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

21 files changed, 184 insertions, 184 deletions

diff --git a/llvm/test/Analysis/AliasSet/memtransfer.ll b/llvm/test/Analysis/AliasSet/memtransfer.ll
index 9f1ed63edf2..c1940fcd8cd 100644
--- a/llvm/test/Analysis/AliasSet/memtransfer.ll
+++ b/llvm/test/Analysis/AliasSet/memtransfer.ll
@@ -14,7 +14,7 @@ entry:
   %a = alloca i8, align 1
   %b = alloca i8, align 1
   store i8 1, i8* %a, align 1
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %d, i8* %s, i64 1, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %d, i8* %s, i64 1, i1 false)
   store i8 1, i8* %b, align 1
   ret void
 }
@@ -30,7 +30,7 @@ entry:
   %a = alloca i8, align 1
   %b = alloca i8, align 1
   store i8 1, i8* %a, align 1
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %d, i8* %s, i64 1, i32 1, i1 true)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %d, i8* %s, i64 1, i1 true)
   store i8 1, i8* %b, align 1
   ret void
 }
@@ -46,7 +46,7 @@ entry:
   %a = alloca i8, align 1
   %b = alloca i8, align 1
   store i8 1, i8* %a, align 1
-  call void @llvm.memmove.p0i8.p0i8.i64(i8* %d, i8* %s, i64 1, i32 1, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i64(i8* %d, i8* %s, i64 1, i1 false)
   store i8 1, i8* %b, align 1
   ret void
 }
@@ -62,7 +62,7 @@ entry:
   %a = alloca i8, align 1
   %b = alloca i8, align 1
   store i8 1, i8* %a, align 1
-  call void @llvm.memmove.p0i8.p0i8.i64(i8* %d, i8* %s, i64 1, i32 1, i1 true)
+  call void @llvm.memmove.p0i8.p0i8.i64(i8* %d, i8* %s, i64 1, i1 true)
   store i8 1, i8* %b, align 1
   ret void
 }
@@ -76,7 +76,7 @@ entry:
   %a = alloca i8, align 1
   %b = alloca i8, align 1
   store i8 1, i8* %a, align 1
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 1, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 1, i1 false)
   store i8 1, i8* %b, align 1
   ret void
 }
@@ -90,7 +90,7 @@ entry:
   %a = alloca i8, align 1
   %b = alloca i8, align 1
   store i8 1, i8* %a, align 1
-  call void @llvm.memmove.p0i8.p0i8.i64(i8* %b, i8* %a, i64 1, i32 1, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i64(i8* %b, i8* %a, i64 1, i1 false)
   store i8 1, i8* %b, align 1
   ret void
 }
@@ -104,11 +104,11 @@ entry:
   %a = alloca i8, align 1
   %b = alloca i8, align 1
   store i8 1, i8* %a, align 1
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 1, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 1, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 1, i1 false)
   store i8 1, i8* %b, align 1
   ret void
 }
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1)
-declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1)
+declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1)
diff --git a/llvm/test/Analysis/BasicAA/assume.ll b/llvm/test/Analysis/BasicAA/assume.ll
index f9f5353a452..49189dee035 100644
--- a/llvm/test/Analysis/BasicAA/assume.ll
+++ b/llvm/test/Analysis/BasicAA/assume.ll
@@ -1,12 +1,12 @@
 ; RUN: opt < %s -basicaa -aa-eval -print-all-alias-modref-info -disable-output 2>&1 | FileCheck %s
 target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:32:64-v128:32:128-a0:0:32-n32"
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) #0
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) #0
 declare void @llvm.assume(i1) #0
 
 define void @test1(i8* %P, i8* %Q) nounwind ssp {
   tail call void @llvm.assume(i1 true)
-  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)
   ret void
 
 ; CHECK-LABEL: Function: test1:
@@ -14,10 +14,10 @@ define void @test1(i8* %P, i8* %Q) nounwind ssp {
 ; CHECK: MayAlias:	i8* %P, i8* %Q
 ; CHECK: NoModRef:  Ptr: i8* %P	<->  tail call void @llvm.assume(i1 true)
 ; CHECK: NoModRef:  Ptr: i8* %Q	<->  tail call void @llvm.assume(i1 true)
-; CHECK: Just Mod:  Ptr: i8* %P	<->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q	<->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:   tail call void @llvm.assume(i1 true) <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <->   tail call void @llvm.assume(i1 true)
+; CHECK: Just Mod:  Ptr: i8* %P	<->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q	<->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:   tail call void @llvm.assume(i1 true) <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <->   tail call void @llvm.assume(i1 true)
 }
 
 attributes #0 = { nounwind }
diff --git a/llvm/test/Analysis/BasicAA/cs-cs.ll b/llvm/test/Analysis/BasicAA/cs-cs.ll
index 30b7e0720f0..314aff849f9 100644
--- a/llvm/test/Analysis/BasicAA/cs-cs.ll
+++ b/llvm/test/Analysis/BasicAA/cs-cs.ll
@@ -2,48 +2,48 @@
 target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:32:64-v128:32:128-a0:0:32-n32"
 target triple = "arm-apple-ios"
 
-declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i32, i1) #0
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #0
+declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1) #0
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #0
 
 declare void @a_readonly_func(i8*) #1
 declare void @a_writeonly_func(i8*) #2
 
 define void @test2(i8* %P, i8* %Q) #3 {
-  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: Function: test2:
 
 ; CHECK:   MayAlias:     i8* %P, i8* %Q
-; CHECK:   Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK:   Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK:   Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK:   Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK:   Just Mod:   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)
-; CHECK:   Just Mod:   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)
+; CHECK:   Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK:   Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK:   Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK:   Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK:   Just Mod:   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)
+; CHECK:   Just Mod:   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)
 }
 
 define void @test2a(i8* noalias %P, i8* noalias %Q) #3 {
-  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: Function: test2a:
 
 ; CHECK: NoAlias:      i8* %P, i8* %Q
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   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)
-; CHECK: Just Mod:   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)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:   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)
+; CHECK: Just Mod:   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)
 }
 
 define void @test2b(i8* noalias %P, i8* noalias %Q) #3 {
-  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)
   %R = getelementptr i8, i8* %P, i64 12
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
   ret void
 
 ; CHECK-LABEL: Function: test2b:
@@ -51,20 +51,20 @@ define void @test2b(i8* noalias %P, i8* noalias %Q) #3 {
 ; CHECK: NoAlias:      i8* %P, i8* %Q
 ; CHECK: NoAlias:      i8* %P, i8* %R
 ; CHECK: NoAlias:      i8* %Q, i8* %R
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:   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* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, 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)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:   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* %R, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false) <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
 }
 
 define void @test2c(i8* noalias %P, i8* noalias %Q) #3 {
-  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)
   %R = getelementptr i8, i8* %P, i64 11
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
   ret void
 
 ; CHECK-LABEL: Function: test2c:
@@ -72,20 +72,20 @@ define void @test2c(i8* noalias %P, i8* noalias %Q) #3 {
 ; CHECK: NoAlias:      i8* %P, i8* %Q
 ; CHECK: NoAlias:      i8* %P, i8* %R
 ; CHECK: NoAlias:      i8* %Q, i8* %R
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   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* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, 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)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:   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* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false) <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
 }
 
 define void @test2d(i8* noalias %P, i8* noalias %Q) #3 {
-  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)
   %R = getelementptr i8, i8* %P, i64 -12
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
   ret void
 
 ; CHECK-LABEL: Function: test2d:
@@ -93,20 +93,20 @@ define void @test2d(i8* noalias %P, i8* noalias %Q) #3 {
 ; CHECK: NoAlias:      i8* %P, i8* %Q
 ; CHECK: NoAlias:      i8* %P, i8* %R
 ; CHECK: NoAlias:      i8* %Q, i8* %R
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:   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* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, 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)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:   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* %R, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false) <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
 }
 
 define void @test2e(i8* noalias %P, i8* noalias %Q) #3 {
-  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)
   %R = getelementptr i8, i8* %P, i64 -11
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
   ret void
 
 ; CHECK-LABEL: Function: test2e:
@@ -114,67 +114,67 @@ define void @test2e(i8* noalias %P, i8* noalias %Q) #3 {
 ; CHECK: NoAlias:      i8* %P, i8* %Q
 ; CHECK: NoAlias:      i8* %P, i8* %R
 ; CHECK: NoAlias:      i8* %Q, i8* %R
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   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* %R, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, 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)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %R        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:   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* %R, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %R, i8* %Q, i64 12, i1 false) <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
 }
 
 define void @test3(i8* %P, i8* %Q) #3 {
-  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: Function: test3:
 
 ; CHECK: MayAlias:     i8* %P, i8* %Q
-; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   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)
-; CHECK: Just Mod:   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, i32 1, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:   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)
+; CHECK: Just Mod:   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 8, i1 false)
 }
 
 define void @test3a(i8* noalias %P, i8* noalias %Q) #3 {
-  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: Function: test3a:
 
 ; CHECK: NoAlias:      i8* %P, i8* %Q
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   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)
-; CHECK: Just Mod:   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, i32 1, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:   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)
+; CHECK: Just Mod:   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 8, i1 false)
 }
 
 define void @test4(i8* %P, i8* noalias %Q) #3 {
-  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: Function: test4:
 
