[Mlir-commits] [mlir] [MLIR] support dynamic indexing of `vector.maskedload` in `VectorEmulateNarrowTypes` (PR #115070)

[llvmlistbot at llvm.org]

================
@@ -53,6 +53,7 @@ static FailureOr<Operation *> getCompressedMaskOp(OpBuilder &rewriter,
                                                   Location loc, Value mask,
                                                   int origElements, int scale,
                                                   int intraDataOffset = 0) {
+  assert(intraDataOffset < scale && "intraDataOffset must be less than scale");
----------------
lialan wrote:

you are right! Here I just exposed some intermediate calculating details to the comment, as in this case `scale == 2` so making the padded mask a multiple of `scale` in the intermediary result is easier.

https://github.com/llvm/llvm-project/pull/115070