X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=blobdiff_plain;f=lib%2FTarget%2FX86%2FX86CallingConv.td;h=26100a56ee6bc0779b59b281a3ea6f0f3905178c;hp=40c5d91b6054611ae3490bd5ddec6953f181e670;hb=9889174eadb0f269ef132b3bd34a9f6fe3baa642;hpb=ac226bbf457f6b5e5210a4a82b1ce678298b2d89

diff --git a/lib/Target/X86/X86CallingConv.td b/lib/Target/X86/X86CallingConv.td
index 40c5d91b605..26100a56ee6 100644
--- a/lib/Target/X86/X86CallingConv.td
+++ b/lib/Target/X86/X86CallingConv.td
@@ -14,7 +14,9 @@
 
 /// CCIfSubtarget - Match if the current subtarget has a feature F.
 class CCIfSubtarget<string F, CCAction A>
- : CCIf<!strconcat("State.getTarget().getSubtarget<X86Subtarget>().", F), A>;
+    : CCIf<!strconcat("static_cast<const X86Subtarget&>"
+                       "(State.getMachineFunction().getSubtarget()).", F),
+           A>;
 
 //===----------------------------------------------------------------------===//
 // Return Value Calling Conventions
@@ -32,11 +34,22 @@ def RetCC_X86Common : CallingConv<[
   //
   // For code that doesn't care about the ABI, we allow returning more than two
   // integer values in registers.
+  CCIfType<[i1],  CCPromoteToType<i8>>,
   CCIfType<[i8] , CCAssignToReg<[AL, DL, CL]>>,
   CCIfType<[i16], CCAssignToReg<[AX, DX, CX]>>,
   CCIfType<[i32], CCAssignToReg<[EAX, EDX, ECX]>>,
   CCIfType<[i64], CCAssignToReg<[RAX, RDX, RCX]>>,
 
+  // Boolean vectors of AVX-512 are returned in SIMD registers.
+  // The call from AVX to AVX-512 function should work,
+  // since the boolean types in AVX/AVX2 are promoted by default.
+  CCIfType<[v2i1],  CCPromoteToType<v2i64>>,
+  CCIfType<[v4i1],  CCPromoteToType<v4i32>>,
+  CCIfType<[v8i1],  CCPromoteToType<v8i16>>,
+  CCIfType<[v16i1], CCPromoteToType<v16i8>>,
+  CCIfType<[v32i1], CCPromoteToType<v32i8>>,
+  CCIfType<[v64i1], CCPromoteToType<v64i8>>,
+
   // Vector types are returned in XMM0 and XMM1, when they fit.  XMM2 and XMM3
   // can only be used by ABI non-compliant code. If the target doesn't have XMM
   // registers, it won't have vector types.
@@ -49,24 +62,30 @@ def RetCC_X86Common : CallingConv<[
   CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
             CCAssignToReg<[YMM0,YMM1,YMM2,YMM3]>>,
 
+  // 512-bit vectors are returned in ZMM0 and ZMM1, when they fit. ZMM2 and ZMM3
+  // can only be used by ABI non-compliant code. This vector type is only
+  // supported while using the AVX-512 target feature.
+  CCIfType<[v64i8, v32i16, v16i32, v8i64, v16f32, v8f64],
+            CCAssignToReg<[ZMM0,ZMM1,ZMM2,ZMM3]>>,
+
   // MMX vector types are always returned in MM0. If the target doesn't have
   // MM0, it doesn't support these vector types.
   CCIfType<[x86mmx], CCAssignToReg<[MM0]>>,
 
-  // Long double types are always returned in ST0 (even with SSE).
-  CCIfType<[f80], CCAssignToReg<[ST0, ST1]>>
+  // Long double types are always returned in FP0 (even with SSE).
+  CCIfType<[f80], CCAssignToReg<[FP0, FP1]>>
 ]>;
 
 // X86-32 C return-value convention.
 def RetCC_X86_32_C : CallingConv<[
-  // The X86-32 calling convention returns FP values in ST0, unless marked
+  // The X86-32 calling convention returns FP values in FP0, unless marked
   // with "inreg" (used here to distinguish one kind of reg from another,
   // weirdly; this is really the sse-regparm calling convention) in which
   // case they use XMM0, otherwise it is the same as the common X86 calling
   // conv.
   CCIfInReg<CCIfSubtarget<"hasSSE2()",
     CCIfType<[f32, f64], CCAssignToReg<[XMM0,XMM1,XMM2]>>>>,
-  CCIfType<[f32,f64], CCAssignToReg<[ST0, ST1]>>,
+  CCIfType<[f32,f64], CCAssignToReg<[FP0, FP1]>>,
   CCDelegateTo<RetCC_X86Common>
 ]>;
 
