[MLIR] Remove dead affine.applys while generating pointwise copies

This makes no impact on the test cases because affine-data-copy-generate
runs whole function canonicalization at its end; however, the latter
will be removed in a pending revision. It is thus useful to clean up
these affine.applys right here, and eventually, not even generate
these (when the right API to compose by construction is in place).

Differential Revision: https://reviews.llvm.org/D78055

diff --git a/mlir/lib/Transforms/Utils/LoopUtils.cpp b/mlir/lib/Transforms/Utils/LoopUtils.cpp
index 01df259..15f5c25 100644 (file)
--- a/mlir/lib/Transforms/Utils/LoopUtils.cpp
+++ b/mlir/lib/Transforms/Utils/LoopUtils.cpp
@@ -1492,6 +1492,7 @@ generatePointWiseCopy(Location loc, Value memref, Value fastMemRef,
   SmallVector<AffineExpr, 4> fastBufExprs;
   SmallVector<Value, 4> fastBufMapOperands;
   AffineForOp copyNestRoot;
+  SmallVector<AffineApplyOp, 4> mayBeDeadApplys;
   for (unsigned d = 0; d < rank; ++d) {
     auto forOp = createCanonicalizedAffineForOp(b, loc, lbOperands, lbMaps[d],
                                                 ubOperands, ubMaps[d]);
@@ -1510,6 +1511,7 @@ generatePointWiseCopy(Location loc, Value memref, Value fastMemRef,
                            b.getAffineDimExpr(2 * d));
     fastBufMapOperands.push_back(offset);
     fastBufMapOperands.push_back(forOp.getInductionVar());
+    mayBeDeadApplys.push_back(offset);
 
     // Subscript for the slow memref being copied.
     memIndices.push_back(forOp.getInductionVar());
@@ -1520,6 +1522,11 @@ generatePointWiseCopy(Location loc, Value memref, Value fastMemRef,
   fastBufMap = simplifyAffineMap(fastBufMap);
   canonicalizeMapAndOperands(&fastBufMap, &fastBufMapOperands);
 
+  // Drop any dead affine.applys.
+  for (auto applyOp : mayBeDeadApplys)
+    if (applyOp.use_empty())
+      applyOp.erase();
+
   if (!isCopyOut) {
     // Copy in.
     auto load = b.create<AffineLoadOp>(loc, memref, memIndices);
@@ -2191,7 +2198,7 @@ static AffineIfOp createSeparationCondition(MutableArrayRef<AffineForOp> loops,
   // larger (and resp. smaller) than any other lower (or upper bound).
   SmallVector<int64_t, 8> fullTileLb, fullTileUb;
   for (auto loop : loops) {
-    (void) loop;
+    (void)loop;
     // TODO: Non-unit stride is not an issue to generalize to.
     assert(loop.getStep() == 1 && "point loop step expected to be one");
     // Mark everything symbols for the purpose of finding a constant diff pair.