commit e3b8d9a312bf5eb02808763a4b265c4a77952e25
author Guozhi Wei <carrot@google.com> Mon Nov 06 19:09:38 2017 +0000
committer Guozhi Wei <carrot@google.com> Mon Nov 06 19:09:38 2017 +0000
tree b1807a55414ec593f4c60abac1cd3169b407cd88
parent 5ebf7a87f33992197add391b98db58a056c22faa

[PPC] Use xxbrd to speed up bswap64

Power doesn't have bswap instructions, so llvm generates following code sequence for bswap64.

  rotldi   5, 3, 16
  rotldi   4, 3, 8
  rotldi   9, 3, 24
  rotldi   10, 3, 32
  rotldi   11, 3, 48
  rotldi   12, 3, 56
  rldimi 4, 5, 8, 48
  rldimi 4, 9, 16, 40
  rldimi 4, 10, 24, 32
  rldimi 4, 11, 40, 16
  rldimi 4, 12, 48, 8
  rldimi 4, 3, 56, 0

But Power9 has vector bswap instructions, they can also be used to speed up scalar bswap intrinsic. With this patch, bswap64 can be translated to:

  mtvsrdd 34, 3, 3
  xxbrd 34, 34
  mfvsrld 3, 34

Differential Revision: https://reviews.llvm.org/D39510

llvm-svn: 317499

llvm/lib/Target/PowerPC/PPCISelLowering.h

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.h b/llvm/lib/Target/PowerPC/PPCISelLowering.h
index 1a5efeb..d06c10a 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.h
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.h
@@ -953,6 +953,7 @@
     SDValue LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerINTRINSIC_VOID(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerREM(SDValue Op, SelectionDAG &DAG) const;
+    SDValue LowerBSWAP(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerSCALAR_TO_VECTOR(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerSIGN_EXTEND_INREG(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerMUL(SDValue Op, SelectionDAG &DAG) const;