[PATCH] D75775: [mlir][Vector] Add a vector.matrix_multiply op on 1-D vectors

[Nicolas Vasilache via Phabricator via llvm-commits]

nicolasvasilache marked an inline comment as done.
nicolasvasilache added inline comments.


================
Comment at: mlir/include/mlir/Conversion/VectorToLLVM/ConvertVectorToLLVM.h:20
+/// Intrinsics. This needs to go through memory atm.
+void populateVectorToLLVMMatrixConversionPatterns(
+    LLVMTypeConverter &converter, OwningRewritePatternList &patterns);
----------------
aartbik wrote:
> why is this in its own population (instead of adding it to the general VectorToLLVM)?
> I don't object, but just curious. I can see isolated testing, but you don't seem to exploit that
Since lowering matrix intrinsics in LLVM requires a special flag, it makes sense to group those patterns together.
Updated the doc to reflect this.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D75775/new/

https://reviews.llvm.org/D75775