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

22 files changed, 210 insertions, 215 deletions

diff --git a/llvm/test/Transforms/MemCpyOpt/2008-02-24-MultipleUseofSRet.ll b/llvm/test/Transforms/MemCpyOpt/2008-02-24-MultipleUseofSRet.ll
index f73addd6268..7ff149f6f77 100644
--- a/llvm/test/Transforms/MemCpyOpt/2008-02-24-MultipleUseofSRet.ll
+++ b/llvm/test/Transforms/MemCpyOpt/2008-02-24-MultipleUseofSRet.ll
@@ -25,12 +25,12 @@ entry:
   call fastcc void @initialize(%0* noalias sret %memtmp)
   %tmp1 = bitcast %0* %tmp to i8*
   %memtmp2 = bitcast %0* %memtmp to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp1, i8* %memtmp2, i32 24, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %tmp1, i8* align 8 %memtmp2, i32 24, i1 false)
   %z3 = bitcast %0* %z to i8*
   %tmp4 = bitcast %0* %tmp to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %z3, i8* %tmp4, i32 24, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %z3, i8* align 8 %tmp4, i32 24, i1 false)
   %tmp5 = call fastcc x86_fp80 @passed_uninitialized(%0* %z)
   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
diff --git a/llvm/test/Transforms/MemCpyOpt/2008-03-13-ReturnSlotBitcast.ll b/llvm/test/Transforms/MemCpyOpt/2008-03-13-ReturnSlotBitcast.ll
index ffbb2992557..26c221d6786 100644
--- a/llvm/test/Transforms/MemCpyOpt/2008-03-13-ReturnSlotBitcast.ll
+++ b/llvm/test/Transforms/MemCpyOpt/2008-03-13-ReturnSlotBitcast.ll
@@ -13,10 +13,10 @@ entry:
   call void @g(%a* %a_var)
   %a_i8 = bitcast %a* %a_var to i8*
   %b_i8 = bitcast %b* %b_var to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b_i8, i8* %a_i8, i32 4, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b_i8, i8* %a_i8, i32 4, i1 false)
   %tmp1 = getelementptr %b, %b* %b_var, i32 0, i32 0
   %tmp2 = load float, float* %tmp1
   ret float %tmp2
 }
 
-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/Transforms/MemCpyOpt/align.ll b/llvm/test/Transforms/MemCpyOpt/align.ll
index 9074684f6c7..738928bac62 100644
--- a/llvm/test/Transforms/MemCpyOpt/align.ll
+++ b/llvm/test/Transforms/MemCpyOpt/align.ll
@@ -1,15 +1,15 @@
 ; RUN: opt < %s -S -basicaa -memcpyopt | FileCheck %s
 target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64"
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
 
 ; The resulting memset is only 4-byte aligned, despite containing
 ; a 16-byte aligned store in the middle.
 
 define void @foo(i32* %p) {
 ; CHECK-LABEL: @foo(
-; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 16, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 {{.*}}, i8 0, i64 16, i1 false)
   %a0 = getelementptr i32, i32* %p, i64 0
   store i32 0, i32* %a0, align 4
   %a1 = getelementptr i32, i32* %p, i64 1
@@ -31,7 +31,7 @@ define void @bar() {
   %a8 = alloca i32, align 8
   %a8.cast = bitcast i32* %a8 to i8*
   %a4.cast = bitcast i32* %a4 to i8*
-  call void @llvm.memset.p0i8.i64(i8* %a8.cast, i8 0, i64 4, i32 8, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a4.cast, i8* %a8.cast, i64 4, i32 4, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %a8.cast, i8 0, i64 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a4.cast, i8* align 4 %a8.cast, i64 4, i1 false)
   ret void
 }
diff --git a/llvm/test/Transforms/MemCpyOpt/atomic.ll b/llvm/test/Transforms/MemCpyOpt/atomic.ll
index 5be6b1555b5..f8fc39faa58 100644
--- a/llvm/test/Transforms/MemCpyOpt/atomic.ll
+++ b/llvm/test/Transforms/MemCpyOpt/atomic.ll
@@ -7,7 +7,7 @@ target triple = "x86_64-apple-macosx10.7.0"
 
 declare void @otherf(i32*)
 
-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
 
 ; memcpyopt should not touch atomic ops
 define void @test1() nounwind uwtable ssp {
@@ -15,7 +15,7 @@ define void @test1() nounwind uwtable ssp {
 ; CHECK: store atomic
   %x = alloca [101 x i32], align 16
   %bc = bitcast [101 x i32]* %x to i8*
-  call void @llvm.memset.p0i8.i64(i8* %bc, i8 0, i64 400, i32 16, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 16 %bc, i8 0, i64 400, i1 false)
   %gep1 = getelementptr inbounds [101 x i32], [101 x i32]* %x, i32 0, i32 100
   store atomic i32 0, i32* %gep1 unordered, align 4
   %gep2 = getelementptr inbounds [101 x i32], [101 x i32]* %x, i32 0, i32 0
diff --git a/llvm/test/Transforms/MemCpyOpt/callslot_aa.ll b/llvm/test/Transforms/MemCpyOpt/callslot_aa.ll
index b6ea129ccfa..d840b726a9a 100644
--- a/llvm/test/Transforms/MemCpyOpt/callslot_aa.ll
+++ b/llvm/test/Transforms/MemCpyOpt/callslot_aa.ll
@@ -6,14 +6,14 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 define void @test(i8* %src) {
   %tmp = alloca i8
   %dst = alloca i8
-; CHECK:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 1, i32 8, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp, i8* %src, i64 1, i32 8, i1 false), !noalias !2
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %tmp, i64 1, i32 8, i1 false)
+; CHECK:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst, i8* align 8 %src, i64 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %tmp, i8* align 8 %src, i64 1, i1 false), !noalias !2
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst, i8* align 8 %tmp, i64 1, i1 false)
 
   ret void
 }
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i32, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i1)
 
 ; Check that the noalias for "dst" was removed by checking that the metadata is gone
 ; CHECK-NOT: "dst"
diff --git a/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll b/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll
index 4c3e3e86bf3..a1ba2bae79e 100644
--- a/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll
+++ b/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll
@@ -1,8 +1,8 @@
 ; RUN: opt < %s -S -basicaa -memcpyopt | FileCheck %s
 target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) unnamed_addr nounwind
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) unnamed_addr nounwind
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
 
