Enable tail calls on ARM by default, with some

basic tests.

This has been well tested on Darwin but not elsewhere.
It should work provided the linker correctly resolves
  B.W  <label in other function>
which it has not seen before, at least from llvm-based
compilers.  I'm leaving the arm-tail-calls switch in
until I see if there's any problems because of that;
it might need to be disabled for some environments.

llvm-svn: 106299

1 files changed, 36 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/ARM/call-tc.ll b/llvm/test/CodeGen/ARM/call-tc.ll
new file mode 100644
index 00000000000..8103fab2092
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/call-tc.ll
@@ -0,0 +1,36 @@
+; RUN: llc < %s -march=arm | FileCheck %s -check-prefix=CHECKV4
+; RUN: llc < %s -march=arm -mattr=+v5t | FileCheck %s -check-prefix=CHECKV5
+; RUN: llc < %s -march=arm -mtriple=arm-linux-gnueabi\
+; RUN:   -relocation-model=pic | FileCheck %s -check-prefix=CHECKELF
+
+@t = weak global i32 ()* null           ; <i32 ()**> [#uses=1]
+
+declare void @g(i32, i32, i32, i32)
+
+define void @f() {
+; CHECKELF: PLT
+        call void @g( i32 1, i32 2, i32 3, i32 4 )
+        ret void
+}
+
+define void @g.upgrd.1() {
+; CHECKV4: bx r0 @ TAILCALL
+; CHECKV5: bx r0 @ TAILCALL
+        %tmp = load i32 ()** @t         ; <i32 ()*> [#uses=1]
+        %tmp.upgrd.2 = tail call i32 %tmp( )            ; <i32> [#uses=0]
+        ret void
+}
+
+define i32* @m_231b(i32, i32, i32*, i32*, i32*) nounwind {
+; CHECKV4: m_231b
+; CHECKV4: bx r{{.*}}
+BB0:
+  %5 = inttoptr i32 %0 to i32*                    ; <i32*> [#uses=1]
+  %t35 = volatile load i32* %5                    ; <i32> [#uses=1]
+  %6 = inttoptr i32 %t35 to i32**                 ; <i32**> [#uses=1]
+  %7 = getelementptr i32** %6, i32 86             ; <i32**> [#uses=1]
+  %8 = load i32** %7                              ; <i32*> [#uses=1]
+  %9 = bitcast i32* %8 to i32* (i32, i32*, i32, i32*, i32*, i32*)* ; <i32* (i32, i32*, i32, i32*, i32*, i32*)*> [#uses=1]
+  %10 = call i32* %9(i32 %0, i32* null, i32 %1, i32* %2, i32* %3, i32* %4) ; <i32*> [#uses=1]
+  ret i32* %10
+}