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
diff --git a/llvm/test/Transforms/SROA/address-spaces.ll b/llvm/test/Transforms/SROA/address-spaces.ll
index a54a3af..9cd9137 100644
--- a/llvm/test/Transforms/SROA/address-spaces.ll
+++ b/llvm/test/Transforms/SROA/address-spaces.ll
@@ -1,10 +1,10 @@
; 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, i32, i1)
-declare void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* nocapture, i8* nocapture readonly, i32, i32, i1)
-declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture readonly, i32, i32, i1)
-declare void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i32, i1)
+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
@@ -16,9 +16,9 @@
%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* %aaptr, i8 addrspace(1)* %aptr, i32 16, i32 2, i1 false)
+ 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)* %bptr, i8* %aaptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false)
ret void
}
@@ -30,9 +30,9 @@
%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* %aaptr, i8 addrspace(1)* %aptr, i32 16, i32 2, i1 false)
+ 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* %bptr, i8* %aaptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false)
ret void
}
@@ -44,9 +44,9 @@
%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* %aaptr, i8* %aptr, i32 16, i32 2, i1 false)
+ 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)* %bptr, i8* %aaptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false)
ret void
}
@@ -62,7 +62,7 @@
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)* undef, i8* %scevgep910, i32 16, i32 4, i1 false)
+ call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 4 undef, i8* align 4 %scevgep910, i32 16, i1 false)
ret void
}
diff --git a/llvm/test/Transforms/SROA/alignment.ll b/llvm/test/Transforms/SROA/alignment.ll
index 455d142..dd06613 100644
--- a/llvm/test/Transforms/SROA/alignment.ll
+++ b/llvm/test/Transforms/SROA/alignment.ll
@@ -1,7 +1,7 @@
; RUN: opt < %s -sroa -S | FileCheck %s
target datalayout = "e-p:64:64:64-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*, i8*, i32, i32, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i1)
define void @test1({ i8, i8 }* %a, { i8, i8 }* %b) {
; CHECK-LABEL: @test1(
@@ -23,8 +23,8 @@
store i8 420, i8* %gep_alloca, align 16
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %gep_alloca, i8* %gep_a, i32 2, i32 16, i1 false)
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %gep_b, i8* %gep_alloca, i32 2, i32 16, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %gep_alloca, i8* align 16 %gep_a, i32 2, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %gep_b, i8* align 16 %gep_alloca, i32 2, i1 false)
ret void
}
@@ -57,9 +57,9 @@
%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* %aaptr, i8* %aptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %aaptr, i8* align 2 %aptr, i32 16, i1 false)
%bptr = bitcast i16* %b to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %bptr, i8* %aaptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false)
ret void
}
@@ -77,10 +77,10 @@
%a = alloca { i8*, i8*, i8* }
%b = alloca { i8*, i8*, i8* }
%a_raw = bitcast { i8*, i8*, i8* }* %a to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a_raw, i8* %x, i32 22, i32 8, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %a_raw, i8* align 8 %x, i32 22, i1 false)
%b_raw = bitcast { i8*, i8*, i8* }* %b to i8*
%b_gep = getelementptr i8, i8* %b_raw, i32 6
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b_gep, i8* %x, i32 18, i32 2, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %b_gep, i8* align 2 %x, i32 18, i1 false)
ret void
}
@@ -155,7 +155,7 @@
%raw2 = getelementptr inbounds [16 x i8], [16 x i8]* %a, i32 0, i32 8
%ptr2 = bitcast i8* %raw2 to double*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %raw1, i8* %out, i32 16, i32 0, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %raw1, i8* %out, i32 16, i1 false)
; CHECK: %[[val2:.*]] = load double, double* %{{.*}}, align 1
; CHECK: %[[val1:.*]] = load double, double* %{{.*}}, align 1
@@ -165,7 +165,7 @@
store double %val1, double* %ptr1, align 1
store double %val2, double* %ptr2, align 1
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %raw1, i32 16, i32 0, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %raw1, i32 16, i1 false)
; CHECK: store double %[[val1]], double* %{{.*}}, align 1
; CHECK: store double %[[val2]], double* %{{.*}}, align 1
diff --git a/llvm/test/Transforms/SROA/alloca-address-space.ll b/llvm/test/Transforms/SROA/alloca-address-space.ll
index 9d9f78f..d28bc39 100644
--- a/llvm/test/Transforms/SROA/alloca-address-space.ll
+++ b/llvm/test/Transforms/SROA/alloca-address-space.ll
@@ -1,10 +1,10 @@
; RUN: opt < %s -sroa -S | FileCheck %s
target datalayout = "e-p:64:64:64-p1:16:16:16-p2:32:32-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-A2"
-declare void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* nocapture, i8 addrspace(2)* nocapture readonly, i32, i32, i1)
-declare void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(2)* nocapture readonly, i32, i32, i1)
-declare void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i32, i1)
-declare void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i32, i1)
+declare void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* nocapture, i8 addrspace(2)* nocapture readonly, i32, i1)
+declare void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(2)* nocapture readonly, i32, i1)
+declare void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* 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)
@@ -16,9 +16,9 @@
%aa = alloca <2 x i64>, align 16, addrspace(2)
%aptr = bitcast <2 x i64> addrspace(1)* %a to i8 addrspace(1)*
%aaptr = bitcast <2 x i64> addrspace(2)* %aa to i8 addrspace(2)*
- call void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* %aaptr, i8 addrspace(1)* %aptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* 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.p2i8.i32(i8 addrspace(1)* %bptr, i8 addrspace(2)* %aaptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* align 2 %bptr, i8 addrspace(2)* align 2 %aaptr, i32 16, i1 false)