 ; CHECK: NoAlias:      i8* %P, i8* %Q
-; CHECK: Just Mod (MustAlias):  Ptr: i8* %P        <->  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 false)
-; CHECK: NoModRef:  Ptr: i8* %Q        <->  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   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)
-; CHECK: Just Mod:   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, i32 1, i1 false)
+; CHECK: Just Mod (MustAlias):  Ptr: i8* %P        <->  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i1 false)
+; CHECK: NoModRef:  Ptr: i8* %Q        <->  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q        <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:   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)
+; CHECK: Just Mod:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <->   tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i1 false)
 }
 
 define void @test5(i8* %P, i8* %Q, i8* %R) #3 {
-  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: Function: test5:
@@ -182,19 +182,19 @@ define void @test5(i8* %P, i8* %Q, i8* %R) #3 {
 ; CHECK: MayAlias:     i8* %P, i8* %Q
 ; CHECK: MayAlias:     i8* %P, i8* %R
 ; CHECK: MayAlias:     i8* %Q, i8* %R
-; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Both ModRef:  Ptr: i8* %R     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
-; CHECK: Both ModRef:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %R     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   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)
-; CHECK: Just Mod:   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, i32 1, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Both ModRef:  Ptr: i8* %R     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false)
+; CHECK: Both ModRef:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %R     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false)
+; CHECK: Just Mod:   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)
+; CHECK: Just Mod:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
 }
 
 define void @test5a(i8* noalias %P, i8* noalias %Q, i8* noalias %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: Function: test5a:
@@ -202,27 +202,27 @@ define void @test5a(i8* noalias %P, i8* noalias %Q, i8* noalias %R) nounwind ssp
 ; CHECK: NoAlias:     i8* %P, i8* %Q
 ; CHECK: NoAlias:     i8* %P, i8* %R
 ; CHECK: NoAlias:     i8* %Q, i8* %R
-; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:  Ptr: i8* %R     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
-; CHECK: NoModRef:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
-; CHECK: Just Ref:  Ptr: i8* %R     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false)
-; CHECK: Just Mod:   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)
-; CHECK: Just Mod:   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, i32 1, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: NoModRef:  Ptr: i8* %R     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK: Just Mod:  Ptr: i8* %P     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false)
+; CHECK: NoModRef:  Ptr: i8* %Q     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false)
+; CHECK: Just Ref:  Ptr: i8* %R     <->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false)
+; CHECK: Just Mod:   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)
+; CHECK: Just Mod:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
 }
 
 define void @test6(i8* %P) #3 {
-  call void @llvm.memset.p0i8.i64(i8* %P, i8 -51, i64 32, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %P, i8 -51, i64 32, i1 false)
   call void @a_readonly_func(i8* %P)
   ret void
 
 ; CHECK-LABEL: Function: test6:
 
-; CHECK: Just Mod (MustAlias):  Ptr: i8* %P        <->  call void @llvm.memset.p0i8.i64(i8* %P, i8 -51, i64 32, i32 8, i1 false)
+; CHECK: Just Mod (MustAlias):  Ptr: i8* %P        <->  call void @llvm.memset.p0i8.i64(i8* align 8 %P, i8 -51, i64 32, i1 false)
 ; CHECK: Just Ref:  Ptr: i8* %P        <->  call void @a_readonly_func(i8* %P)
-; CHECK: Just Mod:   call void @llvm.memset.p0i8.i64(i8* %P, i8 -51, i64 32, i32 8, i1 false) <->   call void @a_readonly_func(i8* %P)
-; CHECK: Just Ref:   call void @a_readonly_func(i8* %P) <->   call void @llvm.memset.p0i8.i64(i8* %P, i8 -51, i64 32, i32 8, i1 false)
+; CHECK: Just Mod:   call void @llvm.memset.p0i8.i64(i8* align 8 %P, i8 -51, i64 32, i1 false) <->   call void @a_readonly_func(i8* %P)
+; CHECK: Just Ref:   call void @a_readonly_func(i8* %P) <->   call void @llvm.memset.p0i8.i64(i8* align 8 %P, i8 -51, i64 32, i1 false)
 }
 
 define void @test7(i8* %P) #3 {
diff --git a/llvm/test/Analysis/BasicAA/gep-and-alias.ll b/llvm/test/Analysis/BasicAA/gep-and-alias.ll
index 4ec64305900..e2e5811d263 100644
--- a/llvm/test/Analysis/BasicAA/gep-and-alias.ll
+++ b/llvm/test/Analysis/BasicAA/gep-and-alias.ll
@@ -6,13 +6,13 @@ target triple = "i386-apple-macosx10.6.0"
 ; The load and store address in the loop body could alias so the load
 ; can't be hoisted above the store and out of the loop.
 
-declare void @llvm.memset.p0i8.i32(i8* nocapture writeonly, i8, i32, i32, i1)
+declare void @llvm.memset.p0i8.i32(i8* nocapture writeonly, i8, i32, i1)
 
 define i32 @foo(i32 %x, i32 %z, i32 %n) {
 entry:
   %pool = alloca [59 x i32], align 4
   %tmp = bitcast [59 x i32]* %pool to i8*
-  call void @llvm.memset.p0i8.i32(i8* nonnull %tmp, i8 0, i32 236, i32 4, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 4 nonnull %tmp, i8 0, i32 236, i1 false)
   %cmp3 = icmp eq i32 %n, 0
   br i1 %cmp3, label %for.end, label %for.body.lr.ph
 
diff --git a/llvm/test/Analysis/BasicAA/getmodrefinfo-cs-cs.ll b/llvm/test/Analysis/BasicAA/getmodrefinfo-cs-cs.ll
index f0f1a631d08..755a9ccb23c 100644
--- a/llvm/test/Analysis/BasicAA/getmodrefinfo-cs-cs.ll
+++ b/llvm/test/Analysis/BasicAA/getmodrefinfo-cs-cs.ll
@@ -12,15 +12,15 @@ define void @test0() {
   ret void
 }
 
