[PATCH] D44565: [SLP] Add a check before skipping inserting a trunc after z|sext vectorization tree root

[Haicheng Wu via Phabricator via llvm-commits]

haicheng created this revision.
haicheng added reviewers: mssimpso, ABataev.
Herald added subscribers: javed.absar, mcrosier.

If the vectorization tree root operations are integer cast operations, https://reviews.llvm.org/D41948 does not consider them as candidates for truncation. However, sometimes the trunc is needed by instcombine to trigger type shrinking or prevent type extension.

One example is like this, when vectorizing

    %800 = zext <16 x i16> %799 to <16 x i32>
    %803 = zext <16 x i16> %802 to <16 x i32>
    %804 = sub nsw <16 x i32> %800, %803
    %805 = extractelement <16 x i32> %804, i32 0
    %806 = sext i32 %805 to i64
    %808 = extractelement <16 x i32> %804, i32 1
    %809 = sext i32 %808 to i64
  ...
    %850 = extractelement <16 x i32> %804, i32 15
    %851 = sext i32 %850 to i64

to

    %800 = zext <16 x i16> %799 to <16 x i32>
    %803 = zext <16 x i16> %802 to <16 x i32>
    %804 = sub nsw <16 x i32> %800, %803
    %805 = sext <16 x i32> %804 to <16 x i64>
    %806 = trunc <16 x i64> %805 to <16 x i32>
    %807 = extractelement <16 x i32> %806, i32 0
    %808 = extractelement <16 x i32> %806, i32 1
  ...
    %837 = extractelement <16 x i32> %806, i32 15

A trunc after the vectorized sext is needed to prevent the types of the first three IRs (2 zext and 1 sub) from being expanded to i64.

This patch checks if the sources of the vectorized cast operations can be changed to evaluate in different types.  If so, the trunc is still added.


Repository:
  rL LLVM

https://reviews.llvm.org/D44565

Files:
  lib/Transforms/Vectorize/SLPVectorizer.cpp
  test/Transforms/SLPVectorizer/AArch64/ext-trunc.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D44565.138695.patch
Type: text/x-patch
Size: 4970 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180316/a3393a96/attachment.bin>