure that the ifOp has
+    // no else block with content, as that would complicate the transformation.
+    // TODO: support else blocks with content.
+    if (!ifOp || ifOp.getCondition() != conditionOp.getCondition() ||
+        (ifOp.elseBlock() && !ifOp.elseBlock()->without_terminator().empty()))
+      return failure();
+
+    assert(ifOp->use_empty() || (llvm::all_equal(ifOp->getUsers()) &&
+                                 *ifOp->user_begin() == conditionOp) &&
+                                    "ifOp has unexpected uses");
+
+    Location loc = op.getLoc();
+
+    // Replace uses of ifOp results in the conditionOp with the yielded values
+    // from the ifOp branches.
+    for (auto [idx, arg] : llvm::enumerate(conditionOp.getArgs())) {
+      auto it = llvm::find(ifOp->getResults(), arg);
+      if (it != ifOp->getResults().end()) {
+        size_t ifOpIdx = it.getIndex();
+        Value thenValue = ifOp.thenYield()->getOperand(ifOpIdx);
+        Value elseValue = ifOp.elseYield()->getOperand(ifOpIdx);
+
+        rewriter.replaceAllUsesWith(ifOp->getResults()[ifOpIdx], elseValue);
+        rewriter.replaceAllUsesWith(op.getAfterArguments()[idx], thenValue);
+      }
+    }
+
+    // Collect additional used values from before region.
+    SetVector<Value> additionalUsedValues;
+    visitUsedValuesDefinedAbove(ifOp.getThenRegion(), [&](OpOperand *operand) {
+      if (op.getBefore().isAncestor(operand->get().getParentRegion()))
+        additionalUsedValues.insert(operand->get());
+    });
+
+    // Create new whileOp with additional used values as results.
+    auto additionalValueTypes = llvm::map_to_vector(
+        additionalUsedValues, [](Value val) { return val.getType(); });
+    size_t additionalValueSize = additionalUsedValues.size();
+    SmallVector<Type> newResultTypes(op.getResultTypes());
+    newResultTypes.append(additionalValueTypes);
+
+    auto newWhileOp =
+        scf::WhileOp::create(rewriter, loc, newResultTypes, op.getInits());
+
+    newWhileOp.getBefore().takeBody(op.getBefore());
+    newWhileOp.getAfter().takeBody(op.getAfter());
+    newWhileOp.getAfter().addArguments(
+        additionalValueTypes, SmallVector<Location>(additionalValueSize, loc));
+
+    SmallVector<Value> conditionArgs = conditionOp.getArgs();
+    llvm::append_range(conditionArgs, additionalUsedValues);
+
+    // Update conditionOp inside new whileOp before region.
+    rewriter.setInsertionPoint(conditionOp);
+    rewriter.replaceOpWithNewOp<scf::ConditionOp>(
+        conditionOp, conditionOp.getCondition(), conditionArgs);
+
+    // Replace uses of additional used values inside the ifOp then region with
+    // the whileOp after region arguments.
+    rewriter.replaceUsesWithIf(
+        additionalUsedValues.takeVector(),
+        newWhileOp.getAfterArguments().take_back(additionalValueSize),
+        [&](OpOperand &use) {
+          return ifOp.getThenRegion().isAncestor(
+              use.getOwner()->getParentRegion());
----------------
NexMing wrote:

Changing that would be wrong. In the def–use chain, a value’s definition will always be in the `before` region, but its users may be located in subregions of the `scf.if` region.

https://github.com/llvm/llvm-project/pull/169892