@@ -99,6 +118,10 @@ def RetCC_Intel_OCL_BI : CallingConv<[
   CCIfType<[v8f32, v4f64, v8i32, v4i64],
             CCAssignToReg<[YMM0,YMM1,YMM2,YMM3]>>,
 
+  // 512-bit FP vectors
+  CCIfType<[v16f32, v8f64, v16i32, v8i64],
+            CCAssignToReg<[ZMM0,ZMM1,ZMM2,ZMM3]>>,
+
   // i32, i64 in the standard way
   CCDelegateTo<RetCC_X86Common>
 ]>;
@@ -112,11 +135,30 @@ def RetCC_X86_32_HiPE : CallingConv<[
   CCIfType<[i32], CCAssignToReg<[ESI, EBP, EAX, EDX]>>
 ]>;
 
+// X86-32 HiPE return-value convention.
+def RetCC_X86_32_VectorCall : CallingConv<[
+  // Vector types are returned in XMM0,XMM1,XMMM2 and XMM3.
+  CCIfType<[f32, f64, v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
+            CCAssignToReg<[XMM0,XMM1,XMM2,XMM3]>>,
+
+  // 256-bit FP vectors
+  CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
+            CCAssignToReg<[YMM0,YMM1,YMM2,YMM3]>>,
+
+  // 512-bit FP vectors
+  CCIfType<[v64i8, v32i16, v16i32, v8i64, v16f32, v8f64],
+            CCAssignToReg<[ZMM0,ZMM1,ZMM2,ZMM3]>>,
+
+  // Return integers in the standard way.
+  CCDelegateTo<RetCC_X86Common>
+]>;
+
 // X86-64 C return-value convention.
 def RetCC_X86_64_C : CallingConv<[
   // The X86-64 calling convention always returns FP values in XMM0.
   CCIfType<[f32], CCAssignToReg<[XMM0, XMM1]>>,
   CCIfType<[f64], CCAssignToReg<[XMM0, XMM1]>>,
+  CCIfType<[f128], CCAssignToReg<[XMM0, XMM1]>>,
 
   // MMX vector types are always returned in XMM0.
   CCIfType<[x86mmx], CCAssignToReg<[XMM0, XMM1]>>,
@@ -141,12 +183,43 @@ def RetCC_X86_64_HiPE : CallingConv<[
   CCIfType<[i64], CCAssignToReg<[R15, RBP, RAX, RDX]>>
 ]>;
 
+// X86-64 WebKit_JS return-value convention.
+def RetCC_X86_64_WebKit_JS : CallingConv<[
+  // Promote all types to i64
+  CCIfType<[i8, i16, i32], CCPromoteToType<i64>>,
+
+  // Return: RAX
+  CCIfType<[i64], CCAssignToReg<[RAX]>>
+]>;
+
+// X86-64 AnyReg return-value convention. No explicit register is specified for
+// the return-value. The register allocator is allowed and expected to choose
+// any free register.
+//
+// This calling convention is currently only supported by the stackmap and
+// patchpoint intrinsics. All other uses will result in an assert on Debug
+// builds. On Release builds we fallback to the X86 C calling convention.
+def RetCC_X86_64_AnyReg : CallingConv<[
+  CCCustom<"CC_X86_AnyReg_Error">
+]>;
+
+// X86-64 HHVM return-value convention.
+def RetCC_X86_64_HHVM: CallingConv<[
+  // Promote all types to i64
+  CCIfType<[i8, i16, i32], CCPromoteToType<i64>>,
+
+  // Return: could return in any GP register save RSP and R12.
+  CCIfType<[i64], CCAssignToReg<[RBX, RBP, RDI, RSI, RDX, RCX, R8, R9,
+                                 RAX, R10, R11, R13, R14, R15]>>
+]>;
+
 // This is the root return-value convention for the X86-32 backend.
 def RetCC_X86_32 : CallingConv<[
   // If FastCC, use RetCC_X86_32_Fast.
   CCIfCC<"CallingConv::Fast", CCDelegateTo<RetCC_X86_32_Fast>>,
   // If HiPE, use RetCC_X86_32_HiPE.
   CCIfCC<"CallingConv::HiPE", CCDelegateTo<RetCC_X86_32_HiPE>>,
+  CCIfCC<"CallingConv::X86_VectorCall", CCDelegateTo<RetCC_X86_32_VectorCall>>,
 
   // Otherwise, use RetCC_X86_32_C.
   CCDelegateTo<RetCC_X86_32_C>
@@ -157,10 +230,17 @@ def RetCC_X86_64 : CallingConv<[
   // HiPE uses RetCC_X86_64_HiPE
   CCIfCC<"CallingConv::HiPE", CCDelegateTo<RetCC_X86_64_HiPE>>,
 
