Automerge: [mlir][affine] Add fold logic when the affine.yield has IV as operand in the AffineForEmptyLoopFolder (#164064)

Co-authored-by: Jakub Kuderski <[email protected]>

Author: 2 people

mlir/lib/Dialect/Affine/IR/AffineOps.cpp

@@ -2610,6 +2610,21 @@ static std::optional<uint64_t> getTrivialConstantTripCount(AffineForOp forOp) {
   return ub - lb <= 0 ? 0 : (ub - lb + step - 1) / step;
 }
 
+/// Calculate the constant value of the loop's induction variable for its last
+/// trip.
+static std::optional<int64_t>
+getConstantInductionVarForLastTrip(AffineForOp forOp) {
+  std::optional<uint64_t> tripCount = getTrivialConstantTripCount(forOp);
+  if (!tripCount.has_value())
+    return std::nullopt;
+  if (tripCount.value() == 0)
+    return std::nullopt;
+  int64_t lb = forOp.getConstantLowerBound();
+  int64_t step = forOp.getStepAsInt();
+  int64_t lastTripIv = lb + (tripCount.value() - 1) * step;
+  return lastTripIv;
+}
+
 /// Fold the empty loop.
 static SmallVector<OpFoldResult> AffineForEmptyLoopFolder(AffineForOp forOp) {
   if (!llvm::hasSingleElement(*forOp.getBody()))
@@ -2622,18 +2637,22 @@ static SmallVector<OpFoldResult> AffineForEmptyLoopFolder(AffineForOp forOp) {
     // results.
     return forOp.getInits();
   }
-  SmallVector<Value, 4> replacements;
+  SmallVector<OpFoldResult, 4> replacements;
   auto yieldOp = cast<AffineYieldOp>(forOp.getBody()->getTerminator());
   auto iterArgs = forOp.getRegionIterArgs();
   bool hasValDefinedOutsideLoop = false;
   bool iterArgsNotInOrder = false;
   for (unsigned i = 0, e = yieldOp->getNumOperands(); i < e; ++i) {
     Value val = yieldOp.getOperand(i);
     BlockArgument *iterArgIt = llvm::find(iterArgs, val);
-    // TODO: It should be possible to perform a replacement by computing the
-    // last value of the IV based on the bounds and the step.
-    if (val == forOp.getInductionVar())
+    if (val == forOp.getInductionVar()) {
+      if (auto lastTripIv = getConstantInductionVarForLastTrip(forOp)) {
+        replacements.push_back(IntegerAttr::get(
+            IndexType::get(forOp.getContext()), lastTripIv.value()));
+        continue;
+      }
       return {};
+    }
     if (iterArgIt == iterArgs.end()) {
       // `val` is defined outside of the loop.
       assert(forOp.isDefinedOutsideOfLoop(val) &&
@@ -2656,7 +2675,7 @@ static SmallVector<OpFoldResult> AffineForEmptyLoopFolder(AffineForOp forOp) {
   // out of order.
   if (tripCount.has_value() && tripCount.value() >= 2 && iterArgsNotInOrder)
     return {};
-  return llvm::to_vector_of<OpFoldResult>(replacements);
+  return replacements;
 }
 
 /// Canonicalize the bounds of the given loop.

mlir/test/Dialect/Affine/canonicalize.mlir

@@ -609,6 +609,19 @@ func.func @fold_zero_iter_loops(%in : index) -> index {
 
 // -----
 
+// CHECK-LABEL: func @fold_empty_loop_iv
+//  CHECK-SAME:   %[[INIT:.*]]: index
+func.func @fold_empty_loop_iv(%init: index) -> (index, index) {
+  %res:2 = affine.for %i = 0 to 10 step 1 iter_args(%arg0 = %init, %arg1 = %init) -> (index, index) {
+    affine.yield %i, %arg1 : index, index
+  }
+  // CHECK: %[[C9:.*]] = arith.constant 9 : index
+  // CHECK: return %[[C9]], %[[INIT]] : index, index
+  return %res#0, %res#1 : index, index
+}
+
+// -----
+
 // CHECK-DAG: #[[$SET:.*]] = affine_set<(d0, d1)[s0] : (d0 >= 0, -d0 + 1022 >= 0, d1 >= 0, -d1 + s0 - 2 >= 0)>
 
 // CHECK-LABEL: func @canonicalize_affine_if