2017-02-16 05:10:09 +08:00
|
|
|
; RUN: opt -o %t %s -instcombine -simplifycfg -thinlto-bc -verify-assumption-cache
|
2017-02-15 11:01:11 +08:00
|
|
|
; RUN: llvm-dis -o - %t | FileCheck %s
|
|
|
|
|
|
|
|
; Test that the simplifycfg pass correctly updates the assumption cache
|
|
|
|
; when it clones the llvm.assume call as part of creating a critical
|
|
|
|
; edge. To do that, we set up a pass pipeline such that (1) an assumption
|
|
|
|
; cache is created for foo before simplifycfg updates it, and (2) foo's
|
|
|
|
; assumption cache is verified after simplifycfg has run. To satisfy 1, we
|
|
|
|
; run the instcombine pass first in our pipeline. To satisfy 2, we use the
|
|
|
|
; ThinLTOBitcodeWriter pass to write bitcode (that pass uses the assumption
|
|
|
|
; cache). That ensures that the pass manager does not call releaseMemory()
|
|
|
|
; on the AssumptionCacheTracker before the end of the pipeline, which would
|
|
|
|
; wipe out the bad assumption cache before it is verified.
|
|
|
|
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
|
|
|
|
%class.F = type { i8 }
|
|
|
|
%class.B = type { i8 }
|
|
|
|
%class.A = type { %class.C }
|
|
|
|
%class.C = type { i32 (...)** }
|
|
|
|
|
|
|
|
define void @foo(%class.F* %this, %class.B* %out) {
|
|
|
|
entry:
|
|
|
|
%call = tail call i32 @_ZNK1F5beginEv(%class.F* %this)
|
|
|
|
%call2 = tail call i32 @_ZNK1F3endEv(%class.F* %this)
|
|
|
|
%cmp.i22 = icmp eq i32 %call, %call2
|
|
|
|
br i1 %cmp.i22, label %while.end, label %while.body.preheader
|
|
|
|
|
|
|
|
while.body.preheader:
|
|
|
|
br label %while.body
|
|
|
|
|
|
|
|
while.body:
|
|
|
|
%frame_node.sroa.0.023 = phi i32 [ %inc.i, %_ZN10unique_ptrD2Ev.exit ], [ %call, %while.body.preheader ]
|
|
|
|
%call8 = tail call i8* @_Znwm(i64 8)
|
|
|
|
%inc.i = add nsw i32 %frame_node.sroa.0.023, 1
|
|
|
|
%cmp = icmp eq i32 %inc.i, %call2
|
|
|
|
br i1 %cmp, label %_ZN10unique_ptrD2Ev.exit, label %if.then
|
|
|
|
|
|
|
|
if.then:
|
|
|
|
tail call void @_ZN1B6appendEv(%class.B* %out)
|
|
|
|
br label %_ZN10unique_ptrD2Ev.exit
|
|
|
|
|
|
|
|
_ZN10unique_ptrD2Ev.exit:
|
|
|
|
%x1 = bitcast i8* %call8 to void (%class.A*)***
|
|
|
|
%vtable.i.i = load void (%class.A*)**, void (%class.A*)*** %x1, align 8
|
|
|
|
%x2 = bitcast void (%class.A*)** %vtable.i.i to i8*
|
|
|
|
%x3 = tail call i1 @llvm.type.test(i8* %x2, metadata !"foo")
|
|
|
|
; CHECK: call void @llvm.assume
|
|
|
|
; CHECK: call void @llvm.assume
|
|
|
|
tail call void @llvm.assume(i1 %x3) #5
|
|
|
|
br i1 %cmp, label %while.end.loopexit, label %while.body
|
|
|
|
|
|
|
|
while.end.loopexit:
|
|
|
|
br label %while.end
|
|
|
|
|
|
|
|
while.end:
|
|
|
|
ret void
|
|
|
|
}
|
|
|
|
|
2017-04-11 04:18:21 +08:00
|
|
|
declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture)
|
2017-02-15 11:01:11 +08:00
|
|
|
|
|
|
|
declare i32 @_ZNK1F5beginEv(%class.F*)
|
|
|
|
|
|
|
|
declare i32 @_ZNK1F3endEv(%class.F*)
|
|
|
|
|
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)
Summary:
This is a resurrection of work first proposed and discussed in Aug 2015:
http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
and initially landed (but then backed out) in Nov 2015:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html
The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument
which is required to be a constant integer. It represents the alignment of the
dest (and source), and so must be the minimum of the actual alignment of the
two.
This change is the first in a series that allows source and dest to each
have their own alignments by using the alignment attribute on their arguments.
In this change we:
1) Remove the alignment argument.
2) Add alignment attributes to the source & dest arguments. We, temporarily,
require that the alignments for source & dest be equal.
For example, code which used to read:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false)
will now read
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false)
Downstream users may have to update their lit tests that check for
@llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script
may help with updating the majority of your tests, but it does not catch all possible
patterns so some manual checking and updating will be required.
s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g
s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g
s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g
s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g
The remaining changes in the series will:
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments.
Step 3) Update Clang to use the new IRBuilder API.
Step 4) Update Polly to use the new IRBuilder API.
Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API,
and those that use use MemIntrinsicInst::[get|set]Alignment() to use
getDestAlignment() and getSourceAlignment() instead.
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.
Reviewers: pete, hfinkel, lhames, reames, bollu
Reviewed By: reames
Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits
Differential Revision: https://reviews.llvm.org/D41675
llvm-svn: 322965
2018-01-20 01:13:12 +08:00
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1)
|
2017-02-15 11:01:11 +08:00
|
|
|
|
|
|
|
declare noalias nonnull i8* @_Znwm(i64)
|
|
|
|
|
|
|
|
declare void @_ZN1B6appendEv(%class.B*)
|
|
|
|
|
2017-04-11 04:18:21 +08:00
|
|
|
declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture)
|
2017-02-15 11:01:11 +08:00
|
|
|
|
|
|
|
declare i1 @llvm.type.test(i8*, metadata)
|
|
|
|
|
|
|
|
declare void @llvm.assume(i1)
|
|
|
|
|
|
|
|
!llvm.module.flags = !{!0}
|
|
|
|
!llvm.ident = !{!1}
|
|
|
|
|
|
|
|
!0 = !{i32 1, !"PIC Level", i32 2}
|
|
|
|
!1 = !{!"clang version 5.0.0 "}
|