RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00
Code Issues Projects Releases Wiki Activity
98e2405ef3
llvm-mirror/test/CodeGen/ARM/constantpool-promote.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

196 lines
8.2 KiB
LLVM
Raw Blame History

; RUN: llc -mtriple armv7--linux-gnueabihf -relocation-model=static -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V7,CHECK-V7ARM
; RUN: llc -mtriple armv7--linux-gnueabihf -relocation-model=pic -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V7,CHECK-V7ARM
; RUN: llc -mtriple armv7--linux-gnueabihf -relocation-model=ropi -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V7,CHECK-V7ARM
; RUN: llc -mtriple armv7--linux-gnueabihf -relocation-model=rwpi -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V7,CHECK-V7ARM
; RUN: llc -mtriple thumbv7--linux-gnueabihf -relocation-model=static -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V7,CHECK-V7THUMB
; RUN: llc -mtriple thumbv7--linux-gnueabihf -relocation-model=pic -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V7,CHECK-V7THUMB
; RUN: llc -mtriple thumbv7--linux-gnueabihf -relocation-model=ropi -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V7,CHECK-V7THUMB
; RUN: llc -mtriple thumbv7--linux-gnueabihf -relocation-model=rwpi -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V7,CHECK-V7THUMB
; RUN: llc -mtriple thumbv6m--linux-gnueabihf -relocation-model=static -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V6M
; RUN: llc -mtriple thumbv6m--linux-gnueabihf -relocation-model=pic -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V6M
; RUN: llc -mtriple thumbv6m--linux-gnueabihf -relocation-model=ropi -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V6M
; RUN: llc -mtriple thumbv6m--linux-gnueabihf -relocation-model=rwpi -arm-promote-constant < %s | FileCheck %s --check-prefixes=CHECK,CHECK-V6M
@.str = private unnamed_addr constant [2 x i8] c"s\00", align 1
@.str1 = private unnamed_addr constant [69 x i8] c"this string is far too long to fit in a literal pool by far and away\00", align 1
@.str2 = private unnamed_addr constant [27 x i8] c"this string is just right!\00", align 1
@.str3 = private unnamed_addr constant [26 x i8] c"this string is used twice\00", align 1
@.str4 = private unnamed_addr constant [29 x i8] c"same string in two functions\00", align 1
@.arr1 = private unnamed_addr constant [2 x i16] [i16 3, i16 4], align 2
@.arr2 = private unnamed_addr constant [2 x i16] [i16 7, i16 8], align 2
@.arr3 = private unnamed_addr constant [2 x i16*] [i16* null, i16* null], align 4
@.ptr = private unnamed_addr constant [2 x i16*] [i16* getelementptr inbounds ([2 x i16], [2 x i16]* @.arr2, i32 0, i32 0), i16* null], align 2
@.arr4 = private unnamed_addr constant [2 x i16] [i16 3, i16 4], align 16
@.zerosize = private unnamed_addr constant [0 x i16] zeroinitializer, align 4
; CHECK-LABEL: @test1
; CHECK: adr r0, [[x:.*]]
; CHECK: [[x]]:
; CHECK: .asciz "s\000\000"
define void @test1() #0 {
tail call void @a(i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str, i32 0, i32 0)) #2
ret void
}
declare void @a(i8*) #1
; CHECK-LABEL: @test2
; CHECK-NOT: .asci
; CHECK: .fnend
define void @test2() #0 {
tail call void @a(i8* getelementptr inbounds ([69 x i8], [69 x i8]* @.str1, i32 0, i32 0)) #2
ret void
}
; CHECK-LABEL: @test3
; CHECK: adr r0, [[x:.*]]
; CHECK: [[x]]:
; CHECK: .asciz "this string is just right!\000"
define void @test3() #0 {
tail call void @a(i8* getelementptr inbounds ([27 x i8], [27 x i8]* @.str2, i32 0, i32 0)) #2
ret void
}
; CHECK-LABEL: @test4
; CHECK: adr r{{.*}}, [[x:.*]]
; CHECK: [[x]]:
; CHECK: .asciz "this string is used twice\000\000"
define void @test4() #0 {
tail call void @a(i8* getelementptr inbounds ([26 x i8], [26 x i8]* @.str3, i32 0, i32 0)) #2
tail call void @a(i8* getelementptr inbounds ([26 x i8], [26 x i8]* @.str3, i32 0, i32 0)) #2
ret void
}
; CHECK-LABEL: @test5a
; CHECK-NOT: adr
define void @test5a() #0 {
tail call void @a(i8* getelementptr inbounds ([29 x i8], [29 x i8]* @.str4, i32 0, i32 0)) #2
ret void
}
define void @test5b() #0 {
tail call void @b(i8* getelementptr inbounds ([29 x i8], [29 x i8]* @.str4, i32 0, i32 0)) #2
ret void
}
; CHECK-LABEL: @test6a
; CHECK: adr r0, [[x:.*]]
; CHECK: [[x]]:
; CHECK: .short 3
; CHECK: .short 4
define void @test6a() #0 {
tail call void @c(i16* getelementptr inbounds ([2 x i16], [2 x i16]* @.arr1, i32 0, i32 0)) #2
ret void
}
; CHECK-LABEL: @test6b
; CHECK: adr r0, [[x:.*]]
; CHECK: [[x]]:
; CHECK: .short 3
; CHECK: .short 4
define void @test6b() #0 {
tail call void @c(i16* getelementptr inbounds ([2 x i16], [2 x i16]* @.arr1, i32 0, i32 0)) #2
ret void
}
; This shouldn't be promoted, as the string is used by another global.