ret void
}
@@ -30,9 +30,9 @@
%aa = alloca <2 x i64>, align 16, addrspace(2)
%aptr = bitcast <2 x i64> addrspace(1)* %a to i8 addrspace(1)*
%aaptr = bitcast <2 x i64> addrspace(2)* %aa to i8 addrspace(2)*
- call void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* %aaptr, i8 addrspace(1)* %aptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* align 2 %aaptr, i8 addrspace(1)* align 2 %aptr, i32 16, i1 false)
%bptr = bitcast i16 addrspace(2)* %b to i8 addrspace(2)*
- call void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* %bptr, i8 addrspace(2)* %aaptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* align 2 %bptr, i8 addrspace(2)* align 2 %aaptr, i32 16, i1 false)
ret void
}
@@ -44,9 +44,9 @@
%aa = alloca <2 x i64>, align 16, addrspace(2)
%aptr = bitcast <2 x i64> addrspace(2)* %a to i8 addrspace(2)*
%aaptr = bitcast <2 x i64> addrspace(2)* %aa to i8 addrspace(2)*
- call void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* %aaptr, i8 addrspace(2)* %aptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* align 2 %aaptr, i8 addrspace(2)* align 2 %aptr, i32 16, i1 false)
%bptr = bitcast i16 addrspace(1)* %b to i8 addrspace(1)*
- call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* %bptr, i8 addrspace(2)* %aaptr, i32 16, i32 2, i1 false)
+ call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* align 2 %bptr, i8 addrspace(2)* align 2 %aaptr, i32 16, i1 false)
ret void
}
@@ -61,7 +61,7 @@
store [5 x i64] %in.coerce, [5 x i64] addrspace(2)* %0, align 8
%scevgep9 = getelementptr %struct.struct_test_27.0.13, %struct.struct_test_27.0.13 addrspace(2)* %in, i32 0, i32 4, i32 0
%scevgep910 = bitcast i32 addrspace(2)* %scevgep9 to i8 addrspace(2)*
- call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* undef, i8 addrspace(2)* %scevgep910, i32 16, i32 4, i1 false)
+ call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* align 4 undef, i8 addrspace(2)* align 4 %scevgep910, i32 16, i1 false)
ret void
}
diff --git a/llvm/test/Transforms/SROA/basictest.ll b/llvm/test/Transforms/SROA/basictest.ll
index 8a30be9..948663a 100644
--- a/llvm/test/Transforms/SROA/basictest.ll
+++ b/llvm/test/Transforms/SROA/basictest.ll
@@ -80,31 +80,31 @@
; CHECK-NEXT: %[[test3_a7:.*]] = alloca [85 x i8]
%b = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 0
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 300, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 300, i1 false)
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a1]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %src, i32 42
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %src, i32 42
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 42
; CHECK-NEXT: %[[test3_r1:.*]] = load i8, i8* %[[gep]]
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 43
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [99 x i8], [99 x i8]* %[[test3_a2]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 99
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 99
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 142
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [16 x i8], [16 x i8]* %[[test3_a3]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 16
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 16
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 158
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a4]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 42
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 42
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 200
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 207
; CHECK-NEXT: %[[test3_r2:.*]] = load i8, i8* %[[gep]]
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 208
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 215
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [85 x i8], [85 x i8]* %[[test3_a7]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 85
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 85
; Clobber a single element of the array, this should be promotable.
%c = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 42
@@ -244,59 +244,59 @@
; CHECK-NEXT: store i32 4, i32* %[[bitcast]]
%overlap2.prefix = getelementptr i8, i8* %overlap2.1.1.i8, i64 -4
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.prefix, i8* %src, i32 8, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.prefix, i8* %src, i32 8, i1 false)
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a4]], i64 0, i64 39
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %src, i32 3
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %src, i32 3
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 3
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 5
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 5
; Bridge between the overlapping areas
- call void @llvm.memset.p0i8.i32(i8* %overlap2.1.2.i8, i8 42, i32 8, i32 1, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %overlap2.1.2.i8, i8 42, i32 8, i1 false)
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 2
-; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %[[gep]], i8 42, i32 5
+; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 %[[gep]], i8 42, i32 5
; ...promoted i8 store...
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %[[gep]], i8 42, i32 2
+; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 %[[gep]], i8 42, i32 2
; Entirely within the second overlap.
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.1.i8, i8* %src, i32 5, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.1.i8, i8* %src, i32 5, i1 false)
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 1
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep]], i8* %src, i32 5
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep]], i8* align 1 %src, i32 5
; Trailing past the second overlap.
