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

25 files changed, 144 insertions, 144 deletions

diff --git a/llvm/test/CodeGen/ARM/2009-03-07-SpillerBug.ll b/llvm/test/CodeGen/ARM/2009-03-07-SpillerBug.ll
index 567400318ee..62a9aa23f29 100644
--- a/llvm/test/CodeGen/ARM/2009-03-07-SpillerBug.ll
+++ b/llvm/test/CodeGen/ARM/2009-03-07-SpillerBug.ll
@@ -59,7 +59,7 @@ bb3:                                              ; preds = %entry
   %34 = fadd double %31, 0.000000e+00
   %35 = fadd double %32, 0.000000e+00
   %36 = bitcast %struct.ggPoint3* %x to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* null, i8* %36, i32 24, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 null, i8* align 4 %36, i32 24, i1 false)
   store double %33, double* null, align 8
   br i1 false, label %_Z20ggRaySphereIntersectRK6ggRay3RK8ggSphereddRd.exit, label %bb5.i.i.i
 
@@ -76,4 +76,4 @@ bb7:                                              ; preds = %entry
   ret i32 0
 }
 
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
diff --git a/llvm/test/CodeGen/ARM/2011-03-10-DAGCombineCrash.ll b/llvm/test/CodeGen/ARM/2011-03-10-DAGCombineCrash.ll
index c447a1f25b6..30a388bb587 100644
--- a/llvm/test/CodeGen/ARM/2011-03-10-DAGCombineCrash.ll
+++ b/llvm/test/CodeGen/ARM/2011-03-10-DAGCombineCrash.ll
@@ -16,7 +16,7 @@ bb:                                               ; preds = %entry
 
 bb1:                                              ; preds = %entry
   %0 = call %struct.ui* @vn_pp_to_ui(i32* undef) nounwind
-  call void @llvm.memset.p0i8.i32(i8* undef, i8 0, i32 40, i32 4, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 4 undef, i8 0, i32 40, i1 false)
   %1 = getelementptr inbounds %struct.ui, %struct.ui* %0, i32 0, i32 0
   store %struct.mo* undef, %struct.mo** %1, align 4
   %2 = getelementptr inbounds %struct.ui, %struct.ui* %0, i32 0, i32 5
@@ -40,7 +40,7 @@ bb6:                                              ; preds = %bb3
 
 declare %struct.ui* @vn_pp_to_ui(i32*)
 
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
 
 declare i32 @mo_create_nnm(%struct.mo*, i64, i32**)
 
diff --git a/llvm/test/CodeGen/ARM/2011-10-26-memset-inline.ll b/llvm/test/CodeGen/ARM/2011-10-26-memset-inline.ll
index c3b7c4ea86c..8d6ce34c26d 100644
--- a/llvm/test/CodeGen/ARM/2011-10-26-memset-inline.ll
+++ b/llvm/test/CodeGen/ARM/2011-10-26-memset-inline.ll
@@ -14,8 +14,8 @@ target triple = "thumbv7-apple-ios5.0.0"
 ; CHECK-UNALIGNED:    str
 define void @foo(i8* nocapture %c) nounwind optsize {
 entry:
-  call void @llvm.memset.p0i8.i64(i8* %c, i8 -1, i64 5, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %c, i8 -1, i64 5, i1 false)
   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/CodeGen/ARM/2011-10-26-memset-with-neon.ll b/llvm/test/CodeGen/ARM/2011-10-26-memset-with-neon.ll
index c8e08c22ab1..7024a653b6c 100644
--- a/llvm/test/CodeGen/ARM/2011-10-26-memset-with-neon.ll
+++ b/llvm/test/CodeGen/ARM/2011-10-26-memset-with-neon.ll
@@ -5,8 +5,8 @@
 ; CHECK: vst1.64
 define void @f_0_40(i8* nocapture %c) nounwind optsize {
 entry:
-  call void @llvm.memset.p0i8.i64(i8* %c, i8 0, i64 40, i32 16, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 16 %c, i8 0, i64 40, i1 false)
   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/CodeGen/ARM/2012-04-24-SplitEHCriticalEdge.ll b/llvm/test/CodeGen/ARM/2012-04-24-SplitEHCriticalEdge.ll
index ce0dcc70952..ef33b2f5018 100644
--- a/llvm/test/CodeGen/ARM/2012-04-24-SplitEHCriticalEdge.ll
+++ b/llvm/test/CodeGen/ARM/2012-04-24-SplitEHCriticalEdge.ll
@@ -19,7 +19,7 @@ declare i32 @llvm.eh.typeid.for(i8*) nounwind readnone
 
 declare i8* @__cxa_begin_catch(i8*)
 
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
 
 declare void @__cxa_end_catch()
 
diff --git a/llvm/test/CodeGen/ARM/Windows/memset.ll b/llvm/test/CodeGen/ARM/Windows/memset.ll
index 500e25e259c..c9b22f47a15 100644
--- a/llvm/test/CodeGen/ARM/Windows/memset.ll
+++ b/llvm/test/CodeGen/ARM/Windows/memset.ll
@@ -2,11 +2,11 @@
 
 @source = common global [512 x i8] zeroinitializer, align 4
 
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
 
 define void @function() {
 entry:
-  call void @llvm.memset.p0i8.i32(i8* bitcast ([512 x i8]* @source to i8*), i8 0, i32 512, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* bitcast ([512 x i8]* @source to i8*), i8 0, i32 512, i1 false)
   unreachable
 }
 
diff --git a/llvm/test/CodeGen/ARM/Windows/no-aeabi.ll b/llvm/test/CodeGen/ARM/Windows/no-aeabi.ll
index a4103b0a676..a5f7fc8daf6 100644
--- a/llvm/test/CodeGen/ARM/Windows/no-aeabi.ll
+++ b/llvm/test/CodeGen/ARM/Windows/no-aeabi.ll
@@ -1,14 +1,14 @@
 ; RUN: llc -mtriple=thumbv7-windows-itanium -mcpu=cortex-a9 -verify-machineinstrs -o - %s | FileCheck %s
 
-declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
 
 @source = common global [512 x i8] zeroinitializer, align 4
 @target = common global [512 x i8] zeroinitializer, align 4
 
 define void @move() nounwind {
 entry:
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* bitcast ([512 x i8]* @target to i8*), i8* bitcast ([512 x i8]* @source to i8*), i32 512, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* bitcast ([512 x i8]* @target to i8*), i8* bitcast ([512 x i8]* @source to i8*), i32 512, i1 false)
   unreachable
 }
 
