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

13 files changed, 80 insertions, 80 deletions

diff --git a/llvm/test/Transforms/DeadStoreElimination/2011-09-06-MemCpy.ll b/llvm/test/Transforms/DeadStoreElimination/2011-09-06-MemCpy.ll
index d30e9a2e6c1..665d772d03b 100644
--- a/llvm/test/Transforms/DeadStoreElimination/2011-09-06-MemCpy.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/2011-09-06-MemCpy.ll
@@ -60,7 +60,7 @@ target triple = "x86_64-unknown-linux-gnu"
 %struct.AttrListPtr = type { %struct.AttributeListImpl* }
 %struct.AttributeListImpl = type opaque
 
-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
 
 ; CHECK: _ZSt9iter_swapIPSt4pairIPN4llvm10BasicBlockEjES5_EvT_T0_
 ; CHECK: store
@@ -78,8 +78,8 @@ entry:
   store i32 %5, i32* %3, align 8
   %6 = bitcast %struct.pair.162* %__a to i8*
   %7 = bitcast %struct.pair.162* %__b to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %6, i8* %7, i64 12, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %6, i8* %7, i64 12, i1 false)
   %8 = bitcast %struct.pair.162* %memtmp to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %7, i8* %8, i64 12, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %7, i8* %8, i64 12, i1 false)
   ret void
 }
diff --git a/llvm/test/Transforms/DeadStoreElimination/2016-07-17-UseAfterFree.ll b/llvm/test/Transforms/DeadStoreElimination/2016-07-17-UseAfterFree.ll
index 0a39ccbef64..90629a263f7 100644
--- a/llvm/test/Transforms/DeadStoreElimination/2016-07-17-UseAfterFree.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/2016-07-17-UseAfterFree.ll
@@ -9,10 +9,10 @@ define void @_UPT_destroy(i8* nocapture %ptr) local_unnamed_addr #0 {
 entry:
   %edi = getelementptr inbounds i8, i8* %ptr, i64 8
 
-; CHECK-NOT: tail call void @llvm.memset.p0i8.i64(i8* %edi, i8 0, i64 176, i32 8, i1 false)
+; CHECK-NOT: tail call void @llvm.memset.p0i8.i64(i8* align 8 %edi, i8 0, i64 176, i1 false)
 ; CHECK-NOT: store i32 -1, i32* %addr
 
-  tail call void @llvm.memset.p0i8.i64(i8* %edi, i8 0, i64 176, i32 8, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* align 8 %edi, i8 0, i64 176, i1 false)
   %format4.i = getelementptr inbounds i8, i8* %ptr, i64 144
   %addr = bitcast i8* %format4.i to i32*
   store i32 -1, i32* %addr, align 8
@@ -26,7 +26,7 @@ entry:
 declare void @free(i8* nocapture) local_unnamed_addr #0
 
 ; Function Attrs: argmemonly nounwind
-declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i32, i1) #1
+declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1) #1
 
