[PATCH] D78925: [mlir][VectorOps] Extend VectorTransfer lowering to n-D memref with minor identity map

[Nicolas Vasilache via Phabricator via llvm-commits]

nicolasvasilache created this revision.
nicolasvasilache added reviewers: ftynse, aartbik.
Herald added subscribers: llvm-commits, Kayjukh, frgossen, grosul1, Joonsoo, liufengdb, lucyrfox, mgester, arpith-jacob, antiagainst, shauheen, jpienaar, rriddle, mehdi_amini.
Herald added a project: LLVM.
ftynse accepted this revision.
ftynse added inline comments.
This revision is now accepted and ready to land.


================
Comment at: mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp:858
+    // `k` dimensions here.
+    unsigned lastIndex = llvm::size(xferOp.indices()) - 1;
+    Value offsetIndex = *(xferOp.indices().begin() + lastIndex);
----------------
Nit: I don't remember if the transfer_op verifier checks for the list of indices being non-empty


This revision extends the lowering of vector transfers to work with n-D memref and 1-D vector where the permutation map is an identity on the most minor dimensions (1 for now).


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D78925

Files:
  mlir/lib/Conversion/VectorToLLVM/ConvertVectorToLLVM.cpp
  mlir/test/Conversion/VectorToLLVM/vector-to-llvm.mlir

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D78925.260309.patch
Type: text/x-patch
Size: 5291 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200427/b9d27270/attachment.bin>