shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/llvm/test/Instrumentation/EfficiencySanitizer/working_set_basic.ll
Daniel Neilson 1e68724d24 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
2018-01-19 17:13:12 +00:00

276 lines
9.7 KiB
LLVM
Raw Blame History

; Test basic EfficiencySanitizer working set instrumentation.
;
; RUN: opt < %s -esan -esan-working-set -S | FileCheck %s
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
; Intra-cache-line
define i8 @aligned1(i8* %a) {
entry:
%tmp1 = load i8, i8* %a, align 1
ret i8 %tmp1
; CHECK: @llvm.global_ctors = {{.*}}@esan.module_ctor
; CHECK: %0 = ptrtoint i8* %a to i64
; CHECK-NEXT: %1 = and i64 %0, 17592186044415
; CHECK-NEXT: %2 = add i64 %1, 1337006139375616
; CHECK-NEXT: %3 = lshr i64 %2, 6
; CHECK-NEXT: %4 = inttoptr i64 %3 to i8*
; CHECK-NEXT: %5 = load i8, i8* %4
; CHECK-NEXT: %6 = and i8 %5, -127
; CHECK-NEXT: %7 = icmp ne i8 %6, -127
; CHECK-NEXT: br i1 %7, label %8, label %11
; CHECK: %9 = or i8 %5, -127
; CHECK-NEXT: %10 = inttoptr i64 %3 to i8*
; CHECK-NEXT: store i8 %9, i8* %10
; CHECK-NEXT: br label %11
; CHECK: %tmp1 = load i8, i8* %a, align 1
; CHECK-NEXT: ret i8 %tmp1
}
define i16 @aligned2(i16* %a) {
entry:
%tmp1 = load i16, i16* %a, align 2
ret i16 %tmp1
; CHECK: %0 = ptrtoint i16* %a to i64
; CHECK-NEXT: %1 = and i64 %0, 17592186044415
; CHECK-NEXT: %2 = add i64 %1, 1337006139375616
; CHECK-NEXT: %3 = lshr i64 %2, 6
; CHECK-NEXT: %4 = inttoptr i64 %3 to i8*
; CHECK-NEXT: %5 = load i8, i8* %4
; CHECK-NEXT: %6 = and i8 %5, -127
; CHECK-NEXT: %7 = icmp ne i8 %6, -127
; CHECK-NEXT: br i1 %7, label %8, label %11
; CHECK: %9 = or i8 %5, -127
; CHECK-NEXT: %10 = inttoptr i64 %3 to i8*
; CHECK-NEXT: store i8 %9, i8* %10
; CHECK-NEXT: br label %11
; CHECK: %tmp1 = load i16, i16* %a, align 2
; CHECK-NEXT: ret i16 %tmp1
}
define i32 @aligned4(i32* %a) {
entry:
%tmp1 = load i32, i32* %a, align 4
ret i32 %tmp1
; CHECK: %0 = ptrtoint i32* %a to i64
; CHECK-NEXT: %1 = and i64 %0, 17592186044415
; CHECK-NEXT: %2 = add i64 %1, 1337006139375616
; CHECK-NEXT: %3 = lshr i64 %2, 6
; CHECK-NEXT: %4 = inttoptr i64 %3 to i8*
; CHECK-NEXT: %5 = load i8, i8* %4
; CHECK-NEXT: %6 = and i8 %5, -127
; CHECK-NEXT: %7 = icmp ne i8 %6, -127
; CHECK-NEXT: br i1 %7, label %8, label %11
; CHECK: %9 = or i8 %5, -127
; CHECK-NEXT: %10 = inttoptr i64 %3 to i8*
; CHECK-NEXT: store i8 %9, i8* %10
; CHECK-NEXT: br label %11
; CHECK: %tmp1 = load i32, i32* %a, align 4
; CHECK-NEXT: ret i32 %tmp1
}
define i64 @aligned8(i64* %a) {
entry:
%tmp1 = load i64, i64* %a, align 8
ret i64 %tmp1
; CHECK: %0 = ptrtoint i64* %a to i64
; CHECK-NEXT: %1 = and i64 %0, 17592186044415
; CHECK-NEXT: %2 = add i64 %1, 1337006139375616
; CHECK-NEXT: %3 = lshr i64 %2, 6
; CHECK-NEXT: %4 = inttoptr i64 %3 to i8*
; CHECK-NEXT: %5 = load i8, i8* %4
; CHECK-NEXT: %6 = and i8 %5, -127
; CHECK-NEXT: %7 = icmp ne i8 %6, -127
; CHECK-NEXT: br i1 %7, label %8, label %11
; CHECK: %9 = or i8 %5, -127
; CHECK-NEXT: %10 = inttoptr i64 %3 to i8*
; CHECK-NEXT: store i8 %9, i8* %10
; CHECK-NEXT: br label %11
; CHECK: %tmp1 = load i64, i64* %a, align 8
; CHECK-NEXT: ret i64 %tmp1