 attributes #0 = { nounwind }
 attributes #1 = { argmemonly nounwind }
diff --git a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll
index 1614a529ddd..843436fd7da 100644
--- a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll
@@ -6,8 +6,8 @@ entry:
   %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1
   %p3 = bitcast i32* %arrayidx0 to i8*
 ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 4
-; CHECK: call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 24, i32 4, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 28, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], 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 1
   store i32 1, i32* %arrayidx1, align 4
   ret void
@@ -18,8 +18,8 @@ define void @write0to3(i32* nocapture %p) {
 entry:
   %p3 = bitcast i32* %p to i8*
 ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 4
-; CHECK: call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 24, i32 4, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 28, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false)
   store i32 1, i32* %p, align 4
   ret void
 }
@@ -29,8 +29,8 @@ define void @write0to7(i32* nocapture %p) {
 entry:
   %p3 = bitcast i32* %p to i8*
 ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 8
-; CHECK: call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 24, i32 4, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
   %p4 = bitcast i32* %p to i64*
   store i64 1, i64* %p4, align 8
   ret void
@@ -42,8 +42,8 @@ entry:
   %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1
   %p3 = bitcast i32* %arrayidx0 to i8*
 ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 4
-; CHECK: call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 24, i32 4, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 28, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false)
   %p4 = bitcast i32* %p to i64*
   store i64 1, i64* %p4, align 8
   ret void
@@ -55,8 +55,8 @@ define void @dontwrite0to3_align8(i32* nocapture %p) {
 ; CHECK-LABEL: @dontwrite0to3_align8(
 entry:
   %p3 = bitcast i32* %p to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 8, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 8, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %p3, i8 0, i64 32, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %p3, i8 0, i64 32, i1 false)
   store i32 1, i32* %p, align 4
   ret void
 }
@@ -65,8 +65,8 @@ define void @dontwrite0to1(i32* nocapture %p) {
 ; CHECK-LABEL: @dontwrite0to1(
 entry:
   %p3 = bitcast i32* %p to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
   %p4 = bitcast i32* %p to i16*
   store i16 1, i16* %p4, align 4
   ret void
@@ -77,8 +77,8 @@ define void @dontwrite2to9(i32* nocapture %p) {
 entry:
   %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1
   %p3 = bitcast i32* %arrayidx0 to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false)
   %p4 = bitcast i32* %p to i16*
   %arrayidx2 = getelementptr inbounds i16, i16* %p4, i64 1
   %p5 = bitcast i16* %arrayidx2 to i64*
@@ -90,11 +90,11 @@ define void @write8To15AndThen0To7(i64* nocapture %P) {
 entry:
 ; CHECK-LABEL: @write8To15AndThen0To7(
 ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %mybase0, i64 16
-; CHECK: tail call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 16, i32 8, i1 false)
+; CHECK: tail call void @llvm.memset.p0i8.i64(i8* align 8 [[GEP]], 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* %mybase0, i8 0, i64 32, i32 8, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* align 8 %mybase0, i8 0, i64 32, i1 false)
 
   %base64_0 = getelementptr inbounds i64, i64* %P, i64 0
   %base64_1 = getelementptr inbounds i64, i64* %P, i64 1
@@ -104,5 +104,5 @@ entry:
   ret void
 }
 
-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
 
diff --git a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll
index 65acc08629a..7743c619ae1 100644
--- a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll
@@ -12,8 +12,8 @@ define void @write24to28(i32* nocapture %p) nounwind uwtable ssp {
 entry:
   %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1
   %p3 = bitcast i32* %arrayidx0 to i8*
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 24, i32 4, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 28, i32 4, i1 false)
+; 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
@@ -23,8 +23,8 @@ 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* %p3, i8 0, i64 28, i32 4, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false)
+; 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
@@ -34,8 +34,8 @@ 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* %p3, i8 0, i64 32, i32 16, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 16, i1 false)
+; 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
@@ -45,8 +45,8 @@ 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* %0, i8* bitcast (%struct.vec2plusi* @glob2 to i8*), i64 32, i32 16, i1 false)
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2plusi* @glob2 to i8*), i64 36, i32 16, i1 false)
+; 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
@@ -56,8 +56,8 @@ 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* %0, i8* bitcast (%struct.vec2* @glob1 to i8*), i64 16, i32 16, i1 false)
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2* @glob1 to i8*), i64 32, i32 16, i1 false)
+; 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
@@ -67,15 +67,15 @@ define void @dontwrite28to32memcpy(%struct.vec2* nocapture %p) nounwind uwtable
 ; CHECK-LABEL: @dontwrite28to32memcpy(
 entry:
   %0 = bitcast %struct.vec2* %p to i8*
-; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2* @glob1 to i8*), i64 32, i32 16, i1 false)
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2* @glob1 to i8*), i64 32, i32 16, i1 false)
+; 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, i32, i1) nounwind
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
+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 }
 
@@ -87,8 +87,8 @@ entry:
   %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, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 24, i32 1, i1 false)
+; 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
@@ -97,11 +97,11 @@ entry:
 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* %mybase0, i8 0, i64 16, i32 8, i1 false)
+; 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* %mybase0, i8 0, i64 32, i32 8, i1 false)
+  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
diff --git a/llvm/test/Transforms/DeadStoreElimination/combined-partial-overwrites.ll b/llvm/test/Transforms/DeadStoreElimination/combined-partial-overwrites.ll
index 2932307beaf..2a61fff15ad 100644
--- a/llvm/test/Transforms/DeadStoreElimination/combined-partial-overwrites.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/combined-partial-overwrites.ll
@@ -146,7 +146,7 @@ i32 (i8*, i8**, i32, i8, i8*)*,
 i32 (i8*, i8**, i32, i8, i8*)*,
 void (i8*, i32, i32)*
 }
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1)
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
 declare void @goFunc(%struct.foostruct*)
 declare i32 @fa(i8*, i8**, i32, i8, i8*)
 