@@ -16,7 +16,7 @@ entry:
 
 define void @copy() nounwind {
 entry:
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* bitcast ([512 x i8]* @target to i8*), i8* bitcast ([512 x i8]* @source to i8*), i32 512, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* bitcast ([512 x i8]* @target to i8*), i8* bitcast ([512 x i8]* @source to i8*), i32 512, i1 false)
   unreachable
 }
 
diff --git a/llvm/test/CodeGen/ARM/arm-eabi.ll b/llvm/test/CodeGen/ARM/arm-eabi.ll
index 898055dd109..c2f364ab92b 100644
--- a/llvm/test/CodeGen/ARM/arm-eabi.ll
+++ b/llvm/test/CodeGen/ARM/arm-eabi.ll
@@ -39,7 +39,7 @@ define void @foo(i32* %t) {
   %4 = bitcast %struct.my_s* %3 to i8*
   ; CHECK-EABI: bl __aeabi_memcpy
   ; CHECK-GNUEABI: bl memcpy
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %4, i8* inttoptr (i32 1 to i8*), i32 72, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %4, i8* align 4 inttoptr (i32 1 to i8*), i32 72, i1 false)
   ret void
 }
 
@@ -50,22 +50,22 @@ entry:
   ; memmove
   ; CHECK-EABI: bl __aeabi_memmove
   ; CHECK-GNUEABI: bl memmove
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i1 false)
 
   ; memcpy
   ; CHECK-EABI: bl __aeabi_memcpy
   ; CHECK-GNUEABI: bl memcpy
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i1 false)
 
   ; memset
   ; CHECK-EABI: mov r2, #1
   ; CHECK-EABI: bl __aeabi_memset
   ; CHECK-GNUEABI: mov r1, #1
   ; CHECK-GNUEABI: bl memset
-  call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i1 false)
   ret void
 }
 
-declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, 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, i32, i1) nounwind
+declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, 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/CodeGen/ARM/constantpool-promote-ldrh.ll b/llvm/test/CodeGen/ARM/constantpool-promote-ldrh.ll
index 59970495874..0767d729a0a 100644
--- a/llvm/test/CodeGen/ARM/constantpool-promote-ldrh.ll
+++ b/llvm/test/CodeGen/ARM/constantpool-promote-ldrh.ll
@@ -12,10 +12,10 @@ target triple = "thumbv6m-arm-linux-gnueabi"
 ; CHECK: ldrh r{{[0-9]+}}, {{\[}}[[base]]]
 define hidden i32 @fn1() #0 {
 entry:
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* bitcast ([4 x i16]* @fn1.a to i8*), i32 8, i32 2, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 undef, i8* align 2 bitcast ([4 x i16]* @fn1.a to i8*), i32 8, i1 false)
   ret i32 undef
 }
 
 ; Function Attrs: argmemonly nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i32, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1)
 attributes #0 = { "target-features"="+strict-align" }
diff --git a/llvm/test/CodeGen/ARM/constantpool-promote.ll b/llvm/test/CodeGen/ARM/constantpool-promote.ll
index d5361f33a98..ccd86257dd3 100644
--- a/llvm/test/CodeGen/ARM/constantpool-promote.ll
+++ b/llvm/test/CodeGen/ARM/constantpool-promote.ll
@@ -120,7 +120,7 @@ define void @fn1() "target-features"="+strict-align"  {
 entry:
   %a = alloca [4 x i16], align 2
   %0 = bitcast [4 x i16]* %a to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* bitcast ([4 x i16]* @fn1.a to i8*), i32 8, i32 2, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %0, i8* align 2 bitcast ([4 x i16]* @fn1.a to i8*), i32 8, i1 false)
   ret void
 }
 
@@ -128,7 +128,7 @@ define void @fn2() "target-features"="+strict-align"  {
 entry:
   %a = alloca [8 x i8], align 2
   %0 = bitcast [8 x i8]* %a to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* bitcast ([8 x i8]* @fn2.a to i8*), i32 16, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* bitcast ([8 x i8]* @fn2.a to i8*), i32 16, i1 false)
   ret void
 }
 
@@ -156,7 +156,7 @@ define void @pr32130() #0 {
 ; CHECK-V7: [[x]]:
 ; CHECK-V7: .asciz "s\000\000"
 define void @test10(i8* %a) local_unnamed_addr #0 {
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %a, i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str, i32 0, i32 0), i32 1, i32 1, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* align 1 %a, i8* align 1 getelementptr inbounds ([2 x i8], [2 x i8]* @.str, i32 0, i32 0), i32 1, i1 false)
   ret void
 }
 
@@ -174,16 +174,16 @@ define void @test10(i8* %a) local_unnamed_addr #0 {
 ; CHECK-V7ARM: .short 3
 ; CHECK-V7ARM: .short 4
 define void @test11(i16* %a) local_unnamed_addr #0 {
-  call void @llvm.memmove.p0i16.p0i16.i32(i16* %a, i16* getelementptr inbounds ([2 x i16], [2 x i16]* @.arr1, i32 0, i32 0), i32 2, i32 2, i1 false)
+  call void @llvm.memmove.p0i16.p0i16.i32(i16* align 2 %a, i16* align 2 getelementptr inbounds ([2 x i16], [2 x i16]* @.arr1, i32 0, i32 0), i32 2, i1 false)
   ret void
 }
 
 
 declare void @b(i8*) #1
 declare void @c(i16*) #1
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i32, i1)
-declare void @llvm.memmove.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) local_unnamed_addr
-declare void @llvm.memmove.p0i16.p0i16.i32(i16*, i16*, i32, i32, i1) local_unnamed_addr
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1)
+declare void @llvm.memmove.p0i8.p0i8.i32(i8*, i8*, i32, i1) local_unnamed_addr
+declare void @llvm.memmove.p0i16.p0i16.i32(i16*, i16*, i32, i1) local_unnamed_addr
 
 attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
 attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
diff --git a/llvm/test/CodeGen/ARM/crash-O0.ll b/llvm/test/CodeGen/ARM/crash-O0.ll
index f92af999be5..bfbab8a9933 100644
--- a/llvm/test/CodeGen/ARM/crash-O0.ll
+++ b/llvm/test/CodeGen/ARM/crash-O0.ll
@@ -12,7 +12,7 @@ entry:
 }
 
 @.str523 = private constant [256 x i8] c"<Unknown>\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00", align 4 ; <[256 x i8]*> [#uses=1]
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
 
