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

4 files changed, 16 insertions, 16 deletions

diff --git a/llvm/test/Transforms/LoopIdiom/basic-address-space.ll b/llvm/test/Transforms/LoopIdiom/basic-address-space.ll
index 67cabf36eec..c709b9acd58 100644
--- a/llvm/test/Transforms/LoopIdiom/basic-address-space.ll
+++ b/llvm/test/Transforms/LoopIdiom/basic-address-space.ll
@@ -7,7 +7,7 @@ target triple = "x86_64-apple-darwin10.0.0"
 define void @test10(i8 addrspace(2)* %X) nounwind ssp {
 ; CHECK-LABEL: @test10(
 ; CHECK: entry:
-; CHECK-NEXT: call void @llvm.memset.p2i8.i16(i8 addrspace(2)* %X, i8 0, i16 10000, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p2i8.i16(i8 addrspace(2)* align 1 %X, i8 0, i16 10000, i1 false)
 ; CHECK-NOT: store
 ; CHECK: ret void
 
diff --git a/llvm/test/Transforms/LoopIdiom/basic.ll b/llvm/test/Transforms/LoopIdiom/basic.ll
index ba3e8a04704..e16817fe364 100644
--- a/llvm/test/Transforms/LoopIdiom/basic.ll
+++ b/llvm/test/Transforms/LoopIdiom/basic.ll
@@ -24,7 +24,7 @@ for.body:                                         ; preds = %bb.nph, %for.body
 for.end:                                          ; preds = %for.body, %entry
   ret void
 ; CHECK-LABEL: @test1(
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %Base, i8 0, i64 %Size, i1 false)
 ; CHECK-NOT: store
 }
 
@@ -47,7 +47,7 @@ for.body.cont:
 for.end:                                          ; preds = %for.body, %entry
   ret void
 ; CHECK-LABEL: @test1a(
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %Base, i8 0, i64 %Size, i1 false)
 ; CHECK-NOT: store
 }
 
@@ -70,7 +70,7 @@ for.end:                                          ; preds = %for.body, %entry
 ; CHECK-LABEL: @test2(
 ; CHECK: br i1 %cmp10,
 ; CHECK: %0 = shl i64 %Size, 2
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base1, i8 1, i64 %0, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %Base1, i8 1, i64 %0, i1 false)
 ; CHECK-NOT: store
 }
 
@@ -118,7 +118,7 @@ for.body:                                         ; preds = %bb.nph, %for.body
 for.end:                                          ; preds = %for.body, %entry
   ret void
 ; CHECK-LABEL: @test4(
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 100, i32 1, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %Base, i8 0, i64 100, i1 false)
 }
 
 ; This can't be promoted: the memset is a store of a loop variant value.
@@ -164,7 +164,7 @@ for.body:                                         ; preds = %bb.nph, %for.body
 for.end:                                          ; preds = %for.body, %entry
   ret void
 ; CHECK-LABEL: @test6(
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %Dest, i8* %Base, i64 %Size, i32 1, i1 false)
+; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i1 false)
 ; CHECK-NOT: store
 ; CHECK: ret void
 }
@@ -189,7 +189,7 @@ for.body.cont:
 for.end:                                          ; preds = %for.body, %entry
   ret void
 ; CHECK-LABEL: @test7(
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %Base, i8 0, i64 %Size, i1 false)
 ; CHECK-NOT: store
 }
 
