[Mlir-commits] [mlir] [MLIR] Add continuous tiling to TileUsingForOp (PR #82792)

[Oleksandr Alex Zinenko]

================
@@ -309,6 +311,188 @@ static LogicalResult generateLoopNest(RewriterBase &rewriter, Location loc,
   return rewriter.notifyMatchFailure(loc, "unhandled loop type");
 }
 
+static void continuousLoopNestHelper(
+    OpBuilder &builder, Location loc, ArrayRef<Range> loopRanges,
+    SmallVector<LoopLikeOpInterface> &loops, uint64_t loopLevelIdx,
+    uint64_t &loopIdx, ArrayRef<OpFoldResult> tileSizes,
+    SmallVector<bool> &CTileVector, std::map<int, OpFoldResult> &sizesMap,
+    SmallVector<scf::ForOp> &innermostLoops, ValueRange destinationTensors = {},
+    bool isHeadOrInsideHeadLoop = false) {
+
+  Value offset = getValueOrCreateConstantIndexOp(
+      builder, loc, loopRanges[loopLevelIdx].offset);
+  Value size = getValueOrCreateConstantIndexOp(builder, loc,
+                                               loopRanges[loopLevelIdx].size);
+  Value tileSize =
+      getValueOrCreateConstantIndexOp(builder, loc, tileSizes[loopLevelIdx]);
+
+  AffineExpr sym0, sym1, sym2;
+  bindSymbols(builder.getContext(), sym0, sym1, sym2);
+  AffineMap defaultSplitMap =
+      AffineMap::get(0, 3, {sym1 - ((sym1 - sym0) % sym2)});
+  // Simplified map for use when step is power of 2 and lower bound
+  // is exactly divisble by step.
+  AffineMap powerSplitMap = AffineMap::get(0, 3, {sym1 - (sym1 % sym2)});
+
+  uint64_t tileSizeInt = *getConstantIntValue(tileSize);
+
+  // Enforce no tiling when tile size is zero.
+  // No need to create a loop here.
+  if (tileSizeInt == 0) {
+    continuousLoopNestHelper(builder, loc, loopRanges, loops, loopLevelIdx + 1,
----------------
ftynse wrote:

If the tile size is zero for the innermost loop, this will recurse and assert in `loopRanges[loopLevelIdx]` above because there is no depth check / other recursion exit condition at the beginning of the function.

https://github.com/llvm/llvm-project/pull/82792