1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
llvm-mirror/test/Transforms/InstCombine/alloca.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

180 lines
5.3 KiB
LLVM

; RUN: opt < %s -instcombine -S -data-layout="E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128" | FileCheck %s -check-prefix=CHECK -check-prefix=ALL
; RUN: opt < %s -instcombine -S -data-layout="E-p:32:32:32-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128" | FileCheck %s -check-prefix=P32 -check-prefix=ALL
; RUN: opt < %s -instcombine -S | FileCheck %s -check-prefix=NODL -check-prefix=ALL
declare void @use(...)
@int = global i32 zeroinitializer
; Zero byte allocas should be merged if they can't be deleted.
; CHECK-LABEL: @test(
; CHECK: alloca
; CHECK-NOT: alloca
define void @test() {
%X = alloca [0 x i32] ; <[0 x i32]*> [#uses=1]
call void (...) @use( [0 x i32]* %X )
%Y = alloca i32, i32 0 ; <i32*> [#uses=1]
call void (...) @use( i32* %Y )
%Z = alloca { } ; <{ }*> [#uses=1]
call void (...) @use( { }* %Z )
%size = load i32, i32* @int
%A = alloca {{}}, i32 %size
call void (...) @use( {{}}* %A )
ret void
}
; Zero byte allocas should be deleted.
; CHECK-LABEL: @test2(
; CHECK-NOT: alloca
define void @test2() {
%A = alloca i32 ; <i32*> [#uses=1]
store i32 123, i32* %A
ret void
}
; Zero byte allocas should be deleted.
; CHECK-LABEL: @test3(
; CHECK-NOT: alloca
define void @test3() {
%A = alloca { i32 } ; <{ i32 }*> [#uses=1]
%B = getelementptr { i32 }, { i32 }* %A, i32 0, i32 0 ; <i32*> [#uses=1]
store i32 123, i32* %B
ret void
}
; CHECK-LABEL: @test4(
; CHECK: = zext i32 %n to i64
; CHECK: %A = alloca i32, i64 %
define i32* @test4(i32 %n) {
%A = alloca i32, i32 %n
ret i32* %A
}
; Allocas which are only used by GEPs, bitcasts, addrspacecasts, and stores
; (transitively) should be deleted.
define void @test5() {
; CHECK-LABEL: @test5(
; CHECK-NOT: alloca
; CHECK-NOT: store
; CHECK: ret
entry:
%a = alloca { i32 }
%b = alloca i32*
%c = alloca i32
%a.1 = getelementptr { i32 }, { i32 }* %a, i32 0, i32 0
store i32 123, i32* %a.1
store i32* %a.1, i32** %b
%b.1 = bitcast i32** %b to i32*
store i32 123, i32* %b.1
%a.2 = getelementptr { i32 }, { i32 }* %a, i32 0, i32 0
store atomic i32 2, i32* %a.2 unordered, align 4
%a.3 = getelementptr { i32 }, { i32 }* %a, i32 0, i32 0
store atomic i32 3, i32* %a.3 release, align 4
%a.4 = getelementptr { i32 }, { i32 }* %a, i32 0, i32 0
store atomic i32 4, i32* %a.4 seq_cst, align 4
%c.1 = addrspacecast i32* %c to i32 addrspace(1)*
store i32 123, i32 addrspace(1)* %c.1
ret void
}
declare void @f(i32* %p)
; Check that we don't delete allocas in some erroneous cases.
define void @test6() {
; CHECK-LABEL: @test6(
; CHECK-NOT: ret
; CHECK: alloca
; CHECK-NEXT: alloca
; CHECK: ret
entry:
%a = alloca { i32 }
%b = alloca i32
%a.1 = getelementptr { i32 }, { i32 }* %a, i32 0, i32 0
store volatile i32 123, i32* %a.1
tail call void @f(i32* %b)
ret void
}
; PR14371
%opaque_type = type opaque
%real_type = type { { i32, i32* } }
@opaque_global = external constant %opaque_type, align 4
define void @test7() {
entry:
%0 = alloca %real_type, align 4
%1 = bitcast %real_type* %0 to i8*
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* bitcast (%opaque_type* @opaque_global to i8*), i32 8, i1 false)
ret void
}
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
; Check that the GEP indices use the pointer size, or 64 if unknown
define void @test8() {
; CHECK-LABEL: @test8(
; CHECK: alloca [100 x i32]
; CHECK: getelementptr inbounds [100 x i32], [100 x i32]* %x1, i64 0, i64 0
; P32-LABEL: @test8(
; P32: alloca [100 x i32]
; P32: getelementptr inbounds [100 x i32], [100 x i32]* %x1, i32 0, i32 0
; NODL-LABEL: @test8(
; NODL: alloca [100 x i32]
; NODL: getelementptr inbounds [100 x i32], [100 x i32]* %x1, i64 0, i64 0
%x = alloca i32, i32 100
call void (...) @use(i32* %x)
ret void
}
; PR19569
%struct_type = type { i32, i32 }
declare void @test9_aux(<{ %struct_type }>* inalloca)
declare i8* @llvm.stacksave()
declare void @llvm.stackrestore(i8*)
define void @test9(%struct_type* %a) {
; CHECK-LABEL: @test9(
entry:
%inalloca.save = call i8* @llvm.stacksave()
%argmem = alloca inalloca <{ %struct_type }>
; CHECK: alloca inalloca i64, align 8
%0 = getelementptr inbounds <{ %struct_type }>, <{ %struct_type }>* %argmem, i32 0, i32 0
%1 = bitcast %struct_type* %0 to i8*
%2 = bitcast %struct_type* %a to i8*
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %1, i8* align 4 %2, i32 8, i1 false)
call void @test9_aux(<{ %struct_type }>* inalloca %argmem)
call void @llvm.stackrestore(i8* %inalloca.save)
ret void
}
define void @test10() {
entry:
; ALL-LABEL: @test10(
; ALL: %v32 = alloca i1, align 8
; ALL: %v64 = alloca i1, align 8
; ALL: %v33 = alloca i1, align 8
%v32 = alloca i1, align 8
%v64 = alloca i1, i64 1, align 8
%v33 = alloca i1, i33 1, align 8
call void (...) @use(i1* %v32, i1* %v64, i1* %v33)
ret void
}
define void @test11() {
entry:
; ALL-LABEL: @test11(
; ALL: %y = alloca i32
; ALL: call void (...) @use(i32* nonnull @int) [ "blah"(i32* %y) ]
; ALL: ret void
%y = alloca i32
call void (...) @use(i32* nonnull @int) [ "blah"(i32* %y) ]
ret void
}