[AArch64] Place the first ldp at the end when ReverseCSRRestoreSeq is true

Put the first ldp at the end, so that the load-store optimizer can run
and merge the ldp and the add into a post-index ldp.

This didn't work in case no frame was needed and resulted in code size
regressions.

llvm-svn: 331044

1 files changed, 33 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/AArch64/reverse-csr-restore-seq.mir b/llvm/test/CodeGen/AArch64/reverse-csr-restore-seq.mir
index 32234fd5db2..2b168b31a51 100644
--- a/llvm/test/CodeGen/AArch64/reverse-csr-restore-seq.mir
+++ b/llvm/test/CodeGen/AArch64/reverse-csr-restore-seq.mir
@@ -7,6 +7,8 @@
 
   define void @bar() nounwind { entry: unreachable }
 
+  define void @baz() nounwind { entry: unreachable }
+
 ...
 ---
 name:            foo
@@ -71,3 +73,34 @@ body:             |
   ; CHECK-NEXT: $sp = frame-destroy ADDXri $sp, 80, 0
     RET_ReallyLR
 ...
+---
+# Check that the load from the offset 0 is moved at the end even when hasFP is
+# false.
+name:            baz
+# CHECK-LABEL: name: baz
+alignment:       2
+tracksRegLiveness: true
+frameInfo:
+  adjustsStack:    true
+  hasCalls:        true
+body:             |
+  bb.0:
+    successors: %bb.1
+
+    $x0 = IMPLICIT_DEF
+    $x20 = IMPLICIT_DEF
+    $x21 = IMPLICIT_DEF
+
+    ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
+    BL @foo, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit $x0, implicit-def $sp, implicit-def $x0
+    ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
+    B %bb.1
+
+  bb.1:
+   ; CHECK: $x20, $lr = frame-destroy LDPXi $sp, 2
+   ; BEFORELDSTOPT-NEXT: $x21 = frame-destroy LDRXui $sp, 0
+   ; BEFORELDSTOPT-NEXT: $sp = frame-destroy ADDXri $sp, 32, 0
+
+   ; AFTERLDSTOPT-NEXT: early-clobber $sp, $x21 = frame-destroy LDRXpost $sp, 32
+    RET_ReallyLR
+...