}
define i128 @aligned16(i128* %a) {
entry:
%tmp1 = load i128, i128* %a, align 16
ret i128 %tmp1
; CHECK: %0 = ptrtoint i128* %a to i64
; CHECK-NEXT: %1 = and i64 %0, 17592186044415
; CHECK-NEXT: %2 = add i64 %1, 1337006139375616
; CHECK-NEXT: %3 = lshr i64 %2, 6
; CHECK-NEXT: %4 = inttoptr i64 %3 to i8*
; CHECK-NEXT: %5 = load i8, i8* %4
; CHECK-NEXT: %6 = and i8 %5, -127
; CHECK-NEXT: %7 = icmp ne i8 %6, -127
; CHECK-NEXT: br i1 %7, label %8, label %11
; CHECK: %9 = or i8 %5, -127
; CHECK-NEXT: %10 = inttoptr i64 %3 to i8*
; CHECK-NEXT: store i8 %9, i8* %10
; CHECK-NEXT: br label %11
; CHECK: %tmp1 = load i128, i128* %a, align 16
; CHECK-NEXT: ret i128 %tmp1
}
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
; Not guaranteed to be intra-cache-line, but our defaults are to
; assume they are:
define i16 @unaligned2(i16* %a) {
entry:
%tmp1 = load i16, i16* %a, align 1
ret i16 %tmp1
; CHECK: %0 = ptrtoint i16* %a to i64
; CHECK-NEXT: %1 = and i64 %0, 17592186044415
; CHECK-NEXT: %2 = add i64 %1, 1337006139375616
; CHECK-NEXT: %3 = lshr i64 %2, 6
; CHECK-NEXT: %4 = inttoptr i64 %3 to i8*
; CHECK-NEXT: %5 = load i8, i8* %4
; CHECK-NEXT: %6 = and i8 %5, -127
; CHECK-NEXT: %7 = icmp ne i8 %6, -127
; CHECK-NEXT: br i1 %7, label %8, label %11
; CHECK: %9 = or i8 %5, -127
; CHECK-NEXT: %10 = inttoptr i64 %3 to i8*
; CHECK-NEXT: store i8 %9, i8* %10
; CHECK-NEXT: br label %11
; CHECK: %tmp1 = load i16, i16* %a, align 1
; CHECK-NEXT: ret i16 %tmp1
}
define i32 @unaligned4(i32* %a) {
entry:
%tmp1 = load i32, i32* %a, align 2
ret i32 %tmp1
; CHECK: %0 = ptrtoint i32* %a to i64
; CHECK-NEXT: %1 = and i64 %0, 17592186044415
; CHECK-NEXT: %2 = add i64 %1, 1337006139375616
; CHECK-NEXT: %3 = lshr i64 %2, 6
; CHECK-NEXT: %4 = inttoptr i64 %3 to i8*
; CHECK-NEXT: %5 = load i8, i8* %4
; CHECK-NEXT: %6 = and i8 %5, -127
; CHECK-NEXT: %7 = icmp ne i8 %6, -127
; CHECK-NEXT: br i1 %7, label %8, label %11
; CHECK: %9 = or i8 %5, -127
; CHECK-NEXT: %10 = inttoptr i64 %3 to i8*
; CHECK-NEXT: store i8 %9, i8* %10
; CHECK-NEXT: br label %11
; CHECK: %tmp1 = load i32, i32* %a, align 2
; CHECK-NEXT: ret i32 %tmp1
}
define i64 @unaligned8(i64* %a) {
entry:
%tmp1 = load i64, i64* %a, align 4
ret i64 %tmp1
; CHECK: %0 = ptrtoint i64* %a to i64
; CHECK-NEXT: %1 = and i64 %0, 17592186044415
; CHECK-NEXT: %2 = add i64 %1, 1337006139375616
; CHECK-NEXT: %3 = lshr i64 %2, 6
; CHECK-NEXT: %4 = inttoptr i64 %3 to i8*
; CHECK-NEXT: %5 = load i8, i8* %4
; CHECK-NEXT: %6 = and i8 %5, -127
; CHECK-NEXT: %7 = icmp ne i8 %6, -127
; CHECK-NEXT: br i1 %7, label %8, label %11
; CHECK: %9 = or i8 %5, -127
; CHECK-NEXT: %10 = inttoptr i64 %3 to i8*
; CHECK-NEXT: store i8 %9, i8* %10
; CHECK-NEXT: br label %11
; CHECK: %tmp1 = load i64, i64* %a, align 4
; CHECK-NEXT: ret i64 %tmp1
}
define i128 @unaligned16(i128* %a) {
entry:
%tmp1 = load i128, i128* %a, align 8
ret i128 %tmp1
; CHECK: %0 = ptrtoint i128* %a to i64
; CHECK-NEXT: %1 = and i64 %0, 17592186044415
; CHECK-NEXT: %2 = add i64 %1, 1337006139375616
; CHECK-NEXT: %3 = lshr i64 %2, 6
; CHECK-NEXT: %4 = inttoptr i64 %3 to i8*
; CHECK-NEXT: %5 = load i8, i8* %4
