From 76f920d316dc6a9e5e77c8e36f9312d1708e376b Mon Sep 17 00:00:00 2001
From: Evan Cheng <evan.cheng@apple.com>
Date: Fri, 22 Oct 2010 18:23:05 +0000
Subject: [PATCH] Add fastcc cc: pass and return VFP / NEON values in
 registers. Controlled by -arm-fastcc for now.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117119 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/ARM/ARMCallingConv.td   | 29 +++++++++++++++++++++++++
 lib/Target/ARM/ARMISelLowering.cpp | 34 +++++++++++++++++++-----------
 2 files changed, 51 insertions(+), 12 deletions(-)

diff --git a/lib/Target/ARM/ARMCallingConv.td b/lib/Target/ARM/ARMCallingConv.td
index 293e32aa537..426ba13a8e1 100644
--- a/lib/Target/ARM/ARMCallingConv.td
+++ b/lib/Target/ARM/ARMCallingConv.td
@@ -52,6 +52,34 @@ def RetCC_ARM_APCS : CallingConv<[
   CCIfType<[i64], CCAssignToRegWithShadow<[R0, R2], [R1, R3]>>
 ]>;
 
+//===----------------------------------------------------------------------===//
+// ARM APCS Calling Convention for FastCC (when VFP2 or later is available)
+//===----------------------------------------------------------------------===//
+def FastCC_ARM_APCS : CallingConv<[
+  // Handle all vector types as either f64 or v2f64.
+  CCIfType<[v1i64, v2i32, v4i16, v8i8, v2f32], CCBitConvertToType<f64>>,
+  CCIfType<[v2i64, v4i32, v8i16, v16i8, v4f32], CCBitConvertToType<v2f64>>,
+
+  CCIfType<[v2f64], CCAssignToReg<[Q0, Q1, Q2, Q3]>>,
+  CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>,
+  CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7, S8,
+                                 S9, S10, S11, S12, S13, S14, S15]>>,
+  CCDelegateTo<CC_ARM_APCS>
+]>;
+
+def RetFastCC_ARM_APCS : CallingConv<[
+  // Handle all vector types as either f64 or v2f64.
+  CCIfType<[v1i64, v2i32, v4i16, v8i8, v2f32], CCBitConvertToType<f64>>,
+  CCIfType<[v2i64, v4i32, v8i16, v16i8, v4f32], CCBitConvertToType<v2f64>>,
+
+  CCIfType<[v2f64], CCAssignToReg<[Q0, Q1, Q2, Q3]>>,
+  CCIfType<[f64], CCAssignToReg<[D0, D1, D2, D3, D4, D5, D6, D7]>>,
+  CCIfType<[f32], CCAssignToReg<[S0, S1, S2, S3, S4, S5, S6, S7, S8,
+                                 S9, S10, S11, S12, S13, S14, S15]>>,
+  CCDelegateTo<RetCC_ARM_APCS>
+]>;
+
+
 //===----------------------------------------------------------------------===//
 // ARM AAPCS (EABI) Calling Convention, common parts
 //===----------------------------------------------------------------------===//
@@ -105,6 +133,7 @@ def RetCC_ARM_AAPCS : CallingConv<[
 
 //===----------------------------------------------------------------------===//
 // ARM AAPCS-VFP (EABI) Calling Convention
+// Also used for FastCC (when VFP2 or later is available)
 //===----------------------------------------------------------------------===//
 
 def CC_ARM_AAPCS_VFP : CallingConv<[
diff --git a/lib/Target/ARM/ARMISelLowering.cpp b/lib/Target/ARM/ARMISelLowering.cpp
index c01a9ddb660..ceddca0561a 100644
--- a/lib/Target/ARM/ARMISelLowering.cpp
+++ b/lib/Target/ARM/ARMISelLowering.cpp
@@ -69,6 +69,10 @@ ARMInterworking("arm-interworking", cl::Hidden,
   cl::desc("Enable / disable ARM interworking (for debugging only)"),
   cl::init(true));
 
+static cl::opt<bool>
+ARMFastCC("arm-fastcc", cl::Hidden,
+  cl::desc("Use AAPCS / AAPCS-VFP calling conventions for fastcc"));
+
 void ARMTargetLowering::addTypeForNEON(EVT VT, EVT PromotedLdStVT,
                                        EVT PromotedBitwiseVT) {
   if (VT != PromotedLdStVT) {
@@ -955,23 +959,29 @@ CCAssignFn *ARMTargetLowering::CCAssignFnForNode(CallingConv::ID CC,
   switch (CC) {
   default:
     llvm_unreachable("Unsupported calling convention");
-  case CallingConv::C:
   case CallingConv::Fast:
+    if (ARMFastCC && Subtarget->hasVFP2() && !isVarArg) {
+      if (!Subtarget->isAAPCS_ABI())
+        return (Return ? RetFastCC_ARM_APCS : FastCC_ARM_APCS);
+      // For AAPCS ABI targets, just use VFP variant of the calling convention.
+      return (Return ? RetCC_ARM_AAPCS_VFP : CC_ARM_AAPCS_VFP);
+    }
+    // Fallthrough
+  case CallingConv::C: {
     // Use target triple & subtarget features to do actual dispatch.
-    if (Subtarget->isAAPCS_ABI()) {
-      if (Subtarget->hasVFP2() &&
-          FloatABIType == FloatABI::Hard && !isVarArg)
-        return (Return ? RetCC_ARM_AAPCS_VFP: CC_ARM_AAPCS_VFP);
-      else
-        return (Return ? RetCC_ARM_AAPCS: CC_ARM_AAPCS);
-    } else
-        return (Return ? RetCC_ARM_APCS: CC_ARM_APCS);
+    if (!Subtarget->isAAPCS_ABI())
+      return (Return ? RetCC_ARM_APCS : CC_ARM_APCS);
+    else if (Subtarget->hasVFP2() &&
+             FloatABIType == FloatABI::Hard && !isVarArg)
+      return (Return ? RetCC_ARM_AAPCS_VFP : CC_ARM_AAPCS_VFP);
+    return (Return ? RetCC_ARM_AAPCS : CC_ARM_AAPCS);
+  }
   case CallingConv::ARM_AAPCS_VFP:
-    return (Return ? RetCC_ARM_AAPCS_VFP: CC_ARM_AAPCS_VFP);
+    return (Return ? RetCC_ARM_AAPCS_VFP : CC_ARM_AAPCS_VFP);
   case CallingConv::ARM_AAPCS:
-    return (Return ? RetCC_ARM_AAPCS: CC_ARM_AAPCS);
+    return (Return ? RetCC_ARM_AAPCS : CC_ARM_AAPCS);
   case CallingConv::ARM_APCS:
-    return (Return ? RetCC_ARM_APCS: CC_ARM_APCS);
+    return (Return ? RetCC_ARM_APCS : CC_ARM_APCS);
   }
 }