RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity
llvm-mirror/test/CodeGen/ARM/memfunc.ll
Daniel Neilson f59acc15ad 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

434 lines
16 KiB
LLVM
Raw Blame History

; RUN: llc < %s -mtriple=armv7-apple-ios -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-IOS --check-prefix=CHECK
; RUN: llc < %s -mtriple=thumbv7m-none-macho -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-DARWIN --check-prefix=CHECK
; RUN: llc < %s -mtriple=arm-none-eabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI --check-prefix=CHECK
; RUN: llc < %s -mtriple=arm-none-eabihf -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI --check-prefix=CHECK
; RUN: llc < %s -mtriple=arm-none-androideabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI --check-prefix=CHECK
; RUN: llc < %s -mtriple=arm-none-gnueabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI --check-prefix=CHECK
; RUN: llc < %s -mtriple=arm-none-gnueabihf -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI --check-prefix=CHECK
; RUN: llc < %s -mtriple=arm-none-musleabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI --check-prefix=CHECK
; RUN: llc < %s -mtriple=arm-none-musleabihf -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI --check-prefix=CHECK
define void @f1(i8* %dest, i8* %src) "no-frame-pointer-elim"="true" {
entry:
; CHECK-LABEL: f1
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: bl __aeabi_memmove
; CHECK-GNUEABI: bl memmove
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i1 false)
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy
; CHECK-GNUEABI: bl memcpy
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i1 false)
; EABI memset swaps arguments
; CHECK-IOS: mov r1, #1
; CHECK-IOS: bl _memset
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: bl _memset
; CHECK-EABI: mov r2, #1
; CHECK-EABI: bl __aeabi_memset
; CHECK-GNUEABI: mov r1, #1
; CHECK-GNUEABI: bl memset
call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i1 false)
; EABI uses memclr if value set to 0
; CHECK-IOS: mov r1, #0
; CHECK-IOS: bl _memset
; CHECK-DARWIN: movs r1, #0
; CHECK-DARWIN: bl _memset
; CHECK-EABI: bl __aeabi_memclr
; CHECK-GNUEABI: bl memset
call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i1 false)
; EABI uses aligned function variants if possible
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: bl __aeabi_memmove4
; CHECK-GNUEABI: bl memmove
call void @llvm.memmove.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 500, i1 false)
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy4
; CHECK-GNUEABI: bl memcpy
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 500, i1 false)
; CHECK-IOS: bl _memset
; CHECK-DARWIN: bl _memset
; CHECK-EABI: bl __aeabi_memset4
; CHECK-GNUEABI: bl memset
call void @llvm.memset.p0i8.i32(i8* align 4 %dest, i8 1, i32 500, i1 false)
; CHECK-IOS: bl _memset
; CHECK-DARWIN: bl _memset
; CHECK-EABI: bl __aeabi_memclr4
; CHECK-GNUEABI: bl memset
call void @llvm.memset.p0i8.i32(i8* align 4 %dest, i8 0, i32 500, i1 false)
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: bl __aeabi_memmove8
; CHECK-GNUEABI: bl memmove
call void @llvm.memmove.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false)
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy8
; CHECK-GNUEABI: bl memcpy
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false)
; CHECK-IOS: bl _memset
; CHECK-DARWIN: bl _memset
; CHECK-EABI: bl __aeabi_memset8
; CHECK-GNUEABI: bl memset
call void @llvm.memset.p0i8.i32(i8* align 8 %dest, i8 1, i32 500, i1 false)
; CHECK-IOS: bl _memset