; CHECK-NEXT: %6 = and i8 %5, -127
; CHECK-NEXT: %7 = icmp ne i8 %6, -127
; CHECK-NEXT: br i1 %7, label %8, label %11
; CHECK: %9 = or i8 %5, -127
; CHECK-NEXT: %10 = inttoptr i64 %3 to i8*
; CHECK-NEXT: store i8 %9, i8* %10
; CHECK-NEXT: br label %11
; CHECK: %tmp1 = load i128, i128* %a, align 8
; CHECK-NEXT: ret i128 %tmp1
}
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
; Ensure that esan converts intrinsics to calls:
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1)
declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1)
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
define void @memCpyTest(i8* nocapture %x, i8* nocapture %y) {
entry:
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %x, i8* align 4 %y, i64 16, i1 false)
ret void
; CHECK: define void @memCpyTest
; CHECK: call i8* @memcpy
; CHECK: ret void
}
define void @memMoveTest(i8* nocapture %x, i8* nocapture %y) {
entry:
tail call void @llvm.memmove.p0i8.p0i8.i64(i8* align 4 %x, i8* align 4 %y, i64 16, i1 false)
ret void
; CHECK: define void @memMoveTest
; CHECK: call i8* @memmove
; CHECK: ret void
}
define void @memSetTest(i8* nocapture %x) {
entry:
tail call void @llvm.memset.p0i8.i64(i8* align 4 %x, i8 77, i64 16, i1 false)
ret void
; CHECK: define void @memSetTest
; CHECK: call i8* @memset
; CHECK: ret void
}
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
; Ensure that esan doesn't convert element atomic memory intrinsics to
; calls.
declare void @llvm.memset.element.unordered.atomic.p0i8.i64(i8* nocapture writeonly, i8, i64, i32) nounwind
declare void @llvm.memmove.element.unordered.atomic.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32) nounwind
declare void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32) nounwind
define void @elementAtomic_memCpyTest(i8* nocapture %x, i8* nocapture %y) {
; CHECK-LABEL: elementAtomic_memCpyTest
; CHECK-NEXT: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %x, i8* align 1 %y, i64 16, i32 1)
; CHECK-NEXT: ret void
tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %x, i8* align 1 %y, i64 16, i32 1)
ret void
}
define void @elementAtomic_memMoveTest(i8* nocapture %x, i8* nocapture %y) {
; CHECK-LABEL: elementAtomic_memMoveTest
; CHECK-NEXT: tail call void @llvm.memmove.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %x, i8* align 1 %y, i64 16, i32 1)
; CHECK-NEXT: ret void
tail call void @llvm.memmove.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %x, i8* align 1 %y, i64 16, i32 1)
ret void
}
define void @elementAtomic_memSetTest(i8* nocapture %x) {
; CHECK-LABEL: elementAtomic_memSetTest
; CHECK-NEXT: tail call void @llvm.memset.element.unordered.atomic.p0i8.i64(i8* align 1 %x, i8 77, i64 16, i32 1)
; CHECK-NEXT: ret void
tail call void @llvm.memset.element.unordered.atomic.p0i8.i64(i8* align 1 %x, i8 77, i64 16, i32 1)
ret void
}
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
; Top-level:
; CHECK: define internal void @esan.module_ctor()
; CHECK: call void @__esan_init(i32 2, i8* null)
; CHECK: define internal void @esan.module_dtor()
; CHECK: call void @__esan_exit(i8* null)
Reference in New Issue View Git Blame Copy Permalink