+  // Handle JavaScript calls.
+  CCIfCC<"CallingConv::WebKit_JS", CCDelegateTo<RetCC_X86_64_WebKit_JS>>,
+  CCIfCC<"CallingConv::AnyReg", CCDelegateTo<RetCC_X86_64_AnyReg>>,
+
   // Handle explicit CC selection
   CCIfCC<"CallingConv::X86_64_Win64", CCDelegateTo<RetCC_X86_Win64_C>>,
   CCIfCC<"CallingConv::X86_64_SysV", CCDelegateTo<RetCC_X86_64_C>>,
 
+  // Handle HHVM calls.
+  CCIfCC<"CallingConv::HHVM", CCDelegateTo<RetCC_X86_64_HHVM>>,
+
   // Mingw64 and native Win64 use Win64 CC
   CCIfSubtarget<"isTargetWin64()", CCDelegateTo<RetCC_X86_Win64_C>>,
 
@@ -186,10 +266,11 @@ def CC_X86_64_C : CallingConv<[
   // Handles byval parameters.
   CCIfByVal<CCPassByVal<8, 8>>,
 
-  // Promote i8/i16 arguments to i32.
-  CCIfType<[i8, i16], CCPromoteToType<i32>>,
+  // Promote i1/i8/i16 arguments to i32.
+  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,
 
   // The 'nest' parameter, if any, is passed in R10.
+  CCIfNest<CCIfSubtarget<"isTarget64BitILP32()", CCAssignToReg<[R10D]>>>,
   CCIfNest<CCAssignToReg<[R10]>>,
 
   // The first 6 integer arguments are passed in integer registers.
@@ -202,8 +283,18 @@ def CC_X86_64_C : CallingConv<[
             CCIfSubtarget<"hasSSE2()",
             CCPromoteToType<v2i64>>>>,
 
+  // Boolean vectors of AVX-512 are passed in SIMD registers.
+  // The call from AVX to AVX-512 function should work,
+  // since the boolean types in AVX/AVX2 are promoted by default.
+  CCIfType<[v2i1],  CCPromoteToType<v2i64>>,
+  CCIfType<[v4i1],  CCPromoteToType<v4i32>>,
+  CCIfType<[v8i1],  CCPromoteToType<v8i16>>,
+  CCIfType<[v16i1], CCPromoteToType<v16i8>>,
+  CCIfType<[v32i1], CCPromoteToType<v32i8>>,
+  CCIfType<[v64i1], CCPromoteToType<v64i8>>,
+
   // The first 8 FP/Vector arguments are passed in XMM registers.
-  CCIfType<[f32, f64, v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
+  CCIfType<[f32, f64, f128, v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
             CCIfSubtarget<"hasSSE1()",
             CCAssignToReg<[XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7]>>>,
 
@@ -213,24 +304,50 @@ def CC_X86_64_C : CallingConv<[
   // fixed arguments to vararg functions are supposed to be passed in
   // registers.  Actually modeling that would be a lot of work, though.
   CCIfNotVarArg<CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
-                          CCIfSubtarget<"hasAVX()",
+                          CCIfSubtarget<"hasFp256()",
                           CCAssignToReg<[YMM0, YMM1, YMM2, YMM3,
                                          YMM4, YMM5, YMM6, YMM7]>>>>,
 
+  // The first 8 512-bit vector arguments are passed in ZMM registers.
+  CCIfNotVarArg<CCIfType<[v64i8, v32i16, v16i32, v8i64, v16f32, v8f64],
+            CCIfSubtarget<"hasAVX512()",
+            CCAssignToReg<[ZMM0, ZMM1, ZMM2, ZMM3, ZMM4, ZMM5, ZMM6, ZMM7]>>>>,
+
   // Integer/FP values get stored in stack slots that are 8 bytes in size and
   // 8-byte aligned if there are no more registers to hold them.
   CCIfType<[i32, i64, f32, f64], CCAssignToStack<8, 8>>,
 
   // Long doubles get stack slots whose size and alignment depends on the
   // subtarget.
-  CCIfType<[f80], CCAssignToStack<0, 0>>,
+  CCIfType<[f80, f128], CCAssignToStack<0, 0>>,
 
   // Vectors get 16-byte stack slots that are 16-byte aligned.
   CCIfType<[v16i8, v8i16, v4i32, v2i64, v4f32, v2f64], CCAssignToStack<16, 16>>,
 