 ; This function uses the scavenger for an ADDri instruction.
 ; ARMBaseRegisterInfo::estimateRSStackSizeLimit must return a 255 limit.
@@ -21,8 +21,8 @@ entry:
   %letter = alloca i8                             ; <i8*> [#uses=0]
   %prodvers = alloca [256 x i8]                   ; <[256 x i8]*> [#uses=1]
   %buildver = alloca [256 x i8]                   ; <[256 x i8]*> [#uses=0]
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* getelementptr inbounds ([256 x i8], [256 x i8]* @.str523, i32 0, i32 0), i32 256, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 undef, i8* align 1 getelementptr inbounds ([256 x i8], [256 x i8]* @.str523, i32 0, i32 0), i32 256, i1 false)
   %prodvers2 = bitcast [256 x i8]* %prodvers to i8* ; <i8*> [#uses=1]
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %prodvers2, i8* getelementptr inbounds ([256 x i8], [256 x i8]* @.str523, i32 0, i32 0), i32 256, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %prodvers2, i8* align 1 getelementptr inbounds ([256 x i8], [256 x i8]* @.str523, i32 0, i32 0), i32 256, i1 false)
   unreachable
 }
diff --git a/llvm/test/CodeGen/ARM/debug-info-blocks.ll b/llvm/test/CodeGen/ARM/debug-info-blocks.ll
index ba265cc3547..cc1a45f23da 100644
--- a/llvm/test/CodeGen/ARM/debug-info-blocks.ll
+++ b/llvm/test/CodeGen/ARM/debug-info-blocks.ll
@@ -35,7 +35,7 @@ declare i8* @objc_msgSend(i8*, i8*, ...)
 
 declare void @llvm.dbg.value(metadata, metadata, metadata) nounwind readnone
 
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
 
 define hidden void @foobar_func_block_invoke_0(i8* %.block_descriptor, %0* %loadedMydata, [4 x i32] %bounds.coerce0, [4 x i32] %data.coerce0) ssp !dbg !23 {
   %1 = alloca %0*, align 4
@@ -77,7 +77,7 @@ define hidden void @foobar_func_block_invoke_0(i8* %.block_descriptor, %0* %load
   %24 = bitcast i8* %23 to %struct.CR*, !dbg !143
   %25 = bitcast %struct.CR* %24 to i8*, !dbg !143
   %26 = bitcast %struct.CR* %data to i8*, !dbg !143
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %25, i8* %26, i32 16, i32 4, i1 false), !dbg !143
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %25, i8* align 4 %26, i32 16, i1 false), !dbg !143
   %27 = getelementptr inbounds %2, %2* %6, i32 0, i32 6, !dbg !144
   %28 = load %3*, %3** %27, align 4, !dbg !144
   %29 = load i32, i32* @"OBJC_IVAR_$_MyWork._bounds", !dbg !144
@@ -86,7 +86,7 @@ define hidden void @foobar_func_block_invoke_0(i8* %.block_descriptor, %0* %load
   %32 = bitcast i8* %31 to %struct.CR*, !dbg !144
   %33 = bitcast %struct.CR* %32 to i8*, !dbg !144
   %34 = bitcast %struct.CR* %bounds to i8*, !dbg !144
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %33, i8* %34, i32 16, i32 4, i1 false), !dbg !144
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %33, i8* align 4 %34, i32 16, i1 false), !dbg !144
   %35 = getelementptr inbounds %2, %2* %6, i32 0, i32 6, !dbg !145
   %36 = load %3*, %3** %35, align 4, !dbg !145
   %37 = getelementptr inbounds %2, %2* %6, i32 0, i32 5, !dbg !145
diff --git a/llvm/test/CodeGen/ARM/dyn-stackalloc.ll b/llvm/test/CodeGen/ARM/dyn-stackalloc.ll
index 5b963fd64de..b653acbd6a7 100644
--- a/llvm/test/CodeGen/ARM/dyn-stackalloc.ll
+++ b/llvm/test/CodeGen/ARM/dyn-stackalloc.ll
@@ -51,7 +51,7 @@ define void @t2(%struct.comment* %vc, i8* %tag, i8* %contents) {
   %tmp9 = call i8* @strcpy(i8* %tmp6, i8* %tag)
   %tmp6.len = call i32 @strlen(i8* %tmp6)
   %tmp6.indexed = getelementptr i8, i8* %tmp6, i32 %tmp6.len
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp6.indexed, i8* getelementptr inbounds ([2 x i8], [2 x i8]* @str215, i32 0, i32 0), i32 2, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %tmp6.indexed, i8* align 1 getelementptr inbounds ([2 x i8], [2 x i8]* @str215, i32 0, i32 0), i32 2, i1 false)
   %tmp15 = call i8* @strcat(i8* %tmp6, i8* %contents)
   call fastcc void @comment_add(%struct.comment* %vc, i8* %tmp6)
   ret void
@@ -65,4 +65,4 @@ declare fastcc void @comment_add(%struct.comment*, i8*)
 
 declare i8* @strcpy(i8*, i8*)
 
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
diff --git a/llvm/test/CodeGen/ARM/fast-isel-intrinsic.ll b/llvm/test/CodeGen/ARM/fast-isel-intrinsic.ll
index 277461aa566..8d9c27b6f22 100644
--- a/llvm/test/CodeGen/ARM/fast-isel-intrinsic.ll
+++ b/llvm/test/CodeGen/ARM/fast-isel-intrinsic.ll
@@ -44,11 +44,11 @@ define void @t1() nounwind ssp {
 ; THUMB-LONG: movt r3, :upper16:L_memset$non_lazy_ptr
 ; THUMB-LONG: ldr r3, [r3]
 ; THUMB-LONG: blx r3
-  call void @llvm.memset.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @message1, i32 0, i32 5), i8 64, i32 10, i32 4, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 4 getelementptr inbounds ([60 x i8], [60 x i8]* @message1, i32 0, i32 5), i8 64, i32 10, i1 false)
   ret void
 }
 
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
 
 define void @t2() nounwind ssp {
 ; ARM-LABEL: t2:
@@ -93,11 +93,11 @@ define void @t2() nounwind ssp {
 ; THUMB-LONG: movt r3, :upper16:L_memcpy$non_lazy_ptr
 ; THUMB-LONG: ldr r3, [r3]
 ; THUMB-LONG: blx r3
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 17, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* align 4 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 17, i1 false)
   ret void
 }
 
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
 
 define void @t3() nounwind ssp {
 ; ARM-LABEL: t3:
@@ -141,7 +141,7 @@ define void @t3() nounwind ssp {
 ; THUMB-LONG: movt r3, :upper16:L_memmove$non_lazy_ptr
 ; THUMB-LONG: ldr r3, [r3]
 ; THUMB-LONG: blx r3
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 10, i32 1, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 10, i1 false)
   ret void
 }
 
