From 37aee91a35043e250dbdd548b95d60e336ad7cd0 Mon Sep 17 00:00:00 2001
From: Erich Keane <erich.keane@intel.com>
Date: Fri, 21 Jul 2017 18:50:36 +0000
Subject: [PATCH] Complex Long Double classification In RegCall calling
 convention

This change is part of the RegCall calling convention support for LLVM.
Existing RegCall implementation was extended to include correct handling of
Complex Long Double type. Complex long double types should be returned/passed
in memory and not register stack. This patch implements this behavior.

Patch by: eandrews

Differential Revision: https://reviews.llvm.org/D35259


git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@308769 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/CodeGen/TargetInfo.cpp  | 41 +++++++++++++++++++++++++------------
 test/CodeGenCXX/regcall.cpp | 12 +++++++++--
 2 files changed, 38 insertions(+), 15 deletions(-)

diff --git a/lib/CodeGen/TargetInfo.cpp b/lib/CodeGen/TargetInfo.cpp
index af23769012..23874e3d5b 100644
--- a/lib/CodeGen/TargetInfo.cpp
+++ b/lib/CodeGen/TargetInfo.cpp
@@ -882,8 +882,14 @@ static llvm::Type* X86AdjustInlineAsmType(CodeGen::CodeGenFunction &CGF,
 /// X86_VectorCall calling convention. Shared between x86_32 and x86_64.
 static bool isX86VectorTypeForVectorCall(ASTContext &Context, QualType Ty) {
   if (const BuiltinType *BT = Ty->getAs<BuiltinType>()) {
-    if (BT->isFloatingPoint() && BT->getKind() != BuiltinType::Half)
+    if (BT->isFloatingPoint() && BT->getKind() != BuiltinType::Half) {
+      if (BT->getKind() == BuiltinType::LongDouble) {
+        if (&Context.getTargetInfo().getLongDoubleFormat() ==
+            &llvm::APFloat::x87DoubleExtended())
+          return false;
+      }
       return true;
+    }
   } else if (const VectorType *VT = Ty->getAs<VectorType>()) {
     // vectorcall can pass XMM, YMM, and ZMM vectors. We don't pass SSE1 MMX
     // registers specially.
@@ -3515,18 +3521,27 @@ void X86_64ABIInfo::computeInfo(CGFunctionInfo &FI) const {
   unsigned FreeSSERegs = IsRegCall ? 16 : 8;
   unsigned NeededInt, NeededSSE;
 
-  if (IsRegCall && FI.getReturnType()->getTypePtr()->isRecordType() &&
-      !FI.getReturnType()->getTypePtr()->isUnionType()) {
-    FI.getReturnInfo() =
-        classifyRegCallStructType(FI.getReturnType(), NeededInt, NeededSSE);
-    if (FreeIntRegs >= NeededInt && FreeSSERegs >= NeededSSE) {
-      FreeIntRegs -= NeededInt;
-      FreeSSERegs -= NeededSSE;
-    } else {
-      FI.getReturnInfo() = getIndirectReturnResult(FI.getReturnType());
-    }
-  } else if (!getCXXABI().classifyReturnType(FI))
-    FI.getReturnInfo() = classifyReturnType(FI.getReturnType());
+  if (!getCXXABI().classifyReturnType(FI)) {
+    if (IsRegCall && FI.getReturnType()->getTypePtr()->isRecordType() &&
+        !FI.getReturnType()->getTypePtr()->isUnionType()) {
+      FI.getReturnInfo() =
+          classifyRegCallStructType(FI.getReturnType(), NeededInt, NeededSSE);
+      if (FreeIntRegs >= NeededInt && FreeSSERegs >= NeededSSE) {
+        FreeIntRegs -= NeededInt;
+        FreeSSERegs -= NeededSSE;
+      } else {
+        FI.getReturnInfo() = getIndirectReturnResult(FI.getReturnType());
+      }
+    } else if (IsRegCall && FI.getReturnType()->getAs<ComplexType>()) {
+      // Complex Long Double Type is passed in Memory when Regcall
+      // calling convention is used.
+      const ComplexType *CT = FI.getReturnType()->getAs<ComplexType>();
+      if (getContext().getCanonicalType(CT->getElementType()) ==
+          getContext().LongDoubleTy)
+        FI.getReturnInfo() = getIndirectReturnResult(FI.getReturnType());
+    } else
+      FI.getReturnInfo() = classifyReturnType(FI.getReturnType());
+  }
 
   // If the return value is indirect, then the hidden argument is consuming one
   // integer register.
diff --git a/test/CodeGenCXX/regcall.cpp b/test/CodeGenCXX/regcall.cpp
index 0ff6fdf12a..2b7b9e2a6e 100644
--- a/test/CodeGenCXX/regcall.cpp
+++ b/test/CodeGenCXX/regcall.cpp
@@ -73,8 +73,8 @@ bool __regcall operator ==(const test_class&, const test_class&){ --x; return fa
 // CHECK-WIN64-DAG: define x86_regcallcc zeroext i1 @"\01??8@Yw_NAEBVtest_class@@0@Z"
 // CHECK-WIN32-DAG: define x86_regcallcc zeroext i1 @"\01??8@Yw_NABVtest_class@@0@Z"
 
-test_class __regcall operator""_test_class (unsigned long long) { ++x; return test_class{};} 
-// CHECK-LIN64-DAG: define x86_regcallcc %class.test_class @_Zli11_test_classy(i64)
+test_class __regcall operator""_test_class (unsigned long long) { ++x; return test_class{};}
+// CHECK-LIN64-DAG: define x86_regcallcc void @_Zli11_test_classy(%class.test_class* noalias sret %agg.result, i64)
 // CHECK-LIN32-DAG: define x86_regcallcc void @_Zli11_test_classy(%class.test_class* inreg noalias sret %agg.result, i64)
 // CHECK-WIN64-DAG: \01??__K_test_class@@Yw?AVtest_class@@_K@Z"
 // CHECK-WIN32-DAG: \01??__K_test_class@@Yw?AVtest_class@@_K@Z"
@@ -95,3 +95,11 @@ void force_gen() {
   freeTempFunc(1);
   t3.do_thing();
 }
+
+long double _Complex __regcall foo(long double _Complex f) {
+  return f;
+}
+// CHECK-LIN64-DAG: define x86_regcallcc void @_Z15__regcall3__fooCe({ x86_fp80, x86_fp80 }* noalias sret %agg.result, { x86_fp80, x86_fp80 }* byval align 16 %f)
+// CHECK-LIN32-DAG: define x86_regcallcc void @_Z15__regcall3__fooCe({ x86_fp80, x86_fp80 }* inreg noalias sret %agg.result, { x86_fp80, x86_fp80 }* byval align 4 %f)
+// CHECK-WIN64-DAG: define x86_regcallcc { double, double } @"\01?foo@@YwU?$_Complex@O@__clang@@U12@@Z"(double %f.0, double %f.1)
+// CHECK-WIN32-DAG: define x86_regcallcc { double, double } @"\01?foo@@YwU?$_Complex@O@__clang@@U12@@Z"(double %f.0, double %f.1)
-- 
2.50.1