   // 256-bit vectors get 32-byte stack slots that are 32-byte aligned.
   CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
-           CCAssignToStack<32, 32>>
+           CCAssignToStack<32, 32>>,
+
+  // 512-bit vectors get 64-byte stack slots that are 64-byte aligned.
+  CCIfType<[v16i32, v8i64, v16f32, v8f64],
+           CCAssignToStack<64, 64>>
+]>;
+
+// Calling convention for X86-64 HHVM.
+def CC_X86_64_HHVM : CallingConv<[
+  // Use all/any GP registers for args, except RSP.
+  CCIfType<[i64], CCAssignToReg<[RBX, R12, RBP, R15,
+                                 RDI, RSI, RDX, RCX, R8, R9,
+                                 RAX, R10, R11, R13, R14]>>
+]>;
+
+// Calling convention for helper functions in HHVM.
+def CC_X86_64_HHVM_C : CallingConv<[
+  // Pass the first argument in RBP.
+  CCIfType<[i64], CCAssignToReg<[RBP]>>,
+
+  // Otherwise it's the same as the regular C calling convention.
+  CCDelegateTo<CC_X86_64_C>
 ]>;
 
 // Calling convention used on Win64
@@ -238,8 +355,8 @@ def CC_X86_Win64_C : CallingConv<[
   // FIXME: Handle byval stuff.
   // FIXME: Handle varargs.
 
-  // Promote i8/i16 arguments to i32.
-  CCIfType<[i8, i16], CCPromoteToType<i32>>,
+  // Promote i1/i8/i16 arguments to i32.
+  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,
 
   // The 'nest' parameter, if any, is passed in R10.
   CCIfNest<CCAssignToReg<[R10]>>,
@@ -251,16 +368,19 @@ def CC_X86_Win64_C : CallingConv<[
   // 256 bit vectors are passed by pointer
   CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64], CCPassIndirect<i64>>,
 
+  // 512 bit vectors are passed by pointer
+  CCIfType<[v16i32, v16f32, v8f64, v8i64], CCPassIndirect<i64>>,
+
   // The first 4 MMX vector arguments are passed in GPRs.
   CCIfType<[x86mmx], CCBitConvertToType<i64>>,
 
   // The first 4 integer arguments are passed in integer registers.
   CCIfType<[i32], CCAssignToRegWithShadow<[ECX , EDX , R8D , R9D ],
                                           [XMM0, XMM1, XMM2, XMM3]>>,
-  
+
   // Do not pass the sret argument in RCX, the Win64 thiscall calling
-  // convention requires "this" to be passed in RCX.                                        
-  CCIfCC<"CallingConv::X86_ThisCall", 
+  // convention requires "this" to be passed in RCX.
+  CCIfCC<"CallingConv::X86_ThisCall",
     CCIfSRet<CCIfType<[i64], CCAssignToRegWithShadow<[RDX , R8  , R9  ],
                                                      [XMM1, XMM2, XMM3]>>>>,
 
@@ -281,6 +401,25 @@ def CC_X86_Win64_C : CallingConv<[
   CCIfType<[f80], CCAssignToStack<0, 0>>
 ]>;
 
+def CC_X86_Win64_VectorCall : CallingConv<[
+  // The first 6 floating point and vector types of 128 bits or less use
+  // XMM0-XMM5.
+  CCIfType<[f32, f64, v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
+           CCAssignToReg<[XMM0, XMM1, XMM2, XMM3, XMM4, XMM5]>>,
+
+  // 256-bit vectors use YMM registers.
+  CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
+           CCAssignToReg<[YMM0, YMM1, YMM2, YMM3, YMM4, YMM5]>>,
+
+  // 512-bit vectors use ZMM registers.
+  CCIfType<[v64i8, v32i16, v16i32, v8i64, v16f32, v8f64],
+           CCAssignToReg<[ZMM0, ZMM1, ZMM2, ZMM3, ZMM4, ZMM5]>>,
+
+  // Delegate to fastcall to handle integer types.
+  CCDelegateTo<CC_X86_Win64_C>
+]>;
+
+
 def CC_X86_64_GHC : CallingConv<[
   // Promote i8/i16/i32 arguments to i64.
   CCIfType<[i8, i16, i32], CCPromoteToType<i64>>,
@@ -307,13 +446,91 @@ def CC_X86_64_HiPE : CallingConv<[
   CCIfType<[i32, i64, f32, f64], CCAssignToStack<8, 8>>
 ]>;
 
+def CC_X86_64_WebKit_JS : CallingConv<[
+  // Promote i8/i16 arguments to i32.
+  CCIfType<[i8, i16], CCPromoteToType<i32>>,
+
+  // Only the first integer argument is passed in register.
+  CCIfType<[i32], CCAssignToReg<[EAX]>>,
+  CCIfType<[i64], CCAssignToReg<[RAX]>>,
+
+  // The remaining integer arguments are passed on the stack. 32bit integer and
+  // floating-point arguments are aligned to 4 byte and stored in 4 byte slots.
+  // 64bit integer and floating-point arguments are aligned to 8 byte and stored
+  // in 8 byte stack slots.
+  CCIfType<[i32, f32], CCAssignToStack<4, 4>>,
+  CCIfType<[i64, f64], CCAssignToStack<8, 8>>
+]>;
+
+// No explicit register is specified for the AnyReg calling convention. The
+// register allocator may assign the arguments to any free register.
+//
+// This calling convention is currently only supported by the stackmap and
+// patchpoint intrinsics. All other uses will result in an assert on Debug
+// builds. On Release builds we fallback to the X86 C calling convention.
+def CC_X86_64_AnyReg : CallingConv<[
+  CCCustom<"CC_X86_AnyReg_Error">
+]>;
+
 //===----------------------------------------------------------------------===//
 // X86 C Calling Convention
 //===----------------------------------------------------------------------===//
 
