From: Jakob Stoklund Olesen <stoklund@2pi.dk>
Date: Tue, 20 Dec 2011 22:15:04 +0000 (+0000)
Subject: Heed spill slot alignment on ARM.
X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=52346e964ff1108729c2b8990b859c10f09a1822;p=oota-llvm.git

Heed spill slot alignment on ARM.

Use the spill slot alignment as well as the local variable alignment to
determine when the stack needs to be realigned. This works now that the
ARM target can always realign the stack by using a base pointer.

Still respect the ARMBaseRegisterInfo::canRealignStack() function
vetoing a realigned stack.  Don't use aligned spill code in that case.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146997 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/ARM/ARMBaseInstrInfo.cpp b/lib/Target/ARM/ARMBaseInstrInfo.cpp
index 8bf5475fcd7..3cb69828c6c 100644
--- a/lib/Target/ARM/ARMBaseInstrInfo.cpp
+++ b/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -765,7 +765,8 @@ storeRegToStackSlot(MachineBasicBlock &MBB, MachineBasicBlock::iterator I,
       break;
     case 16:
       if (ARM::QPRRegClass.hasSubClassEq(RC)) {
-        if (Align >= 16 && getRegisterInfo().needsStackRealignment(MF)) {
+        // Use aligned spills if the stack can be realigned.
+        if (Align >= 16 && getRegisterInfo().canRealignStack(MF)) {
           AddDefaultPred(BuildMI(MBB, I, DL, get(ARM::VST1q64Pseudo))
                      .addFrameIndex(FI).addImm(16)
                      .addReg(SrcReg, getKillRegState(isKill))
@@ -914,7 +915,7 @@ loadRegFromStackSlot(MachineBasicBlock &MBB, MachineBasicBlock::iterator I,
     break;
   case 16:
     if (ARM::QPRRegClass.hasSubClassEq(RC)) {
-      if (Align >= 16 && getRegisterInfo().needsStackRealignment(MF)) {
+      if (Align >= 16 && getRegisterInfo().canRealignStack(MF)) {
         AddDefaultPred(BuildMI(MBB, I, DL, get(ARM::VLD1q64Pseudo), DestReg)
                      .addFrameIndex(FI).addImm(16)
                      .addMemOperand(MMO));
diff --git a/lib/Target/ARM/ARMBaseRegisterInfo.cpp b/lib/Target/ARM/ARMBaseRegisterInfo.cpp
index 9c91bcc3075..44efb6a761e 100644
--- a/lib/Target/ARM/ARMBaseRegisterInfo.cpp
+++ b/lib/Target/ARM/ARMBaseRegisterInfo.cpp
@@ -542,7 +542,7 @@ needsStackRealignment(const MachineFunction &MF) const {
   const MachineFrameInfo *MFI = MF.getFrameInfo();
   const Function *F = MF.getFunction();
   unsigned StackAlign = MF.getTarget().getFrameLowering()->getStackAlignment();
-  bool requiresRealignment = ((MFI->getLocalFrameMaxAlign() > StackAlign) ||
+  bool requiresRealignment = ((MFI->getMaxAlignment() > StackAlign) ||
                                F->hasFnAttr(Attribute::StackAlignment));
 
   return requiresRealignment && canRealignStack(MF);
diff --git a/test/CodeGen/ARM/fast-isel-deadcode.ll b/test/CodeGen/ARM/fast-isel-deadcode.ll
index 1d77975ee86..7e147c7b4d7 100644
--- a/test/CodeGen/ARM/fast-isel-deadcode.ll
+++ b/test/CodeGen/ARM/fast-isel-deadcode.ll
@@ -15,8 +15,7 @@ entry:
 ; THUMB-NOT: sxtb
 ; THUMB: movs r0, #0
 ; THUMB: movt r0, #0
-; THUMB: add sp, #32
-; THUMb: pop {r7, pc}
+; THUMB: pop
   ret i32 0
 }
 
diff --git a/test/CodeGen/Thumb2/aligned-spill.ll b/test/CodeGen/Thumb2/aligned-spill.ll
new file mode 100644
index 00000000000..1a987d02d07
--- /dev/null
+++ b/test/CodeGen/Thumb2/aligned-spill.ll
@@ -0,0 +1,22 @@
+; RUN: llc < %s -mcpu=cortex-a8 | FileCheck %s
+target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
+target triple = "thumbv7-apple-ios"
+
+; CHECK: f
+; This function is forced to spill a double.
+; Verify that the spill slot is properly aligned.
+;
+; The caller-saved r4 is used as a scratch register for stack realignment.
+; CHECK: push {r4, r7, lr}
+; CHECK: bic r4, r4, #7
+; CHECK: mov sp, r4
+define void @f(double* nocapture %p) nounwind ssp {
+entry:
+  %0 = load double* %p, align 4
+  tail call void asm sideeffect "", "~{d8},~{d9},~{d10},~{d11},~{d12},~{d13},~{d14},~{d15}"() nounwind
+  tail call void @g() nounwind
+  store double %0, double* %p, align 4
+  ret void
+}
+
+declare void @g()