; CHECK-LABEL: @test7
; CHECK-NOT: adr
define void @test7() #0 {
tail call void @c(i16* getelementptr inbounds ([2 x i16], [2 x i16]* @.arr2, i32 0, i32 0)) #2
ret void
}
; This shouldn't be promoted, because the array contains pointers.
; CHECK-LABEL: @test8
; CHECK-NOT: .zero
; CHECK: .fnend
define void @test8() #0 {
%a = load i16*, i16** getelementptr inbounds ([2 x i16*], [2 x i16*]* @.arr3, i32 0, i32 0)
tail call void @c(i16* %a) #2
ret void
}
@fn1.a = private unnamed_addr constant [4 x i16] [i16 4, i16 0, i16 0, i16 0], align 2
@fn2.a = private unnamed_addr constant [8 x i8] [i8 4, i8 0, i8 0, i8 0, i8 23, i8 0, i8 6, i8 0], align 1
; Just check these don't crash.
define void @fn1() "target-features"="+strict-align" {
entry:
%a = alloca [4 x i16], align 2
%0 = bitcast [4 x i16]* %a to i8*
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %0, i8* align 2 bitcast ([4 x i16]* @fn1.a to i8*), i32 8, i1 false)
ret void
}
define void @fn2() "target-features"="+strict-align" {
entry:
%a = alloca [8 x i8], align 2
%0 = bitcast [8 x i8]* %a to i8*
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* bitcast ([8 x i8]* @fn2.a to i8*), i32 16, i1 false)
ret void
}
; This shouldn't be promoted, as the global requires >4 byte alignment.
; CHECK-LABEL: @test9
; CHECK-NOT: adr
define void @test9() #0 {
tail call void @c(i16* getelementptr inbounds ([2 x i16], [2 x i16]* @.arr4, i32 0, i32 0)) #2
ret void
}
; Ensure that zero sized values are supported / not promoted.
; CHECK-LABEL: @pr32130
; CHECK-NOT: adr
define void @pr32130() #0 {
tail call void @c(i16* getelementptr inbounds ([0 x i16], [0 x i16]* @.zerosize, i32 0, i32 0)) #2
ret void
}
; CHECK-LABEL: @test10
; CHECK-V6M: adr r{{[0-9]*}}, [[x:.*]]
; CHECK-V6M: [[x]]:
; CHECK-V6M: .asciz "s\000\000"
; CHECK-V7: ldrb{{(.w)?}} r{{[0-9]*}}, [[x:.*]]
; CHECK-V7: [[x]]:
; CHECK-V7: .asciz "s\000\000"
define void @test10(i8* %a) local_unnamed_addr #0 {
call void @llvm.memmove.p0i8.p0i8.i32(i8* align 1 %a, i8* align 1 getelementptr inbounds ([2 x i8], [2 x i8]* @.str, i32 0, i32 0), i32 1, i1 false)
ret void
}
; CHECK-LABEL: @test11
; CHECK-V6M: adr r{{[0-9]*}}, [[x:.*]]
; CHECK-V6M: [[x]]:
; CHECK-V6M: .short 3
; CHECK-V6M: .short 4
; CHECK-V7THUMB: ldrh{{(.w)?}} r{{[0-9]*}}, [[x:.*]]
; CHECK-V7THUMB: [[x]]:
; CHECK-V7THUMB: .short 3
; CHECK-V7THUMB: .short 4
; CHECK-V7ARM: adr r{{[0-9]*}}, [[x:.*]]
; CHECK-V7ARM: [[x]]:
; CHECK-V7ARM: .short 3
; CHECK-V7ARM: .short 4
define void @test11(i16* %a) local_unnamed_addr #0 {
call void @llvm.memmove.p0i16.p0i16.i32(i16* align 2 %a, i16* align 2 getelementptr inbounds ([2 x i16], [2 x i16]* @.arr1, i32 0, i32 0), i32 2, i1 false)
ret void
}
declare void @b(i8*) #1
declare void @c(i16*) #1
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1)
declare void @llvm.memmove.p0i8.p0i8.i32(i8*, i8*, i32, i1) local_unnamed_addr
declare void @llvm.memmove.p0i16.p0i16.i32(i16*, i16*, i32, i1) local_unnamed_addr
attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { nounwind }
!llvm.module.flags = !{!0, !1}
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 1, !"min_enum_size", i32 4}
Reference in New Issue View Git Blame Copy Permalink