@@ -173,11 +173,11 @@ define void @t4() nounwind ssp {
 ; THUMB: ldrh r1, [r0, #24]
 ; THUMB: strh r1, [r0, #12]
 ; THUMB: bx lr
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 10, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* align 4 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 10, i1 false)
   ret void
 }
 
-declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
 
 define void @t5() nounwind ssp {
 ; ARM-LABEL: t5:
@@ -215,7 +215,7 @@ define void @t5() nounwind ssp {
 ; THUMB: ldrh r1, [r0, #24]
 ; THUMB: strh r1, [r0, #12]
 ; THUMB: bx lr
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 10, i32 2, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* align 2 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 10, i1 false)
   ret void
 }
 
@@ -275,14 +275,14 @@ define void @t6() nounwind ssp {
 ; THUMB: ldrb r1, [r0, #25]
 ; THUMB: strb r1, [r0, #13]
 ; THUMB: bx lr
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 10, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 10, i1 false)
   ret void
 }
 
 ; rdar://13202135
 define void @t7() nounwind ssp {
 ; Just make sure this doesn't assert when we have an odd length and an alignment of 2.
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 3, i32 2, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 4), i8* align 2 getelementptr inbounds ([60 x i8], [60 x i8]* @temp, i32 0, i32 16), i32 3, i1 false)
   ret void
 }
 
diff --git a/llvm/test/CodeGen/ARM/interval-update-remat.ll b/llvm/test/CodeGen/ARM/interval-update-remat.ll
index 524e8a0aa49..216f7e915a8 100644
--- a/llvm/test/CodeGen/ARM/interval-update-remat.ll
+++ b/llvm/test/CodeGen/ARM/interval-update-remat.ll
@@ -85,7 +85,7 @@ _ZN7MessageD1Ev.exit33:                           ; preds = %delete.notnull.i.i.
 if.end:                                           ; preds = %_ZN7MessageD1Ev.exit33, %entry
   %message_.i.i = getelementptr inbounds %class.AssertionResult.24.249.299.1324.2349, %class.AssertionResult.24.249.299.1324.2349* %gtest_ar, i32 0, i32 1
   %call.i.i.i = call %class.scoped_ptr.23.248.298.1323.2348* @_ZN10scoped_ptrI25Trans_NS___1_basic_stringIciiEED2Ev(%class.scoped_ptr.23.248.298.1323.2348* %message_.i.i)
-  call void @llvm.memset.p0i8.i32(i8* null, i8 0, i32 12, i32 4, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 4 null, i8 0, i32 12, i1 false)
   call void @_ZN25Trans_NS___1_basic_stringIciiE5m_fn2Ev(%class.Trans_NS___1_basic_string.18.243.293.1318.2343* nonnull %ref.tmp)
   call void @_Z19CreateSOCKSv5Paramsv(%class.scoped_refptr.19.244.294.1319.2344* nonnull sret %agg.tmp16)
   %callback_.i = getelementptr inbounds %class.TestCompletionCallback.9.234.284.1309.2334, %class.TestCompletionCallback.9.234.284.1309.2334* %callback, i32 0, i32 1
@@ -137,7 +137,7 @@ declare void @_ZN18ClientSocketHandle5m_fn3IPiEEvRK25Trans_NS___1_basic_stringIc
 declare void @_Z19CreateSOCKSv5Paramsv(%class.scoped_refptr.19.244.294.1319.2344* sret)
 
 ; Function Attrs: argmemonly nounwind
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) #0
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) #0
 
 declare %class.BoundNetLog.20.245.295.1320.2345* @_ZN11BoundNetLogD1Ev(%class.BoundNetLog.20.245.295.1320.2345* returned) unnamed_addr
 
diff --git a/llvm/test/CodeGen/ARM/ldm-stm-base-materialization.ll b/llvm/test/CodeGen/ARM/ldm-stm-base-materialization.ll
index a3231f95f47..755619e8b3e 100644
--- a/llvm/test/CodeGen/ARM/ldm-stm-base-materialization.ll
+++ b/llvm/test/CodeGen/ARM/ldm-stm-base-materialization.ll
@@ -22,7 +22,7 @@ entry:
   %2 = load i32*, i32** @b, align 4
   %arrayidx1 = getelementptr inbounds i32, i32* %2, i32 1
   %3 = bitcast i32* %arrayidx1 to i8*
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* %3, i32 24, i32 4, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %1, i8* align 4 %3, i32 24, i1 false)
   ret void
 }
 
@@ -43,7 +43,7 @@ entry:
   %2 = load i32*, i32** @b, align 4
   %arrayidx1 = getelementptr inbounds i32, i32* %2, i32 1
   %3 = bitcast i32* %arrayidx1 to i8*
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* %3, i32 28, i32 4, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %1, i8* align 4 %3, i32 28, i1 false)
   ret void
 }
 
@@ -64,7 +64,7 @@ entry:
   %2 = load i32*, i32** @b, align 4
   %arrayidx1 = getelementptr inbounds i32, i32* %2, i32 1
   %3 = bitcast i32* %arrayidx1 to i8*
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* %3, i32 32, i32 4, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %1, i8* align 4 %3, i32 32, i1 false)
   ret void
 }
 
@@ -85,9 +85,9 @@ entry:
   %2 = load i32*, i32** @b, align 4
   %arrayidx1 = getelementptr inbounds i32, i32* %2, i32 1
   %3 = bitcast i32* %arrayidx1 to i8*
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* %3, i32 36, i32 4, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %1, i8* align 4 %3, i32 36, i1 false)
   ret void
 }
 
 ; Function Attrs: nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #1
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) #1
diff --git a/llvm/test/CodeGen/ARM/machine-cse-cmp.ll b/llvm/test/CodeGen/ARM/machine-cse-cmp.ll
index 611cba6ed1f..10e56a346a2 100644
--- a/llvm/test/CodeGen/ARM/machine-cse-cmp.ll
+++ b/llvm/test/CodeGen/ARM/machine-cse-cmp.ll
@@ -37,14 +37,14 @@ entry:
 for.body.lr.ph:                                   ; preds = %entry
   %1 = icmp sgt i32 %0, 1
   %smax = select i1 %1, i32 %0, i32 1
-  call void @llvm.memset.p0i8.i32(i8* getelementptr inbounds ([250 x i8], [250 x i8]* @bar, i32 0, i32 0), i8 0, i32 %smax, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* getelementptr inbounds ([250 x i8], [250 x i8]* @bar, i32 0, i32 0), i8 0, i32 %smax, i1 false)
   unreachable
 
 for.cond1.preheader:                              ; preds = %entry
   ret void
 }
 
