caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
132d6d73ea024beab3df99df2ecf4d345995fdfd
clang-p2996/llvm/test/Transforms/LoopStrengthReduce/post-inc-icmpzero.ll
Roman Lebedev 81fc53a36a [SCEV] Introduce SCEVPtrToIntExpr (PR46786) 
And use it to model LLVM IR's `ptrtoint` cast.

This is essentially an alternative to D88806, but with no chance for
all the problems it caused due to having the cast as implicit there.
(see rG7ee6c402474a2f5fd21c403e7529f97f6362fdb3)

As we've established by now, there are at least two reasons why we want this:
* It will allow SCEV to actually model the `ptrtoint` casts
  and their operands, instead of treating them as `SCEVUnknown`
* It should help with initial problem of PR46786 - this should eventually allow us
  to not loose pointer-ness of an expression in more cases

As discussed in [[ https://bugs.llvm.org/show_bug.cgi?id=46786 | PR46786 ]], in principle,
we could just extend `SCEVUnknown` with a `is ptrtoint` cast, because `ScalarEvolution::getPtrToIntExpr()`
should sink the cast as far down into the expression as possible,
so in the end we should always end up with `SCEVPtrToIntExpr` of `SCEVUnknown`.

But i think that it isn't the best solution, because it doesn't really matter
from memory consumption side - there probably won't be *that* many `SCEVPtrToIntExpr`s
for it to matter, and it allows for much better discoverability.

Reviewed By: mkazantsev

Differential Revision: https://reviews.llvm.org/D89456
2020-10-30 11:13:35 +03:00

