RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 03:02:36 +01:00
Code Issues Projects Releases Wiki Activity
3f01fba31d
llvm-mirror/test/Analysis/BasicAA/modref.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

234 lines
5.8 KiB
LLVM
Raw Blame History

; RUN: opt < %s -basicaa -gvn -dse -S | FileCheck %s
target datalayout = "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"
declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture)
declare void @external(i32*)
define i32 @test0(i8* %P) {
%A = alloca i32
call void @external(i32* %A)
store i32 0, i32* %A
call void @llvm.memset.p0i8.i32(i8* %P, i8 0, i32 42, i1 false)
%B = load i32, i32* %A
ret i32 %B
; CHECK-LABEL: @test0
; CHECK: ret i32 0
}
define i8 @test1() {
; CHECK-LABEL: @test1
%A = alloca i8
%B = alloca i8
store i8 2, i8* %B ;; Not written to by memcpy
call void @llvm.memcpy.p0i8.p0i8.i8(i8* %A, i8* %B, i8 -1, i1 false)
%C = load i8, i8* %B
ret i8 %C
; CHECK: ret i8 2
}
define i8 @test2(i8* %P) {
; CHECK-LABEL: @test2
%P2 = getelementptr i8, i8* %P, i32 127
store i8 1, i8* %P2 ;; Not dead across memset
call void @llvm.memset.p0i8.i8(i8* %P, i8 2, i8 127, i1 false)
%A = load i8, i8* %P2
ret i8 %A
; CHECK: ret i8 1
}
define i8 @test2a(i8* %P) {
; CHECK-LABEL: @test2
%P2 = getelementptr i8, i8* %P, i32 126
;; FIXME: DSE isn't zapping this dead store.
store i8 1, i8* %P2 ;; Dead, clobbered by memset.
call void @llvm.memset.p0i8.i8(i8* %P, i8 2, i8 127, i1 false)
%A = load i8, i8* %P2
ret i8 %A
; CHECK-NOT: load
; CHECK: ret i8 2
}
define void @test3(i8* %P, i8 %X) {
; CHECK-LABEL: @test3
; CHECK-NOT: store
; CHECK-NOT: %Y
%Y = add i8 %X, 1 ;; Dead, because the only use (the store) is dead.
%P2 = getelementptr i8, i8* %P, i32 2
store i8 %Y, i8* %P2 ;; Not read by lifetime.end, should be removed.
; CHECK: store i8 2, i8* %P2
call void @llvm.lifetime.end.p0i8(i64 1, i8* %P)
store i8 2, i8* %P2
; CHECK-NOT: store
ret void
; CHECK: ret void
}
define void @test3a(i8* %P, i8 %X) {
; CHECK-LABEL: @test3a
%Y = add i8 %X, 1 ;; Dead, because the only use (the store) is dead.
%P2 = getelementptr i8, i8* %P, i32 2
store i8 %Y, i8* %P2
; CHECK-NEXT: call void @llvm.lifetime.end
call void @llvm.lifetime.end.p0i8(i64 10, i8* %P)
ret void
; CHECK-NEXT: ret void
}
@G1 = external global i32
@G2 = external global [4000 x i32]
define i32 @test4(i8* %P) {
%tmp = load i32, i32* @G1
call void @llvm.memset.p0i8.i32(i8* bitcast ([4000 x i32]* @G2 to i8*), i8 0, i32 4000, i1 false)
%tmp2 = load i32, i32* @G1
%sub = sub i32 %tmp2, %tmp
ret i32 %sub
; CHECK-LABEL: @test4
; CHECK-NOT: load
; CHECK: memset.p0i8.i32
; CHECK-NOT: load
; CHECK: ret i32 0
}
; Verify that basicaa is handling variable length memcpy, knowing it doesn't
; write to G1.
