[PATCH] D80100: [mlir][Vector] Add option to fully unroll for VectorTransfer to SCF lowering

Nicolas Vasilache via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed May 20 08:10:57 PDT 2020


nicolasvasilache marked 16 inline comments as done.
nicolasvasilache added inline comments.


================
Comment at: mlir/include/mlir/Conversion/VectorToSCF/VectorToSCF.h:16
 class MLIRContext;
+class LogicalResult;
 class OwningRewritePatternList;
----------------
ftynse wrote:
> `struct` or you'll break msvc
dropped it from here


================
Comment at: mlir/lib/Conversion/VectorToSCF/VectorToSCF.cpp:239
+      // 3.a. If in-bounds, progressively lower to a 1-D transfer read.
+      BlockBuilder(&ifOp.thenRegion().front(), Append())([&] {
+        Value loaded1D = load1DVector(majorIvsPlusOffsets);
----------------
ftynse wrote:
> Plz remind me if `Append()` appends to the end of the block or before the terminator
before the terminator if it is there otherwise end of the block.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80100/new/

https://reviews.llvm.org/D80100





More information about the llvm-commits mailing list