[SDAG] Use ABI type alignment for constant pools when optimizing for size

SelectionDAG::getConstantPool will automatically determine an appropriate alignment if one is not specified. It does this by querying the type's preferred alignment. This can end up creating quite a lot of padding when the preferred alignment for vectors is 128.

In optimize-for-size mode, it makes sense to instead query the ABI type alignment which is often smaller and causes less padding.

llvm-svn: 284381

2 files changed, 22 insertions, 1 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 19fae7fa748..7cca214da49 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -1315,7 +1315,9 @@ SDValue SelectionDAG::getConstantPool(const Constant *C, EVT VT,
   assert((TargetFlags == 0 || isTarget) &&
          "Cannot set target flags on target-independent globals");
   if (Alignment == 0)
-    Alignment = getDataLayout().getPrefTypeAlignment(C->getType());
+    Alignment = MF->getFunction()->optForSize()
+                    ? getDataLayout().getABITypeAlignment(C->getType())
+                    : getDataLayout().getPrefTypeAlignment(C->getType());
   unsigned Opc = isTarget ? ISD::TargetConstantPool : ISD::ConstantPool;
   FoldingSetNodeID ID;
   AddNodeIDNode(ID, Opc, getVTList(VT), None);
diff --git a/llvm/test/CodeGen/ARM/constantpool-align.ll b/llvm/test/CodeGen/ARM/constantpool-align.ll
new file mode 100644
index 00000000000..1815b87469b
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/constantpool-align.ll
@@ -0,0 +1,19 @@
+; RUN: llc < %s | FileCheck %s
+target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
+target triple = "thumbv7-arm-none-eabi"
+
+; CHECK-LABEL: f:
+; CHECK: vld1.64 {{.*}}, [r1:128]
+; CHECK: .p2align 4
+define void @f(<4 x i32>* %p) {
+  store <4 x i32> <i32 -1, i32 0, i32 0, i32 -1>, <4 x i32>* %p, align 4
+  ret void 
+}
+
+; CHECK-LABEL: f_optsize:
+; CHECK: vld1.64 {{.*}}, [r1]
+; CHECK: .p2align 3
+define void @f_optsize(<4 x i32>* %p) optsize {
+  store <4 x i32> <i32 -1, i32 0, i32 0, i32 -1>, <4 x i32>* %p, align 4
+  ret void 
+}