-; CHECK: NoModRef:   call void @llvm.memset.p0i8.i64(i8* @A, i8 0, i64 1, i32 1, i1 false) <->   call void @llvm.memset.p0i8.i64(i8* @B, i8 0, i64 1, i32 1, i1 false)
-; CHECK: NoModRef:   call void @llvm.memset.p0i8.i64(i8* @B, i8 0, i64 1, i32 1, i1 false) <->   call void @llvm.memset.p0i8.i64(i8* @A, i8 0, i64 1, i32 1, i1 false)
+; CHECK: NoModRef:   call void @llvm.memset.p0i8.i64(i8* @A, i8 0, i64 1, i1 false) <->   call void @llvm.memset.p0i8.i64(i8* @B, i8 0, i64 1, i1 false)
+; CHECK: NoModRef:   call void @llvm.memset.p0i8.i64(i8* @B, i8 0, i64 1, i1 false) <->   call void @llvm.memset.p0i8.i64(i8* @A, i8 0, i64 1, i1 false)
 
-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
 
 @A = external global i8
 @B = external global i8
 define void @test1() {
-  call void @llvm.memset.p0i8.i64(i8* @A, i8 0, i64 1, i32 1, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* @B, i8 0, i64 1, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* @A, i8 0, i64 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* @B, i8 0, i64 1, i1 false)
   ret void
 }
diff --git a/llvm/test/Analysis/BasicAA/guards.ll b/llvm/test/Analysis/BasicAA/guards.ll
index e9032825525..c5d078346a2 100644
--- a/llvm/test/Analysis/BasicAA/guards.ll
+++ b/llvm/test/Analysis/BasicAA/guards.ll
@@ -1,23 +1,23 @@
 ; RUN: opt < %s -basicaa -aa-eval -print-all-alias-modref-info -disable-output 2>&1 | FileCheck %s
 target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:32-f32:32:32-f64:32:32-v64:32:64-v128:32:128-a0:0:32-n32"
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) #0
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) #0
 declare void @llvm.experimental.guard(i1, ...)
 declare void @unknown_but_readonly() readonly
 
 define void @test1(i8* %P, i8* %Q) {
   tail call void(i1,...) @llvm.experimental.guard(i1 true) [ "deopt"() ]
-  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)
   ret void
 
 ; CHECK-LABEL: Function: test1:
 
 ; CHECK:  Just Ref:  Ptr: i8* %P	<->  tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ]
 ; CHECK:  Just Ref:  Ptr: i8* %Q	<->  tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ]
-; CHECK:  Just Mod:  Ptr: i8* %P	<->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK:  Just Ref:  Ptr: i8* %Q	<->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK:  Just Ref:   tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ] <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false)
-; CHECK:  Just Mod:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) <->   tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ]
+; CHECK:  Just Mod:  Ptr: i8* %P	<->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK:  Just Ref:  Ptr: i8* %Q	<->  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK:  Just Ref:   tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ] <->   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false)
+; CHECK:  Just Mod:   tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <->   tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ]
 }
 
 define void @test2() {
diff --git a/llvm/test/Analysis/BasicAA/modref.ll b/llvm/test/Analysis/BasicAA/modref.ll
index 71a3eac3a74..a364a81a4e0 100644
--- a/llvm/test/Analysis/BasicAA/modref.ll
+++ b/llvm/test/Analysis/BasicAA/modref.ll
@@ -11,7 +11,7 @@ define i32 @test0(i8* %P) {
 
   store i32 0, i32* %A
 
-  call void @llvm.memset.p0i8.i32(i8* %P, i8 0, i32 42, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %P, i8 0, i32 42, i1 false)
 
   %B = load i32, i32* %A
   ret i32 %B
@@ -27,7 +27,7 @@ define i8 @test1() {
 
   store i8 2, i8* %B  ;; Not written to by memcpy
 
-  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)
 
   %C = load i8, i8* %B
   ret i8 %C
@@ -38,7 +38,7 @@ define i8 @test2(i8* %P) {
 ; CHECK-LABEL: @test2
   %P2 = getelementptr i8, i8* %P, i32 127
   store i8 1, i8* %P2  ;; Not dead across memset
-  call void @llvm.memset.p0i8.i8(i8* %P, i8 2, i8 127, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i8(i8* %P, i8 2, i8 127, i1 false)
   %A = load i8, i8* %P2
   ret i8 %A
 ; CHECK: ret i8 1
@@ -51,7 +51,7 @@ define i8 @test2a(i8* %P) {
   ;; FIXME: DSE isn't zapping this dead store.
   store i8 1, i8* %P2  ;; Dead, clobbered by memset.
 