 ; all bytes of %dst that are touch by the memset are dereferenceable
 define void @must_remove_memcpy(i8* noalias nocapture dereferenceable(4096) %dst) {
@@ -11,8 +11,8 @@ define void @must_remove_memcpy(i8* noalias nocapture dereferenceable(4096) %dst
 ; CHECK-NOT: call void @llvm.memcpy.p0i8.p0i8.i64
   %src = alloca [4096 x i8], align 1
   %p = getelementptr inbounds [4096 x i8], [4096 x i8]* %src, i64 0, i64 0
-  call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i32 1, i1 false) #2
+  call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i1 false) #2
   ret void
 }
 
@@ -24,7 +24,7 @@ define void @must_not_remove_memcpy(i8* noalias nocapture dereferenceable(1024)
 ; CHECK: call void @llvm.memset.p0i8.i64
   %src = alloca [4096 x i8], align 1
   %p = getelementptr inbounds [4096 x i8], [4096 x i8]* %src, i64 0, i64 0
-  call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i32 1, i1 false) #2
+  call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i1 false) #2
   ret void
 }
diff --git a/llvm/test/Transforms/MemCpyOpt/capturing-func.ll b/llvm/test/Transforms/MemCpyOpt/capturing-func.ll
index 17614fd181d..2671a9aad81 100644
--- a/llvm/test/Transforms/MemCpyOpt/capturing-func.ll
+++ b/llvm/test/Transforms/MemCpyOpt/capturing-func.ll
@@ -3,13 +3,13 @@
 target datalayout = "e"
 
 declare void @foo(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
 
 define void @test() {
   %ptr1 = alloca i8
   %ptr2 = alloca i8
   call void @foo(i8* %ptr2)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr1, i8* %ptr2, i32 1, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr1, i8* %ptr2, i32 1, i1 false)
   call void @foo(i8* %ptr1)
   ret void
 
diff --git a/llvm/test/Transforms/MemCpyOpt/crash.ll b/llvm/test/Transforms/MemCpyOpt/crash.ll
index 56757a6d1f8..464a261e4e4 100644
--- a/llvm/test/Transforms/MemCpyOpt/crash.ll
+++ b/llvm/test/Transforms/MemCpyOpt/crash.ll
@@ -46,13 +46,10 @@ entry:
 
 ; PR8753
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32,
-i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
 
 define void @test2(i32 %cmd) nounwind {
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* undef, i64 20, i32 1, i1
-false) nounwind
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* null, i8* undef, i64 20, i32 1, i1
-false) nounwind
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* undef, i64 20, i1 false) nounwind
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* null, i8* undef, i64 20, i1 false) nounwind
   ret void
 }
diff --git a/llvm/test/Transforms/MemCpyOpt/form-memset.ll b/llvm/test/Transforms/MemCpyOpt/form-memset.ll
index 7d7f3a6dac3..836a6107d24 100644
--- a/llvm/test/Transforms/MemCpyOpt/form-memset.ll
+++ b/llvm/test/Transforms/MemCpyOpt/form-memset.ll
@@ -152,11 +152,11 @@ entry:
         
 ; CHECK-LABEL: @test2(
 ; CHECK-NOT: store
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %tmp41, i8 -1, i64 8, i32 1, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %tmp41, i8 -1, i64 8, i1 false)
 ; CHECK-NOT: store
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 32, i32 8, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %0, i8 0, i64 32, i1 false)
 ; CHECK-NOT: store
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 32, i32 8, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %1, i8 0, i64 32, i1 false)
 ; CHECK-NOT: store
 ; CHECK: ret
 }
@@ -171,11 +171,11 @@ entry:
   store i32 0, i32* %arrayidx, align 4
   %add.ptr = getelementptr inbounds i32, i32* %P, i64 2
   %0 = bitcast i32* %add.ptr to i8*
-  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i1 false)
   ret void
 ; CHECK-LABEL: @test3(
 ; CHECK-NOT: store
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 15, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %1, i8 0, i64 15, i1 false)
 }
 
 ; store followed by memset, different offset scenario
@@ -184,40 +184,40 @@ entry:
   store i32 0, i32* %P, align 4
   %add.ptr = getelementptr inbounds i32, i32* %P, i64 1
   %0 = bitcast i32* %add.ptr to i8*
-  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i1 false)
   ret void
 ; CHECK-LABEL: @test4(
 ; CHECK-NOT: store
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 15, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %1, i8 0, i64 15, i1 false)
 }
 
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
 
 ; Memset followed by store.
 define void @test5(i32* nocapture %P) nounwind ssp {
 entry:
   %add.ptr = getelementptr inbounds i32, i32* %P, i64 2
   %0 = bitcast i32* %add.ptr to i8*
-  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i1 false)
   %arrayidx = getelementptr inbounds i32, i32* %P, i64 1
   store i32 0, i32* %arrayidx, align 4
   ret void
 ; CHECK-LABEL: @test5(
 ; CHECK-NOT: store
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 15, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %1, i8 0, i64 15, i1 false)
 }
 
 ;; Memset followed by memset.
 define void @test6(i32* nocapture %P) nounwind ssp {
 entry:
   %0 = bitcast i32* %P to i8*
-  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 12, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 12, i1 false)
   %add.ptr = getelementptr inbounds i32, i32* %P, i64 3
   %1 = bitcast i32* %add.ptr to i8*
-  tail call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 12, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 12, i1 false)
   ret void
 ; CHECK-LABEL: @test6(
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %2, i8 0, i64 24, i32 1, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %2, i8 0, i64 24, i1 false)
 }
 
 ; More aggressive heuristic
@@ -233,7 +233,7 @@ define void @test7(i32* nocapture %c) nounwind optsize {
   %4 = getelementptr inbounds i32, i32* %c, i32 4
   store i32 -1, i32* %4, align 4
 ; CHECK-LABEL: @test7(
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %5, i8 -1, i64 20, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %5, i8 -1, i64 20, i1 false)
   ret void
 }
 