+/// CC_X86_32_Vector_Common - In all X86-32 calling conventions, extra vector
+/// values are spilled on the stack.
+def CC_X86_32_Vector_Common : CallingConv<[
+  // Other SSE vectors get 16-byte stack slots that are 16-byte aligned.
+  CCIfType<[v16i8, v8i16, v4i32, v2i64, v4f32, v2f64], CCAssignToStack<16, 16>>,
+
+  // 256-bit AVX vectors get 32-byte stack slots that are 32-byte aligned.
+  CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
+           CCAssignToStack<32, 32>>,
+
+  // 512-bit AVX 512-bit vectors get 64-byte stack slots that are 64-byte aligned.
+  CCIfType<[v64i8, v32i16, v16i32, v8i64, v16f32, v8f64],
+           CCAssignToStack<64, 64>>
+]>;
+
+// CC_X86_32_Vector_Standard - The first 3 vector arguments are passed in
+// vector registers
+def CC_X86_32_Vector_Standard : CallingConv<[
+  // SSE vector arguments are passed in XMM registers.
+  CCIfNotVarArg<CCIfType<[v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
+                CCAssignToReg<[XMM0, XMM1, XMM2]>>>,
+
+  // AVX 256-bit vector arguments are passed in YMM registers.
+  CCIfNotVarArg<CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
+                CCIfSubtarget<"hasFp256()",
+                CCAssignToReg<[YMM0, YMM1, YMM2]>>>>,
+
+  // AVX 512-bit vector arguments are passed in ZMM registers.
+  CCIfNotVarArg<CCIfType<[v64i8, v32i16, v16i32, v8i64, v16f32, v8f64],
+                CCAssignToReg<[ZMM0, ZMM1, ZMM2]>>>,
+
+  CCDelegateTo<CC_X86_32_Vector_Common>
+]>;
+
+// CC_X86_32_Vector_Darwin - The first 4 vector arguments are passed in
+// vector registers.
+def CC_X86_32_Vector_Darwin : CallingConv<[
+  // SSE vector arguments are passed in XMM registers.
+  CCIfNotVarArg<CCIfType<[v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
+                CCAssignToReg<[XMM0, XMM1, XMM2, XMM3]>>>,
+
+  // AVX 256-bit vector arguments are passed in YMM registers.
+  CCIfNotVarArg<CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
+                CCIfSubtarget<"hasFp256()",
+                CCAssignToReg<[YMM0, YMM1, YMM2, YMM3]>>>>,
+
+  // AVX 512-bit vector arguments are passed in ZMM registers.
+  CCIfNotVarArg<CCIfType<[v64i8, v32i16, v16i32, v8i64, v16f32, v8f64],
+                CCAssignToReg<[ZMM0, ZMM1, ZMM2, ZMM3]>>>,
+
+  CCDelegateTo<CC_X86_32_Vector_Common>
+]>;
+
 /// CC_X86_32_Common - In all X86-32 calling conventions, extra integers and FP
-/// values are spilled on the stack, and the first 4 vector values go in XMM
-/// regs.
+/// values are spilled on the stack.
 def CC_X86_32_Common : CallingConv<[
   // Handles byval parameters.
   CCIfByVal<CCPassByVal<4, 4>>,
@@ -332,36 +549,37 @@ def CC_X86_32_Common : CallingConv<[
   // Integer/Float values get stored in stack slots that are 4 bytes in
   // size and 4-byte aligned.
   CCIfType<[i32, f32], CCAssignToStack<4, 4>>,
-  
+
   // Doubles get 8-byte slots that are 4-byte aligned.
   CCIfType<[f64], CCAssignToStack<8, 4>>,
 
   // Long doubles get slots whose size depends on the subtarget.
   CCIfType<[f80], CCAssignToStack<0, 4>>,
 