-  call void @llvm.memset.p0i8.i8(i8* %P, i8 2, i8 127, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i8(i8* %P, i8 2, i8 127, i1 false)
   %A = load i8, i8* %P2
   ret i8 %A
 ; CHECK-NOT: load
@@ -91,7 +91,7 @@ define void @test3a(i8* %P, i8 %X) {
 
 define i32 @test4(i8* %P) {
   %tmp = load i32, i32* @G1
-  call void @llvm.memset.p0i8.i32(i8* bitcast ([4000 x i32]* @G2 to i8*), i8 0, i32 4000, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* bitcast ([4000 x i32]* @G2 to i8*), i8 0, i32 4000, i1 false)
   %tmp2 = load i32, i32* @G1
   %sub = sub i32 %tmp2, %tmp
   ret i32 %sub
@@ -106,7 +106,7 @@ define i32 @test4(i8* %P) {
 ; write to G1.
 define i32 @test5(i8* %P, i32 %Len) {
   %tmp = load i32, i32* @G1
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* bitcast ([4000 x i32]* @G2 to i8*), i8* bitcast (i32* @G1 to i8*), i32 %Len, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* bitcast ([4000 x i32]* @G2 to i8*), i8* bitcast (i32* @G1 to i8*), i32 %Len, i1 false)
   %tmp2 = load i32, i32* @G1
   %sub = sub i32 %tmp2, %tmp
   ret i32 %sub
@@ -227,7 +227,7 @@ define i32 @test13(i32* %P, i32* %P2) {
   ; CHECK: ret i32 0
 }
 
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, 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, i32, i1) nounwind
-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, i1) nounwind
+declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
diff --git a/llvm/test/Analysis/CallGraph/no-intrinsics.ll b/llvm/test/Analysis/CallGraph/no-intrinsics.ll
index 69bfce77918..3d941039edb 100644
--- a/llvm/test/Analysis/CallGraph/no-intrinsics.ll
+++ b/llvm/test/Analysis/CallGraph/no-intrinsics.ll
@@ -3,10 +3,10 @@
 
 ; Check that intrinsics aren't added to the call graph
 
-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 @f(i8* %out, i8* %in) {
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %in, i32 100, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %out, i8* align 4 %in, i32 100, i1 false)
   ret void
 }
 
diff --git a/llvm/test/Analysis/ConstantFolding/gep-constanfolding-error.ll b/llvm/test/Analysis/ConstantFolding/gep-constanfolding-error.ll
index 16bc8a983e4..a09fd550715 100644
--- a/llvm/test/Analysis/ConstantFolding/gep-constanfolding-error.ll
+++ b/llvm/test/Analysis/ConstantFolding/gep-constanfolding-error.ll
@@ -43,10 +43,10 @@ entry:
   %scevgep = getelementptr [6 x [6 x [7 x i8]]], [6 x [6 x [7 x i8]]]* @j, i32 0, i32 0, i32 %5, i32 %8
   %9 = add i32 %f.promoted, %smax
   %10 = add i32 %9, 2
-  call void @llvm.memset.p0i8.i32(i8* %scevgep, i8 %conv6, i32 %10, i32 1, i1 false)
-; CHECK:  call void @llvm.memset.p0i8.i32(i8* getelementptr inbounds ([6 x [6 x [7 x i8]]], [6 x [6 x [7 x i8]]]* @j, i32 0, i{{32|64}} 5, i{{32|64}} 4, i32 1), i8 %conv6, i32 1, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %scevgep, i8 %conv6, i32 %10, i1 false)
+; CHECK:  call void @llvm.memset.p0i8.i32(i8* getelementptr inbounds ([6 x [6 x [7 x i8]]], [6 x [6 x [7 x i8]]]* @j, i32 0, i{{32|64}} 5, i{{32|64}} 4, i32 1), i8 %conv6, i32 1, i1 false)
 ; CHECK-NOT: call void @llvm.memset.p0i8.i32(i8* getelementptr ([6 x [6 x [7 x i8]]], [6 x [6 x [7 x i8]]]* @j, i64 1, i64 4, i64 4, i32 1)
   ret i32 0
 }
 ; Function Attrs: argmemonly nounwind
-declare void @llvm.memset.p0i8.i32(i8* nocapture writeonly, i8, i32, i32, i1)
+declare void @llvm.memset.p0i8.i32(i8* nocapture writeonly, i8, i32, i1)
diff --git a/llvm/test/Analysis/DependenceAnalysis/Preliminary.ll b/llvm/test/Analysis/DependenceAnalysis/Preliminary.ll
index d6500cc0336..31bd5712af8 100644
--- a/llvm/test/Analysis/DependenceAnalysis/Preliminary.ll
+++ b/llvm/test/Analysis/DependenceAnalysis/Preliminary.ll
@@ -696,4 +696,4 @@ while.end:                                        ; preds = %while.end.loopexit,
   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
diff --git a/llvm/test/Analysis/GlobalsModRef/memset-escape.ll b/llvm/test/Analysis/GlobalsModRef/memset-escape.ll
index b26f3138905..b3b902b3dfb 100644
--- a/llvm/test/Analysis/GlobalsModRef/memset-escape.ll
+++ b/llvm/test/Analysis/GlobalsModRef/memset-escape.ll
@@ -22,7 +22,7 @@ entry:
   %c = alloca [1 x i32], align 4
   store i32 0, i32* %retval, align 4
   %0 = bitcast [1 x i32]* %c to i8*
-  call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 4, i32 4, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 4 %0, i8 0, i64 4, i1 false)
   store i32 1, i32* getelementptr inbounds ([3 x i32], [3 x i32]* @a, i64 0, i64 2), align 4
   store i32 0, i32* @b, align 4
   br label %for.cond
@@ -59,7 +59,7 @@ if.end:                                           ; preds = %for.end
 }
 