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
 
 ; rdar://12462006
 define i8* @f3(i8* %base, i32* nocapture %offset, i32 %size) nounwind {
diff --git a/llvm/test/CodeGen/ARM/memcpy-inline.ll b/llvm/test/CodeGen/ARM/memcpy-inline.ll
index b447497b270..1dccf0b9905 100644
--- a/llvm/test/CodeGen/ARM/memcpy-inline.ll
+++ b/llvm/test/CodeGen/ARM/memcpy-inline.ll
@@ -23,7 +23,7 @@ entry:
 ; CHECK-T1: strb [[TREG1]],
 ; CHECK-T1: ldrh [[TREG2:r[0-9]]],
 ; CHECK-T1: strh [[TREG2]]
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds (%struct.x, %struct.x* @dst, i32 0, i32 0), i8* getelementptr inbounds (%struct.x, %struct.x* @src, i32 0, i32 0), i32 11, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 getelementptr inbounds (%struct.x, %struct.x* @dst, i32 0, i32 0), i8* align 8 getelementptr inbounds (%struct.x, %struct.x* @src, i32 0, i32 0), i32 11, i1 false)
   ret i32 0
 }
 
@@ -37,7 +37,7 @@ entry:
 ; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
 ; CHECK-T1-LABEL: t1:
 ; CHECK-T1: bl _memcpy
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([31 x i8], [31 x i8]* @.str1, i64 0, i64 0), i64 31, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([31 x i8], [31 x i8]* @.str1, i64 0, i64 0), i64 31, i1 false)
   ret void
 }
 
@@ -55,7 +55,7 @@ entry:
 ; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r3]
 ; CHECK-T1-LABEL: t2:
 ; CHECK-T1: bl _memcpy
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([36 x i8], [36 x i8]* @.str2, i64 0, i64 0), i64 36, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([36 x i8], [36 x i8]* @.str2, i64 0, i64 0), i64 36, i1 false)
   ret void
 }
 
@@ -68,7 +68,7 @@ entry:
 ; CHECK: vst1.8 {d{{[0-9]+}}}, [r0]
 ; CHECK-T1-LABEL: t3:
 ; CHECK-T1: bl _memcpy
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([24 x i8], [24 x i8]* @.str3, i64 0, i64 0), i64 24, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([24 x i8], [24 x i8]* @.str3, i64 0, i64 0), i64 24, i1 false)
   ret void
 }
 
@@ -80,7 +80,7 @@ entry:
 ; CHECK: strh [[REG5:r[0-9]+]], [r0]
 ; CHECK-T1-LABEL: t4:
 ; CHECK-T1: bl _memcpy
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([18 x i8], [18 x i8]* @.str4, i64 0, i64 0), i64 18, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([18 x i8], [18 x i8]* @.str4, i64 0, i64 0), i64 18, i1 false)
   ret void
 }
 
@@ -96,7 +96,7 @@ entry:
 ; CHECK: str [[REG7]]
 ; CHECK-T1-LABEL: t5:
 ; CHECK-T1: bl _memcpy
-  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @.str5, i64 0, i64 0), i64 7, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %C, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @.str5, i64 0, i64 0), i64 7, i1 false)
   ret void
 }
 
@@ -114,7 +114,7 @@ entry:
 ; CHECK-T1: strh [[TREG5]],
 ; CHECK-T1: ldr [[TREG6:r[0-9]]],
 ; CHECK-T1: str [[TREG6]]
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds ([512 x i8], [512 x i8]* @spool.splbuf, i64 0, i64 0), i8* getelementptr inbounds ([14 x i8], [14 x i8]* @.str6, i64 0, i64 0), i64 14, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds ([512 x i8], [512 x i8]* @spool.splbuf, i64 0, i64 0), i8* getelementptr inbounds ([14 x i8], [14 x i8]* @.str6, i64 0, i64 0), i64 14, i1 false)
   ret void
 }
 
@@ -130,9 +130,9 @@ entry:
 ; CHECK-T1: str
   %0 = bitcast %struct.Foo* %a to i8*
   %1 = bitcast %struct.Foo* %b to i8*
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* %1, i32 16, i32 4, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %0, i8* align 4 %1, i32 16, i1 false)
   ret void
 }
 
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
diff --git a/llvm/test/CodeGen/ARM/memcpy-ldm-stm.ll b/llvm/test/CodeGen/ARM/memcpy-ldm-stm.ll
index 2ebe7ed5b14..314f559e357 100644
--- a/llvm/test/CodeGen/ARM/memcpy-ldm-stm.ll
+++ b/llvm/test/CodeGen/ARM/memcpy-ldm-stm.ll
@@ -24,7 +24,7 @@ entry:
 ; Think of the monstrosity '{{\[}}[[LB]]]' as '[ [[LB]] ]' without the spaces.
 ; CHECK-NEXT: ldrb{{(\.w)?}} {{.*}}, {{\[}}[[LB]]]
 ; CHECK-NEXT: strb{{(\.w)?}} {{.*}}, {{\[}}[[SB]]]
-    tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* bitcast ([64 x i32]* @s to i8*), i8* bitcast ([64 x i32]* @d to i8*), i32 17, i32 4, i1 false)
+    tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 bitcast ([64 x i32]* @s to i8*), i8* align 4 bitcast ([64 x i32]* @d to i8*), i32 17, i1 false)
     ret void
 }
 
@@ -42,7 +42,7 @@ entry:
 ; CHECK-NEXT: ldrb{{(\.w)?}} {{.*}}, {{\[}}[[LB]], #2]
 ; CHECK-NEXT: strb{{(\.w)?}} {{.*}}, {{\[}}[[SB]], #2]
 ; CHECK-NEXT: strh{{(\.w)?}} {{.*}}, {{\[}}[[SB]]]
-    tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* bitcast ([64 x i32]* @s to i8*), i8* bitcast ([64 x i32]* @d to i8*), i32 15, i32 4, i1 false)
+    tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 bitcast ([64 x i32]* @s to i8*), i8* align 4 bitcast ([64 x i32]* @d to i8*), i32 15, i1 false)
     ret void
 }
 
@@ -54,13 +54,13 @@ entry:
 
 define void @t3() {
   call void @llvm.memcpy.p0i8.p0i8.i32(
-     i8* getelementptr inbounds (%struct.T, %struct.T* @copy, i32 0, i32 0),
-     i8* getelementptr inbounds (%struct.T, %struct.T* @etest, i32 0, i32 0),
-     i32 24, i32 8, i1 false)
+     i8* align 8 getelementptr inbounds (%struct.T, %struct.T* @copy, i32 0, i32 0),
+     i8* align 8 getelementptr inbounds (%struct.T, %struct.T* @etest, i32 0, i32 0),
+     i32 24, i1 false)
   call void @llvm.memcpy.p0i8.p0i8.i32(
-     i8* getelementptr inbounds (%struct.T, %struct.T* @copy, i32 0, i32 0),
-     i8* getelementptr inbounds (%struct.T, %struct.T* @etest, i32 0, i32 0),
-     i32 24, i32 8, i1 false)
+     i8* align 8 getelementptr inbounds (%struct.T, %struct.T* @copy, i32 0, i32 0),
+     i8* align 8 getelementptr inbounds (%struct.T, %struct.T* @etest, i32 0, i32 0),
+     i32 24, i1 false)
   ret void
 }
 
