[ARM] Use preferred alignment for constants in promoteToConstantPool.

[efriedma]

Summary

This mostly affects IR generated by non-clang frontends because clang generally sets the alignment of globals explicitly.

Fixes https://bugs.llvm.org//show_bug.cgi?id=32394 .

(-arm-promote-constant is currently off by default, and it stays off with this patch. I'll look into turning it on again when all the known issues are fixed.)

[dmgreen]

This looks fine to me, if like you say the over aligning to 16 thing is not something that should come up a lot.

Do we check anywhere that the global is not in a section?

[efriedma]

Do we check anywhere that the global is not in a section?

Looks like no? It's not particularly like to come up, I would guess: a constant with a section marking would usually also either have external linkage or be marked used (which would both suppress the transform). But I'll write a followup patch.

llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp

static SDValue promoteToConstantPool(const GlobalValue *GV, SelectionDAG &DAG,
   // The constant islands pass can only really deal with alignment requests
   // <= 4 bytes and cannot pad constants itself. Therefore we cannot promote
   // any type wanting greater alignment requirements than 4 bytes. We also
   // can only promote constants that are multiples of 4 bytes in size or
   // are paddable to a multiple of 4. Currently we only try and pad constants
   // that are strings for simplicity.
   auto *CDAInit = dyn_cast<ConstantDataArray>(Init);
   unsigned Size = DAG.getDataLayout().getTypeAllocSize(Init->getType());
-  unsigned Align = GVar->getAlignment();
+  unsigned Align = DAG.getDataLayout().getPreferredAlignment(GVar);
   unsigned RequiredPadding = 4 - (Size % 4);
   bool PaddingPossible =
     RequiredPadding == 4 || (CDAInit && CDAInit->isString());
   if (!PaddingPossible || Align > 4 || Size > ConstpoolPromotionMaxSize ||
       Size == 0)
     return SDValue();
 
   unsigned PaddedSize = Size + ((RequiredPadding == 4) ? 0 : RequiredPadding);

llvm/trunk/test/CodeGen/ARM/constantpool-promote.ll

 @.str3 = private unnamed_addr constant [26 x i8] c"this string is used twice\00", align 1
 @.str4 = private unnamed_addr constant [29 x i8] c"same string in two functions\00", align 1
 @.arr1 = private unnamed_addr constant [2 x i16] [i16 3, i16 4], align 2
 @.arr2 = private unnamed_addr constant [2 x i16] [i16 7, i16 8], align 2
 @.arr3 = private unnamed_addr constant [2 x i16*] [i16* null, i16* null], align 4
 @.ptr = private unnamed_addr constant [2 x i16*] [i16* getelementptr inbounds ([2 x i16], [2 x i16]* @.arr2, i32 0, i32 0), i16* null], align 2
 @.arr4 = private unnamed_addr constant [2 x i16] [i16 3, i16 4], align 16
 @.zerosize = private unnamed_addr constant [0 x i16] zeroinitializer, align 4
+@implicit_alignment_vector = private unnamed_addr constant <4 x i32> <i32 1, i32 2, i32 3, i32 4>
 
 ; CHECK-LABEL: @test1
 ; CHECK: adr r0, [[x:.*]]
 ; CHECK: [[x]]:
 ; CHECK: .asciz "s\000\000"
 define void @test1() #0 {
   tail call void @a(i8* getelementptr inbounds ([2 x i8], [2 x i8]* @.str, i32 0, i32 0)) #2
   ret void

 ; CHECK-V7ARM: [[x]]:
 ; CHECK-V7ARM: .short 3
 ; CHECK-V7ARM: .short 4
 define void @test11(i16* %a) local_unnamed_addr #0 {
   call void @llvm.memmove.p0i16.p0i16.i32(i16* align 2 %a, i16* align 2 getelementptr inbounds ([2 x i16], [2 x i16]* @.arr1, i32 0, i32 0), i32 2, i1 false)
   ret void
 }
 
+; Promotion only works with globals with alignment 4 or less; a vector has
+; implicit alignment 16.
+; CHECK-LABEL: @test12
+; CHECK-NOT: adr
+define void @test12() local_unnamed_addr #0 {
+  call void @d(<4 x i32>* @implicit_alignment_vector)
+  ret void
+}
+
 
 declare void @b(i8*) #1
 declare void @c(i16*) #1
+declare void @d(<4 x i32>*) #1
 declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1)
 declare void @llvm.memmove.p0i8.p0i8.i32(i8*, i8*, i32, i1) local_unnamed_addr
 declare void @llvm.memmove.p0i16.p0i16.i32(i16*, i16*, i32, i1) local_unnamed_addr
 
 attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
 attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
 attributes #2 = { nounwind }
 
 !llvm.module.flags = !{!0, !1}
 
 !0 = !{i32 1, !"wchar_size", i32 4}
 !1 = !{i32 1, !"min_enum_size", i32 4}