@@ -274,7 +274,7 @@ for.end13:                                        ; preds = %for.inc10
   ret void
 ; CHECK-LABEL: @test10(
 ; CHECK: entry:
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %X, i8 0, i64 10000, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 %X, i8 0, i64 10000, i1 false)
 ; CHECK-NOT: store
 ; CHECK: ret void
 }
@@ -322,7 +322,7 @@ for.end:                                          ; preds = %for.body
 ; CHECK-LABEL: @test12(
 ; CHECK-NEXT: entry:
 ; CHECK-NEXT: bitcast
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %P1, i8 0, i64 80000, i32 4, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 %P1, i8 0, i64 80000, i1 false)
 ; CHECK-NOT: store
 ; CHECK: ret void
 }
@@ -439,7 +439,7 @@ for.body:
 for.cond.cleanup:
   ret void
 ; CHECK-LABEL: @test15(
-; CHECK: call void @llvm.memset.p0i8.i64(i8* %f1, i8 0, i64 262148, i32 4, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %f1, i8 0, i64 262148, i1 false)
 ; CHECK-NOT: store
 ; CHECK: ret void
 }
@@ -559,7 +559,7 @@ for.end6:                                         ; preds = %for.inc4
   ret void
 ; CHECK-LABEL: @test19(
 ; CHECK: entry:
-; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %X, i8 0, i64 10000, i32 1, i1 false)
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 %X, i8 0, i64 10000, i1 false)
 ; CHECK: ret void
 }
 
@@ -579,7 +579,7 @@ loop.ph:
 ; CHECK:       loop.ph:
 ; CHECK-NEXT:    %[[ZEXT_SIZE:.*]] = zext i32 %size to i64
 ; CHECK-NEXT:    %[[SCALED_SIZE:.*]] = shl i64 %[[ZEXT_SIZE]], 3
-; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* %{{.*}}, i8 0, i64 %[[SCALED_SIZE]], i32 8, i1 false)
+; CHECK-NEXT:    call void @llvm.memset.p0i8.i64(i8* align 8 %{{.*}}, i8 0, i64 %[[SCALED_SIZE]], i1 false)
 
 loop.body:
   %storemerge4 = phi i32 [ 0, %loop.ph ], [ %inc, %loop.body ]
@@ -611,7 +611,7 @@ loop.ph:
 ; CHECK:       loop.ph:
 ; CHECK-NEXT:    %[[ZEXT_SIZE:.*]] = zext i32 %size to i64
 ; CHECK-NEXT:    %[[SCALED_SIZE:.*]] = shl i64 %[[ZEXT_SIZE]], 3
-; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* %{{.*}}, i8* %{{.*}}, i64 %[[SCALED_SIZE]], i32 8, i1 false)
+; CHECK-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %{{.*}}, i8* align 8 %{{.*}}, i64 %[[SCALED_SIZE]], i1 false)
 
 loop.body:
   %storemerge4 = phi i32 [ 0, %loop.ph ], [ %inc, %loop.body ]
diff --git a/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll b/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll
index 61c14694c3c..e1e07a06d69 100644
--- a/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll
+++ b/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll
@@ -5,7 +5,7 @@
 ; - a loop_memset idiom, or
 ; - a memset/memcpy idiom in a nested loop.
 
-declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1)
+declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1)
 @APPLES = common global i32 0, align 4
 @ORANGES = common global i32 0, align 4
 
@@ -28,7 +28,7 @@ for.body:                                         ; preds = %for.body.preheader,
   %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.inc ]
   %BASKET.013 = phi i32 [ %BASKET.1, %for.inc ], [ 0, %for.body.preheader ]
   %arraydecay = getelementptr inbounds [2048 x i8], [2048 x i8]* %DST, i64 %indvars.iv, i64 0
-  tail call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 -1, i64 2048, i32 1, i1 false)
+  tail call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 -1, i64 2048, i1 false)
   %0 = trunc i64 %indvars.iv to i32
   %rem11 = and i32 %0, 1
   %cmp1 = icmp eq i32 %rem11, 0
diff --git a/llvm/test/Transforms/LoopIdiom/pr28196.ll b/llvm/test/Transforms/LoopIdiom/pr28196.ll
index 10f49fbcd09..9057bdbb103 100644
--- a/llvm/test/Transforms/LoopIdiom/pr28196.ll
+++ b/llvm/test/Transforms/LoopIdiom/pr28196.ll
@@ -22,5 +22,5 @@ for.body:                                         ; preds = %for.body, %for.body
 }
 
 ; CHECK-LABEL: define void @test1(
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* null, i8* inttoptr (i64 4 to i8*), i64 24, i32 4, i1 false)
+; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 null, i8* align 4 inttoptr (i64 4 to i8*), i64 24, i1 false)
 ; CHECK-NOT: store