@@ -270,17 +270,17 @@ define void @test9() nounwind {
   store i8 -1, i8* getelementptr (i8, i8* bitcast ([16 x i64]* @test9buf to i8*), i64 15), align 1
   ret void
 ; CHECK-LABEL: @test9(
-; CHECK: call void @llvm.memset.p0i8.i64(i8* bitcast ([16 x i64]* @test9buf to i8*), i8 -1, i64 16, i32 16, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 16 bitcast ([16 x i64]* @test9buf to i8*), i8 -1, i64 16, i1 false)
 }
 
 ; PR19092
 define void @test10(i8* nocapture %P) nounwind {
-  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 42, i32 1, i1 false)
-  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 23, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 42, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 23, i1 false)
   ret void
 ; CHECK-LABEL: @test10(
 ; CHECK-NOT: memset
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 42, i32 1, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %P, i8 0, i64 42, i1 false)
 ; CHECK-NOT: memset
 ; CHECK: ret void
 }
@@ -290,12 +290,12 @@ define void @test11(i32* nocapture %P) nounwind ssp {
 entry:
   %add.ptr = getelementptr inbounds i32, i32* %P, i64 3
   %0 = bitcast i32* %add.ptr to i8*
-  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 1, i64 11, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %0, i8 1, i64 11, i1 false)
   %arrayidx = getelementptr inbounds i32, i32* %P, i64 0
   %arrayidx.cast = bitcast i32* %arrayidx to i96*
   store i96 310698676526526814092329217, i96* %arrayidx.cast, align 4
   ret void
 ; CHECK-LABEL: @test11(
 ; CHECK-NOT: store
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 1, i64 23, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %1, i8 1, i64 23, i1 false)
 }
diff --git a/llvm/test/Transforms/MemCpyOpt/invariant.start.ll b/llvm/test/Transforms/MemCpyOpt/invariant.start.ll
index ed8d7ede7eb..4842114b584 100644
--- a/llvm/test/Transforms/MemCpyOpt/invariant.start.ll
+++ b/llvm/test/Transforms/MemCpyOpt/invariant.start.ll
@@ -6,11 +6,9 @@ target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f3
 target triple = "i686-apple-darwin9"
 
 %0 = type { x86_fp80, x86_fp80 }
-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 readonly,
-i64, i32, i1)
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1)
+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 readonly, i64, i1)
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
 
 declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) nounwind readonly
 
@@ -20,16 +18,16 @@ declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) nounwind readonly
 define void @test1(i8* %P, i8* %Q) nounwind  {
   %memtmp = alloca %0, align 16
   %R = bitcast %0* %memtmp to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %R, i8* %P, i32 32, i32 16, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %R, i8* align 16 %P, i32 32, i1 false)
   %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %P)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %Q, i8* %R, i32 32, i32 16, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %Q, i8* align 16 %R, i32 32, i1 false)
   ret void
 ; CHECK-LABEL: @test1(
 ; CHECK-NEXT: %memtmp = alloca %0, align 16
 ; CHECK-NEXT: %R = bitcast %0* %memtmp to i8*
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %R, i8* %P, i32 32, i32 16, i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %R, i8* align 16 %P, i32 32, i1 false)
 ; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %P)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %Q, i8* %R, i32 32, i32 16, i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %Q, i8* align 16 %R, i32 32, i1 false)
 ; CHECK-NEXT: ret void
 }
 
@@ -38,12 +36,12 @@ define void @test1(i8* %P, i8* %Q) nounwind  {
 ; memset.
 define void @test2(i8* %dst1, i8* %dst2, i8 %c) {
 ; CHECK-LABEL: define void @test2(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
 ; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %dst1)
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 128, i32 8, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %dst2, i8 %c, i64 128, i1 false)
 ; CHECK-NEXT: ret void
-  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
   %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %dst1)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst2, i8* align 8 %dst1, i64 128, i1 false)
   ret void
 }
diff --git a/llvm/test/Transforms/MemCpyOpt/lifetime.ll b/llvm/test/Transforms/MemCpyOpt/lifetime.ll
index 77b495f2b58..9ddf3f4f9c2 100644
--- a/llvm/test/Transforms/MemCpyOpt/lifetime.ll
+++ b/llvm/test/Transforms/MemCpyOpt/lifetime.ll
@@ -3,7 +3,7 @@
 ; performCallSlotOptzn in MemCpy should not exchange the calls to
 ; @llvm.lifetime.start and @llvm.memcpy.
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) #1
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) #1
 declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1
 declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1
 
@@ -17,7 +17,7 @@ bb:
   call void @llvm.lifetime.start.p0i8(i64 16, i8* %tmp5)
   %tmp10 = getelementptr inbounds i8, i8* %tmp5, i64 7
   store i8 0, i8* %tmp10, align 1
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arg1, i8* %tmp5, i64 16, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %arg1, i8* align 8 %tmp5, i64 16, i1 false)
   call void @llvm.lifetime.end.p0i8(i64 16, i8* %tmp5)
   ret void
 }
diff --git a/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll b/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll
index e21dc87cb6a..1b8e8bc2828 100644
--- a/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll
+++ b/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll
@@ -8,15 +8,15 @@ entry-block:
   %a = alloca [8 x i64], align 8
   %a.cast = bitcast [8 x i64]* %a to i8*
   call void @llvm.lifetime.start.p0i8(i64 64, i8* %a.cast)
-  call void @llvm.memset.p0i8.i64(i8* %a.cast, i8 0, i64 64, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %a.cast, i8 0, i64 64, i1 false)
   %sret.cast = bitcast [8 x i64]* %sret to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %sret.cast, i8* %a.cast, i64 64, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %sret.cast, i8* align 8 %a.cast, i64 64, i1 false)
   call void @llvm.lifetime.end.p0i8(i64 64, i8* %a.cast)
   ret void
 