-  // The first 4 SSE vector arguments are passed in XMM registers.
-  CCIfNotVarArg<CCIfType<[v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
-                CCAssignToReg<[XMM0, XMM1, XMM2, XMM3]>>>,
-
-  // The first 4 AVX 256-bit vector arguments are passed in YMM registers.
-  CCIfNotVarArg<CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
-                CCIfSubtarget<"hasAVX()",
-                CCAssignToReg<[YMM0, YMM1, YMM2, YMM3]>>>>,
-
-  // Other SSE vectors get 16-byte stack slots that are 16-byte aligned.
-  CCIfType<[v16i8, v8i16, v4i32, v2i64, v4f32, v2f64], CCAssignToStack<16, 16>>,
-
-  // 256-bit AVX vectors get 32-byte stack slots that are 32-byte aligned.
-  CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
-           CCAssignToStack<32, 32>>,
+  // Boolean vectors of AVX-512 are passed in SIMD registers.
+  // The call from AVX to AVX-512 function should work,
+  // since the boolean types in AVX/AVX2 are promoted by default.
+  CCIfType<[v2i1],  CCPromoteToType<v2i64>>,
+  CCIfType<[v4i1],  CCPromoteToType<v4i32>>,
+  CCIfType<[v8i1],  CCPromoteToType<v8i16>>,
+  CCIfType<[v16i1], CCPromoteToType<v16i8>>,
+  CCIfType<[v32i1], CCPromoteToType<v32i8>>,
+  CCIfType<[v64i1], CCPromoteToType<v64i8>>,
 
   // __m64 vectors get 8-byte stack slots that are 4-byte aligned. They are
   // passed in the parameter area.
-  CCIfType<[x86mmx], CCAssignToStack<8, 4>>]>;
+  CCIfType<[x86mmx], CCAssignToStack<8, 4>>,
+
+  // Darwin passes vectors in a form that differs from the i386 psABI
+  CCIfSubtarget<"isTargetDarwin()", CCDelegateTo<CC_X86_32_Vector_Darwin>>,
+
+  // Otherwise, drop to 'normal' X86-32 CC
+  CCDelegateTo<CC_X86_32_Vector_Standard>
+]>;
 
 def CC_X86_32_C : CallingConv<[
-  // Promote i8/i16 arguments to i32.
-  CCIfType<[i8, i16], CCPromoteToType<i32>>,
+  // Promote i1/i8/i16 arguments to i32.
+  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,
 
   // The 'nest' parameter, if any, is passed in ECX.
   CCIfNest<CCAssignToReg<[ECX]>>,
@@ -375,8 +593,8 @@ def CC_X86_32_C : CallingConv<[
 ]>;
 
 def CC_X86_32_FastCall : CallingConv<[
-  // Promote i8/i16 arguments to i32.
-  CCIfType<[i8, i16], CCPromoteToType<i32>>,
+  // Promote i1/i8/i16 arguments to i32.
+  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,
 
   // The 'nest' parameter, if any, is passed in EAX.
   CCIfNest<CCAssignToReg<[EAX]>>,
@@ -388,13 +606,31 @@ def CC_X86_32_FastCall : CallingConv<[
   CCDelegateTo<CC_X86_32_Common>
 ]>;
 
-def CC_X86_32_ThisCall : CallingConv<[
-  // Promote i8/i16 arguments to i32.
-  CCIfType<[i8, i16], CCPromoteToType<i32>>,
+def CC_X86_32_VectorCall : CallingConv<[
+  // The first 6 floating point and vector types of 128 bits or less use
+  // XMM0-XMM5.
+  CCIfType<[f32, f64, v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
+           CCAssignToReg<[XMM0, XMM1, XMM2, XMM3, XMM4, XMM5]>>,
 
-  // Pass sret arguments indirectly through stack.
-  CCIfSRet<CCAssignToStack<4, 4>>,
+  // 256-bit vectors use YMM registers.
+  CCIfType<[v32i8, v16i16, v8i32, v4i64, v8f32, v4f64],
+           CCAssignToReg<[YMM0, YMM1, YMM2, YMM3, YMM4, YMM5]>>,
+
+  // 512-bit vectors use ZMM registers.
+  CCIfType<[v64i8, v32i16, v16i32, v8i64, v16f32, v8f64],
+           CCAssignToReg<[ZMM0, ZMM1, ZMM2, ZMM3, ZMM4, ZMM5]>>,
+
+  // Otherwise, pass it indirectly.
+  CCIfType<[v16i8, v8i16, v4i32, v2i64, v4f32, v2f64,
+            v32i8, v16i16, v8i32, v4i64, v8f32, v4f64,
+            v64i8, v32i16, v16i32, v8i64, v16f32, v8f64],
+           CCCustom<"CC_X86_32_VectorCallIndirect">>,
+
+  // Delegate to fastcall to handle integer types.
+  CCDelegateTo<CC_X86_32_FastCall>
+]>;
 
+def CC_X86_32_ThisCall_Common : CallingConv<[
   // The first integer argument is passed in ECX
   CCIfType<[i32], CCAssignToReg<[ECX]>>,
 
@@ -402,14 +638,36 @@ def CC_X86_32_ThisCall : CallingConv<[
   CCDelegateTo<CC_X86_32_Common>
 ]>;
 
