Change memcpy/memset/memmove to have dest and source alignments.

Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html

These intrinsics currently have an explicit alignment argument which is
required to be a constant integer.  It represents the alignment of the
source and dest, and so must be the minimum of those.

This change allows source and dest to each have their own alignments
by using the alignment attribute on their arguments.  The alignment
argument itself is removed.

There are a few places in the code for which the code needs to be
checked by an expert as to whether using only src/dest alignment is
safe.  For those places, they currently take the minimum of src/dest
alignments which matches the current behaviour.

For example, code which used to read:
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false)
will now read:
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false)

For out of tree owners, I was able to strip alignment from calls using sed by replacing:
  (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\)
with:
  $1i1 false)

and similarly for memmove and memcpy.

I then added back in alignment to test cases which needed it.

A similar commit will be made to clang which actually has many differences in alignment as now
IRBuilder can generate different source/dest alignments on calls.

In IRBuilder itself, a new argument was added.  Instead of calling:
  CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false)
you now call
  CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false)

There is a temporary class (IntegerAlignment) which takes the source alignment and rejects
implicit conversion from bool.  This is to prevent isVolatile here from passing its default
parameter to the source alignment.

Note, changes in future can now be made to codegen.  I didn't change anything here, but this
change should enable better memcpy code sequences.

Reviewed by Hal Finkel.

llvm-svn: 253511

17 files changed, 98 insertions, 98 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..0f2f3fecb6f 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* null, i8* %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..73497b2112b 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* 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 5df439389cd..d2d3116cbd0 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 3971b9ccf58..35cc7d5032d 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 -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/crash-O0.ll b/llvm/test/CodeGen/ARM/crash-O0.ll
index f92af999be5..8f3b5f10cd6 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* undef, i8* 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* %prodvers2, i8* 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 2a8898651f0..07fb4ef9ba9 100644
--- a/llvm/test/CodeGen/ARM/debug-info-blocks.ll
+++ b/llvm/test/CodeGen/ARM/debug-info-blocks.ll
@@ -25,7 +25,7 @@ declare i8* @objc_msgSend(i8*, i8*, ...)
 
 declare void @llvm.dbg.value(metadata, i64, 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
@@ -67,7 +67,7 @@ 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* %25, i8* %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
@@ -76,7 +76,7 @@ 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* %33, i8* %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..06d8f8dc179 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* %tmp6.indexed, i8* 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 1c7ff687938..131023e7ab6 100644
--- a/llvm/test/CodeGen/ARM/fast-isel-intrinsic.ll
+++ b/llvm/test/CodeGen/ARM/fast-isel-intrinsic.ll
@@ -39,11 +39,11 @@ 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:
@@ -78,11 +78,11 @@ 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:
@@ -115,7 +115,7 @@ 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* 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, i1 false)
   ret void
 }
 
@@ -142,11 +142,11 @@ 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* 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, 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:
@@ -179,7 +179,7 @@ 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
 }
 
@@ -234,14 +234,14 @@ 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* 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, i1 false)
   ret void
 }
 
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 d874884dcb3..a5c525c062f 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
 }
 
@@ -36,7 +36,7 @@ entry:
 ; CHECK: adds r1, #15
 ; CHECK: vld1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]
 ; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
-  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
 }
 
@@ -50,7 +50,7 @@ entry:
 ; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]!
 ; CHECK: vld1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]
 ; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
-  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
 }
 
@@ -61,7 +61,7 @@ entry:
 ; CHECK: vst1.8 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]!
 ; CHECK: vldr d{{[0-9]+}}, [r1]
 ; CHECK: vst1.8 {d{{[0-9]+}}}, [r0]
-  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
 }
 
@@ -71,7 +71,7 @@ entry:
 ; CHECK: vld1.64 {[[REG3:d[0-9]+]], [[REG4:d[0-9]+]]}, [r1]
 ; CHECK: vst1.8 {[[REG3]], [[REG4]]}, [r0]!
 ; CHECK: strh [[REG5:r[0-9]+]], [r0]
-  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
 }
 