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.2.i8, i8* %src, i32 8, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.2.i8, i8* %src, i32 8, i1 false)
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 2
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep]], i8* %src, i32 5
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep]], i8* align 1 %src, i32 5
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 5
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [85 x i8], [85 x i8]* %[[test3_a7]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 3
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 3
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 300, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 300, i1 false)
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a1]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %[[gep]], i32 42
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %dst, i8* align 1 %[[gep]], i32 42
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 42
; CHECK-NEXT: store i8 0, i8* %[[gep]]
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 43
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [99 x i8], [99 x i8]* %[[test3_a2]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 99
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 99
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 142
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [16 x i8], [16 x i8]* %[[test3_a3]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 16
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 16
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 158
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a4]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 42
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 42
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 200
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 207
; CHECK-NEXT: store i8 42, i8* %[[gep]]
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 208
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 215
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [85 x i8], [85 x i8]* %[[test3_a7]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 85
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 85
ret void
}
@@ -315,9 +315,9 @@
; CHECK-NEXT: %[[test4_a6:.*]] = alloca [40 x i8]
%b = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 0
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 100, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 100, i1 false)
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [20 x i8], [20 x i8]* %[[test4_a1]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep]], i8* %src, i32 20
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep]], i8* align 1 %src, i32 20
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 20
; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16*
; CHECK-NEXT: %[[test4_r1:.*]] = load i16, i16* %[[bitcast]]
@@ -325,10 +325,10 @@
; CHECK-NEXT: %[[test4_r2:.*]] = load i8, i8* %[[gep]]
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 23
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a2]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 30
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [10 x i8], [10 x i8]* %[[test4_a3]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 10
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 10
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 40
; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16*
; CHECK-NEXT: %[[test4_r3:.*]] = load i16, i16* %[[bitcast]]
@@ -336,7 +336,7 @@
; CHECK-NEXT: %[[test4_r4:.*]] = load i8, i8* %[[gep]]
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 43
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a4]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 50
; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16*
; CHECK-NEXT: %[[test4_r5:.*]] = load i16, i16* %[[bitcast]]
@@ -344,31 +344,31 @@
; CHECK-NEXT: %[[test4_r6:.*]] = load i8, i8* %[[gep]]
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 53
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a5]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 60
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [40 x i8], [40 x i8]* %[[test4_a6]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 40
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 40
%a.src.1 = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 20
%a.dst.1 = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 40
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.1, i32 10, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.1, i32 10, i1 false)
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a4]], i64 0, i64 0
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a2]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; Clobber a single element of the array, this should be promotable, and be deleted.
%c = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 42
store i8 0, i8* %c
%a.src.2 = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 50
- call void @llvm.memmove.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.2, i32 10, i32 1, i1 false)
+ call void @llvm.memmove.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.2, i32 10, i1 false)
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a4]], i64 0, i64 0
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a5]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 100, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 100, i1 false)
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [20 x i8], [20 x i8]* %[[test4_a1]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %[[gep]], i32 20
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %dst, i8* align 1 %[[gep]], i32 20
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 20
; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16*
; CHECK-NEXT: store i16 %[[test4_r1]], i16* %[[bitcast]]
@@ -376,10 +376,10 @@
; CHECK-NEXT: store i8 %[[test4_r2]], i8* %[[gep]]
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 23
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a2]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 30
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [10 x i8], [10 x i8]* %[[test4_a3]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 10
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 10
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 40
; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16*
; CHECK-NEXT: store i16 %[[test4_r5]], i16* %[[bitcast]]
@@ -387,7 +387,7 @@
; CHECK-NEXT: store i8 %[[test4_r6]], i8* %[[gep]]
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 43
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a4]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 50
; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16*
; CHECK-NEXT: store i16 %[[test4_r5]], i16* %[[bitcast]]
@@ -395,18 +395,18 @@
