1e68724d24
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
113 lines
4.9 KiB
LLVM
113 lines
4.9 KiB
LLVM
; RUN: opt < %s -basicaa -dse -S | FileCheck %s
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
%struct.vec2 = type { <4 x i32>, <4 x i32> }
|
|
%struct.vec2plusi = type { <4 x i32>, <4 x i32>, i32 }
|
|
|
|
@glob1 = global %struct.vec2 zeroinitializer, align 16
|
|
@glob2 = global %struct.vec2plusi zeroinitializer, align 16
|
|
|
|
define void @write24to28(i32* nocapture %p) nounwind uwtable ssp {
|
|
; CHECK-LABEL: @write24to28(
|
|
entry:
|
|
%arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1
|
|
%p3 = bitcast i32* %arrayidx0 to i8*
|
|
; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 24, i1 false)
|
|
call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false)
|
|
%arrayidx1 = getelementptr inbounds i32, i32* %p, i64 7
|
|
store i32 1, i32* %arrayidx1, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @write28to32(i32* nocapture %p) nounwind uwtable ssp {
|
|
; CHECK-LABEL: @write28to32(
|
|
entry:
|
|
%p3 = bitcast i32* %p to i8*
|
|
; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false)
|
|
call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
|
|
%arrayidx1 = getelementptr inbounds i32, i32* %p, i64 7
|
|
store i32 1, i32* %arrayidx1, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @dontwrite28to32memset(i32* nocapture %p) nounwind uwtable ssp {
|
|
; CHECK-LABEL: @dontwrite28to32memset(
|
|
entry:
|
|
%p3 = bitcast i32* %p to i8*
|
|
; CHECK: call void @llvm.memset.p0i8.i64(i8* align 16 %p3, i8 0, i64 32, i1 false)
|
|
call void @llvm.memset.p0i8.i64(i8* align 16 %p3, i8 0, i64 32, i1 false)
|
|
%arrayidx1 = getelementptr inbounds i32, i32* %p, i64 7
|
|
store i32 1, i32* %arrayidx1, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @write32to36(%struct.vec2plusi* nocapture %p) nounwind uwtable ssp {
|
|
; CHECK-LABEL: @write32to36(
|
|
entry:
|
|
%0 = bitcast %struct.vec2plusi* %p to i8*
|
|
; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2plusi* @glob2 to i8*), i64 32, i1 false)
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2plusi* @glob2 to i8*), i64 36, i1 false)
|
|
%c = getelementptr inbounds %struct.vec2plusi, %struct.vec2plusi* %p, i64 0, i32 2
|
|
store i32 1, i32* %c, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @write16to32(%struct.vec2* nocapture %p) nounwind uwtable ssp {
|
|
; CHECK-LABEL: @write16to32(
|
|
entry:
|
|
%0 = bitcast %struct.vec2* %p to i8*
|
|
; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 16, i1 false)
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false)
|
|
%c = getelementptr inbounds %struct.vec2, %struct.vec2* %p, i64 0, i32 1
|
|
store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32>* %c, align 4
|
|
ret void
|
|
}
|
|
|
|
define void @dontwrite28to32memcpy(%struct.vec2* nocapture %p) nounwind uwtable ssp {
|
|
; CHECK-LABEL: @dontwrite28to32memcpy(
|
|
entry:
|
|
%0 = bitcast %struct.vec2* %p to i8*
|
|
; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false)
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false)
|
|
%arrayidx1 = getelementptr inbounds %struct.vec2, %struct.vec2* %p, i64 0, i32 0, i64 7
|
|
store i32 1, i32* %arrayidx1, align 4
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
|
|
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
|
|
|
|
%struct.trapframe = type { i64, i64, i64 }
|
|
|
|
; bugzilla 11455 - make sure negative GEP's don't break this optimisation
|
|
; CHECK-LABEL: @cpu_lwp_fork(
|
|
define void @cpu_lwp_fork(%struct.trapframe* %md_regs, i64 %pcb_rsp0) nounwind uwtable noinline ssp {
|
|
entry:
|
|
%0 = inttoptr i64 %pcb_rsp0 to %struct.trapframe*
|
|
%add.ptr = getelementptr inbounds %struct.trapframe, %struct.trapframe* %0, i64 -1
|
|
%1 = bitcast %struct.trapframe* %add.ptr to i8*
|
|
%2 = bitcast %struct.trapframe* %md_regs to i8*
|
|
; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 24, i1 false)
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 24, i1 false)
|
|
%tf_trapno = getelementptr inbounds %struct.trapframe, %struct.trapframe* %0, i64 -1, i32 1
|
|
store i64 3, i64* %tf_trapno, align 8
|
|
ret void
|
|
}
|
|
|
|
define void @write16To23AndThen24To31(i64* nocapture %P, i64 %n64, i32 %n32, i16 %n16, i8 %n8) {
|
|
entry:
|
|
; CHECK-LABEL: @write16To23AndThen24To31(
|
|
; CHECK: tail call void @llvm.memset.p0i8.i64(i8* align 8 %mybase0, i8 0, i64 16, i1 false)
|
|
|
|
%base0 = bitcast i64* %P to i8*
|
|
%mybase0 = getelementptr inbounds i8, i8* %base0, i64 0
|
|
tail call void @llvm.memset.p0i8.i64(i8* align 8 %mybase0, i8 0, i64 32, i1 false)
|
|
|
|
%base64_2 = getelementptr inbounds i64, i64* %P, i64 2
|
|
%base64_3 = getelementptr inbounds i64, i64* %P, i64 3
|
|
|
|
store i64 3, i64* %base64_2
|
|
store i64 3, i64* %base64_3
|
|
ret void
|
|
}
|