llvm-capstone/llvm/test/Analysis/MemorySSA/pr40754.ll
Alina Sbirlea fcfa7c5f92 [MemorySSA] Make insertDef insert corresponding phi nodes.
Summary:
The original assumption for the insertDef method was that it would not
materialize Defs out of no-where, hence it will not insert phis needed
after inserting a Def.

However, when cloning an instruction (use case used in LICM), we do
materialize Defs "out of no-where". If the block receiving a Def has at
least one other Def, then no processing is needed. If the block just
received its first Def, we must check where Phi placement is needed.
The only new usage of insertDef is in LICM, hence the trigger for the bug.

But the original goal of the method also fails to apply for the move()
method. If we move a Def from the entry point of a diamond to either the
left or right blocks, then the merge block must add a phi.
While this usecase does not currently occur, or may be viewed as an
incorrect transformation, MSSA must behave corectly given the scenario.

Resolves PR40749 and PR40754.

Reviewers: george.burgess.iv

Subscribers: sanjoy, jlebar, Prazek, jdoerfert, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D58652

llvm-svn: 355040
2019-02-27 22:20:22 +00:00

55 lines
1.9 KiB
LLVM

; RUN: opt -licm -enable-mssa-loop-dependency -verify-memoryssa -S < %s | FileCheck %s
; REQUIRES: asserts
target datalayout = "E-m:e-i1:8:16-i8:8:16-i64:64-f128:64-v128:64-a:8:16-n32:64"
target triple = "systemz-unknown"
@g_120 = external dso_local local_unnamed_addr global [8 x [4 x [6 x i32]]], align 4
@g_185 = external dso_local local_unnamed_addr global i32, align 4
@g_329 = external dso_local local_unnamed_addr global i16, align 2
; Function Attrs: norecurse noreturn nounwind
define dso_local void @func_65() local_unnamed_addr {
; CHECK-LABEL: @func_65()
br label %1
; <label>:1: ; preds = %.thread, %0
br label %2
; <label>:2: ; preds = %.critedge, %1
br label %3
; <label>:3: ; preds = %5, %2
%storemerge = phi i32 [ 0, %2 ], [ %6, %5 ]
store i32 %storemerge, i32* @g_185, align 4
%4 = icmp ult i32 %storemerge, 2
br i1 %4, label %5, label %.thread.loopexit
; <label>:5: ; preds = %3
%6 = add i32 %storemerge, 1
%7 = zext i32 %6 to i64
%8 = getelementptr [8 x [4 x [6 x i32]]], [8 x [4 x [6 x i32]]]* @g_120, i64 0, i64 undef, i64 %7, i64 undef
%9 = load i32, i32* %8, align 4
%10 = icmp eq i32 %9, 0
br i1 %10, label %3, label %11
; <label>:11: ; preds = %5
%storemerge.lcssa4 = phi i32 [ %storemerge, %5 ]
%12 = icmp eq i32 %storemerge.lcssa4, 0
br i1 %12, label %.critedge, label %.thread.loopexit3
.critedge: ; preds = %11
store i16 0, i16* @g_329, align 2
br label %2
.thread.loopexit: ; preds = %3
br label %.thread
.thread.loopexit3: ; preds = %11
br label %.thread
.thread: ; preds = %.thread.loopexit3, %.thread.loopexit
br label %1
}