[PATCH] D45653: Enable sibling-call optimization for functions returning structs

[Ivan Sorokin via Phabricator via llvm-commits]

sorokin updated this revision to Diff 142518.
sorokin added a comment.

I updated the diff with context.


Repository:
  rL LLVM

https://reviews.llvm.org/D45653

Files:
  lib/Target/X86/X86ISelLowering.cpp
  test/CodeGen/X86/sibcall.ll


Index: test/CodeGen/X86/sibcall.ll
===================================================================
--- test/CodeGen/X86/sibcall.ll
+++ test/CodeGen/X86/sibcall.ll
@@ -307,12 +307,10 @@
 ; 32: retl $4
 
 ; 64-LABEL: t15:
-; 64: callq {{_?}}f
-; 64: retq
+; 64: jmp {{_?}}f
 
 ; X32ABI-LABEL: t15:
-; X32ABI: callq {{_?}}f
-; X32ABI: retq
+; X32ABI: jmp {{_?}}f
   tail call fastcc void @f(%struct.foo* noalias sret %agg.result) nounwind
   ret void
 }
@@ -408,3 +406,49 @@
 }
 
 declare fastcc double @foo20(double) nounwind
+
+; bug 28417
+define fastcc void @t21_sret_to_sret(%struct.foo* noalias sret %agg.result) nounwind  {
+; 32-LABEL: t21_sret_to_sret:
+; 32: jmp {{_?}}t21_f_sret
+
+; 64-LABEL: t21_sret_to_sret:
+; 64: jmp {{_?}}t21_f_sret
+
+; X32ABI-LABEL: t21_sret_to_sret:
+; X32ABI: jmp {{_?}}t21_f_sret
+  tail call fastcc void @t21_f_sret(%struct.foo* noalias sret %agg.result) nounwind
+  ret void
+}
+
+define fastcc void @t21_sret_to_non_sret(%struct.foo* noalias sret %agg.result) nounwind  {
+; 32-LABEL: t21_sret_to_non_sret:
+; 32: calll {{_?}}t21_f_non_sret
+; 32: retl
+
+; 64-LABEL: t21_sret_to_non_sret:
+; 64: callq {{_?}}t21_f_non_sret
+; 64: retq
+
+; X32ABI-LABEL: t21_sret_to_non_sret:
+; X32ABI: callq {{_?}}t21_f_non_sret
+; X32ABI: retq
+  tail call fastcc void @t21_f_non_sret(%struct.foo* %agg.result) nounwind
+  ret void
+}
+
+define fastcc void @t21_non_sret_to_sret(%struct.foo* %agg.result) nounwind  {
+; 32-LABEL: t21_non_sret_to_sret:
+; 32: jmp {{_?}}t21_f_sret
+
+; 64-LABEL: t21_non_sret_to_sret:
+; 64: jmp {{_?}}t21_f_sret
+
+; X32ABI-LABEL: t21_non_sret_to_sret:
+; X32ABI: jmp {{_?}}t21_f_sret
+  tail call fastcc void @t21_f_sret(%struct.foo* noalias sret %agg.result) nounwind
+  ret void
+}
+
+declare fastcc void @t21_f_sret(%struct.foo* noalias sret) nounwind
+declare fastcc void @t21_f_non_sret(%struct.foo*) nounwind
Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -4155,9 +4155,9 @@
   if (RegInfo->needsStackRealignment(MF))
     return false;
 
-  // Also avoid sibcall optimization if either caller or callee uses struct
-  // return semantics.
-  if (isCalleeStructRet || isCallerStructRet)
+  // Struct-return functions need to return its argument in RAX, so they can not
+  // sibcall non-struct-return functions.
+  if (!isCalleeStructRet && isCallerStructRet)
     return false;
 
   // Do not sibcall optimize vararg calls unless all arguments are passed via


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D45653.142518.patch
Type: text/x-patch
Size: 2575 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180414/f4e12f24/attachment.bin>