Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
AMDGPU/SI: Disable unrolling in the loop vectorizer if the loop is no…
…t vectorized. Reviewers: arsenm Differential Revision: http://reviews.llvm.org/D30719 llvm-svn: 297328
- Loading branch information
Changpeng Fang
committed
Mar 9, 2017
1 parent
8537d99
commit 1be9b9f
Showing
3 changed files
with
34 additions
and
0 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,2 @@ | ||
if not 'AMDGPU' in config.root.targets: | ||
config.unsupported = True |
28 changes: 28 additions & 0 deletions
28
llvm/test/Transforms/LoopVectorize/AMDGPU/unroll-in-loop-vectorizer.ll
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 +1,28 @@ | ||
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -mcpu=fiji -loop-vectorize < %s | FileCheck %s | ||
|
||
|
||
; For AMDGPU, loop unroll in loop vectorizer is disabled when VF==1. | ||
; | ||
; CHECK-LABEL: @small_loop( | ||
; CHECK: store i32 | ||
; CHECK-NOT: store i32 | ||
; CHECK: ret | ||
define void @small_loop(i32* nocapture %inArray, i32 %size) nounwind { | ||
entry: | ||
%0 = icmp sgt i32 %size, 0 | ||
br i1 %0, label %loop, label %exit | ||
|
||
loop: ; preds = %entry, %loop | ||
%iv = phi i32 [ %iv1, %loop ], [ 0, %entry ] | ||
%1 = getelementptr inbounds i32, i32* %inArray, i32 %iv | ||
%2 = load i32, i32* %1, align 4 | ||
%3 = add nsw i32 %2, 6 | ||
store i32 %3, i32* %1, align 4 | ||
%iv1 = add i32 %iv, 1 | ||
; %lftr.wideiv = trunc i64 %indvars.iv.next to i32 | ||
%cond = icmp eq i32 %iv1, %size | ||
br i1 %cond, label %exit, label %loop | ||
|
||
exit: ; preds = %loop, %entry | ||
ret void | ||
} |