define i32 @test5(i8* %P, i32 %Len) {
%tmp = load i32, i32* @G1
call void @llvm.memcpy.p0i8.p0i8.i32(i8* bitcast ([4000 x i32]* @G2 to i8*), i8* bitcast (i32* @G1 to i8*), i32 %Len, i1 false)
%tmp2 = load i32, i32* @G1
%sub = sub i32 %tmp2, %tmp
ret i32 %sub
; CHECK: @test5
; CHECK-NOT: load
; CHECK: memcpy.p0i8.p0i8.i32
; CHECK-NOT: load
; CHECK: ret i32 0
}
define i8 @test6(i8* %p, i8* noalias %a) {
%x = load i8, i8* %a
%t = va_arg i8* %p, float
%y = load i8, i8* %a
%z = add i8 %x, %y
ret i8 %z
; CHECK-LABEL: @test6
; CHECK: load i8, i8* %a
; CHECK-NOT: load
; CHECK: ret
}
; PR10628
declare void @test7decl(i32* nocapture %x)
define i32 @test7() nounwind uwtable ssp {
entry:
%x = alloca i32, align 4
store i32 0, i32* %x, align 4
%add.ptr = getelementptr inbounds i32, i32* %x, i64 1
call void @test7decl(i32* %add.ptr)
%tmp = load i32, i32* %x, align 4
ret i32 %tmp
; CHECK-LABEL: @test7(
; CHECK: store i32 0
; CHECK: call void @test7decl
; CHECK: load i32, i32*
}
;; Check that aa correctly handles functions marked with argmemonly
;; attribute.
declare i32 @func_argmemonly(i32 * %P) argmemonly
;; Can not remove redundant load, function may write to it.
; CHECK-LABEL: @test8(
define i32 @test8(i32 *%P) {
%V1 = load i32, i32* %P
call i32 @func_argmemonly(i32* %P)
%V2 = load i32, i32* %P
%Diff = sub i32 %V1, %V2
ret i32 %Diff
; CHECK: load
; CHECK: load
; CHECK: sub
; CHECK: ret i32 %Diff
}
;; In this case load can be removed, function clobbers only %P2.
; CHECK-LABEL: @test9(
define i32 @test9(i32* %P, i32* noalias %P2) {
%V1 = load i32, i32* %P
call i32 @func_argmemonly(i32* %P2)
%V2 = load i32, i32* %P
%Diff = sub i32 %V1, %V2
ret i32 %Diff
; CHECK-NOT: load
; CHECK: ret i32 0
}
;; In this case load can *not* be removed. Function clobers only %P2 but it may
;; alias with %P.
; CHECK-LABEL: @test10(
define i32 @test10(i32* %P, i32* %P2) {
%V1 = load i32, i32* %P
call i32 @func_argmemonly(i32* %P2)
%V2 = load i32, i32* %P
%Diff = sub i32 %V1, %V2
ret i32 %Diff
; CHECK: load
; CHECK: load
; CHECK: sub
; CHECK: ret i32 %Diff
}
; CHECK-LABEL: @test11(
define i32 @test11(i32* %P, i32* %P2) {
%V1 = load i32, i32* %P
call i32 @func_argmemonly(i32* readonly %P2)
%V2 = load i32, i32* %P
%Diff = sub i32 %V1, %V2
ret i32 %Diff
; CHECK-NOT: load
; CHECK: ret i32 0
}
declare i32 @func_argmemonly_two_args(i32* %P, i32* %P2) argmemonly
; CHECK-LABEL: @test12(
define i32 @test12(i32* %P, i32* %P2, i32* %P3) {
%V1 = load i32, i32* %P
call i32 @func_argmemonly_two_args(i32* readonly %P2, i32* %P3)
%V2 = load i32, i32* %P
%Diff = sub i32 %V1, %V2
ret i32 %Diff
; CHECK: load
; CHECK: load
; CHECK: sub
; CHECK: ret i32 %Diff
}
; CHECK-LABEL: @test13(
define i32 @test13(i32* %P, i32* %P2) {
%V1 = load i32, i32* %P
call i32 @func_argmemonly(i32* readnone %P2)
%V2 = load i32, i32* %P
%Diff = sub i32 %V1, %V2
ret i32 %Diff
; CHECK-NOT: load
; CHECK: ret i32 0
}
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i1) nounwind
declare void @llvm.memcpy.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i1) nounwind
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
Reference in New Issue View Git Blame Copy Permalink