@@ -70,7 +70,7 @@ define void @t3() {
 define void @test3(%struct.S* %d, %struct.S* %s) #0 {
   %1 = bitcast %struct.S* %d to i8*
   %2 = bitcast %struct.S* %s to i8*
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* %2, i32 48, i32 4, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %1, i8* align 4 %2, i32 48, i1 false)
 ; 3 ldm/stm pairs in v6; 2 in v7
 ; CHECK: ldm{{(\.w)?}} {{[rl0-9]+!?}}, [[REGLIST1:{.*}]]
 ; CHECK: stm{{(\.w)?}} {{[rl0-9]+!?}}, [[REGLIST1]]
@@ -91,4 +91,4 @@ declare void @g(i32*)
 attributes #0 = { "no-frame-pointer-elim"="true" }
 
 ; Function Attrs: nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #1
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) #1
diff --git a/llvm/test/CodeGen/ARM/memcpy-no-inline.ll b/llvm/test/CodeGen/ARM/memcpy-no-inline.ll
index 126546095e1..7aaac19eee3 100644
--- a/llvm/test/CodeGen/ARM/memcpy-no-inline.ll
+++ b/llvm/test/CodeGen/ARM/memcpy-no-inline.ll
@@ -14,7 +14,7 @@ entry:
 ; CHECK-NOT:  ldm
   %mystring = alloca [31 x i8], align 1
   %0 = getelementptr inbounds [31 x i8], [31 x i8]* %mystring, i32 0, i32 0
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* getelementptr inbounds ([31 x i8], [31 x i8]* @.str, i32 0, i32 0), i32 31, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %0, i8* align 1 getelementptr inbounds ([31 x i8], [31 x i8]* @.str, i32 0, i32 0), i32 31, i1 false)
   ret void
 }
 
@@ -24,10 +24,10 @@ entry:
 ; CHECK-NOT:   __aeabi_memcpy
   %mystring = alloca [31 x i8], align 1
   %0 = getelementptr inbounds [31 x i8], [31 x i8]* %mystring, i32 0, i32 0
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* getelementptr inbounds ([21 x i8], [21 x i8]* @.str.1, i32 0, i32 0), i32 21, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %0, i8* align 1 getelementptr inbounds ([21 x i8], [21 x i8]* @.str.1, i32 0, i32 0), i32 21, i1 false)
   ret void
 }
 
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #1
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) #1
 
 attributes #0 = { minsize noinline nounwind optsize }
diff --git a/llvm/test/CodeGen/ARM/memfunc.ll b/llvm/test/CodeGen/ARM/memfunc.ll
index ed6746290b7..882091b67f0 100644
--- a/llvm/test/CodeGen/ARM/memfunc.ll
+++ b/llvm/test/CodeGen/ARM/memfunc.ll
@@ -16,13 +16,13 @@ entry:
   ; CHECK-DARWIN: bl _memmove
   ; CHECK-EABI: bl __aeabi_memmove
   ; CHECK-GNUEABI: bl memmove
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i1 false)
 
   ; CHECK-IOS: bl _memcpy
   ; CHECK-DARWIN: bl _memcpy
   ; CHECK-EABI: bl __aeabi_memcpy
   ; CHECK-GNUEABI: bl memcpy
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i1 false)
 
   ; EABI memset swaps arguments
   ; CHECK-IOS: mov r1, #1
@@ -33,7 +33,7 @@ entry:
   ; CHECK-EABI: bl __aeabi_memset
   ; CHECK-GNUEABI: mov r1, #1
   ; CHECK-GNUEABI: bl memset
-  call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i1 false)
 
   ; EABI uses memclr if value set to 0
   ; CHECK-IOS: mov r1, #0
@@ -42,7 +42,7 @@ entry:
   ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: bl __aeabi_memclr
   ; CHECK-GNUEABI: bl memset
-  call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i1 false)
 
   ; EABI uses aligned function variants if possible
 
@@ -50,49 +50,49 @@ entry:
   ; CHECK-DARWIN: bl _memmove
   ; CHECK-EABI: bl __aeabi_memmove4
   ; CHECK-GNUEABI: bl memmove
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 4, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 500, i1 false)
 
   ; CHECK-IOS: bl _memcpy
   ; CHECK-DARWIN: bl _memcpy
   ; CHECK-EABI: bl __aeabi_memcpy4
   ; CHECK-GNUEABI: bl memcpy
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 500, i1 false)
 
   ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: bl __aeabi_memset4
   ; CHECK-GNUEABI: bl memset
-  call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 4, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 4 %dest, i8 1, i32 500, i1 false)
 
   ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: bl __aeabi_memclr4
   ; CHECK-GNUEABI: bl memset
-  call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i32 4, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 4 %dest, i8 0, i32 500, i1 false)
 
   ; CHECK-IOS: bl _memmove
   ; CHECK-DARWIN: bl _memmove
   ; CHECK-EABI: bl __aeabi_memmove8
   ; CHECK-GNUEABI: bl memmove
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false)
 
   ; CHECK-IOS: bl _memcpy
   ; CHECK-DARWIN: bl _memcpy
   ; CHECK-EABI: bl __aeabi_memcpy8
   ; CHECK-GNUEABI: bl memcpy
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false)
 
   ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: bl __aeabi_memset8
   ; CHECK-GNUEABI: bl memset
-  call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 8 %dest, i8 1, i32 500, i1 false)
 
   ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: bl __aeabi_memclr8
   ; CHECK-GNUEABI: bl memset
-  call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 8 %dest, i8 0, i32 500, i1 false)
 
   unreachable
 }
@@ -113,7 +113,7 @@ entry:
   ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [9 x i8], align 1
   %0 = bitcast [9 x i8]* %arr0 to i8*
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
 
   ; CHECK: add r1, sp, #16
   ; CHECK-IOS: bl _memcpy
@@ -122,7 +122,7 @@ entry:
   ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [9 x i8], align 1
   %1 = bitcast [9 x i8]* %arr1 to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
 
