mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 03:33:20 +01:00
6ba48b6c38
preserve loop simplify of enclosing loops. The problem here starts with LoopRotation which ends up cloning code out of the latch into the new preheader it is buidling. This can create a new edge from the preheader into the exit block of the loop which breaks LoopSimplify form. The code tries to fix this by splitting the critical edge between the latch and the exit block to get a new exit block that only the latch dominates. This sadly isn't sufficient. The exit block may be an exit block for multiple nested loops. When we clone an edge from the latch of the inner loop to the new preheader being built in the outer loop, we create an exiting edge from the outer loop to this exit block. Despite breaking the LoopSimplify form for the inner loop, this is fine for the outer loop. However, when we split the edge from the inner loop to the exit block, we create a new block which is in neither the inner nor outer loop as the new exit block. This is a predecessor to the old exit block, and so the split itself takes the outer loop out of LoopSimplify form. We need to split every edge entering the exit block from inside a loop nested more deeply than the exit block in order to preserve all of the loop simplify constraints. Once we try to do that, a problem with splitting critical edges surfaces. Previously, we tried a very brute force to update LoopSimplify form by re-computing it for all exit blocks. We don't need to do this, and doing this much will sometimes but not always overlap with the LoopRotate bug fix. Instead, the code needs to specifically handle the cases which can start to violate LoopSimplify -- they aren't that common. We need to see if the destination of the split edge was a loop exit block in simplified form for the loop of the source of the edge. For this to be true, all the predecessors need to be in the exact same loop as the source of the edge being split. If the dest block was originally in this form, we have to split all of the deges back into this loop to recover it. The old mechanism of doing this was conservatively correct because at least *one* of the exiting blocks it rewrote was the DestBB and so the DestBB's predecessors were fixed. But this is a much more targeted way of doing it. Making it targeted is important, because ballooning the set of edges touched prevents LoopRotate from being able to split edges *it* needs to split to preserve loop simplify in a coherent way -- the critical edge splitting would sometimes find the other edges in need of splitting but not others. Many, *many* thanks for help from Nick reducing these test cases mightily. And helping lots with the analysis here as this one was quite tricky to track down. llvm-svn: 200393
108 lines
5.0 KiB
LLVM
108 lines
5.0 KiB
LLVM
; RUN: opt -S -loop-rotate < %s | FileCheck %s
|
|
|
|
declare void @llvm.dbg.declare(metadata, metadata) nounwind readnone
|
|
declare void @llvm.dbg.value(metadata, i64, metadata) nounwind readnone
|
|
|
|
define i32 @tak(i32 %x, i32 %y, i32 %z) nounwind ssp {
|
|
; CHECK-LABEL: define i32 @tak(
|
|
; CHECK: entry
|
|
; CHECK-NEXT: call void @llvm.dbg.value(metadata !{i32 %x}
|
|
|
|
entry:
|
|
br label %tailrecurse
|
|
|
|
tailrecurse: ; preds = %if.then, %entry
|
|
%x.tr = phi i32 [ %x, %entry ], [ %call, %if.then ]
|
|
%y.tr = phi i32 [ %y, %entry ], [ %call9, %if.then ]
|
|
%z.tr = phi i32 [ %z, %entry ], [ %call14, %if.then ]
|
|
tail call void @llvm.dbg.value(metadata !{i32 %x.tr}, i64 0, metadata !6), !dbg !7
|
|
tail call void @llvm.dbg.value(metadata !{i32 %y.tr}, i64 0, metadata !8), !dbg !9
|
|
tail call void @llvm.dbg.value(metadata !{i32 %z.tr}, i64 0, metadata !10), !dbg !11
|
|
%cmp = icmp slt i32 %y.tr, %x.tr, !dbg !12
|
|
br i1 %cmp, label %if.then, label %if.end, !dbg !12
|
|
|
|
if.then: ; preds = %tailrecurse
|
|
%sub = sub nsw i32 %x.tr, 1, !dbg !14
|
|
%call = tail call i32 @tak(i32 %sub, i32 %y.tr, i32 %z.tr), !dbg !14
|
|
%sub6 = sub nsw i32 %y.tr, 1, !dbg !14
|
|
%call9 = tail call i32 @tak(i32 %sub6, i32 %z.tr, i32 %x.tr), !dbg !14
|
|
%sub11 = sub nsw i32 %z.tr, 1, !dbg !14
|
|
%call14 = tail call i32 @tak(i32 %sub11, i32 %x.tr, i32 %y.tr), !dbg !14
|
|
br label %tailrecurse
|
|
|
|
if.end: ; preds = %tailrecurse
|
|
br label %return, !dbg !16
|
|
|
|
return: ; preds = %if.end
|
|
ret i32 %z.tr, !dbg !17
|
|
}
|
|
|
|
@channelColumns = external global i64
|
|
@horzPlane = external global i8*, align 8
|
|
|
|
define void @FindFreeHorzSeg(i64 %startCol, i64 %row, i64* %rowStart) {
|
|
; Ensure that the loop increment basic block is rotated into the tail of the
|
|
; body, even though it contains a debug intrinsic call.
