mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-11-10 01:10:48 +00:00
86aef0a4f0
to be extended to a full register. This is modeled in the IR by marking the return value (or argument) with a signext or zeroext attribute. However, while these attributes are respected for function arguments, they are currently ignored for function return values by the PowerPC back-end. This patch updates PPCCallingConv.td to ask for the promotion to i64, and fixes LowerReturn and LowerCallResult to implement it. The new test case verifies that both arguments and return values are properly extended when passing them; and also that the optimizers understand incoming argument and return values are in fact guaranteed by the ABI to be extended. The patch caused a spurious breakage in CodeGen/PowerPC/coalesce-ext.ll, since the test case used a "ret" instruction to create a use of an i32 value at the end of the function (to set up data flow as required for what the test is intended to test). Since there's now an implicit promotion to i64, that data flow no longer works as expected. To fix this, this patch now adds an extra "add" to ensure we have an appropriate use of the i32 value. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167396 91177308-0d34-0410-b5e6-96231b3b80d8
167 lines
7.4 KiB
TableGen
167 lines
7.4 KiB
TableGen
//===- PPCCallingConv.td - Calling Conventions for PowerPC -*- tablegen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This describes the calling conventions for the PowerPC 32- and 64-bit
|
|
// architectures.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
/// CCIfSubtarget - Match if the current subtarget has a feature F.
|
|
class CCIfSubtarget<string F, CCAction A>
|
|
: CCIf<!strconcat("State.getTarget().getSubtarget<PPCSubtarget>().", F), A>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Return Value Calling Convention
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Return-value convention for PowerPC
|
|
def RetCC_PPC : CallingConv<[
|
|
// On PPC64, integer return values are always promoted to i64
|
|
CCIfType<[i32], CCIfSubtarget<"isPPC64()", CCPromoteToType<i64>>>,
|
|
|
|
CCIfType<[i32], CCAssignToReg<[R3, R4, R5, R6, R7, R8, R9, R10]>>,
|
|
CCIfType<[i64], CCAssignToReg<[X3, X4, X5, X6]>>,
|
|
|
|
CCIfType<[f32], CCAssignToReg<[F1]>>,
|
|
CCIfType<[f64], CCAssignToReg<[F1, F2]>>,
|
|
|
|
// Vector types are always returned in V2.
|
|
CCIfType<[v16i8, v8i16, v4i32, v4f32], CCAssignToReg<[V2]>>
|
|
]>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PowerPC Argument Calling Conventions
|
|
//===----------------------------------------------------------------------===//
|
|
/*
|
|
def CC_PPC : CallingConv<[
|
|
// The first 8 integer arguments are passed in integer registers.
|
|
CCIfType<[i32], CCAssignToReg<[R3, R4, R5, R6, R7, R8, R9, R10]>>,
|
|
CCIfType<[i64], CCAssignToReg<[X3, X4, X5, X6, X7, X8, X9, X10]>>,
|
|
|
|
// Common sub-targets passes FP values in F1 - F13
|
|
CCIfType<[f32, f64],
|
|
CCAssignToReg<[F1, F2, F3, F4, F5, F6, F7, F8,F9,F10,F11,F12,F13]>>,
|
|
|
|
// The first 12 Vector arguments are passed in altivec registers.
|
|
CCIfType<[v16i8, v8i16, v4i32, v4f32],
|
|
CCAssignToReg<[V2, V3, V4, V5, V6, V7, V8, V9, V10,V11,V12,V13]>>
|
|
|
|
/*
|
|
// 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>>,
|
|
|
|
// Vectors get 16-byte stack slots that are 16-byte aligned.
|
|
CCIfType<[v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
|
|
CCAssignToStack<16, 16>>*/
|
|
]>;
|
|
|
|
*/
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PowerPC System V Release 4 ABI
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def CC_PPC_SVR4_Common : CallingConv<[
|
|
// The ABI requires i64 to be passed in two adjacent registers with the first
|
|
// register having an odd register number.
|
|
CCIfType<[i32], CCIfSplit<CCCustom<"CC_PPC_SVR4_Custom_AlignArgRegs">>>,
|
|
|
|
// The first 8 integer arguments are passed in integer registers.
|
|
CCIfType<[i32], CCAssignToReg<[R3, R4, R5, R6, R7, R8, R9, R10]>>,
|
|
|
|
// Make sure the i64 words from a long double are either both passed in
|
|
// registers or both passed on the stack.
|
|
CCIfType<[f64], CCIfSplit<CCCustom<"CC_PPC_SVR4_Custom_AlignFPArgRegs">>>,
|
|
|
|
// FP values are passed in F1 - F8.
|
|
CCIfType<[f32, f64], CCAssignToReg<[F1, F2, F3, F4, F5, F6, F7, F8]>>,
|
|
|
|
// Split arguments have an alignment of 8 bytes on the stack.