 ; CHECK-LABEL: @foo(
 ; CHECK:         %[[sret_cast:[^=]+]] = bitcast [8 x i64]* %sret to i8*
-; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* %[[sret_cast]], i8 0, i64 64
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 8 %[[sret_cast]], i8 0, i64 64
 ; CHECK-NOT: call void @llvm.memcpy
 ; CHECK: ret void
 }
@@ -26,24 +26,24 @@ entry-block:
   %a = alloca [8 x i64], align 8
   %a.cast = bitcast [8 x i64]* %a to i8*
   call void @llvm.lifetime.start.p0i8(i64 64, i8* %a.cast)
-  call void @llvm.memset.p0i8.i64(i8* %a.cast, i8 0, i64 64, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %a.cast, i8 0, i64 64, i1 false)
   %sret.cast = bitcast [8 x i64]* %sret to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %sret.cast, i8* %a.cast, i64 64, i32 8, i1 false)
-  call void @llvm.memset.p0i8.i64(i8* %a.cast, i8 42, i64 32, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %sret.cast, i8* align 8 %a.cast, i64 64, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %a.cast, i8 42, i64 32, i1 false)
   %out.cast = bitcast [8 x i64]* %out to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out.cast, i8* %a.cast, i64 64, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %out.cast, i8* align 8 %a.cast, i64 64, i1 false)
   call void @llvm.lifetime.end.p0i8(i64 64, i8* %a.cast)
   ret void
 
 ; CHECK-LABEL: @bar(
 ; CHECK:         %[[a:[^=]+]] = alloca [8 x i64]
 ; CHECK:         %[[a_cast:[^=]+]] = bitcast [8 x i64]* %[[a]] to i8*
-; CHECK:         call void @llvm.memset.p0i8.i64(i8* %[[a_cast]], i8 0, i64 64
+; CHECK:         call void @llvm.memset.p0i8.i64(i8* align 8 %[[a_cast]], i8 0, i64 64
 ; CHECK:         %[[sret_cast:[^=]+]] = bitcast [8 x i64]* %sret to i8*
-; CHECK:         call void @llvm.memset.p0i8.i64(i8* %[[sret_cast]], i8 0, i64 64
-; CHECK:         call void @llvm.memset.p0i8.i64(i8* %[[a_cast]], i8 42, i64 32
+; CHECK:         call void @llvm.memset.p0i8.i64(i8* align 8 %[[sret_cast]], i8 0, i64 64
+; CHECK:         call void @llvm.memset.p0i8.i64(i8* align 8 %[[a_cast]], i8 42, i64 32
 ; CHECK:         %[[out_cast:[^=]+]] = bitcast [8 x i64]* %out to i8*
-; CHECK:         call void @llvm.memcpy.p0i8.p0i8.i64(i8* %[[out_cast]], i8* %[[a_cast]], i64 64
+; CHECK:         call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %[[out_cast]], i8* align 8 %[[a_cast]], i64 64
 ; CHECK-NOT: call void @llvm.memcpy
 ; CHECK: ret void
 }
@@ -51,5 +51,5 @@ entry-block:
 declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) nounwind
 declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) nounwind
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) nounwind
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) nounwind
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
diff --git a/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset.ll b/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset.ll
index fd8b93c19b1..652d1c1d65b 100644
--- a/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset.ll
+++ b/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset.ll
@@ -2,13 +2,13 @@
 
 @cst = internal constant [3 x i32] [i32 -1, i32 -1, i32 -1], align 4
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
 declare void @foo(i32*) nounwind
 
 define void @test1() nounwind {
   %arr = alloca [3 x i32], align 4
   %arr_i8 = bitcast [3 x i32]* %arr to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arr_i8, i8* bitcast ([3 x i32]* @cst to i8*), i64 12, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %arr_i8, i8* align 4 bitcast ([3 x i32]* @cst to i8*), i64 12, i1 false)
   %arraydecay = getelementptr inbounds [3 x i32], [3 x i32]* %arr, i64 0, i64 0
   call void @foo(i32* %arraydecay) nounwind
   ret void
diff --git a/llvm/test/Transforms/MemCpyOpt/memcpy-undef.ll b/llvm/test/Transforms/MemCpyOpt/memcpy-undef.ll
index 06a41829a4e..9cf4f91e6aa 100644
--- a/llvm/test/Transforms/MemCpyOpt/memcpy-undef.ll
+++ b/llvm/test/Transforms/MemCpyOpt/memcpy-undef.ll
@@ -11,7 +11,7 @@ define i32 @test1(%struct.foo* nocapture %foobie) nounwind noinline ssp uwtable
   store i8 98, i8* %1, align 4
   %2 = getelementptr inbounds %struct.foo, %struct.foo* %foobie, i64 0, i32 1, i64 0
   %3 = getelementptr inbounds [7 x i8], [7 x i8]* %bletch.sroa.1, i64 0, i64 0
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %2, i8* %3, i64 7, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %2, i8* %3, i64 7, i1 false)
   %4 = getelementptr inbounds %struct.foo, %struct.foo* %foobie, i64 0, i32 2
   store i32 20, i32* %4, align 4
   ret i32 undef
@@ -23,7 +23,7 @@ define i32 @test1(%struct.foo* nocapture %foobie) nounwind noinline ssp uwtable
 
 define void @test2(i8* sret noalias nocapture %out, i8* %in) nounwind noinline ssp uwtable {
   call void @llvm.lifetime.start.p0i8(i64 8, i8* %in)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 8, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 8, i1 false)
   ret void
 
 ; Check that the memcpy is removed.
@@ -33,7 +33,7 @@ define void @test2(i8* sret noalias nocapture %out, i8* %in) nounwind noinline s
 
 define void @test3(i8* sret noalias nocapture %out, i8* %in) nounwind noinline ssp uwtable {
   call void @llvm.lifetime.start.p0i8(i64 4, i8* %in)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 8, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 8, i1 false)
   ret void
 
 ; Check that the memcpy is not removed.
@@ -41,6 +41,6 @@ define void @test3(i8* sret noalias nocapture %out, i8* %in) nounwind noinline s
 ; CHECK: call void @llvm.memcpy
 }
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
 
 declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) nounwind
diff --git a/llvm/test/Transforms/MemCpyOpt/memcpy.ll b/llvm/test/Transforms/MemCpyOpt/memcpy.ll
index 9f0ad2df86b..7e1e4d54a24 100644
--- a/llvm/test/Transforms/MemCpyOpt/memcpy.ll
+++ b/llvm/test/Transforms/MemCpyOpt/memcpy.ll
@@ -14,9 +14,9 @@ entry:
   call void @ccoshl(%0* sret %memtmp, x86_fp80 %tmp5, x86_fp80 %z.0) nounwind
   %tmp219 = bitcast %0* %tmp2 to i8*
   %memtmp20 = bitcast %0* %memtmp to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp219, i8* %memtmp20, i32 32, i32 16, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %tmp219, i8* align 16 %memtmp20, i32 32, i1 false)
   %agg.result21 = bitcast %0* %agg.result to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %agg.result21, i8* %tmp219, i32 32, i32 16, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %agg.result21, i8* align 16 %tmp219, i32 32, i1 false)
   ret void
 
