[AArch64] Correctly recognize -reserve-regs-for-regalloc=X30,X29

In AArch64 backend X30 is named as LR, X29 is named as FP. So the code in AArch64Subtarget::AArch64Subtarget can't recognize these 2 registers.

  for (unsigned i = 0; i < 31; ++i) {
    if (ReservedRegNames.count(TRI->getName(AArch64::X0 + i)))
      ReserveXRegisterForRA.set(i);
  }

This patch add code to explicitly handle these 2 registers.

Differential Revision: https://reviews.llvm.org/D137810

diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index e54f54b..bf3a9b4 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -312,10 +312,16 @@ AArch64Subtarget::AArch64Subtarget(const Triple &TT, const std::string &CPU,
   auto TRI = getRegisterInfo();
   StringSet<> ReservedRegNames;
   ReservedRegNames.insert(ReservedRegsForRA.begin(), ReservedRegsForRA.end());
-  for (unsigned i = 0; i < 31; ++i) {
+  for (unsigned i = 0; i < 29; ++i) {
     if (ReservedRegNames.count(TRI->getName(AArch64::X0 + i)))
       ReserveXRegisterForRA.set(i);
   }
+  // X30 is named LR, so we can't use TRI->getName to check X30.
+  if (ReservedRegNames.count("X30") || ReservedRegNames.count("LR"))
+    ReserveXRegisterForRA.set(30);
+  // X29 is named FP, so we can't use TRI->getName to check X29.
+  if (ReservedRegNames.count("X29") || ReservedRegNames.count("FP"))
+    ReserveXRegisterForRA.set(29);
 }
 
 const CallLowering *AArch64Subtarget::getCallLowering() const {

diff --git a/llvm/test/CodeGen/AArch64/reserveXreg.ll b/llvm/test/CodeGen/AArch64/reserveXreg.ll
new file mode 100644 (file)
index 0000000..61b9af0
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/reserveXreg.ll
@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=aarch64-unknown-linux-gnu -reserve-regs-for-regalloc=LR,FP,X28,X27,X26,X25,X24,X23,X22,X21,X20,X19,X18,X17,X16,X15,X14,X13,X12,X11,X10,X9,X8,X7,X6,X5,X4 | FileCheck %s
+; RUN: llc < %s -mtriple=aarch64-unknown-linux-gnu -reserve-regs-for-regalloc=X30,X29,X28,X27,X26,X25,X24,X23,X22,X21,X20,X19,X18,X17,X16,X15,X14,X13,X12,X11,X10,X9,X8,X7,X6,X5,X4 | FileCheck %s
+
+; LR, FP, X30 and X29 should be correctly recognized and not used.
+
+define void @foo(i64 %v1, i64 %v2, i64* %ptr) {
+; CHECK-LABEL: foo:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    sub sp, sp, #16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    add x3, x0, x1
+; CHECK-NEXT:    str x3, [sp, #8] // 8-byte Folded Spill
+; CHECK-NEXT:    str x3, [x2, #8]
+; CHECK-NEXT:    ldr x3, [x2, #16]
+; CHECK-NEXT:    add x3, x0, x3
+; CHECK-NEXT:    sub x3, x3, x1
+; CHECK-NEXT:    str x3, [x2, #16]
+; CHECK-NEXT:    ldr x3, [sp, #8] // 8-byte Folded Reload
+; CHECK-NEXT:    str x3, [x2, #24]
+; CHECK-NEXT:    str x0, [x2, #32]
+; CHECK-NEXT:    str x1, [x2, #40]
+; CHECK-NEXT:    add sp, sp, #16
+; CHECK-NEXT:    ret
+  %v3 = add i64 %v1, %v2
+  %p1 = getelementptr i64, i64* %ptr, i64 1
+  store volatile i64 %v3, i64* %p1, align 8
+
+  %p2 = getelementptr i64, i64* %ptr, i64 2
+  %v4 = load volatile i64, i64* %p2, align 8
+  %v5 = add i64 %v1, %v4
+  %v6 = sub i64 %v5, %v2
+  store volatile i64 %v6, i64* %p2, align 8
+
+  %p3 = getelementptr i64, i64* %ptr, i64 3
+  store volatile i64 %v3, i64* %p3, align 8
+
+  %p4 = getelementptr i64, i64* %ptr, i64 4
+  store volatile i64 %v1, i64* %p4, align 8
+  %p5 = getelementptr i64, i64* %ptr, i64 5
+  store volatile i64 %v2, i64* %p5, align 8
+  ret void
+}