@@ -156,7 +156,7 @@ entry:
 
   %bang = alloca %struct.foostruct, align 8
   %v1 = bitcast %struct.foostruct* %bang to i8*
-  call void @llvm.memset.p0i8.i64(i8* %v1, i8 0, i64 40, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %v1, i8 0, i64 40, i1 false)
   %v2 = getelementptr inbounds %struct.foostruct, %struct.foostruct* %bang, i64 0, i32 0
   store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** %v2, align 8
   %v3 = getelementptr inbounds %struct.foostruct, %struct.foostruct* %bang, i64 0, i32 1
diff --git a/llvm/test/Transforms/DeadStoreElimination/crash.ll b/llvm/test/Transforms/DeadStoreElimination/crash.ll
index 78cb842e60e..92765697429 100644
--- a/llvm/test/Transforms/DeadStoreElimination/crash.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/crash.ll
@@ -36,11 +36,11 @@ bb14:                                             ; preds = %bb4
   %6 = getelementptr inbounds i16, i16* %2, i64 undef  ; <i16*> [#uses=1]
   store i16 undef, i16* %6, align 2
   %7 = getelementptr inbounds i8, i8* %5, i64 undef   ; <i8*> [#uses=1]
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %7, i8* undef, i64 undef, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %7, i8* undef, i64 undef, i1 false)
   unreachable
 }
 
-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
 
 
 ; rdar://7635088
diff --git a/llvm/test/Transforms/DeadStoreElimination/cs-cs-aliasing.ll b/llvm/test/Transforms/DeadStoreElimination/cs-cs-aliasing.ll
index 30bb96fa2b4..a225a9023ec 100644
--- a/llvm/test/Transforms/DeadStoreElimination/cs-cs-aliasing.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/cs-cs-aliasing.ll
@@ -9,7 +9,7 @@ target triple = "x86_64-unknown-linux-gnu"
 %union.anon = type { i64, [8 x i8] }
 
 ; Function Attrs: nounwind
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) #0
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) #0
 
 ; Function Attrs: noinline nounwind readonly uwtable
 declare zeroext i1 @callee_takes_string(%class.basic_string* nonnull) #1 align 2
@@ -61,10 +61,10 @@ _ZN9__gnu_cxx17__sso_string_baseIcSt11char_traitsIcESaIcEED2Ev.exit3: ; preds =
 ; CHECK: store i8 0, i8* %tmp14, align 1
 
   %tmp17 = call zeroext i1 @callee_takes_string(%class.basic_string* nonnull %tmp1)
-  call void @llvm.memset.p0i8.i64(i8* %tmp11, i8 -51, i64 16, i32 8, i1 false) #0
-  call void @llvm.memset.p0i8.i64(i8* %tmp15, i8 -51, i64 32, i32 8, i1 false) #0
-  call void @llvm.memset.p0i8.i64(i8* %tmp4, i8 -51, i64 16, i32 8, i1 false) #0
-  call void @llvm.memset.p0i8.i64(i8* %tmp8, i8 -51, i64 32, i32 8, i1 false) #0
+  call void @llvm.memset.p0i8.i64(i8* align 8 %tmp11, i8 -51, i64 16, i1 false) #0
+  call void @llvm.memset.p0i8.i64(i8* align 8 %tmp15, i8 -51, i64 32, i1 false) #0
+  call void @llvm.memset.p0i8.i64(i8* align 8 %tmp4, i8 -51, i64 16, i1 false) #0
+  call void @llvm.memset.p0i8.i64(i8* align 8 %tmp8, i8 -51, i64 32, i1 false) #0
   ret i1 %tmp17
 }
 
diff --git a/llvm/test/Transforms/DeadStoreElimination/lifetime.ll b/llvm/test/Transforms/DeadStoreElimination/lifetime.ll
index 97f199b5e0f..28a164cd8b5 100644
--- a/llvm/test/Transforms/DeadStoreElimination/lifetime.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/lifetime.ll
@@ -4,7 +4,7 @@ target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:1
 
 declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) nounwind
 declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) nounwind
-declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i1) nounwind
 
 define void @test1() {
 ; CHECK-LABEL: @test1(
@@ -14,7 +14,7 @@ define void @test1() {
   call void @llvm.lifetime.end.p0i8(i64 1, i8* %A)
 ; CHECK: lifetime.end
 
