mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-25 14:30:32 +00:00
7ee74a663a
This implements SJLJ lowering on PPC, making the Clang functions
__builtin_{setjmp/longjmp} functional on PPC platforms. The implementation
strategy is similar to that on X86, with the exception that a branch-and-link
variant is used to get the right jump address. Credit goes to Bill Schmidt for
suggesting the use of the unconditional bcl form (instead of the regular bl
instruction) to limit return-address-cache pollution.
Benchmarking the speed at -O3 of:
static jmp_buf env_sigill;
void foo() {
__builtin_longjmp(env_sigill,1);
}
main() {
...
for (int i = 0; i < c; ++i) {
if (__builtin_setjmp(env_sigill)) {
goto done;
} else {
foo();
}
done:;
}
...
}
vs. the same code using the libc setjmp/longjmp functions on a P7 shows that
this builtin implementation is ~4x faster with Altivec enabled and ~7.25x
faster with Altivec disabled. This comparison is somewhat unfair because the
libc version must also save/restore the VSX registers which we don't yet
support.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177666 91177308-0d34-0410-b5e6-96231b3b80d8
144 lines
6.5 KiB
TableGen
144 lines
6.5 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<[i128], CCAssignToReg<[X3, X4, X5, X6]>>,
|
|
|
|
CCIfType<[f32], CCAssignToReg<[F1, F2]>>,
|
|
CCIfType<[f64], CCAssignToReg<[F1, F2, F3, F4]>>,
|
|
|
|
// Vector types are always returned in V2.
|
|
CCIfType<[v16i8, v8i16, v4i32, v4f32], CCAssignToReg<[V2]>>
|
|
]>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PowerPC System V Release 4 32-bit ABI
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def CC_PPC32_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_PPC32_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_PPC32_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_PPC32_SVR4_VarArg : CallingConv<[
|
|
CCDelegateTo<CC_PPC32_SVR4_Common>
|
|
]>;
|
|
|
|
// In contrast to CC_PPC32_SVR4_VarArg, this calling convention first tries to
|
|
// put vector arguments in vector registers before putting them on the stack.
|
|
def CC_PPC32_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_PPC32_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_PPC32_SVR4 calling convention.
|
|
//
|
|
// The only purpose of CC_PPC32_SVR4_Custom_Dummy is to skip arguments which are
|
|
// not passed by value.
|
|
|
|
def CC_PPC32_SVR4_ByVal : CallingConv<[
|
|
CCIfByVal<CCPassByVal<4, 4>>,
|
|
|
|
CCCustom<"CC_PPC32_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)>;
|
|
|
|
def CSR_NoRegs : CalleeSavedRegs<(add)>;
|
|
|
|
def CSR_NoRegs_Altivec : CalleeSavedRegs<(add (sequence "V%u", 0, 31), VRSAVE)>;
|
|
|