@@ -90,7 +90,7 @@ entry:
 ; CHECK-T1: strb [[TREG3]],
 ; CHECK-T1: movs [[TREG4:r[0-9]]],
 ; CHECK-T1: strb [[TREG4]],
-  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
 }
 
@@ -108,7 +108,7 @@ 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
 }
 
@@ -124,9 +124,9 @@ 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/memfunc.ll b/llvm/test/CodeGen/ARM/memfunc.ll
index 66743f3e9d5..1edf53b19d3 100644
--- a/llvm/test/CodeGen/ARM/memfunc.ll
+++ b/llvm/test/CodeGen/ARM/memfunc.ll
@@ -14,13 +14,13 @@ 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
@@ -31,7 +31,7 @@ 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
@@ -40,7 +40,7 @@ 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
 
@@ -48,49 +48,49 @@ 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
 }
@@ -111,7 +111,7 @@ 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
@@ -120,7 +120,7 @@ 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
@@ -136,7 +136,7 @@ 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
 }
@@ -153,7 +153,7 @@ 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}}
   ; CHECK-IOS: bl _memcpy
@@ -162,7 +162,7 @@ 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}}
   ; CHECK-IOS: mov r1, #1
@@ -175,7 +175,7 @@ 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
 }
@@ -192,7 +192,7 @@ 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)}}
   ; CHECK-IOS: bl _memcpy
@@ -201,7 +201,7 @@ 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)}}
   ; CHECK-IOS: mov r1, #1
@@ -214,7 +214,7 @@ 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
 }
@@ -231,7 +231,7 @@ 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)}}
   ; CHECK-IOS: bl _memcpy
@@ -240,7 +240,7 @@ 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)}}
   ; CHECK-IOS: mov r1, #1
@@ -253,7 +253,7 @@ 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
 }
@@ -270,7 +270,7 @@ 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)}}
   ; CHECK-IOS: bl _memcpy
@@ -279,7 +279,7 @@ 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)}}
   ; CHECK-IOS: mov r1, #1
@@ -292,7 +292,7 @@ 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
 }
@@ -309,7 +309,7 @@ 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)}}
   ; CHECK-IOS: bl _memcpy
@@ -318,7 +318,7 @@ 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)}}
   ; CHECK-IOS: mov r1, #1
@@ -331,7 +331,7 @@ 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
 }
@@ -348,7 +348,7 @@ 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)}}
   ; CHECK-IOS: bl _memcpy
@@ -357,7 +357,7 @@ 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)}}
   ; CHECK-IOS: mov r1, #1
@@ -370,7 +370,7 @@ 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
 }
@@ -386,13 +386,13 @@ entry:
 @arr7 = external global [7 x i8], align 1
 define void @f9(i8* %dest, i32 %n) {
 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 ([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)
 
   unreachable
 }
@@ -417,6 +417,6 @@ entry:
 ; CHECK: arr6:
 ; 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 f6f8d562350..98334600ddb 100644
--- a/llvm/test/CodeGen/ARM/memset-inline.ll
+++ b/llvm/test/CodeGen/ARM/memset-inline.ll
@@ -6,7 +6,7 @@ entry:
 ; CHECK: movs r1, #0
 ; CHECK: strd r1, r1, [r0]
 ; CHECK: 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
 }
 
@@ -19,11 +19,11 @@ entry:
 ; CHECK: vst1.64 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
   %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* align 1 %0, i8 0, i32 26, i1 false)
   call void @something(i8* %0) nounwind
   ret void
 }
 
 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..e2fe0cfaabb 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* %0, i8* 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 52f70fe1e0f..a2e2c32f50e 100644
--- a/llvm/test/CodeGen/ARM/struct-byval-frame-index.ll
+++ b/llvm/test/CodeGen/ARM/struct-byval-frame-index.ll
@@ -61,10 +61,10 @@ 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
@@ -123,10 +123,10 @@ 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* undef, i8* 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* %3, i8* 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