[PATCH] D10826: Fix AArch64 prologue for empty frame with dynamic allocas

[Evgeniy Stepanov]

eugenis updated this revision to Diff 29495.
eugenis added a comment.

updated comments


http://reviews.llvm.org/D10826

Files:
  lib/Target/AArch64/AArch64FrameLowering.cpp
  test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll

Index: test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
===================================================================
--- test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
+++ test/CodeGen/AArch64/aarch64-dynamic-stack-layout.ll
@@ -482,6 +482,56 @@
 ; CHECK: ldp	x20, x19, [sp], #32
 ; CHECK: ret
 
+
+define void @realign_conditional(i1 %b) {
+entry:
+  br i1 %b, label %bb0, label %bb1
+
+bb0:
+  %MyAlloca = alloca i8, i64 64, align 32
+  br label %bb1
+
+bb1:
+  ret void
+}
+
+; CHECK-LABEL: realign_conditional
+; No realignment in the prologue.
+; CHECK-NOT:  and
+; CHECK-NOT:  0xffffffffffffffe0
+; CHECK:  tbz  {{.*}} .[[LABEL:.*]]
+; Stack is realigned in a non-entry BB.
+; CHECK:  sub  [[REG:x[01-9]+]], sp, #64
+; CHECK:  and  sp, [[REG]], #0xffffffffffffffe0
+; CHECK:  .[[LABEL]]:
+; CHECK:  ret
+
+
+define void @realign_conditional2(i1 %b) {
+entry:
+  %tmp = alloca i8, i32 4
+  br i1 %b, label %bb0, label %bb1
+
+bb0:
+  %MyAlloca = alloca i8, i64 64, align 32
+  br label %bb1
+
+bb1:
+  ret void
+}
+
+; CHECK-LABEL: realign_conditional2
+; Extra realignment in the prologue (performance issue).
+; CHECK:  sub  x9, sp, #32            // =32
+; CHECK:  and  sp, x9, #0xffffffffffffffe0
+; CHECK:  mov   x19, sp
+; CHECK:  tbz  {{.*}} .[[LABEL:.*]]
+; Stack is realigned in a non-entry BB.
+; CHECK:  sub  [[REG:x[01-9]+]], sp, #64
+; CHECK:  and  sp, [[REG]], #0xffffffffffffffe0
+; CHECK:  .[[LABEL]]:
+; CHECK:  ret
+
 attributes #0 = { "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 = { 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" }
 
Index: lib/Target/AArch64/AArch64FrameLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64FrameLowering.cpp
+++ lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -349,13 +349,12 @@
   // Allocate space for the rest of the frame.
 
   const unsigned Alignment = MFI->getMaxAlignment();
-  const bool NeedsRealignment = (Alignment > 16);
+  const bool NeedsRealignment = RegInfo->needsStackRealignment(MF);
   unsigned scratchSPReg = AArch64::SP;
-  if (NeedsRealignment) {
-    // Use the first callee-saved register as a scratch register
-    assert(MF.getRegInfo().isPhysRegUsed(AArch64::X9) &&
-           "No scratch register to align SP!");
+  if (NumBytes && NeedsRealignment) {
+    // Use the first callee-saved register as a scratch register.
     scratchSPReg = AArch64::X9;
+    MF.getRegInfo().setPhysRegUsed(scratchSPReg);
   }
 
   // If we're a leaf function, try using the red zone.
@@ -366,9 +365,6 @@
     emitFrameOffset(MBB, MBBI, DL, scratchSPReg, AArch64::SP, -NumBytes, TII,
                     MachineInstr::FrameSetup);
 
-  assert(!(NeedsRealignment && NumBytes==0) &&
-         "NumBytes should never be 0 when realignment is needed");
-
   if (NumBytes && NeedsRealignment) {
     const unsigned NrBitsToZero = countTrailingZeros(Alignment);
     assert(NrBitsToZero > 1);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D10826.29495.patch
Type: text/x-patch
Size: 3325 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20150710/8bc20278/attachment.bin>