[CodeGenPrepare] Improve source and dest alignments of memory intrinsics independently

Summary:
  This change is part of step five in the series of changes to remove alignment argument from
memcpy/memmove/memset in favour of alignment attributes. In particular, this changes the
CodeGenPrepare pass to be more aggressive in improving the source and destination alignments
of memcpy/memmove/memset by exploiting our new ability to record independent alignments
for each argument.

Steps:
Step 1) Remove alignment parameter and create alignment parameter attributes for
memcpy/memmove/memset. ( rL322965, rC322964, rL322963 )
Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing
source and dest alignments. ( rL323597 )
Step 3) Update Clang to use the new IRBuilder API. ( rC323617 )
Step 4) Update Polly to use the new IRBuilder API. ( rL323618 )
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 [get|set]DestAlignment()
and [get|set]SourceAlignment() instead. ( rL323886 )
Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the
MemIntrinsicInst::[get|set]Alignment() methods.

Reference
   http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html
   http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html

llvm-svn: 323891

2 files changed, 51 insertions, 5 deletions

diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
index af6f399..78b1ec0 100644
--- a/llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ b/llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -1606,11 +1606,14 @@ bool CodeGenPrepare::optimizeCallInst(CallInst *CI, bool &ModifiedDT) {
     // If this is a memcpy (or similar) then we may be able to improve the
     // alignment
     if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(CI)) {
-      unsigned Align = getKnownAlignment(MI->getDest(), *DL);
-      if (MemTransferInst *MTI = dyn_cast<MemTransferInst>(MI))
-        Align = std::min(Align, getKnownAlignment(MTI->getSource(), *DL));
-      if (Align > MI->getAlignment())
-        MI->setAlignment(Align);
+      unsigned DestAlign = getKnownAlignment(MI->getDest(), *DL);
+      if (DestAlign > MI->getDestAlignment())
+        MI->setDestAlignment(DestAlign);
+      if (MemTransferInst *MTI = dyn_cast<MemTransferInst>(MI)) {
+        unsigned SrcAlign = getKnownAlignment(MTI->getSource(), *DL);
+        if (SrcAlign > MTI->getSourceAlignment())
+          MTI->setSourceAlignment(SrcAlign);
+      }
     }
   }
 
diff --git a/llvm/test/Transforms/CodeGenPrepare/ARM/memory-intrinsics.ll b/llvm/test/Transforms/CodeGenPrepare/ARM/memory-intrinsics.ll
new file mode 100644
index 0000000..8b70d93
--- /dev/null
+++ b/llvm/test/Transforms/CodeGenPrepare/ARM/memory-intrinsics.ll
@@ -0,0 +1,43 @@
+; RUN: opt -codegenprepare -mtriple=arm7-unknown-unknown -S < %s | FileCheck %s
+
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i1) nounwind
+declare void @llvm.memmove.p0i8.p0i8.i32(i8*, i8*, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8*, i8, i32, i1) nounwind
+
+define void @test_memcpy(i8* align 4 %dst, i8* align 8 %src, i32 %N) {
+; CHECK-LABEL: @test_memcpy
+; CHECK: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dst, i8* align 8 %src, i32 %N, i1 false)
+; CHECK: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dst, i8* align 8 %src, i32 %N, i1 false)
+; CHECK: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dst, i8* align 16 %src, i32 %N, i1 false)
+entry:
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %N, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %dst, i8* align 2 %src, i32 %N, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dst, i8* align 16 %src, i32 %N, i1 false)
+  ret void
+}
+
+define void @test_memmove(i8* align 4 %dst, i8* align 8 %src, i32 %N) {
+; CHECK-LABEL: @test_memmove
+; CHECK: call void @llvm.memmove.p0i8.p0i8.i32(i8* align 4 %dst, i8* align 8 %src, i32 %N, i1 false)
+; CHECK: call void @llvm.memmove.p0i8.p0i8.i32(i8* align 4 %dst, i8* align 8 %src, i32 %N, i1 false)
+; CHECK: call void @llvm.memmove.p0i8.p0i8.i32(i8* align 8 %dst, i8* align 16 %src, i32 %N, i1 false)
+entry:
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %N, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* align 2 %dst, i8* align 2 %src, i32 %N, i1 false)
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* align 8 %dst, i8* align 16 %src, i32 %N, i1 false)
+  ret void
+}
+
+define void @test_memset(i8* align 4 %dst, i8 %val, i32 %N) {
+; CHECK-LABEL: @test_memset
+; CHECK: call void @llvm.memset.p0i8.i32(i8* align 4 %dst, i8 %val, i32 %N, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i32(i8* align 4 %dst, i8 %val, i32 %N, i1 false)
+; CHECK: call void @llvm.memset.p0i8.i32(i8* align 8 %dst, i8 %val, i32 %N, i1 false)
+entry:
+  call void @llvm.memset.p0i8.i32(i8* %dst, i8 %val, i32 %N, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 2 %dst, i8 %val, i32 %N, i1 false)
+  call void @llvm.memset.p0i8.i32(i8* align 8 %dst, i8 %val, i32 %N, i1 false)
+  ret void
+}
+
+