; CHECK-NEXT: store i8 %[[test4_r6]], i8* %[[gep]]
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 53
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a5]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 60
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [40 x i8], [40 x i8]* %[[test4_a6]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 40
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 40
ret void
}
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
-declare void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* nocapture, i8* nocapture, i32, i32, i1) nounwind
-declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
+declare void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* nocapture, i8* nocapture, i32, i1) nounwind
+declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
define i16 @test5() {
; CHECK-LABEL: @test5(
@@ -436,7 +436,7 @@
entry:
%a = alloca [4 x i8]
%ptr = getelementptr [4 x i8], [4 x i8]* %a, i32 0, i32 0
- call void @llvm.memset.p0i8.i32(i8* %ptr, i8 42, i32 4, i32 1, i1 true)
+ call void @llvm.memset.p0i8.i32(i8* %ptr, i8 42, i32 4, i1 true)
%iptr = bitcast i8* %ptr to i32*
%val = load i32, i32* %iptr
ret i32 %val
@@ -456,8 +456,8 @@
entry:
%a = alloca [4 x i8]
%ptr = getelementptr [4 x i8], [4 x i8]* %a, i32 0, i32 0
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i32 1, i1 true)
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i32 1, i1 true)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i1 true)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i1 true)
ret void
}
@@ -543,7 +543,7 @@
entry:
%a = alloca [8 x i8]
%ptr = getelementptr [8 x i8], [8 x i8]* %a, i32 0, i32 0
- call void @llvm.memset.p0i8.i32(i8* %ptr, i8 0, i32 8, i32 1, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %ptr, i8 0, i32 8, i1 false)
%s2ptrptr = bitcast i8* %ptr to %S2**
%s2ptr = load %S2*, %S2** %s2ptrptr
ret %S2* %s2ptr
@@ -743,10 +743,10 @@
entry:
%a = alloca [3 x i8]
%ptr = getelementptr [3 x i8], [3 x i8]* %a, i32 0, i32 0
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i1 false)
%cast = bitcast i8* %ptr to i24*
store i24 0, i24* %cast
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i1 false)
ret void
}
@@ -763,8 +763,8 @@
entry:
%a = alloca [3 x i8]
%ptr = getelementptr [3 x i8], [3 x i8]* %a, i32 0, i32 0
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i32 1, i1 true)
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i32 1, i1 true)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i1 true)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i1 true)
ret void
}
@@ -780,7 +780,7 @@
; CHECK-NEXT: %[[agep1:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[agep1]], i8* %src, i32 %size,
; CHECK-NEXT: %[[agep2:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0
-; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %[[agep2]], i8 42, i32 %size,
+; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 %[[agep2]], i8 42, i32 %size,
; CHECK-NEXT: %[[dstcast1:.*]] = bitcast i8* %dst to i32*
; CHECK-NEXT: store i32 42, i32* %[[dstcast1]]
; CHECK-NEXT: %[[dstgep1:.*]] = getelementptr inbounds i8, i8* %dst, i64 4
@@ -793,14 +793,14 @@
entry:
%a = alloca [42 x i8]
%ptr = getelementptr [42 x i8], [42 x i8]* %a, i32 0, i32 0
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 8, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 8, i1 false)
%ptr2 = getelementptr [42 x i8], [42 x i8]* %a, i32 0, i32 8
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr2, i8* %src, i32 %size, i32 1, i1 false)
- call void @llvm.memset.p0i8.i32(i8* %ptr2, i8 42, i32 %size, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr2, i8* %src, i32 %size, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %ptr2, i8 42, i32 %size, i1 false)
%cast = bitcast i8* %ptr to i32*
store i32 42, i32* %cast
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 8, i32 1, i1 false)
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr2, i32 %size, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 8, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr2, i32 %size, i1 false)
ret void
}
@@ -819,7 +819,7 @@
%a = alloca { i64, i8* }
%cast1 = bitcast %opaque* %x to i8*
%cast2 = bitcast { i64, i8* }* %a to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast2, i8* %cast1, i32 16, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast2, i8* %cast1, i32 16, i1 false)
%gep = getelementptr inbounds { i64, i8* }, { i64, i8* }* %a, i32 0, i32 0
%val = load i64, i64* %gep
ret i32 undef
@@ -853,7 +853,7 @@
ret i32 %sum2
}
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
define i8 @test21() {
; Test allocations and offsets which border on overflow of the int64_t used
@@ -869,7 +869,7 @@
store i8 255, i8* %gep0
%gep1 = getelementptr [2305843009213693951 x i8], [2305843009213693951 x i8]* %a, i64 0, i64 -9223372036854775807
%gep2 = getelementptr i8, i8* %gep1, i64 -1
- call void @llvm.memset.p0i8.i64(i8* %gep2, i8 0, i64 18446744073709551615, i32 1, i1 false)
+ call void @llvm.memset.p0i8.i64(i8* %gep2, i8 0, i64 18446744073709551615, i1 false)
%gep3 = getelementptr i8, i8* %gep1, i64 9223372036854775807
%gep4 = getelementptr i8, i8* %gep3, i64 9223372036854775807
%gep5 = getelementptr i8, i8* %gep4, i64 -6917529027641081857
@@ -894,7 +894,7 @@
entry:
%a = alloca i8
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 1, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 1, i1 false)
%tmp2 = load i8, i8* %a
ret void
}
@@ -914,7 +914,7 @@
if.then:
%tmp0 = bitcast %PR13916.struct* %a to i8*
%tmp1 = bitcast %PR13916.struct* %a to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp0, i8* %tmp1, i32 1, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp0, i8* %tmp1, i32 1, i1 false)
br label %if.end
if.end:
@@ -992,7 +992,7 @@
store %PR14034.list* undef, %PR14034.list** %prev
%cast0 = bitcast %PR14034.struct* undef to i8*
%cast1 = bitcast %PR14034.struct* %a to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast0, i8* %cast1, i32 12, i32 0, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast0, i8* %cast1, i32 12, i1 false)
ret void
}
@@ -1065,15 +1065,15 @@
; Also use a memset to the middle 32-bits for fun.
%X.sroa.0.2.raw_idx2.i = getelementptr inbounds i8, i8* %0, i32 2
- call void @llvm.memset.p0i8.i64(i8* %X.sroa.0.2.raw_idx2.i, i8 0, i64 4, i32 1, i1 false)
+ call void @llvm.memset.p0i8.i64(i8* %X.sroa.0.2.raw_idx2.i, i8 0, i64 4, i1 false)
; Or a memset of the whole thing.
- call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 8, i32 1, i1 false)
+ call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 8, i1 false)
; Write to the high 32-bits with a memcpy.
%X.sroa.0.4.raw_idx4.i = getelementptr inbounds i8, i8* %0, i32 4
%d.raw = bitcast double* %d to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %X.sroa.0.4.raw_idx4.i, i8* %d.raw, i32 4, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %X.sroa.0.4.raw_idx4.i, i8* %d.raw, i32 4, i1 false)
; Store to the high 32-bits...