 ; Function Attrs: nounwind argmemonly
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind argmemonly
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind argmemonly
 
 ; Function Attrs: noreturn nounwind
 declare void @abort() noreturn nounwind
diff --git a/llvm/test/Analysis/GlobalsModRef/no-escape.ll b/llvm/test/Analysis/GlobalsModRef/no-escape.ll
index 752763c4347..a47ffeb537c 100644
--- a/llvm/test/Analysis/GlobalsModRef/no-escape.ll
+++ b/llvm/test/Analysis/GlobalsModRef/no-escape.ll
@@ -59,7 +59,7 @@ for.end:                                          ; preds = %for.cond
 }
 
 ; Function Attrs: nounwind argmemonly
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind argmemonly
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind argmemonly
 
 ; Function Attrs: noreturn nounwind
 declare void @abort() noreturn nounwind
diff --git a/llvm/test/Analysis/GlobalsModRef/pr12351.ll b/llvm/test/Analysis/GlobalsModRef/pr12351.ll
index 5cabd6f1f12..2aa270a6b6b 100644
--- a/llvm/test/Analysis/GlobalsModRef/pr12351.ll
+++ b/llvm/test/Analysis/GlobalsModRef/pr12351.ll
@@ -1,8 +1,8 @@
 ; RUN: opt < %s -basicaa -globals-aa -gvn -S -disable-verify | FileCheck %s
 
-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 @foo(i8* %x, i8* %y) {
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %x, i8* %y, i32 1, i32 1, i1 false);
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %x, i8* %y, i32 1, i1 false);
   ret void
 }
 
diff --git a/llvm/test/Analysis/GlobalsModRef/volatile-instrs.ll b/llvm/test/Analysis/GlobalsModRef/volatile-instrs.ll
index 5dd47bca3a0..85d2e887e1c 100644
--- a/llvm/test/Analysis/GlobalsModRef/volatile-instrs.ll
+++ b/llvm/test/Analysis/GlobalsModRef/volatile-instrs.ll
@@ -10,7 +10,7 @@ target triple = "x86_64-apple-macosx10.8.0"
 @.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1
 
 declare i32 @printf(i8* nocapture, ...) 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
 
 
 ; Make sure that the initial memcpy call does not go away
@@ -21,10 +21,10 @@ declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32,
 
 define i32 @main() nounwind uwtable ssp {
 main_entry:
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* bitcast (%struct.anon* @b to i8*), i8* bitcast (%struct.anon* @a to i8*), i64 12, i32 4, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.anon* @b to i8*), i8* align 4 bitcast (%struct.anon* @a to i8*), i64 12, i1 false)
   %0 = load volatile i32, i32* getelementptr inbounds (%struct.anon, %struct.anon* @b, i64 0, i32 0), align 4
   store i32 %0, i32* @c, align 4
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* bitcast (%struct.anon* @b to i8*), i8* bitcast (%struct.anon* @a to i8*), i64 12, i32 4, i1 false) nounwind
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.anon* @b to i8*), i8* align 4 bitcast (%struct.anon* @a to i8*), i64 12, i1 false) nounwind
   %call = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i64 0, i64 0), i32 %0) nounwind
   ret i32 0
 }
diff --git a/llvm/test/Analysis/Lint/noalias-byval.ll b/llvm/test/Analysis/Lint/noalias-byval.ll
index 5b36c6d15df..76e2d03d29f 100644
--- a/llvm/test/Analysis/Lint/noalias-byval.ll
+++ b/llvm/test/Analysis/Lint/noalias-byval.ll
@@ -3,10 +3,10 @@
 %s = type { i8 }
 
 ; Function Attrs: argmemonly nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i32, i1) #0
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1) #0
 
 ; Function Attrs: argmemonly nounwind
-declare void @llvm.memset.p0i8.i8.i32(i8* nocapture writeonly, i8, i32, i32, i1) #0
+declare void @llvm.memset.p0i8.i32(i8* nocapture writeonly, i8, i32, i1) #0
 
 declare void @f1(%s* noalias nocapture sret, %s* nocapture readnone)
 
