[clang] [X86][vectorcall] Do not consume register for indirect return value (PR #97939)

[Phoebe Wang via cfe-commits]

https://github.com/phoebewang created https://github.com/llvm/llvm-project/pull/97939

This is how MSVC handles it. https://godbolt.org/z/Eav3vx7cd

>From cf19ec8d705434ca6d989a72069dba1040c360ca Mon Sep 17 00:00:00 2001
From: Phoebe Wang <phoebe.wang at intel.com>
Date: Sun, 7 Jul 2024 13:14:59 +0800
Subject: [PATCH] [X86][vectorcall] Do not consume register for indirect return
 value

This is how MSVC handles it. https://godbolt.org/z/Eav3vx7cd
---
 clang/lib/CodeGen/Targets/X86.cpp | 2 +-
 clang/test/CodeGen/vectorcall.c   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/clang/lib/CodeGen/Targets/X86.cpp b/clang/lib/CodeGen/Targets/X86.cpp
index 3146caba1c615..3c0947589ce3d 100644
--- a/clang/lib/CodeGen/Targets/X86.cpp
+++ b/clang/lib/CodeGen/Targets/X86.cpp
@@ -469,7 +469,7 @@ bool X86_32ABIInfo::canExpandIndirectArgument(QualType Ty) const {
 ABIArgInfo X86_32ABIInfo::getIndirectReturnResult(QualType RetTy, CCState &State) const {
   // If the return value is indirect, then the hidden argument is consuming one
   // integer register.
-  if (State.FreeRegs) {
+  if (State.CC != llvm::CallingConv::X86_VectorCall && State.FreeRegs) {
     --State.FreeRegs;
     if (!IsMCUABI)
       return getNaturalAlignIndirectInReg(RetTy);
diff --git a/clang/test/CodeGen/vectorcall.c b/clang/test/CodeGen/vectorcall.c
index 71dc3b0b9585a..cab7fc0972d7b 100644
--- a/clang/test/CodeGen/vectorcall.c
+++ b/clang/test/CodeGen/vectorcall.c
@@ -90,7 +90,7 @@ struct HVA4 __vectorcall hva6(struct HVA4 a, struct HVA4 b) { return b;}
 // X64: define dso_local x86_vectorcallcc %struct.HVA4 @"\01hva6@@128"(%struct.HVA4 inreg %a.coerce, ptr noundef %b)
 
 struct HVA5 __vectorcall hva7(void) {struct HVA5 a = {}; return a;}
-// X86: define dso_local x86_vectorcallcc void @"\01hva7@@0"(ptr dead_on_unwind inreg noalias writable sret(%struct.HVA5) align 16 %agg.result)
+// X86: define dso_local x86_vectorcallcc void @"\01hva7@@0"(ptr dead_on_unwind noalias writable sret(%struct.HVA5) align 16 %agg.result)
 // X64: define dso_local x86_vectorcallcc void @"\01hva7@@0"(ptr dead_on_unwind noalias writable sret(%struct.HVA5) align 16 %agg.result)
 
 v4f32 __vectorcall hva8(v4f32 a, v4f32 b, v4f32 c, v4f32 d, int e, v4f32 f) {return f;}