[PATCH] D30057: [NVPTX] Added support for v2f16 operations.

[Artem Belevich via Phabricator via llvm-commits]

tra updated this revision to Diff 89448.
tra marked 12 inline comments as done.
tra added a comment.

Addressed Justin's comments.
Added support for lowering EXTRACT_VECTOR_ELT with non-constant index.
Improved handling of loads/stores of f16 vectors (we can handle v8f16 now).
Added few more test cases.


https://reviews.llvm.org/D30057

Files:
  lib/Target/NVPTX/InstPrinter/NVPTXInstPrinter.cpp
  lib/Target/NVPTX/NVPTXAsmPrinter.cpp
  lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
  lib/Target/NVPTX/NVPTXISelDAGToDAG.h
  lib/Target/NVPTX/NVPTXISelLowering.cpp
  lib/Target/NVPTX/NVPTXISelLowering.h
  lib/Target/NVPTX/NVPTXInstrInfo.cpp
  lib/Target/NVPTX/NVPTXInstrInfo.td
  lib/Target/NVPTX/NVPTXIntrinsics.td
  lib/Target/NVPTX/NVPTXRegisterInfo.cpp
  lib/Target/NVPTX/NVPTXRegisterInfo.td
  test/CodeGen/NVPTX/LoadStoreVectorizer.ll
  test/CodeGen/NVPTX/f16-instructions.ll
  test/CodeGen/NVPTX/f16x2-instructions.ll
  test/CodeGen/NVPTX/param-load-store.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D30057.89448.patch
Type: text/x-patch
Size: 145846 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170223/763119ff/attachment-0001.bin>