%X.sroa.0.4.cast5.i = bitcast i8* %X.sroa.0.4.raw_idx4.i to i32*
@@ -1146,7 +1146,7 @@
%cast1 = bitcast { [16 x i8 ] }* %gep to i8*
%cast2 = bitcast { [16 x i8 ] }* %a to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast1, i8* %cast2, i32 16, i32 8, i1 true)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %cast1, i8* align 8 %cast2, i32 16, i1 true)
ret void
; CHECK: ret
}
@@ -1164,7 +1164,7 @@
%cast1 = bitcast { [16 x i8 ] } addrspace(1)* %gep to i8 addrspace(1)*
%cast2 = bitcast { [16 x i8 ] }* %a to i8*
- call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* %cast1, i8* %cast2, i32 16, i32 8, i1 true)
+ call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 8 %cast1, i8* align 8 %cast2, i32 16, i1 true)
ret void
; CHECK: ret
}
@@ -1177,7 +1177,7 @@
%stack = alloca [1048576 x i32], align 16
; CHECK: alloca [1048576 x i32]
%cast = bitcast [1048576 x i32]* %stack to i8*
- call void @llvm.memset.p0i8.i64(i8* %cast, i8 -2, i64 4194304, i32 16, i1 false)
+ call void @llvm.memset.p0i8.i64(i8* align 16 %cast, i8 -2, i64 4194304, i1 false)
ret void
; CHECK: ret
}
@@ -1206,7 +1206,7 @@
; CHECK-NEXT: {{.*}} = load i8, i8* %[[b]], align 8
%a.i8 = bitcast <{ i1 }>* %a to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.i8, i8* %b.i8, i32 1, i32 1, i1 false) nounwind
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.i8, i8* %b.i8, i32 1, i1 false) nounwind
%bar = load i8, i8* %a.i8, align 1
%a.i1 = getelementptr inbounds <{ i1 }>, <{ i1 }>* %a, i32 0, i32 0
%baz = load i1, i1* %a.i1, align 1
@@ -1261,7 +1261,7 @@
; CHECK: alloca
%a.i8 = bitcast i32* %a to i8*
- call void @llvm.memset.p0i8.i32(i8* %a.i8, i8 0, i32 %x, i32 1, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %a.i8, i8 0, i32 %x, i1 false)
%v = load i32, i32* %a
ret i32 %v
}
@@ -1323,7 +1323,7 @@
end:
%tmp.raw = bitcast [4 x i8]* %tmp to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %data, i8* %tmp.raw, i32 %size, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %data, i8* %tmp.raw, i32 %size, i1 false)
ret void
; CHECK: ret void
}
@@ -1376,7 +1376,7 @@
entry:
%b = alloca i32, align 4
%b.cast = bitcast i32* %b to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b.cast, i8* %a, i32 4, i32 4, i1 true)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %b.cast, i8* align 4 %a, i32 4, i1 true)
%b.gep = getelementptr inbounds i8, i8* %b.cast, i32 2
load i8, i8* %b.gep, align 2
unreachable
@@ -1413,7 +1413,7 @@
%gep0 = getelementptr inbounds i32, i32* %a, i32 0
%cast1 = bitcast i32* %gep1 to i8*
%cast0 = bitcast i32* %gep0 to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast1, i8* %cast0, i32 4, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast1, i8* %cast0, i32 4, i1 false)
ret void
}
@@ -1424,7 +1424,7 @@
entry:
%f = alloca i8
%gep = getelementptr i8, i8* %f, i64 -1
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %gep, i32 1, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %gep, i32 1, i1 false)
ret void
}
@@ -1439,8 +1439,8 @@
entry:
%a = alloca i64, align 16
%ptr = bitcast i64* %a to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 8, i32 1, i1 true)
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 8, i32 1, i1 true)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 8, i1 true)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 8, i1 true)
ret void
}
@@ -1663,12 +1663,12 @@
%3 = load i64, i64* %1, align 8
store i64 %3, i64* %2, align 8
%4 = bitcast %struct.STest* %outData to i8*
- call void @llvm.memcpy.p0i8.p0i8.i64(i8* %4, i8* %0, i64 16, i32 4, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %4, i8* align 4 %0, i64 16, i1 false)
call void @llvm.lifetime.end.p0i8(i64 16, i8* %0)
ret void
}
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
define void @PR27999() unnamed_addr {
; CHECK-LABEL: @PR27999(
diff --git a/llvm/test/Transforms/SROA/big-endian.ll b/llvm/test/Transforms/SROA/big-endian.ll
index fc4b8b2..9116545 100644
--- a/llvm/test/Transforms/SROA/big-endian.ll
+++ b/llvm/test/Transforms/SROA/big-endian.ll
@@ -226,7 +226,7 @@
store i64 34494054408, i64* %a2
%tmp0 = bitcast { i32, i24 }* %a to i8*
%tmp1 = bitcast i64* %a2 to i8*
- call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp0, i8* %tmp1, i64 8, i32 4, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %tmp0, i8* align 4 %tmp1, i64 8, i1 false)
; CHECK: %[[LO_SHR:.*]] = lshr i64 34494054408, 32
; CHECK: %[[LO_START:.*]] = trunc i64 %[[LO_SHR]] to i32
; CHECK: %[[HI_START:.*]] = trunc i64 34494054408 to i32
@@ -249,4 +249,4 @@
; CHECK: ret void
}
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i32, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i1)