-  call void @llvm.memset.p0i8.i8(i8* %A, i8 0, i8 -1, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i8(i8* %A, i8 0, i8 -1, i1 false)
 ; CHECK-NOT: memset
 
   ret void
diff --git a/llvm/test/Transforms/DeadStoreElimination/mda-with-dbg-values.ll b/llvm/test/Transforms/DeadStoreElimination/mda-with-dbg-values.ll
index ad61a165d72..23cd93ac387 100644
--- a/llvm/test/Transforms/DeadStoreElimination/mda-with-dbg-values.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/mda-with-dbg-values.ll
@@ -21,7 +21,7 @@ entry:
   store i8 1, i8* %i, align 1, !dbg !19
   call void @llvm.dbg.value(metadata i32 0, i64 0, metadata !17, metadata !DIExpression()), !dbg !18
   %0 = bitcast [1 x i8]* @g to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %i, i8* %0, i64 1, i32 1, i1 false), !dbg !20
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %i, i8* %0, i64 1, i1 false), !dbg !20
   br label %bb2
 
 bb2:                                              ; preds = %0
@@ -32,7 +32,7 @@ bb2:                                              ; preds = %0
 declare void @llvm.dbg.value(metadata, i64, metadata, metadata) #1
 
 ; 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
 
 attributes #0 = { noinline nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "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" "no-trapping-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 = { nounwind readnone speculatable }
diff --git a/llvm/test/Transforms/DeadStoreElimination/memintrinsics.ll b/llvm/test/Transforms/DeadStoreElimination/memintrinsics.ll
index 5bbb8e099c4..aa9f1a13bba 100644
--- a/llvm/test/Transforms/DeadStoreElimination/memintrinsics.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/memintrinsics.ll
@@ -1,8 +1,8 @@
 ; RUN: opt -S -dse < %s | FileCheck %s
 
-declare void @llvm.memcpy.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i32, i1) nounwind
-declare void @llvm.memmove.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i32, i1) nounwind
-declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i1) nounwind
+declare void @llvm.memmove.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i1) nounwind
+declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i1) nounwind
 
 define void @test1() {
 ; CHECK-LABEL: @test1(
@@ -12,7 +12,7 @@ define void @test1() {
   store i8 0, i8* %A  ;; Written to by memcpy
 ; CHECK-NOT: store
 
-  call void @llvm.memcpy.p0i8.p0i8.i8(i8* %A, i8* %B, i8 -1, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i8(i8* %A, i8* %B, i8 -1, i1 false)
 
   ret void
 ; CHECK: ret void
@@ -26,7 +26,7 @@ define void @test2() {
   store i8 0, i8* %A  ;; Written to by memmove
 ; CHECK-NOT: store
 
-  call void @llvm.memmove.p0i8.p0i8.i8(i8* %A, i8* %B, i8 -1, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i8(i8* %A, i8* %B, i8 -1, i1 false)
 
   ret void
 ; CHECK: ret void
@@ -40,7 +40,7 @@ define void @test3() {
   store i8 0, i8* %A  ;; Written to by memset
 ; CHECK-NOT: store
 
-  call void @llvm.memset.p0i8.i8(i8* %A, i8 0, i8 -1, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i8(i8* %A, i8 0, i8 -1, i1 false)
 
   ret void
 ; CHECK: ret void
diff --git a/llvm/test/Transforms/DeadStoreElimination/no-targetdata.ll b/llvm/test/Transforms/DeadStoreElimination/no-targetdata.ll
index f9262ed54b3..b66b75e14d8 100644
--- a/llvm/test/Transforms/DeadStoreElimination/no-targetdata.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/no-targetdata.ll
@@ -1,6 +1,6 @@
 ; RUN: opt -basicaa -dse -S < %s | FileCheck %s
 
-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 @fn(i8* nocapture %buf) #0 {
 entry:
@@ -13,9 +13,9 @@ entry:
 ; CHECK: ret void
 