 ; Check that one of the memcpy's are removed.
@@ -37,12 +37,12 @@ declare void @ccoshl(%0* nocapture sret, x86_fp80, x86_fp80) nounwind
 define void @test2(i8* %P, i8* %Q) nounwind  {
   %memtmp = alloca %0, align 16
   %R = bitcast %0* %memtmp to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %R, i8* %P, i32 32, i32 16, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %Q, i8* %R, i32 32, i32 16, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %R, i8* align 16 %P, i32 32, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %Q, i8* align 16 %R, i32 32, i1 false)
   ret void
 
 ; CHECK-LABEL: @test2(
-; CHECK-NEXT: call void @llvm.memmove{{.*}}(i8* %Q, i8* %P
+; CHECK-NEXT: call void @llvm.memmove{{.*}}(i8* align 16 %Q, i8* align 16 %P
 ; CHECK-NEXT: ret void
 }
 
@@ -54,9 +54,9 @@ define void @test2(i8* %P, i8* %Q) nounwind  {
 define void @test3(%0* noalias sret %agg.result) nounwind  {
   %x.0 = alloca %0
   %x.01 = bitcast %0* %x.0 to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %x.01, i8* bitcast (%0* @x to i8*), i32 32, i32 16, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %x.01, i8* align 16 bitcast (%0* @x to i8*), i32 32, i1 false)
   %agg.result2 = bitcast %0* %agg.result to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %agg.result2, i8* %x.01, i32 32, i32 16, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %agg.result2, i8* align 16 %x.01, i32 32, i1 false)
   ret void
 ; CHECK-LABEL: @test3(
 ; CHECK-NEXT: %agg.result1 = bitcast
@@ -69,7 +69,7 @@ define void @test3(%0* noalias sret %agg.result) nounwind  {
 define void @test4(i8 *%P) {
   %A = alloca %1
   %a = bitcast %1* %A to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %P, i64 8, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 %P, i64 8, i1 false)
   call void @test4a(i8* align 1 byval %a)
   ret void
 ; CHECK-LABEL: @test4(
@@ -80,7 +80,7 @@ define void @test4(i8 *%P) {
 define void @test4_addrspace(i8 addrspace(1)* %P) {
   %A = alloca %1
   %a = bitcast %1* %A to i8*
-  call void @llvm.memcpy.p0i8.p1i8.i64(i8* %a, i8 addrspace(1)* %P, i64 8, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p1i8.i64(i8* align 4 %a, i8 addrspace(1)* align 4 %P, i64 8, i1 false)
   call void @test4a(i8* align 1 byval %a)
   ret void
 ; CHECK-LABEL: @test4_addrspace(
@@ -89,9 +89,9 @@ define void @test4_addrspace(i8 addrspace(1)* %P) {
 }
 
 declare void @test4a(i8* align 1 byval)
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
-declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind
-declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
+declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind
+declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind
 
 %struct.S = type { i128, [4 x i8]}
 
@@ -105,7 +105,7 @@ define i32 @test5(i32 %x) nounwind ssp {
 entry:
   %y = alloca %struct.S, align 16
   %tmp = bitcast %struct.S* %y to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp, i8* bitcast (%struct.S* @sS to i8*), i64 32, i32 16, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %tmp, i8* align 16 bitcast (%struct.S* @sS to i8*), i64 32, i1 false)
   %a = getelementptr %struct.S, %struct.S* %y, i64 0, i32 1, i64 0
   store i8 4, i8* %a
   call void @test5a(%struct.S* align 16 byval %y)
@@ -117,7 +117,7 @@ entry:
 
 ;; Noop memcpy should be zapped.
 define void @test6(i8 *%P) {
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %P, i64 8, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %P, i8* align 4 %P, i64 8, i1 false)
   ret void
 ; CHECK-LABEL: @test6(
 ; CHECK-NEXT: ret void
@@ -133,7 +133,7 @@ entry:
   %agg.tmp = alloca %struct.p, align 4
   %tmp = bitcast %struct.p* %agg.tmp to i8*
   %tmp1 = bitcast %struct.p* %q to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp, i8* %tmp1, i64 48, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %tmp, i8* align 4 %tmp1, i64 48, i1 false)
   %call = call i32 @g(%struct.p* align 8 byval %agg.tmp) nounwind
   ret i32 %call
 ; CHECK-LABEL: @test7(
@@ -142,7 +142,7 @@ entry:
 
 declare i32 @g(%struct.p* align 8 byval)
 
-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
 
 ; PR11142 - When looking for a memcpy-memcpy dependency, don't get stuck on
 ; instructions between the memcpy's that only affect the destination pointer.
@@ -153,10 +153,10 @@ define void @test8() {
 ; CHECK-NOT: memcpy
   %A = tail call i8* @malloc(i32 10)
   %B = getelementptr inbounds i8, i8* %A, i64 2
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %B, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @test8.str, i64 0, i64 0), i32 7, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %B, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @test8.str, i64 0, i64 0), i32 7, i1 false)
   %C = tail call i8* @malloc(i32 10)
   %D = getelementptr inbounds i8, i8* %C, i64 2
-  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %D, i8* %B, i32 7, i32 1, i1 false)
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %D, i8* %B, i32 7, i1 false)
   ret void
 ; CHECK: ret void
 }
@@ -177,7 +177,7 @@ entry:
   call void @f1(%struct.big* sret %tmp)
   %0 = addrspacecast %struct.big* %b to i8 addrspace(1)*
   %1 = addrspacecast %struct.big* %tmp to i8 addrspace(1)*
-  call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %0, i8 addrspace(1)* %1, i64 200, i32 4, i1 false)
+  call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* align 4 %0, i8 addrspace(1)* align 4 %1, i64 200, i1 false)
   call void @f2(%struct.big* %b)
   ret void
 }
@@ -193,7 +193,7 @@ entry:
   call void @f1(%struct.big* sret %tmp)
   %0 = bitcast %struct.big* %b to i8*
   %1 = bitcast %struct.big* %tmp to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 200, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 200, i1 false)
   call void @f2(%struct.big* %b)
   ret void
 }
@@ -220,15 +220,15 @@ define void @test11([20 x i32] addrspace(1)* nocapture dereferenceable(80) %P) {
   %A = alloca [20 x i32], align 4
   %a = bitcast [20 x i32]* %A to i8*
   %b = bitcast [20 x i32] addrspace(1)* %P to i8 addrspace(1)*
-  call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 80, i32 4, i1 false)
-  call void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* %b, i8* %a, i64 80, i32 4, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 4 %a, i8 0, i64 80, i1 false)
+  call void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* align 4 %b, i8* align 4 %a, i64 80, i1 false)
   ret void
 ; CHECK-LABEL: @test11(
 ; CHECK-NOT: addrspacecast
 }
 