+def CC_X86_32_ThisCall_Mingw : CallingConv<[
+  // Promote i1/i8/i16 arguments to i32.
+  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,
+
+  CCDelegateTo<CC_X86_32_ThisCall_Common>
+]>;
+
+def CC_X86_32_ThisCall_Win : CallingConv<[
+  // Promote i1/i8/i16 arguments to i32.
+  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,
+
+  // Pass sret arguments indirectly through stack.
+  CCIfSRet<CCAssignToStack<4, 4>>,
+
+  CCDelegateTo<CC_X86_32_ThisCall_Common>
+]>;
+
+def CC_X86_32_ThisCall : CallingConv<[
+  CCIfSubtarget<"isTargetCygMing()", CCDelegateTo<CC_X86_32_ThisCall_Mingw>>,
+  CCDelegateTo<CC_X86_32_ThisCall_Win>
+]>;
+
 def CC_X86_32_FastCC : CallingConv<[
   // Handles byval parameters.  Note that we can't rely on the delegation
   // to CC_X86_32_Common for this because that happens after code that
   // puts arguments in registers.
   CCIfByVal<CCPassByVal<4, 4>>,
 
-  // Promote i8/i16 arguments to i32.
-  CCIfType<[i8, i16], CCPromoteToType<i32>>,
+  // Promote i1/i8/i16 arguments to i32.
+  CCIfType<[i1, i8, i16], CCPromoteToType<i32>>,
 
   // The 'nest' parameter, if any, is passed in EAX.
   CCIfNest<CCAssignToReg<[EAX]>>,
@@ -469,11 +727,26 @@ def CC_Intel_OCL_BI : CallingConv<[
   CCIfType<[v8f32, v4f64, v8i32, v4i64],
            CCAssignToReg<[YMM0, YMM1, YMM2, YMM3]>>,
 
+  // The 512-bit vector arguments are passed in ZMM registers.
+  CCIfType<[v16f32, v8f64, v16i32, v8i64],
+           CCAssignToReg<[ZMM0, ZMM1, ZMM2, ZMM3]>>,
+
+  // Pass masks in mask registers
+  CCIfType<[v16i1, v8i1], CCAssignToReg<[K1]>>,
+
   CCIfSubtarget<"isTargetWin64()", CCDelegateTo<CC_X86_Win64_C>>,
   CCIfSubtarget<"is64Bit()",       CCDelegateTo<CC_X86_64_C>>,
   CCDelegateTo<CC_X86_32_C>
 ]>;
 
+def CC_X86_32_Intr : CallingConv<[
+  CCAssignToStack<4, 4>
+]>;
+
+def CC_X86_64_Intr : CallingConv<[
+  CCAssignToStack<8, 8>
+]>;
+
 //===----------------------------------------------------------------------===//
 // X86 Root Argument Calling Conventions
 //===----------------------------------------------------------------------===//
@@ -481,10 +754,12 @@ def CC_Intel_OCL_BI : CallingConv<[
 // This is the root argument convention for the X86-32 backend.
 def CC_X86_32 : CallingConv<[
   CCIfCC<"CallingConv::X86_FastCall", CCDelegateTo<CC_X86_32_FastCall>>,
+  CCIfCC<"CallingConv::X86_VectorCall", CCDelegateTo<CC_X86_32_VectorCall>>,
   CCIfCC<"CallingConv::X86_ThisCall", CCDelegateTo<CC_X86_32_ThisCall>>,
   CCIfCC<"CallingConv::Fast", CCDelegateTo<CC_X86_32_FastCC>>,
   CCIfCC<"CallingConv::GHC", CCDelegateTo<CC_X86_32_GHC>>,
   CCIfCC<"CallingConv::HiPE", CCDelegateTo<CC_X86_32_HiPE>>,
+  CCIfCC<"CallingConv::X86_INTR", CCDelegateTo<CC_X86_32_Intr>>,
 
   // Otherwise, drop to normal X86-32 CC
   CCDelegateTo<CC_X86_32_C>
@@ -494,8 +769,14 @@ def CC_X86_32 : CallingConv<[
 def CC_X86_64 : CallingConv<[
   CCIfCC<"CallingConv::GHC", CCDelegateTo<CC_X86_64_GHC>>,
   CCIfCC<"CallingConv::HiPE", CCDelegateTo<CC_X86_64_HiPE>>,
+  CCIfCC<"CallingConv::WebKit_JS", CCDelegateTo<CC_X86_64_WebKit_JS>>,
+  CCIfCC<"CallingConv::AnyReg", CCDelegateTo<CC_X86_64_AnyReg>>,
   CCIfCC<"CallingConv::X86_64_Win64", CCDelegateTo<CC_X86_Win64_C>>,
   CCIfCC<"CallingConv::X86_64_SysV", CCDelegateTo<CC_X86_64_C>>,
+  CCIfCC<"CallingConv::X86_VectorCall", CCDelegateTo<CC_X86_Win64_VectorCall>>,
+  CCIfCC<"CallingConv::HHVM", CCDelegateTo<CC_X86_64_HHVM>>,
+  CCIfCC<"CallingConv::HHVM_C", CCDelegateTo<CC_X86_64_HHVM_C>>,
+  CCIfCC<"CallingConv::X86_INTR", CCDelegateTo<CC_X86_64_Intr>>,
 
