[mips] Return {f128} correctly for N32/N64.

Summary:
According to the ABI documentation, f128 and {f128} should both be returned
in $f0 and $f2. However, this doesn't match GCC's behaviour which is to
return f128 in $f0 and $f2, but {f128} in $f0 and $f1.

Reviewers: vmedic

Reviewed By: vmedic

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D5578

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@219196 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/Mips/MipsCallingConv.td b/lib/Target/Mips/MipsCallingConv.td
index 8fda1be846933a184432b1831f3b824ff8f9647e..bb45d4195ec7295a5917ec3e4c9eeab6b55b80be 100644 (file)
--- a/lib/Target/Mips/MipsCallingConv.td
+++ b/lib/Target/Mips/MipsCallingConv.td
@@ -29,6 +29,12 @@ def RetCC_F128SoftFloat : CallingConv<[
 // pair of i64's.
 def RetCC_F128HardFloat : CallingConv<[
   CCBitConvertToType<f64>,
+
+  // Contrary to the ABI documentation, a struct containing a long double is
+  // returned in $f0, and $f1 instead of the usual $f0, and $f2. This is to
+  // match the de facto ABI as implemented by GCC.
+  CCIfInReg<CCAssignToReg<[D0_64, D1_64]>>,
+
   CCAssignToReg<[D0_64, D2_64]>
 ]>;
 

diff --git a/lib/Target/Mips/MipsISelLowering.cpp b/lib/Target/Mips/MipsISelLowering.cpp
index 50b8512bc187222ad89a150d8c38cba0c17a0b83..621e932ca56bd9680341f4319596a7ace9c0657c 100644 (file)
--- a/lib/Target/Mips/MipsISelLowering.cpp
+++ b/lib/Target/Mips/MipsISelLowering.cpp
@@ -3496,12 +3496,16 @@ static bool isF128SoftLibCall(const char *CallSym) {
   return std::binary_search(LibCalls, End, CallSym, Comp);
 }
 
-/// This function returns true if Ty is fp128 or i128 which was originally a
-/// fp128.
+/// This function returns true if Ty is fp128, {f128} or i128 which was
+/// originally a fp128.
 static bool originalTypeIsF128(const Type *Ty, const SDNode *CallNode) {
   if (Ty->isFP128Ty())
     return true;
 
+  if (Ty->isStructTy() && Ty->getStructNumElements() == 1 &&
+      Ty->getStructElementType(0)->isFP128Ty())
+    return true;
+
   const ExternalSymbolSDNode *ES =
     dyn_cast_or_null<const ExternalSymbolSDNode>(CallNode);
 

diff --git a/test/CodeGen/Mips/cconv/return-hard-struct-f128.ll b/test/CodeGen/Mips/cconv/return-hard-struct-f128.ll
new file mode 100644 (file)
index 0000000..2e84477
--- /dev/null
+++ b/test/CodeGen/Mips/cconv/return-hard-struct-f128.ll
@@ -0,0 +1,36 @@
+; RUN: llc -mtriple=mips64-linux-gnu -relocation-model=static -mattr=-n64,+n32 < %s | FileCheck --check-prefix=ALL --check-prefix=N32 %s
+; RUN: llc -mtriple=mips64el-linux-gnu -relocation-model=static -mattr=-n64,+n32 < %s | FileCheck --check-prefix=ALL --check-prefix=N32 %s
+
+; RUN: llc -mtriple=mips64-linux-gnu -relocation-model=static -mattr=-n64,+n64 < %s | FileCheck --check-prefix=ALL --check-prefix=N64 %s
+; RUN: llc -mtriple=mips64el-linux-gnu -relocation-model=static -mattr=-n64,+n64 < %s | FileCheck --check-prefix=ALL --check-prefix=N64 %s
+
+; Test return of {fp128} agrees with de-facto N32/N64 ABI.
+
+@struct_fp128 = global {fp128} zeroinitializer
+
+define inreg {fp128} @ret_struct_fp128() nounwind {
+entry:
+        %0 = load volatile {fp128}* @struct_fp128
+        ret {fp128} %0
+}
+
+; ALL-LABEL: ret_struct_fp128:
+
+; O32 generates different IR so we don't test it here. It returns the struct
+; indirectly.
+
+; Contrary to the N32/N64 ABI documentation, a struct containing a long double
+; is returned in $f0, and $f1 instead of the usual $f0, and $f2. This is to
+; match the de facto ABI as implemented by GCC.
+; N32-DAG:        lui [[R1:\$[0-9]+]], %hi(struct_fp128)
+; N32-DAG:        ld  [[R2:\$[0-9]+]], %lo(struct_fp128)([[R1]])
+; N32-DAG:        dmtc1 [[R2]], $f0
+; N32-DAG:        addiu [[R3:\$[0-9]+]], [[R1]], %lo(struct_fp128)
+; N32-DAG:        ld  [[R4:\$[0-9]+]], 8([[R3]])
+; N32-DAG:        dmtc1 [[R4]], $f1
+
+; N64-DAG:        ld  [[R1:\$[0-9]+]], %got_disp(struct_fp128)($1)
+; N64-DAG:        ld  [[R2:\$[0-9]+]], 0([[R1]])
+; N64-DAG:        dmtc1 [[R2]], $f0
+; N64-DAG:        ld  [[R4:\$[0-9]+]], 8([[R1]])
+; N64-DAG:        dmtc1 [[R4]], $f1