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind
-declare void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* nocapture, i8* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
+declare void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* nocapture, i8* nocapture, i64, i1) nounwind
 
 declare void @f1(%struct.big* nocapture sret)
 declare void @f2(%struct.big*)
diff --git a/llvm/test/Transforms/MemCpyOpt/memmove.ll b/llvm/test/Transforms/MemCpyOpt/memmove.ll
index 1af85a1edc5..91f2851ab78 100644
--- a/llvm/test/Transforms/MemCpyOpt/memmove.ll
+++ b/llvm/test/Transforms/MemCpyOpt/memmove.ll
@@ -4,7 +4,7 @@
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
 target triple = "x86_64-apple-darwin9.0"
 
-declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
 
 define i8* @test1(i8* nocapture %src) nounwind {
 entry:
@@ -14,7 +14,7 @@ entry:
   %malloccall = tail call i8* @malloc(i32 trunc (i64 mul nuw (i64 ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64), i64 13) to i32))
   %call3 = bitcast i8* %malloccall to [13 x i8]*
   %call3.sub = getelementptr inbounds [13 x i8], [13 x i8]* %call3, i64 0, i64 0
-  tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %call3.sub, i8* %src, i64 13, i32 1, i1 false)
+  tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %call3.sub, i8* %src, i64 13, i1 false)
   ret i8* %call3.sub
 }
 declare noalias i8* @malloc(i32)
@@ -25,7 +25,7 @@ entry:
 ; CHECK-LABEL: @test2(
 ; CHECK: call void @llvm.memcpy
   %add.ptr = getelementptr i8, i8* %P, i64 16
-  tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 16, i32 1, i1 false)
+  tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 16, i1 false)
   ret void
 }
 
@@ -35,6 +35,6 @@ entry:
 ; CHECK-LABEL: @test3(
 ; CHECK: call void @llvm.memmove
   %add.ptr = getelementptr i8, i8* %P, i64 16
-  tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 17, i32 1, i1 false)
+  tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 17, i1 false)
   ret void
 }
diff --git a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-redundant-memset.ll b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-redundant-memset.ll
index de29caa191d..a3ca96c3ab5 100644
--- a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-redundant-memset.ll
+++ b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-redundant-memset.ll
@@ -7,12 +7,12 @@ target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i64 %dst_size, %src_size
 ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i64 0, i64 [[SIZEDIFF]]
 ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i64 %src_size
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[DST]], i8 %c, i64 [[SIZE]], i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[DST]], i8 %c, i64 [[SIZE]], i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false)
 ; CHECK-NEXT: ret void
 define void @test(i8* %src, i64 %src_size, i8* %dst, i64 %dst_size, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false)
   ret void
 }
 
@@ -22,12 +22,12 @@ define void @test(i8* %src, i64 %src_size, i8* %dst, i64 %dst_size, i8 %c) {
 ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i64 [[DSTSIZE]], %src_size
 ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i64 0, i64 [[SIZEDIFF]]
 ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i64 %src_size
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[DST]], i8 %c, i64 [[SIZE]], i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[DST]], i8 %c, i64 [[SIZE]], i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_different_types_i32_i64(i8* %dst, i8* %src, i32 %dst_size, i64 %src_size, i8 %c) {
-  call void @llvm.memset.p0i8.i32(i8* %dst, i8 %c, i32 %dst_size, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %dst, i8 %c, i32 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false)
   ret void
 }
 
@@ -37,12 +37,12 @@ define void @test_different_types_i32_i64(i8* %dst, i8* %src, i32 %dst_size, i64
 ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i128 %dst_size, [[SRCSIZE]]
 ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i128 0, i128 [[SIZEDIFF]]
 ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i128 [[SRCSIZE]]
-; CHECK-NEXT: call void @llvm.memset.p0i8.i128(i8* [[DST]], i8 %c, i128 [[SIZE]], i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i128(i8* align 1 [[DST]], i8 %c, i128 [[SIZE]], i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_different_types_i128_i32(i8* %dst, i8* %src, i128 %dst_size, i32 %src_size, i8 %c) {
-  call void @llvm.memset.p0i8.i128(i8* %dst, i8 %c, i128 %dst_size, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i128(i8* %dst, i8 %c, i128 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i1 false)
   ret void
 }
 
@@ -52,12 +52,12 @@ define void @test_different_types_i128_i32(i8* %dst, i8* %src, i128 %dst_size, i
 ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i128 [[DSTSIZE]], %src_size
 ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i128 0, i128 [[SIZEDIFF]]
 ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i128 %src_size
-; CHECK-NEXT: call void @llvm.memset.p0i8.i128(i8* [[DST]], i8 %c, i128 [[SIZE]], i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i128(i8* %dst, i8* %src, i128 %src_size, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i128(i8* align 1 [[DST]], i8 %c, i128 [[SIZE]], i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i128(i8* %dst, i8* %src, i128 %src_size, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_different_types_i32_i128(i8* %dst, i8* %src, i32 %dst_size, i128 %src_size, i8 %c) {
-  call void @llvm.memset.p0i8.i32(i8* %dst, i8 %c, i32 %dst_size, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i128(i8* %dst, i8* %src, i128 %src_size, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* %dst, i8 %c, i32 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i128(i8* %dst, i8* %src, i128 %src_size, i1 false)
   ret void
 }
 