; CHECK-DARWIN: bl _memset
; CHECK-EABI: bl __aeabi_memclr8
; CHECK-GNUEABI: bl memset
call void @llvm.memset.p0i8.i32(i8* align 8 %dest, i8 0, i32 500, i1 false)
unreachable
}
; Check that alloca arguments to memory intrinsics are automatically aligned if at least 8 bytes in size
define void @f2(i8* %dest, i32 %n) "no-frame-pointer-elim"="true" {
entry:
; CHECK-LABEL: f2
; IOS (ARMv7) should 8-byte align, others should 4-byte align
; CHECK-IOS: add r1, sp, #32
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: add r1, sp, #28
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: {{add r1, sp, #28|sub r1, r(7|11), #20}}
; CHECK-EABI: bl __aeabi_memmove
; CHECK-GNUEABI: {{add r1, sp, #28|sub r1, r(7|11), #20}}
; CHECK-GNUEABI: bl memmove
%arr0 = alloca [9 x i8], align 1
%0 = bitcast [9 x i8]* %arr0 to i8*
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
; CHECK: add r1, sp, #16
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy
; CHECK-GNUEABI: bl memcpy
%arr1 = alloca [9 x i8], align 1
%1 = bitcast [9 x i8]* %arr1 to i8*
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
; CHECK-IOS: mov r0, sp
; CHECK-IOS: mov r1, #1
; CHECK-IOS: bl _memset
; CHECK-DARWIN: add r0, sp, #4
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: bl _memset
; CHECK-EABI: add r0, sp, #4
; CHECK-EABI: mov r2, #1
; CHECK-EABI: bl __aeabi_memset
; CHECK-GNUEABI: add r0, sp, #4
; CHECK-GNUEABI: mov r1, #1
; CHECK-GNUEABI: bl memset
%arr2 = alloca [9 x i8], align 1
%2 = bitcast [9 x i8]* %arr2 to i8*
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
unreachable
}
; Check that alloca arguments are not aligned if less than 8 bytes in size
define void @f3(i8* %dest, i32 %n) "no-frame-pointer-elim"="true" {
entry:
; CHECK-LABEL: f3
; CHECK: {{add(.w)? r1, sp, #17|sub(.w)? r1, r(7|11), #15}}
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: bl __aeabi_memmove
; CHECK-GNUEABI: bl memmove
%arr0 = alloca [7 x i8], align 1
%0 = bitcast [7 x i8]* %arr0 to i8*
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
; CHECK: {{add(.w)? r1, sp, #10|sub(.w)? r1, r(7|11), #22}}
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy
; CHECK-GNUEABI: bl memcpy
%arr1 = alloca [7 x i8], align 1
%1 = bitcast [7 x i8]* %arr1 to i8*
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
; CHECK: {{add(.w)? r0, sp, #3|sub(.w)? r0, r(7|11), #29}}
; CHECK-IOS: mov r1, #1
; CHECK-IOS: bl _memset
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: bl _memset
; CHECK-EABI: mov r2, #1
; CHECK-EABI: bl __aeabi_memset
; CHECK-GNUEABI: mov r1, #1
; CHECK-GNUEABI: bl memset
%arr2 = alloca [7 x i8], align 1
%2 = bitcast [7 x i8]* %arr2 to i8*
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
unreachable
}
; Check that alloca arguments are not aligned if size+offset is less than 8 bytes
define void @f4(i8* %dest, i32 %n) "no-frame-pointer-elim"="true" {
entry:
; CHECK-LABEL: f4
; CHECK: {{add(.w)? r., sp, #23|sub(.w)? r., r(7|11), #17}}
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: bl __aeabi_memmove
; CHECK-GNUEABI: bl memmove
%arr0 = alloca [9 x i8], align 1
%0 = getelementptr inbounds [9 x i8], [9 x i8]* %arr0, i32 0, i32 4
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w) r., r(7|11), #26}}
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy
; CHECK-GNUEABI: bl memcpy
%arr1 = alloca [9 x i8], align 1
%1 = getelementptr inbounds [9 x i8], [9 x i8]* %arr1, i32 0, i32 4
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w) r., r(7|11), #35}}
; CHECK-IOS: mov r1, #1
; CHECK-IOS: bl _memset
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: bl _memset