diff --git a/llvm/test/Transforms/SROA/dbg-addr-diamond.ll b/llvm/test/Transforms/SROA/dbg-addr-diamond.ll
index 132da99..9ccb82e4 100644
--- a/llvm/test/Transforms/SROA/dbg-addr-diamond.ll
+++ b/llvm/test/Transforms/SROA/dbg-addr-diamond.ll
@@ -39,7 +39,7 @@
if.end: ; preds = %if.else, %if.then
%1 = bitcast %struct.Pair* %p to i8*, !dbg !51
%2 = bitcast %struct.Pair* @pair to i8*, !dbg !51
- call void @llvm.memcpy.p0i8.p0i8.i64(i8* %2, i8* %1, i64 8, i32 4, i1 false), !dbg !51
+ call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %2, i8* align 4 %1, i64 8, i1 false), !dbg !51
ret void
}
@@ -62,7 +62,7 @@
; CHECK: ![[PVAR]] = !DILocalVariable(name: "p", {{.*}})
; Function Attrs: argmemonly nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #2
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #2
; Function Attrs: nounwind readnone speculatable
declare void @llvm.dbg.addr(metadata, metadata, metadata)
diff --git a/llvm/test/Transforms/SROA/mem-par-metadata-sroa.ll b/llvm/test/Transforms/SROA/mem-par-metadata-sroa.ll
index ae5898e..32ea8f5 100644
--- a/llvm/test/Transforms/SROA/mem-par-metadata-sroa.ll
+++ b/llvm/test/Transforms/SROA/mem-par-metadata-sroa.ll
@@ -95,7 +95,7 @@
}
; Function Attrs: argmemonly nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #1
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #1
attributes #0 = { norecurse nounwind uwtable "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { argmemonly nounwind }
diff --git a/llvm/test/Transforms/SROA/preserve-nonnull.ll b/llvm/test/Transforms/SROA/preserve-nonnull.ll
index a29da6d..d6f084f 100644
--- a/llvm/test/Transforms/SROA/preserve-nonnull.ll
+++ b/llvm/test/Transforms/SROA/preserve-nonnull.ll
@@ -3,7 +3,7 @@
; Make sure that SROA doesn't lose nonnull metadata
; on loads from allocas that get optimized out.
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1)
; Check that we do basic propagation of nonnull when rewriting.
define i8* @propagate_nonnull(i32* %v) {
@@ -37,7 +37,7 @@
%buf = alloca float*
%_arg_i8 = bitcast float** %arg to i8*
%_buf_i8 = bitcast float** %buf to i8*
- call void @llvm.memcpy.p0i8.p0i8.i64(i8* %_buf_i8, i8* %_arg_i8, i64 8, i32 8, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %_buf_i8, i8* align 8 %_arg_i8, i64 8, i1 false)
%ret = load float*, float** %buf, align 8, !nonnull !0
ret float* %ret
}
diff --git a/llvm/test/Transforms/SROA/slice-order-independence.ll b/llvm/test/Transforms/SROA/slice-order-independence.ll
index 7d57be6d..19e7143 100644
--- a/llvm/test/Transforms/SROA/slice-order-independence.ll
+++ b/llvm/test/Transforms/SROA/slice-order-independence.ll
@@ -1,7 +1,7 @@
; 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, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
; Check that the chosen type for a split is independent from the order of
; slices even in case of types that are skipped because their width is not a
@@ -12,7 +12,7 @@
%arg = alloca { i16*, i32 }, align 8
%2 = bitcast { i16*, i32 }* %0 to i8*
%3 = bitcast { i16*, i32 }* %arg to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %3, i8* %2, i32 16, i32 8, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %3, i8* align 8 %2, i32 16, i1 false)
%b = getelementptr inbounds { i16*, i32 }, { i16*, i32 }* %arg, i64 0, i32 0
%pb0 = bitcast i16** %b to i63*
%b0 = load i63, i63* %pb0
@@ -27,7 +27,7 @@
%arg = alloca { i16*, i32 }, align 8
%2 = bitcast { i16*, i32 }* %0 to i8*
%3 = bitcast { i16*, i32 }* %arg to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %3, i8* %2, i32 16, i32 8, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %3, i8* align 8 %2, i32 16, i1 false)
%b = getelementptr inbounds { i16*, i32 }, { i16*, i32 }* %arg, i64 0, i32 0
%pb1 = bitcast i16** %b to i8**
%b1 = load i8*, i8** %pb1
diff --git a/llvm/test/Transforms/SROA/slice-width.ll b/llvm/test/Transforms/SROA/slice-width.ll
index 6b6ab93..98ec1e9 100644
--- a/llvm/test/Transforms/SROA/slice-width.ll
+++ b/llvm/test/Transforms/SROA/slice-width.ll
@@ -1,8 +1,8 @@
; 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-f80:128-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64"
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
define void @no_split_on_non_byte_width(i32) {
; This tests that allocas are not split into slices that are not byte width multiple
@@ -39,7 +39,7 @@
; Copy from a global.
%x_i8 = bitcast %union.Foo* %x to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %x_i8, i8* bitcast (%union.Foo* @foo_copy_source to i8*), i32 32, i32 16, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %x_i8, i8* align 16 bitcast (%union.Foo* @foo_copy_source to i8*), i32 32, i1 false)
; Access a slice of the alloca to trigger SROA.
