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
132 lines
5.7 KiB
LLVM
132 lines
5.7 KiB
LLVM
; RUN: opt < %s -sroa -S | FileCheck %s
|
|
target datalayout = "e-p:64:64:64-p1:16:16:16-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64"
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1)
|
|
declare void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* nocapture, i8* nocapture readonly, i32, i1)
|
|
declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture readonly, i32, i1)
|
|
declare void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i1)
|
|
|
|
|
|
; Make sure an illegal bitcast isn't introduced
|
|
define void @test_address_space_1_1(<2 x i64> addrspace(1)* %a, i16 addrspace(1)* %b) {
|
|
; CHECK-LABEL: @test_address_space_1_1(
|
|
; CHECK: load <2 x i64>, <2 x i64> addrspace(1)* %a, align 2
|
|
; CHECK: store <2 x i64> {{.*}}, <2 x i64> addrspace(1)* {{.*}}, align 2
|
|
; CHECK: ret void
|
|
%aa = alloca <2 x i64>, align 16
|
|
%aptr = bitcast <2 x i64> addrspace(1)* %a to i8 addrspace(1)*
|
|
%aaptr = bitcast <2 x i64>* %aa to i8*
|
|
call void @llvm.memcpy.p0i8.p1i8.i32(i8* align 2 %aaptr, i8 addrspace(1)* align 2 %aptr, i32 16, i1 false)
|
|
%bptr = bitcast i16 addrspace(1)* %b to i8 addrspace(1)*
|
|
call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false)
|
|
ret void
|
|
}
|
|
|
|
define void @test_address_space_1_0(<2 x i64> addrspace(1)* %a, i16* %b) {
|
|
; CHECK-LABEL: @test_address_space_1_0(
|
|
; CHECK: load <2 x i64>, <2 x i64> addrspace(1)* %a, align 2
|
|
; CHECK: store <2 x i64> {{.*}}, <2 x i64>* {{.*}}, align 2
|
|
; CHECK: ret void
|
|
%aa = alloca <2 x i64>, align 16
|
|
%aptr = bitcast <2 x i64> addrspace(1)* %a to i8 addrspace(1)*
|
|
%aaptr = bitcast <2 x i64>* %aa to i8*
|
|
call void @llvm.memcpy.p0i8.p1i8.i32(i8* align 2 %aaptr, i8 addrspace(1)* align 2 %aptr, i32 16, i1 false)
|
|
%bptr = bitcast i16* %b to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false)
|
|
ret void
|
|
}
|
|
|
|
define void @test_address_space_0_1(<2 x i64>* %a, i16 addrspace(1)* %b) {
|
|
; CHECK-LABEL: @test_address_space_0_1(
|
|
; CHECK: load <2 x i64>, <2 x i64>* %a, align 2
|
|
; CHECK: store <2 x i64> {{.*}}, <2 x i64> addrspace(1)* {{.*}}, align 2
|
|
; CHECK: ret void
|
|
%aa = alloca <2 x i64>, align 16
|
|
%aptr = bitcast <2 x i64>* %a to i8*
|
|
%aaptr = bitcast <2 x i64>* %aa to i8*
|
|
call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %aaptr, i8* align 2 %aptr, i32 16, i1 false)
|
|
%bptr = bitcast i16 addrspace(1)* %b to i8 addrspace(1)*
|
|
call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false)
|
|
ret void
|
|
}
|
|
|
|
%struct.struct_test_27.0.13 = type { i32, float, i64, i8, [4 x i32] }
|
|
|
|
; Function Attrs: nounwind
|
|
define void @copy_struct([5 x i64] %in.coerce) {
|
|
; CHECK-LABEL: @copy_struct(
|
|
; CHECK-NOT: memcpy
|
|
for.end:
|
|
%in = alloca %struct.struct_test_27.0.13, align 8
|
|
%0 = bitcast %struct.struct_test_27.0.13* %in to [5 x i64]*
|
|