   %arrayidx = getelementptr i8, i8* %buf, i64 18
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arrayidx, i8* %buf, i64 18, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arrayidx, i8* %buf, i64 18, i1 false)
   store i8 1, i8* %arrayidx, align 1
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %buf, i8* %arrayidx, i64 18, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %buf, i8* %arrayidx, i64 18, i1 false)
   ret void
 }
 
diff --git a/llvm/test/Transforms/DeadStoreElimination/pr11390.ll b/llvm/test/Transforms/DeadStoreElimination/pr11390.ll
index faf3b8b47a9..6105a2e3346 100644
--- a/llvm/test/Transforms/DeadStoreElimination/pr11390.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/pr11390.ll
@@ -17,12 +17,12 @@ entry:
   br i1 %tobool, label %return, label %if.end
 
 if.end:                                           ; preds = %entry
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %call4, i8* %name, i64 %call, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %call4, i8* %name, i64 %call, i1 false)
   %arrayidx = getelementptr inbounds i8, i8* %call4, i64 %call
   store i8 46, i8* %arrayidx, align 1
 ; CHECK: store i8 46
   %add.ptr5 = getelementptr inbounds i8, i8* %call4, i64 %add
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %add.ptr5, i8* %domain, i64 %call1, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %add.ptr5, i8* %domain, i64 %call1, i1 false)
   %arrayidx8 = getelementptr inbounds i8, i8* %call4, i64 %add2
   store i8 0, i8* %arrayidx8, align 1
   br label %return
@@ -35,4 +35,4 @@ declare i64 @strlen(i8* nocapture) nounwind readonly
 
 declare noalias i8* @malloc(i64) nounwind
 
-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
diff --git a/llvm/test/Transforms/DeadStoreElimination/simple.ll b/llvm/test/Transforms/DeadStoreElimination/simple.ll
index 4ed27ebfd66..6130fbbf807 100644
--- a/llvm/test/Transforms/DeadStoreElimination/simple.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/simple.ll
@@ -2,8 +2,8 @@
 ; RUN: opt < %s -aa-pipeline=basic-aa -passes=dse -S | FileCheck %s
 target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
 
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
 declare void @llvm.init.trampoline(i8*, i8*, i8*)
 
 define void @test1(i32* %Q, i32* %P) {
@@ -64,7 +64,7 @@ define void @test5(i32* %Q) {
 ; alias).
 define void @test6(i32 *%p, i8 *%q) {
   store i32 10, i32* %p, align 4       ;; dead.
-  call void @llvm.memset.p0i8.i64(i8* %q, i8 42, i64 900, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %q, i8 42, i64 900, i1 false)
   store i32 30, i32* %p, align 4
   ret void
 ; CHECK-LABEL: @test6(
@@ -75,7 +75,7 @@ define void @test6(i32 *%p, i8 *%q) {
 ; alias).
 define void @test7(i32 *%p, i8 *%q, i8* noalias %r) {
   store i32 10, i32* %p, align 4       ;; dead.
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %q, i8* %r, i64 900, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %q, i8* %r, i64 900, i1 false)
   store i32 30, i32* %p, align 4
   ret void
 ; CHECK-LABEL: @test7(
@@ -209,8 +209,8 @@ define void @test14(i32* %Q) {
 
 ;; Fully dead overwrite of memcpy.
 define void @test15(i8* %P, i8* %Q) nounwind ssp {
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
   ret void
 ; CHECK-LABEL: @test15(
 ; CHECK-NEXT: call void @llvm.memcpy
@@ -219,8 +219,8 @@ define void @test15(i8* %P, i8* %Q) nounwind ssp {
 
 ;; Full overwrite of smaller memcpy.
 define void @test16(i8* %P, i8* %Q) nounwind ssp {
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
   ret void
 ; CHECK-LABEL: @test16(
 ; CHECK-NEXT: call void @llvm.memcpy
@@ -229,8 +229,8 @@ define void @test16(i8* %P, i8* %Q) nounwind ssp {
 
 ;; Overwrite of memset by memcpy.
 define void @test17(i8* %P, i8* noalias %Q) nounwind ssp {
-  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 false)
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
   ret void
 ; CHECK-LABEL: @test17(
 ; CHECK-NEXT: call void @llvm.memcpy
@@ -239,8 +239,8 @@ define void @test17(i8* %P, i8* noalias %Q) nounwind ssp {
 
 ; Should not delete the volatile memset.
 define void @test17v(i8* %P, i8* %Q) nounwind ssp {
-  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 true)
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i1 true)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
   ret void
 ; CHECK-LABEL: @test17v(
 ; CHECK-NEXT: call void @llvm.memset
@@ -253,8 +253,8 @@ define void @test17v(i8* %P, i8* %Q) nounwind ssp {
 ; A = B
 ; A = A
 define void @test18(i8* %P, i8* %Q, i8* %R) nounwind ssp {
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false)
   ret void
 ; CHECK-LABEL: @test18(
 ; CHECK-NEXT: call void @llvm.memcpy