@@ -67,36 +67,36 @@ define void @test_different_types_i32_i128(i8* %dst, i8* %src, i32 %dst_size, i1
 ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i64 %dst_size, [[SRCSIZE]]
 ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i64 0, i64 [[SIZEDIFF]]
 ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i64 [[SRCSIZE]]
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[DST]], i8 %c, i64 [[SIZE]], i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[DST]], i8 %c, i64 [[SIZE]], i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_different_types_i64_i32(i8* %dst, i8* %src, i64 %dst_size, i32 %src_size, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_align_same
-; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 {{.*}}, i32 8, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 {{.*}}, i8 0, i64 {{.*}}, i1 false)
 define void @test_align_same(i8* %src, i8* %dst, i64 %dst_size) {
-  call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 8, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 80, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %dst, i8 0, i64 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 80, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_align_min
-; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 {{.*}}, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 {{.*}}, i8 0, i64 {{.*}}, i1 false)
 define void @test_align_min(i8* %src, i8* %dst, i64 %dst_size) {
-  call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 8, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 36, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %dst, i8 0, i64 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 36, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_align_memcpy
-; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 {{.*}}, i32 8, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 {{.*}}, i8 0, i64 {{.*}}, i1 false)
 define void @test_align_memcpy(i8* %src, i8* %dst, i64 %dst_size) {
-  call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 80, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst, i8* align 8 %src, i64 80, i1 false)
   ret void
 }
 
@@ -106,37 +106,37 @@ define void @test_align_memcpy(i8* %src, i8* %dst, i64 %dst_size) {
 ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i64 %dst_size, %src_size
 ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i64 0, i64 [[SIZEDIFF]]
 ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i64 %src_size
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[DST]], i8 %c, i64 [[SIZE]], i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[DST]], i8 %c, i64 [[SIZE]], i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_non_i8_dst_type(i8* %src, i64 %src_size, i64* %dst_pi64, i64 %dst_size, i8 %c) {
   %dst = bitcast i64* %dst_pi64 to i8*
-  call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_different_dst
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src, i64 %src_size, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src, i64 %src_size, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_different_dst(i8* %dst2, i8* %src, i64 %src_size, i8* %dst, i64 %dst_size) {
-  call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src, i64 %src_size, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src, i64 %src_size, i1 false)
   ret void
 }
 
 ; Make sure we also take into account dependencies on the destination.
 
 ; CHECK-LABEL: define i8 @test_intermediate_read
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 64, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 64, i1 false)
 ; CHECK-NEXT: %r = load i8, i8* %a
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 24, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 24, i1 false)
 ; CHECK-NEXT: ret i8 %r
 define i8 @test_intermediate_read(i8* %a, i8* %b) #0 {
-  call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 64, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 64, i1 false)
   %r = load i8, i8* %a
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 24, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 24, i1 false)
   ret i8 %r
 }
 
@@ -146,23 +146,23 @@ define i8 @test_intermediate_read(i8* %a, i8* %b) #0 {
 ; CHECK-NEXT: %a = alloca %struct
 ; CHECK-NEXT: %a0 = getelementptr %struct, %struct* %a, i32 0, i32 0, i32 0
 ; CHECK-NEXT: %a1 = getelementptr %struct, %struct* %a, i32 0, i32 1, i32 0
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %a0, i8 0, i64 16, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %a0, i8 0, i64 16, i1 false)
 ; CHECK-NEXT: store i8 1, i8* %a1
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a0, i8* %b, i64 8, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a0, i8* %b, i64 8, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_intermediate_write(i8* %b) #0 {
   %a = alloca %struct
   %a0 = getelementptr %struct, %struct* %a, i32 0, i32 0, i32 0
   %a1 = getelementptr %struct, %struct* %a, i32 0, i32 1, i32 0
-  call void @llvm.memset.p0i8.i64(i8* %a0, i8 0, i64 16, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %a0, i8 0, i64 16, i1 false)
   store i8 1, i8* %a1
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a0, i8* %b, i64 8, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a0, i8* %b, i64 8, i1 false)
   ret void
 }
 
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1)
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1)
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1)
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1)
-declare void @llvm.memset.p0i8.i128(i8* nocapture, i8, i128, i32, i1)
-declare void @llvm.memcpy.p0i8.p0i8.i128(i8* nocapture, i8* nocapture readonly, i128, i32, i1)
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1)
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1)
+declare void @llvm.memset.p0i8.i128(i8* nocapture, i8, i128, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i128(i8* nocapture, i8* nocapture readonly, i128, i1)
diff --git a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll
index 1c567042ce7..e36389a128f 100644
--- a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll
+++ b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll
@@ -3,99 +3,99 @@
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 ; CHECK-LABEL: define void @test(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 128, i32 8, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %dst2, i8 %c, i64 128, i1 false)
 ; CHECK-NEXT: ret void
 define void @test(i8* %dst1, i8* %dst2, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst2, i8* align 8 %dst1, i64 128, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_smaller_memcpy(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 100, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 100, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_smaller_memcpy(i8* %dst1, i8* %dst2, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 100, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 100, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_smaller_memset(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 100, i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 100, i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_smaller_memset(i8* %dst1, i8* %dst2, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 100, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 100, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_align_memset(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 8, i1 false)
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 128, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %dst1, i8 %c, i64 128, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 128, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_align_memset(i8* %dst1, i8* %dst2, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 8, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %dst1, i8 %c, i64 128, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_different_types(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 8, i1 false)
-; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %dst2, i8 %c, i32 100, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %dst1, i8 %c, i64 128, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %dst2, i8 %c, i32 100, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_different_types(i8* %dst1, i8* %dst2, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 8, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst2, i8* %dst1, i32 100, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %dst1, i8 %c, i64 128, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst2, i8* %dst1, i32 100, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_different_types_2(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %dst1, i8 %c, i32 128, i32 8, i1 false)
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 100, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 8 %dst1, i8 %c, i32 128, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 100, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_different_types_2(i8* %dst1, i8* %dst2, i8 %c) {
-  call void @llvm.memset.p0i8.i32(i8* %dst1, i8 %c, i32 128, i32 8, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 100, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 8 %dst1, i8 %c, i32 128, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 100, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_different_source_gep(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
 ; CHECK-NEXT: %p = getelementptr i8, i8* %dst1, i64 64
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %p, i64 64, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %p, i64 64, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_different_source_gep(i8* %dst1, i8* %dst2, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
   ; FIXME: We could optimize this as well.
   %p = getelementptr i8, i8* %dst1, i64 64
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %p, i64 64, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %p, i64 64, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_variable_size_1(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 %dst1_size, i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 %dst1_size, i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_variable_size_1(i8* %dst1, i64 %dst1_size, i8* %dst2, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 %dst1_size, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 %dst1_size, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false)
   ret void
 }
 