153 lines
8.5 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-reduce -S < %s | FileCheck %s
; PR9939
; LSR should properly handle the post-inc offset when folding the
; non-IV operand of an icmp into the IV.
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
%struct.Vector2 = type { i16*, [64 x i16], i32 }
@.str = private unnamed_addr constant [37 x i8] c"0123456789abcdefghijklmnopqrstuvwxyz\00"
define void @_Z15IntegerToStringjjR7Vector2(i32 %i, i32 %radix, %struct.Vector2* nocapture %result) nounwind noinline {
; CHECK-LABEL: @_Z15IntegerToStringjjR7Vector2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[BUFFER:%.*]] = alloca [33 x i16], align 16
; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds [33 x i16], [33 x i16]* [[BUFFER]], i64 0, i64 33
; CHECK-NEXT: [[SUB_PTR_LHS_CAST:%.*]] = ptrtoint i16* [[ADD_PTR]] to i64
; CHECK-NEXT: [[SUB_PTR_RHS_CAST:%.*]] = ptrtoint i16* [[ADD_PTR]] to i64
; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr [33 x i16], [33 x i16]* [[BUFFER]], i64 0, i64 32
; CHECK-NEXT: [[SCEVGEP45:%.*]] = bitcast i16* [[SCEVGEP4]] to [33 x i16]*
; CHECK-NEXT: [[SCEVGEP11:%.*]] = getelementptr [33 x i16], [33 x i16]* [[BUFFER]], i64 1, i64 0
; CHECK-NEXT: [[SCEVGEP1112:%.*]] = bitcast i16* [[SCEVGEP11]] to [33 x i16]*
; CHECK-NEXT: br label [[DO_BODY:%.*]]
; CHECK: do.body:
; CHECK-NEXT: [[LSR_IV15:%.*]] = phi i64 [ [[LSR_IV_NEXT16:%.*]], [[DO_BODY]] ], [ -1, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[LSR_IV13:%.*]] = phi [33 x i16]* [ [[TMP2:%.*]], [[DO_BODY]] ], [ [[SCEVGEP1112]], [[ENTRY]] ]
; CHECK-NEXT: [[LSR_IV6:%.*]] = phi [33 x i16]* [ [[TMP1:%.*]], [[DO_BODY]] ], [ [[SCEVGEP45]], [[ENTRY]] ]
; CHECK-NEXT: [[I_ADDR_0:%.*]] = phi i32 [ [[DIV:%.*]], [[DO_BODY]] ], [ [[I:%.*]], [[ENTRY]] ]
; CHECK-NEXT: [[LSR_IV617:%.*]] = bitcast [33 x i16]* [[LSR_IV6]] to i16*
; CHECK-NEXT: [[REM:%.*]] = urem i32 [[I_ADDR_0]], 10
; CHECK-NEXT: [[DIV]] = udiv i32 [[I_ADDR_0]], 10
; CHECK-NEXT: [[IDXPROM:%.*]] = zext i32 [[REM]] to i64
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [37 x i8], [37 x i8]* @.str, i64 0, i64 [[IDXPROM]]
; CHECK-NEXT: [[TMP5:%.*]] = load i8, i8* [[ARRAYIDX]], align 1
; CHECK-NEXT: [[CONV:%.*]] = sext i8 [[TMP5]] to i16
; CHECK-NEXT: store i16 [[CONV]], i16* [[LSR_IV617]], align 2
; CHECK-NEXT: [[TMP0:%.*]] = icmp ugt i32 [[I_ADDR_0]], 9
; CHECK-NEXT: [[SCEVGEP7:%.*]] = getelementptr [33 x i16], [33 x i16]* [[LSR_IV6]], i64 0, i64 -1
; CHECK-NEXT: [[TMP1]] = bitcast i16* [[SCEVGEP7]] to [33 x i16]*
; CHECK-NEXT: [[SCEVGEP14:%.*]] = getelementptr [33 x i16], [33 x i16]* [[LSR_IV13]], i64 0, i64 -1
; CHECK-NEXT: [[TMP2]] = bitcast i16* [[SCEVGEP14]] to [33 x i16]*
; CHECK-NEXT: [[LSR_IV_NEXT16]] = add i64 [[LSR_IV15]], 1
; CHECK-NEXT: br i1 [[TMP0]], label [[DO_BODY]], label [[DO_END:%.*]]
; CHECK: do.end:
; CHECK-NEXT: [[XAP_0:%.*]] = inttoptr i64 [[LSR_IV_NEXT16]] to i1*
; CHECK-NEXT: [[CAP_0:%.*]] = ptrtoint i1* [[XAP_0]] to i64
; CHECK-NEXT: [[SUB_PTR_SUB:%.*]] = sub i64 [[SUB_PTR_LHS_CAST]], [[SUB_PTR_RHS_CAST]]
; CHECK-NEXT: [[SUB_PTR_DIV39:%.*]] = lshr exact i64 [[SUB_PTR_SUB]], 1
; CHECK-NEXT: [[CONV11:%.*]] = trunc i64 [[SUB_PTR_DIV39]] to i32
; CHECK-NEXT: [[MLENGTH:%.*]] = getelementptr inbounds [[STRUCT_VECTOR2:%.*]], %struct.Vector2* [[RESULT:%.*]], i64 0, i32 2
; CHECK-NEXT: [[IDX_EXT21:%.*]] = bitcast i64 [[SUB_PTR_DIV39]] to i64
; CHECK-NEXT: [[CMP2740:%.*]] = icmp eq i64 [[IDX_EXT21]], 0
; CHECK-NEXT: br i1 [[CMP2740]], label [[FOR_END:%.*]], label [[FOR_BODY_LR_PH:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[TMP16:%.*]] = load i32, i32* [[MLENGTH]], align 4
; CHECK-NEXT: [[MBEGIN:%.*]] = getelementptr inbounds [[STRUCT_VECTOR2]], %struct.Vector2* [[RESULT]], i64 0, i32 0
; CHECK-NEXT: [[TMP14:%.*]] = load i16*, i16** [[MBEGIN]], align 8
; CHECK-NEXT: [[TMP48:%.*]] = zext i32 [[TMP16]] to i64
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i16, i16* [[TMP14]], i64 [[TMP48]]
; CHECK-NEXT: [[SCEVGEP1:%.*]] = bitcast i16* [[SCEVGEP]] to i8*