; CHECK-EABI: mov r2, #1
; CHECK-EABI: bl __aeabi_memset
; CHECK-GNUEABI: mov r1, #1
; CHECK-GNUEABI: bl memset
%arr2 = alloca [9 x i8], align 1
%2 = getelementptr inbounds [9 x i8], [9 x i8]* %arr2, i32 0, i32 4
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
unreachable
}
; Check that alloca arguments are not aligned if the offset is not a multiple of 4
define void @f5(i8* %dest, i32 %n) "no-frame-pointer-elim"="true" {
entry:
; CHECK-LABEL: f5
; CHECK: {{add(.w)? r., sp, #27|sub(.w)? r., r(7|11), #21}}
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: bl __aeabi_memmove
; CHECK-GNUEABI: bl memmove
%arr0 = alloca [13 x i8], align 1
%0 = getelementptr inbounds [13 x i8], [13 x i8]* %arr0, i32 0, i32 1
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w)? r., r(7|11), #34}}
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy
; CHECK-GNUEABI: bl memcpy
%arr1 = alloca [13 x i8], align 1
%1 = getelementptr inbounds [13 x i8], [13 x i8]* %arr1, i32 0, i32 1
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w)? r., r(7|11), #47}}
; CHECK-IOS: mov r1, #1
; CHECK-IOS: bl _memset
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: bl _memset
; CHECK-EABI: mov r2, #1
; CHECK-EABI: bl __aeabi_memset
; CHECK-GNUEABI: mov r1, #1
; CHECK-GNUEABI: bl memset
%arr2 = alloca [13 x i8], align 1
%2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 1
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
unreachable
}
; Check that alloca arguments are not aligned if the offset is unknown
define void @f6(i8* %dest, i32 %n, i32 %i) "no-frame-pointer-elim"="true" {
entry:
; CHECK-LABEL: f6
; CHECK: {{add(.w)? r., sp, #27|sub(.w)? r., r(7|11), #(25|29)}}
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: bl __aeabi_memmove
; CHECK-GNUEABI: bl memmove
%arr0 = alloca [13 x i8], align 1
%0 = getelementptr inbounds [13 x i8], [13 x i8]* %arr0, i32 0, i32 %i
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w)? r., r(7|11), #42}}
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy
; CHECK-GNUEABI: bl memcpy
%arr1 = alloca [13 x i8], align 1
%1 = getelementptr inbounds [13 x i8], [13 x i8]* %arr1, i32 0, i32 %i
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w)? r., r(7|11), #55}}
; CHECK-IOS: mov r1, #1
; CHECK-IOS: bl _memset
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: bl _memset
; CHECK-EABI: mov r2, #1
; CHECK-EABI: bl __aeabi_memset
; CHECK-GNUEABI: mov r1, #1
; CHECK-GNUEABI: bl memset
%arr2 = alloca [13 x i8], align 1
%2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 %i
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
unreachable
}
; Check that alloca arguments are not aligned if the GEP is not inbounds
define void @f7(i8* %dest, i32 %n) "no-frame-pointer-elim"="true" {
entry:
; CHECK-LABEL: f7
; CHECK: {{add(.w)? r., sp, #27|sub(.w)? r., r(7|11), #21}}
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: bl __aeabi_memmove
; CHECK-GNUEABI: bl memmove
%arr0 = alloca [13 x i8], align 1
%0 = getelementptr [13 x i8], [13 x i8]* %arr0, i32 0, i32 4
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w)? r., r(7|11), #34}}
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy
; CHECK-GNUEABI: bl memcpy
%arr1 = alloca [13 x i8], align 1
%1 = getelementptr [13 x i8], [13 x i8]* %arr1, i32 0, i32 4
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w)? r., r(7|11), #47}}
; CHECK-IOS: mov r1, #1
; CHECK-IOS: bl _memset
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: bl _memset
; CHECK-EABI: mov r2, #1
; CHECK-EABI: bl __aeabi_memset
; CHECK-GNUEABI: mov r1, #1
; CHECK-GNUEABI: bl memset