@@ -16,7 +16,7 @@ entry:
   %tmp = alloca %s
   %0 = bitcast %s* %c to i8*
   %1 = bitcast %s* %tmp to i8*
-  call void @llvm.memset.p0i8.i8.i32(i8* %0, i8 0, i32 1, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %0, i8 0, i32 1, i1 false)
   call void @f1(%s* sret %c, %s* %c)
   ret void
 }
@@ -34,7 +34,7 @@ entry:
   %tmp = alloca %s
   %0 = bitcast %s* %c to i8*
   %1 = bitcast %s* %tmp to i8*
-  call void @llvm.memset.p0i8.i8.i32(i8* %0, i8 0, i32 1, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %0, i8 0, i32 1, i1 false)
   call void @f3(%s* sret %c, %s* byval %c)
   ret void
 }
diff --git a/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll b/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll
index bfd7c899b59..28af1e5238c 100644
--- a/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll
+++ b/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll
@@ -1,16 +1,16 @@
 ; RUN: opt -disable-output -basicaa -print-memoryssa %s 2>&1 | 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 @source_clobber(i8* %a, i8* %b) {
 ; CHECK-LABEL: @source_clobber(
 ; CHECK-NEXT:  ; 1 = MemoryDef(liveOnEntry)
-; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 128, i32 1, i1 false)
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 128, i1 false)
 ; CHECK-NEXT:  ; MemoryUse(liveOnEntry)
 ; CHECK-NEXT:    [[X:%.*]] = load i8, i8* %b
 ; CHECK-NEXT:    ret void
 ;
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 128, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 128, i1 false)
   %x = load i8, i8* %b
   ret void
 }
diff --git a/llvm/test/Analysis/ScalarEvolution/avoid-smax-1.ll b/llvm/test/Analysis/ScalarEvolution/avoid-smax-1.ll
index e6c62ee6b47..50c30431af5 100644
--- a/llvm/test/Analysis/ScalarEvolution/avoid-smax-1.ll
+++ b/llvm/test/Analysis/ScalarEvolution/avoid-smax-1.ll
@@ -172,7 +172,7 @@ bb23:		; preds = %bb24, %bb.nph
 	%55 = mul i32 %y.21, %w		; <i32> [#uses=1]
 	%.sum5 = add i32 %55, %.sum3		; <i32> [#uses=1]
 	%56 = getelementptr i8, i8* %j, i32 %.sum5		; <i8*> [#uses=1]
-	tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %56, i8* %54, i32 %w, i32 1, i1 false)
+	tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %56, i8* %54, i32 %w, i1 false)
 	%57 = add i32 %y.21, 1		; <i32> [#uses=2]
 	br label %bb24
 
@@ -189,7 +189,7 @@ bb26:		; preds = %bb24.bb26_crit_edge, %bb22
 	%60 = getelementptr i8, i8* %j, i32 %.sum4		; <i8*> [#uses=1]
 	%61 = mul i32 %x, %w		; <i32> [#uses=1]
 	%62 = sdiv i32 %61, 2		; <i32> [#uses=1]
-	tail call void @llvm.memset.p0i8.i32(i8* %60, i8 -128, i32 %62, i32 1, i1 false)
+	tail call void @llvm.memset.p0i8.i32(i8* %60, i8 -128, i32 %62, i1 false)
 	ret void
 
 bb29:		; preds = %bb20, %entry
@@ -207,7 +207,7 @@ bb30:		; preds = %bb31, %bb.nph11
 	%67 = getelementptr i8, i8* %r, i32 %66		; <i8*> [#uses=1]
 	%68 = mul i32 %y.310, %w		; <i32> [#uses=1]
 	%69 = getelementptr i8, i8* %j, i32 %68		; <i8*> [#uses=1]
-	tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %69, i8* %67, i32 %w, i32 1, i1 false)
+	tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %69, i8* %67, i32 %w, i1 false)
 	%70 = add i32 %y.310, 1		; <i32> [#uses=2]
 	br label %bb31
 
@@ -223,12 +223,12 @@ bb33:		; preds = %bb31.bb33_crit_edge, %bb29
 	%73 = getelementptr i8, i8* %j, i32 %72		; <i8*> [#uses=1]
 	%74 = mul i32 %x, %w		; <i32> [#uses=1]
 	%75 = sdiv i32 %74, 2		; <i32> [#uses=1]
-	tail call void @llvm.memset.p0i8.i32(i8* %73, i8 -128, i32 %75, i32 1, i1 false)
+	tail call void @llvm.memset.p0i8.i32(i8* %73, i8 -128, i32 %75, i1 false)
 	ret void
 
 return:		; preds = %bb20
 	ret void
 }
 
-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
diff --git a/llvm/test/Analysis/ScalarEvolution/trip-count.ll b/llvm/test/Analysis/ScalarEvolution/trip-count.ll
index d21ace9f250..b5ff1c3d8a3 100644
--- a/llvm/test/Analysis/ScalarEvolution/trip-count.ll
+++ b/llvm/test/Analysis/ScalarEvolution/trip-count.ll
@@ -41,7 +41,7 @@ define i32 @test2() {
 entry:
   %bins = alloca [16 x i64], align 16
   %0 = bitcast [16 x i64]* %bins to i8*
-  call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 128, i32 16, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 16 %0, i8 0, i64 128, i1 false)
   br label %preheader
 
 preheader:                                        ; preds = %for.inc.1, %entry
@@ -88,7 +88,7 @@ for.inc.1:                                        ; preds = %for.body.1, %for.in
 }
 
