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
95 lines
3.6 KiB
LLVM
95 lines
3.6 KiB
LLVM
; RUN: llc -mtriple=thumbv6m-eabi -verify-machineinstrs %s -o - | \
|
|
; RUN: FileCheck %s --check-prefix=CHECK --check-prefix=CHECKV6
|
|
; RUN: llc -mtriple=thumbv6m-eabi -O=0 -verify-machineinstrs %s -o - | \
|
|
; RUN: FileCheck %s --check-prefix=CHECK --check-prefix=CHECKV6
|
|
; RUN: llc -mtriple=thumbv7a-eabi -mattr=-neon -verify-machineinstrs %s -o - | \
|
|
; RUN: FileCheck %s --check-prefix=CHECK --check-prefix=CHECKV7
|
|
; RUN: llc -mtriple=armv7a-eabi -mattr=-neon -verify-machineinstrs %s -o - | \
|
|
; RUN: FileCheck %s --check-prefix=CHECK --check-prefix=CHECKV7
|
|
|
|
@d = external global [64 x i32]
|
|
@s = external global [64 x i32]
|
|
|
|
; Function Attrs: nounwind
|
|
define void @t1() #0 {
|
|
entry:
|
|
; CHECK-LABEL: t1:
|
|
; CHECKV6: ldr [[LB:r[0-7]]],
|
|
; CHECKV6-NEXT: ldr [[SB:r[0-7]]],
|
|
; We use '[rl0-9]+' to allow 'r0'..'r12', 'lr'
|
|
; CHECKV7: movt [[LB:[rl0-9]+]], :upper16:d
|
|
; CHECKV7-NEXT: movt [[SB:[rl0-9]+]], :upper16:s
|
|
; CHECK-NEXT: ldm{{(\.w)?}} [[LB]]!,
|
|
; CHECK-NEXT: stm{{(\.w)?}} [[SB]]!,
|
|
; Think of the monstrosity '{{\[}}[[LB]]]' as '[ [[LB]] ]' without the spaces.
|
|
; CHECK-NEXT: ldrb{{(\.w)?}} {{.*}}, {{\[}}[[LB]]]
|
|
; CHECK-NEXT: strb{{(\.w)?}} {{.*}}, {{\[}}[[SB]]]
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 bitcast ([64 x i32]* @s to i8*), i8* align 4 bitcast ([64 x i32]* @d to i8*), i32 17, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: nounwind
|
|
define void @t2() #0 {
|
|
entry:
|
|
; CHECK-LABEL: t2:
|
|
; CHECKV6: ldr [[LB:r[0-7]]],
|
|
; CHECKV6-NEXT: ldr [[SB:r[0-7]]],
|
|
; CHECKV7: movt [[LB:[rl0-9]+]], :upper16:d
|
|
; CHECKV7-NEXT: movt [[SB:[rl0-9]+]], :upper16:s
|
|
; CHECK-NEXT: ldm{{(\.w)?}} [[LB]]!,
|
|
; CHECK-NEXT: stm{{(\.w)?}} [[SB]]!,
|
|
; CHECK-NEXT: ldrh{{(\.w)?}} {{.*}}, {{\[}}[[LB]]]
|
|
; CHECK-NEXT: ldrb{{(\.w)?}} {{.*}}, {{\[}}[[LB]], #2]
|
|
; CHECK-NEXT: strb{{(\.w)?}} {{.*}}, {{\[}}[[SB]], #2]
|
|
; CHECK-NEXT: strh{{(\.w)?}} {{.*}}, {{\[}}[[SB]]]
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 bitcast ([64 x i32]* @s to i8*), i8* align 4 bitcast ([64 x i32]* @d to i8*), i32 15, i1 false)
|
|
ret void
|
|
}
|
|
|
|
; PR23768
|
|
%struct.T = type { i8, i64, i8 }
|
|
|
|
@copy = external global %struct.T, align 8
|
|
@etest = external global %struct.T, align 8
|
|
|
|
define void @t3() {
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(
|
|
i8* align 8 getelementptr inbounds (%struct.T, %struct.T* @copy, i32 0, i32 0),
|
|
i8* align 8 getelementptr inbounds (%struct.T, %struct.T* @etest, i32 0, i32 0),
|
|
i32 24, i1 false)
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(
|
|
i8* align 8 getelementptr inbounds (%struct.T, %struct.T* @copy, i32 0, i32 0),
|
|
i8* align 8 getelementptr inbounds (%struct.T, %struct.T* @etest, i32 0, i32 0),
|
|
i32 24, i1 false)
|
|
ret void
|
|
}
|
|
|
|
%struct.S = type { [12 x i32] }
|
|
|
|
; CHECK-LABEL: test3
|
|
define void @test3(%struct.S* %d, %struct.S* %s) #0 {
|
|
%1 = bitcast %struct.S* %d to i8*
|
|
%2 = bitcast %struct.S* %s to i8*
|
|
tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %1, i8* align 4 %2, i32 48, i1 false)
|
|
; 3 ldm/stm pairs in v6; 2 in v7
|
|
; CHECK: ldm{{(\.w)?}} {{[rl0-9]+!?}}, [[REGLIST1:{.*}]]
|
|
; CHECK: stm{{(\.w)?}} {{[rl0-9]+!?}}, [[REGLIST1]]
|
|
; CHECK: ldm{{(\.w)?}} {{[rl0-9]+!?}}, [[REGLIST2:{.*}]]
|
|
; CHECK: stm{{(\.w)?}} {{[rl0-9]+!?}}, [[REGLIST2]]
|
|
; CHECKV6: ldm {{r[0-7]!?}}, [[REGLIST3:{.*}]]
|
|
; CHECKV6: stm {{r[0-7]!?}}, [[REGLIST3]]
|
|
; CHECKV7-NOT: ldm
|
|
; CHECKV7-NOT: stm
|
|
%arrayidx = getelementptr inbounds %struct.S, %struct.S* %s, i32 0, i32 0, i32 1
|
|
tail call void @g(i32* %arrayidx) #3
|
|
ret void
|
|
}
|
|
|
|
declare void @g(i32*)
|
|
|
|
; Set "no-frame-pointer-elim" to increase register pressure
|
|
attributes #0 = { "no-frame-pointer-elim"="true" }
|
|
|
|
; Function Attrs: nounwind
|
|
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) #1
|