|
|
; CHECK-LABEL: define void @FindFreeHorzSeg(
|
|
; CHECK: %dec = add
|
|
; CHECK-NEXT: tail call void @llvm.dbg.value
|
|
; CHECK-NEXT: br i1 %tobool, label %for.cond, label %[[LOOP_EXIT:[^,]*]]
|
|
; CHECK: [[LOOP_EXIT]]:
|
|
; CHECK-NEXT: phi i64 [ %{{[^,]*}}, %{{[^,]*}} ]
|
|
; CHECK-NEXT: br label %for.end
|
|
|
|
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond:
|
|
%i.0 = phi i64 [ %startCol, %entry ], [ %dec, %for.inc ]
|
|
%cmp = icmp eq i64 %i.0, 0
|
|
br i1 %cmp, label %for.end, label %for.body
|
|
|
|
for.body:
|
|
%0 = load i64* @channelColumns, align 8
|
|
%mul = mul i64 %0, %row
|
|
%add = add i64 %mul, %i.0
|
|
%1 = load i8** @horzPlane, align 8
|
|
%arrayidx = getelementptr inbounds i8* %1, i64 %add
|
|
%2 = load i8* %arrayidx, align 1
|
|
%tobool = icmp eq i8 %2, 0
|
|
br i1 %tobool, label %for.inc, label %for.end
|
|
|
|
for.inc:
|
|
%dec = add i64 %i.0, -1
|
|
tail call void @llvm.dbg.value(metadata !{i64 %dec}, i64 0, metadata !{metadata !"undef"})
|
|
br label %for.cond
|
|
|
|
for.end:
|
|
%add1 = add i64 %i.0, 1
|
|
store i64 %add1, i64* %rowStart, align 8
|
|
ret void
|
|
}
|
|
|
|
!llvm.module.flags = !{!20}
|
|
!llvm.dbg.sp = !{!0}
|
|
|
|
!0 = metadata !{i32 589870, metadata !18, metadata !1, metadata !"tak", metadata !"tak", metadata !"", i32 32, metadata !3, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 false, i32 (i32, i32, i32)* @tak, null, null, null, i32 0} ; [ DW_TAG_subprogram ] [line 32] [def] [scope 0] [tak]
|
|
!1 = metadata !{i32 589865, metadata !18} ; [ DW_TAG_file_type ]
|
|
!2 = metadata !{i32 589841, metadata !18, i32 12, metadata !"clang version 2.9 (trunk 125492)", i1 true, metadata !"", i32 0, metadata !19, metadata !19, null, null, null, metadata !""} ; [ DW_TAG_compile_unit ]
|
|
!3 = metadata !{i32 589845, metadata !18, metadata !1, metadata !"", i32 0, i64 0, i64 0, i32 0, i32 0, null, metadata !4, i32 0, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ]
|
|
!4 = metadata !{metadata !5}
|
|
!5 = metadata !{i32 589860, null, metadata !2, metadata !"int", i32 0, i64 32, i64 32, i64 0, i32 0, i32 5} ; [ DW_TAG_base_type ]
|
|
!6 = metadata !{i32 590081, metadata !0, metadata !"x", metadata !1, i32 32, metadata !5, i32 0} ; [ DW_TAG_arg_variable ]
|
|
!7 = metadata !{i32 32, i32 13, metadata !0, null}
|
|
!8 = metadata !{i32 590081, metadata !0, metadata !"y", metadata !1, i32 32, metadata !5, i32 0} ; [ DW_TAG_arg_variable ]
|
|
!9 = metadata !{i32 32, i32 20, metadata !0, null}
|
|
!10 = metadata !{i32 590081, metadata !0, metadata !"z", metadata !1, i32 32, metadata !5, i32 0} ; [ DW_TAG_arg_variable ]
|
|
!11 = metadata !{i32 32, i32 27, metadata !0, null}
|
|
!12 = metadata !{i32 33, i32 3, metadata !13, null}
|
|
!13 = metadata !{i32 589835, metadata !18, metadata !0, i32 32, i32 30, i32 6} ; [ DW_TAG_lexical_block ]
|
|
!14 = metadata !{i32 34, i32 5, metadata !15, null}
|
|
!15 = metadata !{i32 589835, metadata !18, metadata !13, i32 33, i32 14, i32 7} ; [ DW_TAG_lexical_block ]
|
|
!16 = metadata !{i32 36, i32 3, metadata !13, null}
|
|
!17 = metadata !{i32 37, i32 1, metadata !13, null}
|
|
!18 = metadata !{metadata !"/Volumes/Lalgate/cj/llvm/projects/llvm-test/SingleSource/Benchmarks/BenchmarkGame/recursive.c", metadata !"/Volumes/Lalgate/cj/D/projects/llvm-test/SingleSource/Benchmarks/BenchmarkGame"}
|
|
!19 = metadata !{i32 0}
|
|
!20 = metadata !{i32 1, metadata !"Debug Info Version", i32 1}
|