maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Analysis/LoopAccessAnalysis/reverse-memcheck-bounds.ll

91 lines
2.7 KiB
LLVM
Raw Normal View History

Fix memcheck interval ends for pointers with negative strides Summary: The checking pointer grouping algorithm assumes that the starts/ends of the pointers are well formed (start <= end). The runtime memory checking algorithm also assumes this by doing: start0 < end1 && start1 < end0 to detect conflicts. This check only works if start0 <= end0 and start1 <= end1. This change correctly orders the interval ends by either checking the stride (if it is constant) or by using min/max SCEV expressions. Reviewers: anemet, rengolin Subscribers: rengolin, llvm-commits Differential Revision: http://reviews.llvm.org/D11149 llvm-svn: 242400
2015-07-16 22:02:58 +08:00
; RUN: opt -loop-accesses -analyze < %s | FileCheck %s
[PM] Avoid getResult on a higher level in LoopAccessAnalysis Note that require<domtree> and require<loops> aren't needed because they come in implicitly via the loop pass manager. llvm-svn: 274712
2016-07-07 09:01:53 +08:00
; RUN: opt -passes='require<scalar-evolution>,require<aa>,loop(print-access-info)' -disable-output < %s 2>&1 | FileCheck %s
Fix memcheck interval ends for pointers with negative strides Summary: The checking pointer grouping algorithm assumes that the starts/ends of the pointers are well formed (start <= end). The runtime memory checking algorithm also assumes this by doing: start0 < end1 && start1 < end0 to detect conflicts. This check only works if start0 <= end0 and start1 <= end1. This change correctly orders the interval ends by either checking the stride (if it is constant) or by using min/max SCEV expressions. Reviewers: anemet, rengolin Subscribers: rengolin, llvm-commits Differential Revision: http://reviews.llvm.org/D11149 llvm-svn: 242400
2015-07-16 22:02:58 +08:00
; The runtime memory check code and the access grouping
; algorithm both assume that the start and end values
; for an access range are ordered (start <= stop).
; When generating checks for accesses with negative stride
; we need to take this into account and swap the interval
; ends.
;
; for (i = 0; i < 10000; i++) {
; B[i] = A[15000 - i] * 3;
; }
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnueabi"
; CHECK: function 'f':
[Loop Vectorizer] Fixed memory confilict checks. Fixed a bug in run-time checks for possible memory conflicts inside loop. The bug is in Low <-> High boundaries calculation. The High boundary should be calculated as "last memory access pointer + element size". Differential revision: https://reviews.llvm.org/D23176 llvm-svn: 279930
2016-08-28 16:53:53 +08:00
; CHECK: (Low: (20000 + %a) High: (60004 + %a))
Fix memcheck interval ends for pointers with negative strides Summary: The checking pointer grouping algorithm assumes that the starts/ends of the pointers are well formed (start <= end). The runtime memory checking algorithm also assumes this by doing: start0 < end1 && start1 < end0 to detect conflicts. This check only works if start0 <= end0 and start1 <= end1. This change correctly orders the interval ends by either checking the stride (if it is constant) or by using min/max SCEV expressions. Reviewers: anemet, rengolin Subscribers: rengolin, llvm-commits Differential Revision: http://reviews.llvm.org/D11149 llvm-svn: 242400
2015-07-16 22:02:58 +08:00
@B = common global i32* null, align 8
@A = common global i32* null, align 8
define void @f() {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
br label %for.body
for.body: ; preds = %for.body, %entry
%idx = phi i64 [ 0, %entry ], [ %add, %for.body ]
%negidx = sub i64 15000, %idx
%arrayidxA0 = getelementptr inbounds i32, i32* %a, i64 %negidx
%loadA0 = load i32, i32* %arrayidxA0, align 2
%res = mul i32 %loadA0, 3
%add = add nuw nsw i64 %idx, 1
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %idx
store i32 %res, i32* %arrayidxB, align 2
%exitcond = icmp eq i64 %idx, 10000
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
; CHECK: function 'g':
; When the stride is not constant, we are forced to do umin/umax to get
; the interval limits.
; for (i = 0; i < 10000; i++) {
; B[i] = A[15000 - step * i] * 3;
; }
; Here it is not obvious what the limits are, since 'step' could be negative.
; CHECK: Low: (-1 + (-1 * ((-60001 + (-1 * %a)) umax (-60001 + (40000 * %step) + (-1 * %a)))))
[Loop Vectorizer] Fixed memory confilict checks. Fixed a bug in run-time checks for possible memory conflicts inside loop. The bug is in Low <-> High boundaries calculation. The High boundary should be calculated as "last memory access pointer + element size". Differential revision: https://reviews.llvm.org/D23176 llvm-svn: 279930
2016-08-28 16:53:53 +08:00
; CHECK: High: (4 + ((60000 + %a)<nsw> umax (60000 + (-40000 * %step) + %a)))
Fix memcheck interval ends for pointers with negative strides Summary: The checking pointer grouping algorithm assumes that the starts/ends of the pointers are well formed (start <= end). The runtime memory checking algorithm also assumes this by doing: start0 < end1 && start1 < end0 to detect conflicts. This check only works if start0 <= end0 and start1 <= end1. This change correctly orders the interval ends by either checking the stride (if it is constant) or by using min/max SCEV expressions. Reviewers: anemet, rengolin Subscribers: rengolin, llvm-commits Differential Revision: http://reviews.llvm.org/D11149 llvm-svn: 242400
2015-07-16 22:02:58 +08:00
define void @g(i64 %step) {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
br label %for.body
for.body: ; preds = %for.body, %entry
%idx = phi i64 [ 0, %entry ], [ %add, %for.body ]
%idx_mul = mul i64 %idx, %step
%negidx = sub i64 15000, %idx_mul
%arrayidxA0 = getelementptr inbounds i32, i32* %a, i64 %negidx
%loadA0 = load i32, i32* %arrayidxA0, align 2
%res = mul i32 %loadA0, 3
%add = add nuw nsw i64 %idx, 1
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %idx
store i32 %res, i32* %arrayidxB, align 2
%exitcond = icmp eq i64 %idx, 10000
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}