   ; CHECK-IOS: mov r0, sp
   ; CHECK-IOS: mov r1, #1
@@ -138,7 +138,7 @@ entry:
   ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [9 x i8], align 1
   %2 = bitcast [9 x i8]* %arr2 to i8*
-  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
 
   unreachable
 }
@@ -155,7 +155,7 @@ entry:
   ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [7 x i8], align 1
   %0 = bitcast [7 x i8]* %arr0 to i8*
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r1, sp, #10|sub(.w)? r1, r(7|11), #22}}
   ; CHECK-IOS: bl _memcpy
@@ -164,7 +164,7 @@ entry:
   ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [7 x i8], align 1
   %1 = bitcast [7 x i8]* %arr1 to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r0, sp, #3|sub(.w)? r0, r(7|11), #29}}
   ; CHECK-IOS: mov r1, #1
@@ -177,7 +177,7 @@ entry:
   ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [7 x i8], align 1
   %2 = bitcast [7 x i8]* %arr2 to i8*
-  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
 
   unreachable
 }
@@ -194,7 +194,7 @@ entry:
   ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [9 x i8], align 1
   %0 = getelementptr inbounds [9 x i8], [9 x i8]* %arr0, i32 0, i32 4
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w) r., r(7|11), #26}}
   ; CHECK-IOS: bl _memcpy
@@ -203,7 +203,7 @@ entry:
   ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [9 x i8], align 1
   %1 = getelementptr inbounds [9 x i8], [9 x i8]* %arr1, i32 0, i32 4
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w) r., r(7|11), #35}}
   ; CHECK-IOS: mov r1, #1
@@ -216,7 +216,7 @@ entry:
   ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [9 x i8], align 1
   %2 = getelementptr inbounds [9 x i8], [9 x i8]* %arr2, i32 0, i32 4
-  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
 
   unreachable
 }
@@ -233,7 +233,7 @@ entry:
   ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [13 x i8], align 1
   %0 = getelementptr inbounds [13 x i8], [13 x i8]* %arr0, i32 0, i32 1
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w)? r., r(7|11), #34}}
   ; CHECK-IOS: bl _memcpy
@@ -242,7 +242,7 @@ entry:
   ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [13 x i8], align 1
   %1 = getelementptr inbounds [13 x i8], [13 x i8]* %arr1, i32 0, i32 1
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w)? r., r(7|11), #47}}
   ; CHECK-IOS: mov r1, #1
@@ -255,7 +255,7 @@ entry:
   ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [13 x i8], align 1
   %2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 1
-  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
 
   unreachable
 }
@@ -272,7 +272,7 @@ entry:
   ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [13 x i8], align 1
   %0 = getelementptr inbounds [13 x i8], [13 x i8]* %arr0, i32 0, i32 %i
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w)? r., r(7|11), #42}}
   ; CHECK-IOS: bl _memcpy
@@ -281,7 +281,7 @@ entry:
   ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [13 x i8], align 1
   %1 = getelementptr inbounds [13 x i8], [13 x i8]* %arr1, i32 0, i32 %i
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w)? r., r(7|11), #55}}
   ; CHECK-IOS: mov r1, #1
@@ -294,7 +294,7 @@ entry:
   ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [13 x i8], align 1
   %2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 %i
-  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
 
   unreachable
 }
@@ -311,7 +311,7 @@ entry:
   ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [13 x i8], align 1
   %0 = getelementptr [13 x i8], [13 x i8]* %arr0, i32 0, i32 4
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w)? r., r(7|11), #34}}
   ; CHECK-IOS: bl _memcpy
@@ -320,7 +320,7 @@ entry:
   ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [13 x i8], align 1
   %1 = getelementptr [13 x i8], [13 x i8]* %arr1, i32 0, i32 4
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w)? r., r(7|11), #47}}
   ; CHECK-IOS: mov r1, #1
@@ -333,7 +333,7 @@ entry:
   ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [13 x i8], align 1
   %2 = getelementptr [13 x i8], [13 x i8]* %arr2, i32 0, i32 4
-  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
 
   unreachable
 }
@@ -350,7 +350,7 @@ entry:
   ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [13 x i8], align 1
   %0 = getelementptr inbounds [13 x i8], [13 x i8]* %arr0, i32 0, i32 16
-  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)|sub(.w)? r., r(7|11), #34}}
   ; CHECK-IOS: bl _memcpy
@@ -359,7 +359,7 @@ entry:
   ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [13 x i8], align 1
   %1 = getelementptr inbounds [13 x i8], [13 x i8]* %arr1, i32 0, i32 16
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)|sub(.w)? r., r(7|11), #47}}
   ; CHECK-IOS: mov r1, #1
@@ -372,7 +372,7 @@ entry:
   ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [13 x i8], align 1
   %2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 16
-  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i1 false)
 
   unreachable
 }
@@ -390,15 +390,15 @@ entry:
 @arr9 = weak_odr global [128 x i8] undef
 define void @f9(i8* %dest, i32 %n) "no-frame-pointer-elim"="true" {
 entry:
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr1, i32 0, i32 0), i32 %n, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([8 x i8], [8 x i8]* @arr2, i32 0, i32 0), i32 %n, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr3, i32 0, i32 0), i32 %n, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([8 x i8], [8 x i8]* @arr4, i32 0, i32 0), i32 %n, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr5, i32 0, i32 0), i32 %n, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr6, i32 0, i32 0), i32 %n, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr7, i32 0, i32 0), i32 %n, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([128 x i8], [128 x i8]* @arr8, i32 0, i32 0), i32 %n, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([128 x i8], [128 x i8]* @arr9, i32 0, i32 0), i32 %n, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr1, i32 0, i32 0), i32 %n, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([8 x i8], [8 x i8]* @arr2, i32 0, i32 0), i32 %n, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr3, i32 0, i32 0), i32 %n, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([8 x i8], [8 x i8]* @arr4, i32 0, i32 0), i32 %n, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr5, i32 0, i32 0), i32 %n, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr6, i32 0, i32 0), i32 %n, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr7, i32 0, i32 0), i32 %n, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([128 x i8], [128 x i8]* @arr8, i32 0, i32 0), i32 %n, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([128 x i8], [128 x i8]* @arr9, i32 0, i32 0), i32 %n, i1 false)
 
   unreachable
 }
@@ -428,6 +428,6 @@ entry:
 
 ; CHECK-NOT: arr7:
 
-declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, 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, i32, i1) nounwind
+declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, 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/CodeGen/ARM/memset-inline.ll b/llvm/test/CodeGen/ARM/memset-inline.ll
index b2bd257701d..01b21e9d387 100644
--- a/llvm/test/CodeGen/ARM/memset-inline.ll
+++ b/llvm/test/CodeGen/ARM/memset-inline.ll
@@ -12,7 +12,7 @@ entry:
 ; CHECK-6M: str r1, [r0]
 ; CHECK-6M: str r1, [r0, #4]
 ; CHECK-6M: str r1, [r0, #8]
-  call void @llvm.memset.p0i8.i64(i8* %c, i8 0, i64 12, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %c, i8 0, i64 12, i1 false)
   ret void
 }
 
