maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/polly/test/ScopInfo/branch-references-loop-scev...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

48 lines
1.2 KiB
LLVM
Raw Normal View History

[ScopDetect] Evaluate and verify branches at branch condition, not icmp The validity of a branch condition must be verified at the location of the branch (the branch instruction), not the location of the icmp that is used in the branch instruction. When verifying at the wrong location, we may accept an icmp that is defined within a loop which itself dominates, but does not contain the branch instruction. Such loops cannot be modeled as we only introduce domain dimensions for surrounding loops. To address this problem we change the scop detection to evaluate and verify SCEV expressions at the right location. This issue has been around since at least r179148 "scop detection: properly instantiate SCEVs to the place where they are used", where we explicitly set the scope to the wrong location. Before this commit the scope was not explicitly set, which probably also resulted in the scope around the ICmp to be choosen. This resolves http://llvm.org/PR30989 Reported-by: Eli Friedman <efriedma@codeaurora.org> llvm-svn: 286769
2016-11-14 03:27:04 +08:00
; RUN: opt %loadPolly -polly-detect -analyze < %s | \
; RUN: FileCheck %s -check-prefix=DETECT
; RUN: opt %loadPolly -polly-scops -analyze < %s | \
; RUN: FileCheck %s -check-prefix=SCOP
; DETECT: Valid Region for Scop: loop => barrier
; DETECT-NEXT: Valid Region for Scop: branch => end
; SCOP: Statements {
; SCOP-NEXT: Stmt_then
; SCOP-NEXT: Domain :=
; SCOP-NEXT: [p_0] -> { Stmt_then[] : p_0 <= -2 or p_0 >= 0 };
; SCOP-NEXT: Schedule :=
; SCOP-NEXT: [p_0] -> { Stmt_then[] -> [] };
; SCOP-NEXT: MustWriteAccess := [Reduction Type: NONE] [Scalar: 0]
; SCOP-NEXT: [p_0] -> { Stmt_then[] -> MemRef_A[0] };
; SCOP-NEXT: }
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-android"
define void @f(i16 %event, float* %A) {
entry:
br label %loop
loop:
%indvar = phi i8 [ 0, %entry ], [ %indvar.next, %loop ]
%indvar.next = add i8 %indvar, -1
store float 1.0, float* %A
%cmp = icmp eq i8 %indvar.next, 0
br i1 false, label %barrier, label %loop
barrier:
fence seq_cst
br label %branch
branch:
br i1 %cmp, label %branch, label %then
then:
store float 1.0, float* %A
br label %end
end:
[tests] Make sure tests do not end in 'unreachable' - Part II There is no point in optimizing unreachable code, hence our test cases should always return. This commit is part of a series that makes Polly more robust on the presence of unreachables. llvm-svn: 297150
2017-03-07 23:23:30 +08:00
ret void
[ScopDetect] Evaluate and verify branches at branch condition, not icmp The validity of a branch condition must be verified at the location of the branch (the branch instruction), not the location of the icmp that is used in the branch instruction. When verifying at the wrong location, we may accept an icmp that is defined within a loop which itself dominates, but does not contain the branch instruction. Such loops cannot be modeled as we only introduce domain dimensions for surrounding loops. To address this problem we change the scop detection to evaluate and verify SCEV expressions at the right location. This issue has been around since at least r179148 "scop detection: properly instantiate SCEVs to the place where they are used", where we explicitly set the scope to the wrong location. Before this commit the scope was not explicitly set, which probably also resulted in the scope around the ICmp to be choosen. This resolves http://llvm.org/PR30989 Reported-by: Eli Friedman <efriedma@codeaurora.org> llvm-svn: 286769
2016-11-14 03:27:04 +08:00
}