Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add a convenience method to copy wrapping, exact, and fast-math flags…
… (NFC). The loop vectorizer preserves wrapping, exact, and fast-math properties of scalar instructions. This patch adds a convenience method to make that operation easier because we need to do this in the loop vectorizer, SLP vectorizer, and possibly other places. Although this is a 'no functional change' patch, I've added a testcase to verify that the exact flag is preserved by the loop vectorizer. The wrapping and fast-math flags are already checked in existing testcases. Differential Revision: http://reviews.llvm.org/D5138 llvm-svn: 216886
- Loading branch information
1 parent
3ae9193
commit 5ad239e
Showing
4 changed files
with
47 additions
and
13 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,24 @@ | ||
; RUN: opt < %s -loop-vectorize -force-vector-width=4 -S | FileCheck %s | ||
|
||
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" | ||
target triple = "x86_64-apple-macosx10.9.0" | ||
|
||
; CHECK-LABEL: @lshr_exact( | ||
; CHECK: lshr exact <4 x i32> | ||
define void @lshr_exact(i32* %x) { | ||
entry: | ||
br label %for.body | ||
|
||
for.body: | ||
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ] | ||
%arrayidx = getelementptr inbounds i32* %x, i64 %iv | ||
%0 = load i32* %arrayidx, align 4 | ||
%conv1 = lshr exact i32 %0, 1 | ||
store i32 %conv1, i32* %arrayidx, align 4 | ||
%iv.next = add nuw nsw i64 %iv, 1 | ||
%exitcond = icmp eq i64 %iv.next, 256 | ||
br i1 %exitcond, label %for.end, label %for.body | ||
|
||
for.end: | ||
ret void | ||
} |