@@ -33,7 +33,7 @@ entry:
 ; CHECK-6M: str  [[REG]], [sp]
   %buf = alloca [26 x i8], align 1
   %0 = getelementptr inbounds [26 x i8], [26 x i8]* %buf, i32 0, i32 0
-  call void @llvm.memset.p0i8.i32(i8* %0, i8 0, i32 26, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %0, i8 0, i32 26, i1 false)
   call void @something(i8* %0) nounwind
   ret void
 }
@@ -54,7 +54,7 @@ entry:
 for.body:
   %i = phi i32 [ 0, %entry ], [ %inc, %for.body ]
   %0 = trunc i32 %i to i8
-  call void @llvm.memset.p0i8.i32(i8* %p, i8 %0, i32 4, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %p, i8 %0, i32 4, i1 false)
   call void @something(i8* %p)
   %inc = add nuw nsw i32 %i, 1
   %exitcond = icmp eq i32 %inc, 255
@@ -78,7 +78,7 @@ entry:
 for.body:
   %i = phi i32 [ 0, %entry ], [ %inc, %for.body ]
   %0 = trunc i32 %i to i8
-  call void @llvm.memset.p0i8.i32(i8* %p, i8 %0, i32 4, i32 2, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 2 %p, i8 %0, i32 4, i1 false)
   call void @something(i8* %p)
   %inc = add nuw nsw i32 %i, 1
   %exitcond = icmp eq i32 %inc, 255
@@ -89,5 +89,5 @@ for.end:
 }
 
 declare void @something(i8*) nounwind
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
diff --git a/llvm/test/CodeGen/ARM/stack-protector-bmovpcb_call.ll b/llvm/test/CodeGen/ARM/stack-protector-bmovpcb_call.ll
index 2a7a82da8f6..84bf7ac826e 100644
--- a/llvm/test/CodeGen/ARM/stack-protector-bmovpcb_call.ll
+++ b/llvm/test/CodeGen/ARM/stack-protector-bmovpcb_call.ll
@@ -15,13 +15,13 @@ define i32 @main() #0 {
 entry:
   %title = alloca [15 x i8], align 1
   %0 = getelementptr inbounds [15 x i8], [15 x i8]* %title, i32 0, i32 0
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* getelementptr inbounds ([15 x i8], [15 x i8]* @main.title, i32 0, i32 0), i32 15, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %0, i8* align 1 getelementptr inbounds ([15 x i8], [15 x i8]* @main.title, i32 0, i32 0), i32 15, i1 false)
   %call = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([3 x i8], [3 x i8]* @.str, i32 0, i32 0), i8* %0) #3
   ret i32 0
 }
 
 ; Function Attrs: nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #1
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) #1
 
 ; Function Attrs: nounwind optsize
 declare i32 @printf(i8* nocapture readonly, ...) #2
diff --git a/llvm/test/CodeGen/ARM/struct-byval-frame-index.ll b/llvm/test/CodeGen/ARM/struct-byval-frame-index.ll
index b3ed5de857b..c6509cfe9cf 100644
--- a/llvm/test/CodeGen/ARM/struct-byval-frame-index.ll
+++ b/llvm/test/CodeGen/ARM/struct-byval-frame-index.ll
@@ -60,10 +60,10 @@ target triple = "armv7l-unknown-linux-gnueabihf"
 @brefframe = external global [4 x [4 x i8]], align 1
 
 ; Function Attrs: nounwind
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) #0
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) #0
 
 ; Function Attrs: nounwind
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) #0
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) #0
 
 ; Function Attrs: nounwind
 declare void @SetMotionVectorsMB(%structK* nocapture, i32) #1
@@ -122,10 +122,10 @@ for.cond210.preheader:                            ; preds = %if.then169
   unreachable
 
 if.end230:                                        ; preds = %if.end164
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* bitcast ([4 x i32]* @b8mode to i8*), i32 16, i32 4, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 undef, i8* align 4 bitcast ([4 x i32]* @b8mode to i8*), i32 16, i1 false)
   %b8pdir = getelementptr inbounds %structK, %structK* %2, i32 %1, i32 15
   %3 = bitcast [4 x i32]* %b8pdir to i8*
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %3, i8* bitcast ([4 x i32]* @b8pdir to i8*), i32 16, i32 4, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %3, i8* align 4 bitcast ([4 x i32]* @b8pdir to i8*), i32 16, i1 false)
   br i1 undef, label %if.end236, label %if.then233
 
 if.then233:                                       ; preds = %if.end230
diff --git a/llvm/test/CodeGen/ARM/tailcall-mem-intrinsics.ll b/llvm/test/CodeGen/ARM/tailcall-mem-intrinsics.ll
index 6744efa8ab8..08370f2bf12 100644
--- a/llvm/test/CodeGen/ARM/tailcall-mem-intrinsics.ll
+++ b/llvm/test/CodeGen/ARM/tailcall-mem-intrinsics.ll
@@ -4,7 +4,7 @@
 ; CHECK: bl	__aeabi_memcpy
 define i8* @tail_memcpy_ret(i8* nocapture %p, i8* nocapture readonly %q, i32 %n) #0 {
 entry:
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %p, i8* %q, i32 %n, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %p, i8* %q, i32 %n, i1 false)
   ret i8* %p
 }
 
@@ -12,7 +12,7 @@ entry:
 ; CHECK: bl	__aeabi_memmove
 define i8* @tail_memmove_ret(i8* nocapture %p, i8* nocapture readonly %q, i32 %n) #0 {
 entry:
-  tail call void @llvm.memmove.p0i8.p0i8.i32(i8* %p, i8* %q, i32 %n, i32 1, i1 false)
+  tail call void @llvm.memmove.p0i8.p0i8.i32(i8* %p, i8* %q, i32 %n, i1 false)
   ret i8* %p
 }
 
@@ -20,12 +20,12 @@ entry:
 ; CHECK: bl	__aeabi_memset
 define i8* @tail_memset_ret(i8* nocapture %p, i8 %c, i32 %n) #0 {
 entry:
-  tail call void @llvm.memset.p0i8.i32(i8* %p, i8 %c, i32 %n, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i32(i8* %p, i8 %c, i32 %n, i1 false)
   ret i8* %p
 }
 
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #0
-declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #0
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) #0
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) #0
+declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) #0
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) #0
 
 attributes #0 = { nounwind }