|
|
CCIfType<[i32], CCIfSplit<CCAssignToStack<4, 8>>>,
|
|
|
|
CCIfType<[i32], CCAssignToStack<4, 4>>,
|
|
|
|
// Floats are stored in double precision format, thus they have the same
|
|
// alignment and size as doubles.
|
|
CCIfType<[f32,f64], CCAssignToStack<8, 8>>,
|
|
|
|
// Vectors get 16-byte stack slots that are 16-byte aligned.
|
|
CCIfType<[v16i8, v8i16, v4i32, v4f32], CCAssignToStack<16, 16>>
|
|
]>;
|
|
|
|
// This calling convention puts vector arguments always on the stack. It is used
|
|
// to assign vector arguments which belong to the variable portion of the
|
|
// parameter list of a variable argument function.
|
|
def CC_PPC_SVR4_VarArg : CallingConv<[
|
|
CCDelegateTo<CC_PPC_SVR4_Common>
|
|
]>;
|
|
|
|
// In contrast to CC_PPC_SVR4_VarArg, this calling convention first tries to put
|
|
// vector arguments in vector registers before putting them on the stack.
|
|
def CC_PPC_SVR4 : CallingConv<[
|
|
// The first 12 Vector arguments are passed in AltiVec registers.
|
|
CCIfType<[v16i8, v8i16, v4i32, v4f32],
|
|
CCAssignToReg<[V2, V3, V4, V5, V6, V7, V8, V9, V10, V11, V12, V13]>>,
|
|
|
|
CCDelegateTo<CC_PPC_SVR4_Common>
|
|
]>;
|
|
|
|
// Helper "calling convention" to handle aggregate by value arguments.
|
|
// Aggregate by value arguments are always placed in the local variable space
|
|
// of the caller. This calling convention is only used to assign those stack
|
|
// offsets in the callers stack frame.
|
|
//
|
|
// Still, the address of the aggregate copy in the callers stack frame is passed
|
|
// in a GPR (or in the parameter list area if all GPRs are allocated) from the
|
|
// caller to the callee. The location for the address argument is assigned by
|
|
// the CC_PPC_SVR4 calling convention.
|
|
//
|
|
// The only purpose of CC_PPC_SVR4_Custom_Dummy is to skip arguments which are
|
|
// not passed by value.
|
|
|
|
def CC_PPC_SVR4_ByVal : CallingConv<[
|
|
CCIfByVal<CCPassByVal<4, 4>>,
|
|
|
|
CCCustom<"CC_PPC_SVR4_Custom_Dummy">
|
|
]>;
|
|
|
|
def CSR_Darwin32 : CalleeSavedRegs<(add R13, R14, R15, R16, R17, R18, R19, R20,
|
|
R21, R22, R23, R24, R25, R26, R27, R28,
|
|
R29, R30, R31, F14, F15, F16, F17, F18,
|
|
F19, F20, F21, F22, F23, F24, F25, F26,
|
|
F27, F28, F29, F30, F31, CR2, CR3, CR4,
|
|
V20, V21, V22, V23, V24, V25, V26, V27,
|
|
V28, V29, V30, V31)>;
|
|
|
|
def CSR_SVR432 : CalleeSavedRegs<(add R14, R15, R16, R17, R18, R19, R20, VRSAVE,
|
|
R21, R22, R23, R24, R25, R26, R27, R28,
|
|
R29, R30, R31, F14, F15, F16, F17, F18,
|
|
F19, F20, F21, F22, F23, F24, F25, F26,
|
|
F27, F28, F29, F30, F31, CR2, CR3, CR4,
|
|
V20, V21, V22, V23, V24, V25, V26, V27,
|
|
V28, V29, V30, V31)>;
|
|
|
|
def CSR_Darwin64 : CalleeSavedRegs<(add X13, X14, X15, X16, X17, X18, X19, X20,
|
|
X21, X22, X23, X24, X25, X26, X27, X28,
|
|
X29, X30, X31, F14, F15, F16, F17, F18,
|
|
F19, F20, F21, F22, F23, F24, F25, F26,
|
|
F27, F28, F29, F30, F31, CR2, CR3, CR4,
|
|
V20, V21, V22, V23, V24, V25, V26, V27,
|
|
V28, V29, V30, V31)>;
|
|
|
|
def CSR_SVR464 : CalleeSavedRegs<(add X14, X15, X16, X17, X18, X19, X20, VRSAVE,
|
|
X21, X22, X23, X24, X25, X26, X27, X28,
|
|
X29, X30, X31, F14, F15, F16, F17, F18,
|
|
F19, F20, F21, F22, F23, F24, F25, F26,
|
|
F27, F28, F29, F30, F31, CR2, CR3, CR4,
|
|
V20, V21, V22, V23, V24, V25, V26, V27,
|
|
V28, V29, V30, V31)>;
|