   // Mingw64 and native Win64 use Win64 CC
   CCIfSubtarget<"isTargetWin64()", CCDelegateTo<CC_X86_Win64_C>>,
@@ -526,15 +807,46 @@ def CSR_64EHRet : CalleeSavedRegs<(add RAX, RDX, CSR_64)>;
 def CSR_Win64 : CalleeSavedRegs<(add RBX, RBP, RDI, RSI, R12, R13, R14, R15,
                                      (sequence "XMM%u", 6, 15))>;
 
-def CSR_MostRegs_64 : CalleeSavedRegs<(add RBX, RCX, RDX, RSI, RDI, R8, R9, R10,
+// The function used by Darwin to obtain the address of a thread-local variable
+// uses rdi to pass a single parameter and rax for the return value. All other
+// GPRs are preserved.
+def CSR_64_TLS_Darwin : CalleeSavedRegs<(add CSR_64, RCX, RDX, RSI,
+                                             R8, R9, R10, R11)>;
+
+// All GPRs - except r11
+def CSR_64_RT_MostRegs : CalleeSavedRegs<(add CSR_64, RAX, RCX, RDX, RSI, RDI,
+                                              R8, R9, R10, RSP)>;
+
+// All registers - except r11
+def CSR_64_RT_AllRegs     : CalleeSavedRegs<(add CSR_64_RT_MostRegs,
+                                                 (sequence "XMM%u", 0, 15))>;
+def CSR_64_RT_AllRegs_AVX : CalleeSavedRegs<(add CSR_64_RT_MostRegs,
+                                                 (sequence "YMM%u", 0, 15))>;
+
+def CSR_64_MostRegs : CalleeSavedRegs<(add RBX, RCX, RDX, RSI, RDI, R8, R9, R10,
                                            R11, R12, R13, R14, R15, RBP,
                                            (sequence "XMM%u", 0, 15))>;
 
+def CSR_32_AllRegs     : CalleeSavedRegs<(add EAX, EBX, ECX, EDX, EBP, ESI,
+                                              EDI, ESP)>;
+def CSR_32_AllRegs_SSE : CalleeSavedRegs<(add CSR_32_AllRegs,
+                                              (sequence "XMM%u", 0, 7))>;
+
+def CSR_64_AllRegs     : CalleeSavedRegs<(add CSR_64_MostRegs, RAX, RSP,
+                                              (sequence "XMM%u", 16, 31))>;
+def CSR_64_AllRegs_AVX : CalleeSavedRegs<(sub (add CSR_64_MostRegs, RAX, RSP,
+                                                   (sequence "YMM%u", 0, 31)),
+                                              (sequence "XMM%u", 0, 15))>;
+
 // Standard C + YMM6-15
 def CSR_Win64_Intel_OCL_BI_AVX : CalleeSavedRegs<(add RBX, RBP, RDI, RSI, R12,
-                                                  R13, R14, R15, 
+                                                  R13, R14, R15,
                                                   (sequence "YMM%u", 6, 15))>;
 
+def CSR_Win64_Intel_OCL_BI_AVX512 : CalleeSavedRegs<(add RBX, RBP, RDI, RSI,
+                                                     R12, R13, R14, R15,
+                                                     (sequence "ZMM%u", 6, 21),
+                                                     K4, K5, K6, K7)>;
 //Standard C + XMM 8-15
 def CSR_64_Intel_OCL_BI       : CalleeSavedRegs<(add CSR_64,
                                                  (sequence "XMM%u", 8, 15))>;
@@ -542,3 +854,10 @@ def CSR_64_Intel_OCL_BI       : CalleeSavedRegs<(add CSR_64,
 //Standard C + YMM 8-15
 def CSR_64_Intel_OCL_BI_AVX    : CalleeSavedRegs<(add CSR_64,
                                                   (sequence "YMM%u", 8, 15))>;
+
+def CSR_64_Intel_OCL_BI_AVX512 : CalleeSavedRegs<(add RBX, RDI, RSI, R14, R15,
+                                                  (sequence "ZMM%u", 16, 31),
+                                                  K4, K5, K6, K7)>;
+
+// Only R12 is preserved for PHP calls in HHVM.
+def CSR_64_HHVM : CalleeSavedRegs<(add R12)>;