 ; CHECK-LABEL: define void @test_variable_size_2(
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
-; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 %dst2_size, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 %dst2_size, i1 false)
 ; CHECK-NEXT: ret void
 define void @test_variable_size_2(i8* %dst1, i8* %dst2, i64 %dst2_size, i8 %c) {
-  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 %dst2_size, i32 1, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 %dst2_size, i1 false)
   ret void
 }
 
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1)
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1)
-declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1)
-declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1)
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1)
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1)
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1)
diff --git a/llvm/test/Transforms/MemCpyOpt/pr29105.ll b/llvm/test/Transforms/MemCpyOpt/pr29105.ll
index 03b176c4d24..e9e9b611aef 100644
--- a/llvm/test/Transforms/MemCpyOpt/pr29105.ll
+++ b/llvm/test/Transforms/MemCpyOpt/pr29105.ll
@@ -13,12 +13,12 @@ entry-block:
   %x.sroa.0.0..sroa_cast6 = bitcast [2048 x i64]* %x.sroa.0 to i8*
   call void @llvm.lifetime.start.p0i8(i64 16384, i8* %x.sroa.0.0..sroa_cast6)
   call void @llvm.lifetime.start.p0i8(i64 16384, i8* %0)
-  call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 16384, i32 8, i1 false)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %x.sroa.0.0..sroa_cast6, i8* %0, i64 16384, i32 8, i1 false)
+  call void @llvm.memset.p0i8.i64(i8* align 8 %0, i8 0, i64 16384, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %x.sroa.0.0..sroa_cast6, i8* align 8 %0, i64 16384, i1 false)
   call void @llvm.lifetime.end.p0i8(i64 16384, i8* %0)
   %1 = bitcast %Foo* %tmp2 to i8*
   call void @llvm.lifetime.start.p0i8(i64 16384, i8* %1)
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %x.sroa.0.0..sroa_cast6, i64 16384, i32 8, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %1, i8* align 8 %x.sroa.0.0..sroa_cast6, i64 16384, i1 false)
   call void @bar(%Foo* noalias nocapture nonnull dereferenceable(16384) %tmp2)
   call void @llvm.lifetime.end.p0i8(i64 16384, i8* %1)
   call void @llvm.lifetime.end.p0i8(i64 16384, i8* %x.sroa.0.0..sroa_cast6)
@@ -27,13 +27,13 @@ entry-block:
 
 declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1
 
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #1
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #1
 
 declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1
 
 declare void @bar(%Foo* noalias nocapture readonly dereferenceable(16384)) unnamed_addr #0
 
-declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i32, i1) #1
+declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1) #1
 
 attributes #0 = { uwtable }
 attributes #1 = { argmemonly nounwind }
diff --git a/llvm/test/Transforms/MemCpyOpt/profitable-memset.ll b/llvm/test/Transforms/MemCpyOpt/profitable-memset.ll
index bbef1244ee3..649d2386f96 100644
--- a/llvm/test/Transforms/MemCpyOpt/profitable-memset.ll
+++ b/llvm/test/Transforms/MemCpyOpt/profitable-memset.ll
@@ -4,7 +4,7 @@ target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 
 ; CHECK-LABEL: @foo(
 ; CHECK-NOT: store
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %2, i8 0, i64 8, i32 2, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 2 %2, i8 0, i64 8, i1 false)
 
 define void @foo(i64* nocapture %P) {
 entry:
diff --git a/llvm/test/Transforms/MemCpyOpt/smaller.ll b/llvm/test/Transforms/MemCpyOpt/smaller.ll
index d0ec56e25dd..0c82b5201dc 100644
--- a/llvm/test/Transforms/MemCpyOpt/smaller.ll
+++ b/llvm/test/Transforms/MemCpyOpt/smaller.ll
@@ -5,7 +5,7 @@
 ; Memcpyopt shouldn't optimize the second memcpy using the first
 ; because the first has a smaller size.
 
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp, i8* getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i32 16, i32 4, i1 false)
+; CHECK: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %tmp, i8* align 4 getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i32 16, i1 false)
 
 target datalayout = "e-p:32:32:32"
 
@@ -15,15 +15,15 @@ target datalayout = "e-p:32:32:32"
 @cell = external global %struct.s
 
 declare void @check(%struct.s* byval %p) nounwind
-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 @foo() nounwind {
 entry:
   %agg.tmp = alloca %struct.s, align 4
   store i32 99, i32* getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 1), align 4
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i8* getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i32 0, i32 0), i32 11, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i8* align 1 getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i32 0, i32 0), i32 11, i1 false)
   %tmp = getelementptr inbounds %struct.s, %struct.s* %agg.tmp, i32 0, i32 0, i32 0
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp, i8* getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i32 16, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %tmp, i8* align 4 getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i32 16, i1 false)
   call void @check(%struct.s* byval %agg.tmp)
   ret void
 }
diff --git a/llvm/test/Transforms/MemCpyOpt/sret.ll b/llvm/test/Transforms/MemCpyOpt/sret.ll
index 34ba4c4d8bb..a99b52d5d6e 100644
--- a/llvm/test/Transforms/MemCpyOpt/sret.ll
+++ b/llvm/test/Transforms/MemCpyOpt/sret.ll
@@ -21,10 +21,10 @@ entry:
   call void @ccoshl(%0* noalias sret %memtmp, %0* byval align 8 %iz) nounwind
   %memtmp14 = bitcast %0* %memtmp to i8*
   %agg.result15 = bitcast %0* %agg.result to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %agg.result15, i8* %memtmp14, i32 32, i32 16, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %agg.result15, i8* align 16 %memtmp14, i32 32, i1 false)
   ret void
 }
 
 declare void @ccoshl(%0* noalias nocapture sret, %0* byval) nounwind
 
-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