%mid_p = getelementptr %union.Foo, %union.Foo* %x, i32 0, i32 1
@@ -58,7 +58,7 @@
; Set to all ones.
%x_i8 = bitcast %union.Foo* %x to i8*
- call void @llvm.memset.p0i8.i32(i8* %x_i8, i8 -1, i32 32, i32 16, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* align 16 %x_i8, i8 -1, i32 32, i1 false)
; Access a slice of the alloca to trigger SROA.
%mid_p = getelementptr %union.Foo, %union.Foo* %x, i32 0, i32 1
@@ -68,7 +68,7 @@
}
; CHECK-LABEL: define void @memset_fp80_padding
; CHECK: alloca x86_fp80
-; CHECK: call void @llvm.memset.p0i8.i32(i8* %{{.*}}, i8 -1, i32 16, i32 16, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i32(i8* align 16 %{{.*}}, i8 -1, i32 16, i1 false)
; CHECK: store i64 -1, i64* @i64_sink
%S.vec3float = type { float, float, float }
@@ -85,7 +85,7 @@
%tmp1 = alloca %S.vec3float, align 4
%0 = bitcast %S.vec3float* %tmp1 to i8*
%1 = bitcast %S.vec3float* %x to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* %1, i32 12, i32 4, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %0, i8* align 4 %1, i32 12, i1 false)
; The following block does nothing; but appears to confuse SROA
%unused1 = bitcast %S.vec3float* %tmp1 to %U.vec3float*
@@ -98,7 +98,7 @@
%3 = bitcast %S.vec3float* %tmp1 to i8*
; CHECK: alloca
; CHECK-NOT: store <4 x float>
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %2, i8* %3, i32 12, i32 4, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %2, i8* align 4 %3, i32 12, i1 false)
%result = call i32 @memcpy_vec3float_helper(%S.vec3float* %tmp2)
ret i32 %result
diff --git a/llvm/test/Transforms/SROA/vector-promotion.ll b/llvm/test/Transforms/SROA/vector-promotion.ll
index 2d9b26b..0bf2d23 100644
--- a/llvm/test/Transforms/SROA/vector-promotion.ll
+++ b/llvm/test/Transforms/SROA/vector-promotion.ll
@@ -81,12 +81,12 @@
; CHECK-NOT: store
%a.y.cast = bitcast <4 x i32>* %a.y to i8*
- call void @llvm.memset.p0i8.i32(i8* %a.y.cast, i8 0, i32 16, i32 1, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %a.y.cast, i8 0, i32 16, i1 false)
; CHECK-NOT: memset
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
%a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
- call void @llvm.memset.p0i8.i32(i8* %a.tmp1.cast, i8 -1, i32 4, i32 1, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %a.tmp1.cast, i8 -1, i32 4, i1 false)
%tmp1 = load i32, i32* %a.tmp1
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
%tmp2 = load i32, i32* %a.tmp2
@@ -120,14 +120,14 @@
%a.y.cast = bitcast <4 x i32>* %a.y to i8*
%z.cast = bitcast <4 x i32>* %z to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.y.cast, i8* %z.cast, i32 16, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.y.cast, i8* %z.cast, i32 16, i1 false)
; CHECK-NOT: memcpy
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
%a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
%z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
%z.tmp1.cast = bitcast i32* %z.tmp1 to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.tmp1.cast, i8* %z.tmp1.cast, i32 4, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.tmp1.cast, i8* %z.tmp1.cast, i32 4, i1 false)
%tmp1 = load i32, i32* %a.tmp1
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
%tmp2 = load i32, i32* %a.tmp2
@@ -150,7 +150,7 @@
; CHECK-NEXT: ret
}
-declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture, i32, i1) nounwind
; Same as test4 with a different sized address space pointer source.