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[LSR_IV8:%.*]] = phi [33 x i16]* [ [[TMP3:%.*]], [[FOR_BODY]] ], [ [[TMP2]], [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[LSR_IV:%.*]] = phi i64 [ [[LSR_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 0, [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[LSR_IV810:%.*]] = bitcast [33 x i16]* [[LSR_IV8]] to i16*
; CHECK-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[SCEVGEP1]], i64 [[LSR_IV]]
; CHECK-NEXT: [[UGLYGEP2:%.*]] = bitcast i8* [[UGLYGEP]] to i16*
; CHECK-NEXT: [[TMP29:%.*]] = load i16, i16* [[LSR_IV810]], align 2
; CHECK-NEXT: store i16 [[TMP29]], i16* [[UGLYGEP2]], align 2
; CHECK-NEXT: [[LSR_IV_NEXT]] = add i64 [[LSR_IV]], 2
; CHECK-NEXT: [[LSR_IV_NEXT3:%.*]] = inttoptr i64 [[LSR_IV_NEXT]] to i16*
; CHECK-NEXT: [[SCEVGEP9:%.*]] = getelementptr [33 x i16], [33 x i16]* [[LSR_IV8]], i64 0, i64 1
; CHECK-NEXT: [[TMP3]] = bitcast i16* [[SCEVGEP9]] to [33 x i16]*
; CHECK-NEXT: [[CMP27:%.*]] = icmp eq i16* [[LSR_IV_NEXT3]], null
; CHECK-NEXT: br i1 [[CMP27]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: [[TMP38:%.*]] = load i32, i32* [[MLENGTH]], align 4
; CHECK-NEXT: [[ADD:%.*]] = add i32 [[TMP38]], [[CONV11]]
; CHECK-NEXT: store i32 [[ADD]], i32* [[MLENGTH]], align 4
; CHECK-NEXT: ret void
;
entry:
%buffer = alloca [33 x i16], align 16
%add.ptr = getelementptr inbounds [33 x i16], [33 x i16]* %buffer, i64 0, i64 33
%sub.ptr.lhs.cast = ptrtoint i16* %add.ptr to i64
%sub.ptr.rhs.cast = ptrtoint i16* %add.ptr to i64
br label %do.body
do.body: ; preds = %do.body, %entry
%0 = phi i64 [ %indvar.next44, %do.body ], [ 0, %entry ]
%i.addr.0 = phi i32 [ %div, %do.body ], [ %i, %entry ]
%tmp51 = sub i64 32, %0
%incdec.ptr = getelementptr [33 x i16], [33 x i16]* %buffer, i64 0, i64 %tmp51
%rem = urem i32 %i.addr.0, 10
%div = udiv i32 %i.addr.0, 10
%idxprom = zext i32 %rem to i64
%arrayidx = getelementptr inbounds [37 x i8], [37 x i8]* @.str, i64 0, i64 %idxprom
%tmp5 = load i8, i8* %arrayidx, align 1
%conv = sext i8 %tmp5 to i16
store i16 %conv, i16* %incdec.ptr, align 2
%1 = icmp ugt i32 %i.addr.0, 9
%indvar.next44 = add i64 %0, 1
br i1 %1, label %do.body, label %do.end
do.end: ; preds = %do.body
%xap.0 = inttoptr i64 %0 to i1*
%cap.0 = ptrtoint i1* %xap.0 to i64
%sub.ptr.sub = sub i64 %sub.ptr.lhs.cast, %sub.ptr.rhs.cast
%sub.ptr.div39 = lshr exact i64 %sub.ptr.sub, 1
%conv11 = trunc i64 %sub.ptr.div39 to i32
%mLength = getelementptr inbounds %struct.Vector2, %struct.Vector2* %result, i64 0, i32 2
%idx.ext21 = bitcast i64 %sub.ptr.div39 to i64
%incdec.ptr.sum = add i64 %idx.ext21, -1
%cp.0.sum = sub i64 %incdec.ptr.sum, %0
%add.ptr22 = getelementptr [33 x i16], [33 x i16]* %buffer, i64 1, i64 %cp.0.sum
%cmp2740 = icmp eq i64 %idx.ext21, 0
br i1 %cmp2740, label %for.end, label %for.body.lr.ph
for.body.lr.ph: ; preds = %do.end
%tmp16 = load i32, i32* %mLength, align 4
%mBegin = getelementptr inbounds %struct.Vector2, %struct.Vector2* %result, i64 0, i32 0
%tmp14 = load i16*, i16** %mBegin, align 8
%tmp48 = zext i32 %tmp16 to i64
br label %for.body
for.body: ; preds = %for.body, %for.body.lr.ph
%indvar = phi i64 [ 0, %for.body.lr.ph ], [ %indvar.next, %for.body ]
%tmp46 = add i64 %tmp51, %indvar
%p.042 = getelementptr [33 x i16], [33 x i16]* %buffer, i64 0, i64 %tmp46
%tmp47 = sub i64 %indvar, %0
%incdec.ptr32 = getelementptr [33 x i16], [33 x i16]* %buffer, i64 1, i64 %tmp47
%tmp49 = add i64 %tmp48, %indvar
%dst.041 = getelementptr i16, i16* %tmp14, i64 %tmp49
%tmp29 = load i16, i16* %p.042, align 2
store i16 %tmp29, i16* %dst.041, align 2
%cmp27 = icmp eq i16* %incdec.ptr32, %add.ptr22
%indvar.next = add i64 %indvar, 1
br i1 %cmp27, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
br label %for.end
for.end: ; preds = %for.end.loopexit, %do.end
%tmp38 = load i32, i32* %mLength, align 4
%add = add i32 %tmp38, %conv11
store i32 %add, i32* %mLength, align 4
ret void
}
Reference in New Issue View Git Blame Copy Permalink