store [5 x i64] %in.coerce, [5 x i64]* %0, align 8
|
|
%scevgep9 = getelementptr %struct.struct_test_27.0.13, %struct.struct_test_27.0.13* %in, i32 0, i32 4, i32 0
|
|
%scevgep910 = bitcast i32* %scevgep9 to i8*
|
|
call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 4 undef, i8* align 4 %scevgep910, i32 16, i1 false)
|
|
ret void
|
|
}
|
|
|
|
%union.anon = type { i32* }
|
|
|
|
@g = common global i32 0, align 4
|
|
@l = common addrspace(3) global i32 0, align 4
|
|
|
|
; Make sure an illegal bitcast isn't introduced
|
|
define void @pr27557() {
|
|
; CHECK-LABEL: @pr27557(
|
|
; CHECK: %[[CAST:.*]] = bitcast i32** {{.*}} to i32 addrspace(3)**
|
|
; CHECK: store i32 addrspace(3)* @l, i32 addrspace(3)** %[[CAST]]
|
|
%1 = alloca %union.anon, align 8
|
|
%2 = bitcast %union.anon* %1 to i32**
|
|
store i32* @g, i32** %2, align 8
|
|
%3 = bitcast %union.anon* %1 to i32 addrspace(3)**
|
|
store i32 addrspace(3)* @l, i32 addrspace(3)** %3, align 8
|
|
ret void
|
|
}
|
|
|
|
; Make sure pre-splitting doesn't try to introduce an illegal bitcast
|
|
define float @presplit(i64 addrspace(1)* %p) {
|
|
entry:
|
|
; CHECK-LABEL: @presplit(
|
|
; CHECK: %[[CAST:.*]] = bitcast i64 addrspace(1)* {{.*}} to i32 addrspace(1)*
|
|
; CHECK: load i32, i32 addrspace(1)* %[[CAST]]
|
|
%b = alloca i64
|
|
%b.cast = bitcast i64* %b to [2 x float]*
|
|
%b.gep1 = getelementptr [2 x float], [2 x float]* %b.cast, i32 0, i32 0
|
|
%b.gep2 = getelementptr [2 x float], [2 x float]* %b.cast, i32 0, i32 1
|
|
%l = load i64, i64 addrspace(1)* %p
|
|
store i64 %l, i64* %b
|
|
%f1 = load float, float* %b.gep1
|
|
%f2 = load float, float* %b.gep2
|
|
%ret = fadd float %f1, %f2
|
|
ret float %ret
|
|
}
|
|
|
|
; Test load from and store to non-zero address space.
|
|
define void @test_load_store_diff_addr_space([2 x float] addrspace(1)* %complex1, [2 x float] addrspace(1)* %complex2) {
|
|
; CHECK-LABEL: @test_load_store_diff_addr_space
|
|
; CHECK-NOT: alloca
|
|
; CHECK: load i32, i32 addrspace(1)*
|
|
; CHECK: load i32, i32 addrspace(1)*
|
|
; CHECK: store i32 %{{.*}}, i32 addrspace(1)*
|
|
; CHECK: store i32 %{{.*}}, i32 addrspace(1)*
|
|
%a = alloca i64
|
|
%a.cast = bitcast i64* %a to [2 x float]*
|
|
%a.gep1 = getelementptr [2 x float], [2 x float]* %a.cast, i32 0, i32 0
|
|
%a.gep2 = getelementptr [2 x float], [2 x float]* %a.cast, i32 0, i32 1
|
|
%complex1.gep = getelementptr [2 x float], [2 x float] addrspace(1)* %complex1, i32 0, i32 0
|
|
%p1 = bitcast float addrspace(1)* %complex1.gep to i64 addrspace(1)*
|
|
%v1 = load i64, i64 addrspace(1)* %p1
|
|
store i64 %v1, i64* %a
|
|
%f1 = load float, float* %a.gep1
|
|
%f2 = load float, float* %a.gep2
|
|
%sum = fadd float %f1, %f2
|
|
store float %sum, float* %a.gep1
|
|
store float %sum, float* %a.gep2
|
|
%v2 = load i64, i64* %a
|
|
%complex2.gep = getelementptr [2 x float], [2 x float] addrspace(1)* %complex2, i32 0, i32 0
|
|
%p2 = bitcast float addrspace(1)* %complex2.gep to i64 addrspace(1)*
|
|
store i64 %v2, i64 addrspace(1)* %p2
|
|
ret void
|
|
}
|