define i32 @test4_as1(<4 x i32> %x, <4 x i32> %y, <4 x i32> addrspace(1)* %z) {
@@ -167,14 +167,14 @@
%a.y.cast = bitcast <4 x i32>* %a.y to i8*
%z.cast = bitcast <4 x i32> addrspace(1)* %z to i8 addrspace(1)*
- call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.y.cast, i8 addrspace(1)* %z.cast, i32 16, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.y.cast, i8 addrspace(1)* %z.cast, i32 16, i1 false)
; CHECK-NOT: memcpy
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
%a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
%z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %z, i16 0, i16 2
%z.tmp1.cast = bitcast i32 addrspace(1)* %z.tmp1 to i8 addrspace(1)*
- call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.tmp1.cast, i8 addrspace(1)* %z.tmp1.cast, i32 4, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.tmp1.cast, i8 addrspace(1)* %z.tmp1.cast, i32 4, i1 false)
%tmp1 = load i32, i32* %a.tmp1
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
%tmp2 = load i32, i32* %a.tmp2
@@ -213,14 +213,14 @@
%a.y.cast = bitcast <4 x i32>* %a.y to i8*
%a.x.cast = bitcast <4 x i32>* %a.x to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.x.cast, i8* %a.y.cast, i32 16, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.x.cast, i8* %a.y.cast, i32 16, i1 false)
; CHECK-NOT: memcpy
%a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
%a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
%z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
%z.tmp1.cast = bitcast i32* %z.tmp1 to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %z.tmp1.cast, i8* %a.tmp1.cast, i32 4, i32 1, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %z.tmp1.cast, i8* %a.tmp1.cast, i32 4, i1 false)
%tmp1 = load i32, i32* %a.tmp1
%a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
%tmp2 = load i32, i32* %a.tmp2
@@ -242,8 +242,8 @@
; CHECK-NEXT: ret
}
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
define i64 @test6(<4 x i64> %x, <4 x i64> %y, i64 %n) {
; CHECK-LABEL: @test6(
@@ -326,7 +326,7 @@
; CHECK-NEXT: ret <4 x i32> %[[ret]]
}
-declare void @llvm.memset.p0i32.i32(i32* nocapture, i32, i32, i32, i1) nounwind
+declare void @llvm.memset.p0i32.i32(i32* nocapture, i32, i32, i1) nounwind
define <4 x float> @test_subvec_memset() {
; CHECK-LABEL: @test_subvec_memset(
@@ -336,23 +336,23 @@
%a.gep0 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 0
%a.cast0 = bitcast float* %a.gep0 to i8*
- call void @llvm.memset.p0i8.i32(i8* %a.cast0, i8 0, i32 8, i32 0, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %a.cast0, i8 0, i32 8, i1 false)
; CHECK-NOT: store
; CHECK: select <4 x i1> <i1 true, i1 true, i1 false, i1 false>
%a.gep1 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 1
%a.cast1 = bitcast float* %a.gep1 to i8*
- call void @llvm.memset.p0i8.i32(i8* %a.cast1, i8 1, i32 8, i32 0, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %a.cast1, i8 1, i32 8, i1 false)
; CHECK-NEXT: select <4 x i1> <i1 false, i1 true, i1 true, i1 false>
%a.gep2 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 2
%a.cast2 = bitcast float* %a.gep2 to i8*
- call void @llvm.memset.p0i8.i32(i8* %a.cast2, i8 3, i32 8, i32 0, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %a.cast2, i8 3, i32 8, i1 false)
; CHECK-NEXT: select <4 x i1> <i1 false, i1 false, i1 true, i1 true>
%a.gep3 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 3
%a.cast3 = bitcast float* %a.gep3 to i8*
- call void @llvm.memset.p0i8.i32(i8* %a.cast3, i8 7, i32 4, i32 0, i1 false)
+ call void @llvm.memset.p0i8.i32(i8* %a.cast3, i8 7, i32 4, i1 false)
; CHECK-NEXT: insertelement <4 x float>
%ret = load <4 x float>, <4 x float>* %a
@@ -369,7 +369,7 @@
%a.gep0 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 0
%a.cast0 = bitcast float* %a.gep0 to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast0, i8* %x, i32 8, i32 0, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast0, i8* %x, i32 8, i1 false)
; CHECK: %[[xptr:.*]] = bitcast i8* %x to <2 x float>*
; CHECK-NEXT: %[[x:.*]] = load <2 x float>, <2 x float>* %[[xptr]]
; CHECK-NEXT: %[[expand_x:.*]] = shufflevector <2 x float> %[[x]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
@@ -377,7 +377,7 @@
%a.gep1 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 1
%a.cast1 = bitcast float* %a.gep1 to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast1, i8* %y, i32 8, i32 0, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast1, i8* %y, i32 8, i1 false)
; CHECK-NEXT: %[[yptr:.*]] = bitcast i8* %y to <2 x float>*
; CHECK-NEXT: %[[y:.*]] = load <2 x float>, <2 x float>* %[[yptr]]
; CHECK-NEXT: %[[expand_y:.*]] = shufflevector <2 x float> %[[y]], <2 x float> undef, <4 x i32> <i32 undef, i32 0, i32 1, i32 undef>
@@ -385,7 +385,7 @@
%a.gep2 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 2
%a.cast2 = bitcast float* %a.gep2 to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast2, i8* %z, i32 8, i32 0, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast2, i8* %z, i32 8, i1 false)
; CHECK-NEXT: %[[zptr:.*]] = bitcast i8* %z to <2 x float>*
; CHECK-NEXT: %[[z:.*]] = load <2 x float>, <2 x float>* %[[zptr]]
; CHECK-NEXT: %[[expand_z:.*]] = shufflevector <2 x float> %[[z]], <2 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 1>
@@ -393,12 +393,12 @@
%a.gep3 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 3
%a.cast3 = bitcast float* %a.gep3 to i8*
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast3, i8* %f, i32 4, i32 0, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast3, i8* %f, i32 4, i1 false)
; CHECK-NEXT: %[[fptr:.*]] = bitcast i8* %f to float*
; CHECK-NEXT: %[[f:.*]] = load float, float* %[[fptr]]
; CHECK-NEXT: %[[insert_f:.*]] = insertelement <4 x float>
- call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %a.cast2, i32 8, i32 0, i1 false)
+ call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %a.cast2, i32 8, i1 false)
; CHECK-NEXT: %[[outptr:.*]] = bitcast i8* %out to <2 x float>*
; CHECK-NEXT: %[[extract_out:.*]] = shufflevector <4 x float> %[[insert_f]], <4 x float> undef, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT: store <2 x float> %[[extract_out]], <2 x float>* %[[outptr]]