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

1 files changed, 51 insertions, 51 deletions

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)