%arr2 = alloca [13 x i8], align 1
%2 = getelementptr [13 x i8], [13 x i8]* %arr2, i32 0, i32 4
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
unreachable
}
; Check that alloca arguments are not aligned when the offset is past the end of the allocation
define void @f8(i8* %dest, i32 %n) "no-frame-pointer-elim"="true" {
entry:
; CHECK-LABEL: f8
; CHECK: {{add(.w)? r., sp, #27|sub(.w)? r., r(7|11), #21}}
; CHECK-IOS: bl _memmove
; CHECK-DARWIN: bl _memmove
; CHECK-EABI: bl __aeabi_memmove
; CHECK-GNUEABI: bl memmove
%arr0 = alloca [13 x i8], align 1
%0 = getelementptr inbounds [13 x i8], [13 x i8]* %arr0, i32 0, i32 16
call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w)? r., r(7|11), #34}}
; CHECK-IOS: bl _memcpy
; CHECK-DARWIN: bl _memcpy
; CHECK-EABI: bl __aeabi_memcpy
; CHECK-GNUEABI: bl memcpy
%arr1 = alloca [13 x i8], align 1
%1 = getelementptr inbounds [13 x i8], [13 x i8]* %arr1, i32 0, i32 16
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w)? r., r(7|11), #47}}
; CHECK-IOS: mov r1, #1
; CHECK-IOS: bl _memset
; CHECK-DARWIN: movs r1, #1
; CHECK-DARWIN: bl _memset
; CHECK-EABI: mov r2, #1
; CHECK-EABI: bl __aeabi_memset
; CHECK-GNUEABI: mov r1, #1
; CHECK-GNUEABI: bl memset
%arr2 = alloca [13 x i8], align 1
%2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 16
call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
unreachable
}
; Check that global variables are aligned if they are large enough, but only if
; they are defined in this object and don't have an explicit section.
@arr1 = global [7 x i8] c"\01\02\03\04\05\06\07", align 1
@arr2 = global [8 x i8] c"\01\02\03\04\05\06\07\08", align 1
@arr3 = global [7 x i8] c"\01\02\03\04\05\06\07", section "foo,bar", align 1
@arr4 = global [8 x i8] c"\01\02\03\04\05\06\07\08", section "foo,bar", align 1
@arr5 = weak global [7 x i8] c"\01\02\03\04\05\06\07", align 1
@arr6 = weak_odr global [7 x i8] c"\01\02\03\04\05\06\07", align 1
@arr7 = external global [7 x i8], align 1
@arr8 = internal global [128 x i8] undef
@arr9 = weak_odr global [128 x i8] undef
define void @f9(i8* %dest, i32 %n) "no-frame-pointer-elim"="true" {
entry:
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr1, i32 0, i32 0), i32 %n, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([8 x i8], [8 x i8]* @arr2, i32 0, i32 0), i32 %n, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr3, i32 0, i32 0), i32 %n, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([8 x i8], [8 x i8]* @arr4, i32 0, i32 0), i32 %n, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr5, i32 0, i32 0), i32 %n, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr6, i32 0, i32 0), i32 %n, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr7, i32 0, i32 0), i32 %n, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([128 x i8], [128 x i8]* @arr8, i32 0, i32 0), i32 %n, i1 false)
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([128 x i8], [128 x i8]* @arr9, i32 0, i32 0), i32 %n, i1 false)
unreachable
}
; CHECK: {{\.data|\.section.+data}}
; CHECK-NOT: .p2align
; CHECK: arr1:
; CHECK-IOS: .p2align 3
; CHECK-DARWIN: .p2align 2
; CHECK-EABI-NOT: .p2align
; CHECK-GNUEABI-NOT: .p2align
; CHECK: arr2:
; CHECK: {{\.section.+foo,bar}}
; CHECK-NOT: .p2align
; CHECK: arr3:
; CHECK-NOT: .p2align
; CHECK: arr4:
; CHECK: {{\.data|\.section.+data}}
; CHECK-NOT: .p2align
; CHECK: arr5:
; CHECK-NOT: .p2align
; CHECK: arr6:
; CHECK: .p2align 4
; CHECK: arr8:
; CHECK: .p2align 4
; CHECK: arr9:
; CHECK-NOT: arr7:
declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
Reference in New Issue View Git Blame Copy Permalink