 ; 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
 
 declare void @may_exit() nounwind
 
diff --git a/llvm/test/Analysis/ScalarEvolution/trip-count3.ll b/llvm/test/Analysis/ScalarEvolution/trip-count3.ll
index cce0182d649..df6637a4ced 100644
--- a/llvm/test/Analysis/ScalarEvolution/trip-count3.ll
+++ b/llvm/test/Analysis/ScalarEvolution/trip-count3.ll
@@ -50,7 +50,7 @@ sha_update.exit.exitStub:                         ; preds = %bb3.i
 bb2.i:                                            ; preds = %bb3.i
   %1 = getelementptr %struct.SHA_INFO, %struct.SHA_INFO* %sha_info, i64 0, i32 3
   %2 = bitcast [16 x i32]* %1 to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %2, i8* %buffer_addr.0.i, i64 64, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %2, i8* %buffer_addr.0.i, i64 64, i1 false)
   %3 = getelementptr %struct.SHA_INFO, %struct.SHA_INFO* %sha_info, i64 0, i32 3, i64 0
   %4 = bitcast i32* %3 to i8*
   br label %codeRepl
@@ -74,7 +74,7 @@ bb3.i:                                            ; preds = %byte_reverse.exit.i
 
 declare void @sha_stream_bb3_2E_i_bb1_2E_i_2E_i(i8*) nounwind
 
-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
 
-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/Analysis/TypeBasedAliasAnalysis/functionattrs.ll b/llvm/test/Analysis/TypeBasedAliasAnalysis/functionattrs.ll
index ed091466165..71f606c37f6 100644
--- a/llvm/test/Analysis/TypeBasedAliasAnalysis/functionattrs.ll
+++ b/llvm/test/Analysis/TypeBasedAliasAnalysis/functionattrs.ll
@@ -45,13 +45,13 @@ define void @test1_no(i32* %p) nounwind {
 
 ; CHECK: define void @test2_yes(i8* nocapture %p, i8* nocapture %q, i64 %n) #4 {
 define void @test2_yes(i8* %p, i8* %q, i64 %n) nounwind {
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %p, i8* %q, i64 %n, i32 1, i1 false), !tbaa !1
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %p, i8* %q, i64 %n, i1 false), !tbaa !1
   ret void
 }
 
 ; CHECK: define void @test2_no(i8* nocapture %p, i8* nocapture readonly %q, i64 %n) #3 {
 define void @test2_no(i8* %p, i8* %q, i64 %n) nounwind {
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %p, i8* %q, i64 %n, i32 1, i1 false), !tbaa !2
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %p, i8* %q, i64 %n, i1 false), !tbaa !2
   ret void
 }
 
@@ -70,7 +70,7 @@ define i32 @test3_no(i8* %p) nounwind {
 }
 
 declare void @callee(i32* %p) nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i1) nounwind
 
 ; CHECK: attributes #0 = { norecurse nounwind readnone }
 ; CHECK: attributes #1 = { norecurse nounwind }
diff --git a/llvm/test/Analysis/TypeBasedAliasAnalysis/memcpyopt.ll b/llvm/test/Analysis/TypeBasedAliasAnalysis/memcpyopt.ll
index 64e35788429..ecc737c77e4 100644
--- a/llvm/test/Analysis/TypeBasedAliasAnalysis/memcpyopt.ll
+++ b/llvm/test/Analysis/TypeBasedAliasAnalysis/memcpyopt.ll
@@ -6,17 +6,17 @@ target datalayout = "e-p:64:64:64"
 ; it has a TBAA tag which declares that it is unrelated.
 
 ; CHECK: @foo
-; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %p, i8* %q, i64 16, i32 1, i1 false), !tbaa !0
+; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 %p, i8* align 1 %q, i64 16, i1 false), !tbaa !0
 ; CHECK-NEXT: store i8 2, i8* %s, align 1, !tbaa [[TAGA:!.*]]
 ; CHECK-NEXT: ret void
 define void @foo(i8* nocapture %p, i8* nocapture %q, i8* nocapture %s) nounwind {
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %p, i8* %q, i64 16, i32 1, i1 false), !tbaa !2
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %p, i8* %q, i64 16, i1 false), !tbaa !2
   store i8 2, i8* %s, align 1, !tbaa !1
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %q, i8* %p, i64 16, i32 1, i1 false), !tbaa !2
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %q, i8* %p, i64 16, i1 false), !tbaa !2
   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
 
 ; CHECK: [[TAGA]] = !{[[TYPEA:!.*]], [[TYPEA]], i64 0}
 ; CHECK: [[TYPEA]] = !{!"A", !{{.*}}}