mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-02-26 10:29:36 +00:00
Function pointers under PPC64 ELFv1 (which is used on PPC64/Linux on the POWER7, A2 and earlier cores) are really pointers to a function descriptor, a structure with three pointers: the actual pointer to the code to which to jump, the pointer to the TOC needed by the callee, and an environment pointer. We used to chain these loads, and make them opaque to the rest of the optimizer, so that they'd always occur directly before the call. This is not necessary, and in fact, highly suboptimal on embedded cores. Once the function pointer is known, the loads can be performed ahead of time; in fact, they can be hoisted out of loops. Now these function descriptors are almost always generated by the linker, and thus the contents of the descriptors are invariant. As a result, by default, we'll mark the associated loads as invariant (allowing them to be hoisted out of loops). I've added a target feature to turn this off, however, just in case someone needs that option (constructing an on-stack descriptor, casting it to a function pointer, and then calling it cannot be well-defined C/C++ code, but I can imagine some JIT-compilation system doing so). Consider this simple test: $ cat call.c typedef void (*fp)(); void bar(fp x) { for (int i = 0; i < 1600000000; ++i) x(); } $ cat main.c typedef void (*fp)(); void bar(fp x); void foo() {} int main() { bar(foo); } On the PPC A2 (the BG/Q supercomputer), marking the function-descriptor loads as invariant brings the execution time down to ~8 seconds from ~32 seconds with the loads in the loop. The difference on the POWER7 is smaller. Compiling with: gcc -std=c99 -O3 -mcpu=native call.c main.c : ~6 seconds [this is 4.8.2] clang -O3 -mcpu=native call.c main.c : ~5.3 seconds clang -O3 -mcpu=native call.c main.c -mno-invariant-function-descriptors : ~4 seconds (looks like we'd benefit from additional loop unrolling here, as a first guess, because this is faster with the extra loads) The -mno-invariant-function-descriptors will be added to Clang shortly. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@226207 91177308-0d34-0410-b5e6-96231b3b80d8
247 lines
7.6 KiB
C++
247 lines
7.6 KiB
C++
//===-- PowerPCSubtarget.cpp - PPC Subtarget Information ------------------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file implements the PPC specific subclass of TargetSubtargetInfo.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "PPCSubtarget.h"
|
|
#include "PPC.h"
|
|
#include "PPCRegisterInfo.h"
|
|
#include "llvm/CodeGen/MachineFunction.h"
|
|
#include "llvm/CodeGen/MachineScheduler.h"
|
|
#include "llvm/IR/Attributes.h"
|
|
#include "llvm/IR/Function.h"
|
|
#include "llvm/IR/GlobalValue.h"
|
|
#include "llvm/Support/CommandLine.h"
|
|
#include "llvm/Support/Host.h"
|
|
#include "llvm/Support/TargetRegistry.h"
|
|
#include "llvm/Target/TargetMachine.h"
|
|
#include <cstdlib>
|
|
|
|
using namespace llvm;
|
|
|
|
#define DEBUG_TYPE "ppc-subtarget"
|
|
|
|
#define GET_SUBTARGETINFO_TARGET_DESC
|
|
#define GET_SUBTARGETINFO_CTOR
|
|
#include "PPCGenSubtargetInfo.inc"
|
|
|
|
static cl::opt<bool> UseSubRegLiveness("ppc-track-subreg-liveness",
|
|
cl::desc("Enable subregister liveness tracking for PPC"), cl::Hidden);
|
|
|
|
/// Return the datalayout string of a subtarget.
|
|
static std::string getDataLayoutString(const Triple &T) {
|
|
bool is64Bit = T.getArch() == Triple::ppc64 || T.getArch() == Triple::ppc64le;
|
|
std::string Ret;
|
|
|
|
// Most PPC* platforms are big endian, PPC64LE is little endian.
|
|
if (T.getArch() == Triple::ppc64le)
|
|
Ret = "e";
|
|
else
|
|
Ret = "E";
|
|
|
|
Ret += DataLayout::getManglingComponent(T);
|
|
|
|
// PPC32 has 32 bit pointers. The PS3 (OS Lv2) is a PPC64 machine with 32 bit
|
|
// pointers.
|
|
if (!is64Bit || T.getOS() == Triple::Lv2)
|
|
Ret += "-p:32:32";
|
|
|
|
// Note, the alignment values for f64 and i64 on ppc64 in Darwin
|
|
// documentation are wrong; these are correct (i.e. "what gcc does").
|
|
if (is64Bit || !T.isOSDarwin())
|
|
Ret += "-i64:64";
|
|
else
|
|
Ret += "-f64:32:64";
|
|
|
|
// PPC64 has 32 and 64 bit registers, PPC32 has only 32 bit ones.
|
|
if (is64Bit)
|
|
Ret += "-n32:64";
|
|
else
|
|
Ret += "-n32";
|
|
|
|
return Ret;
|
|
}
|
|
|
|
PPCSubtarget &PPCSubtarget::initializeSubtargetDependencies(StringRef CPU,
|
|
StringRef FS) {
|
|
initializeEnvironment();
|
|
initSubtargetFeatures(CPU, FS);
|
|
return *this;
|
|
}
|
|
|
|
PPCSubtarget::PPCSubtarget(const std::string &TT, const std::string &CPU,
|
|
const std::string &FS, const PPCTargetMachine &TM)
|
|
: PPCGenSubtargetInfo(TT, CPU, FS), TargetTriple(TT),
|
|
DL(getDataLayoutString(TargetTriple)),
|
|
IsPPC64(TargetTriple.getArch() == Triple::ppc64 ||
|
|
TargetTriple.getArch() == Triple::ppc64le),
|
|
TargetABI(PPC_ABI_UNKNOWN),
|
|
FrameLowering(initializeSubtargetDependencies(CPU, FS)), InstrInfo(*this),
|
|
TLInfo(TM), TSInfo(&DL) {}
|
|
|
|
void PPCSubtarget::initializeEnvironment() {
|
|
StackAlignment = 16;
|
|
DarwinDirective = PPC::DIR_NONE;
|
|
HasMFOCRF = false;
|
|
Has64BitSupport = false;
|
|
Use64BitRegs = false;
|
|
UseCRBits = false;
|
|
HasAltivec = false;
|
|
HasSPE = false;
|
|
HasQPX = false;
|
|
HasVSX = false;
|
|
HasP8Vector = false;
|
|
HasFCPSGN = false;
|
|
HasFSQRT = false;
|
|
HasFRE = false;
|
|
HasFRES = false;
|
|
HasFRSQRTE = false;
|
|
HasFRSQRTES = false;
|
|
HasRecipPrec = false;
|
|
HasSTFIWX = false;
|
|
HasLFIWAX = false;
|
|
HasFPRND = false;
|
|
HasFPCVT = false;
|
|
HasISEL = false;
|
|
HasPOPCNTD = false;
|
|
HasCMPB = false;
|
|
HasLDBRX = false;
|
|
IsBookE = false;
|
|
HasOnlyMSYNC = false;
|
|
IsPPC4xx = false;
|
|
IsPPC6xx = false;
|
|
IsE500 = false;
|
|
DeprecatedMFTB = false;
|
|
DeprecatedDST = false;
|
|
HasLazyResolverStubs = false;
|
|
HasICBT = false;
|
|
HasInvariantFunctionDescriptors = false;
|
|
}
|
|
|
|
void PPCSubtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
|
|
// Determine default and user specified characteristics
|
|
std::string CPUName = CPU;
|
|
if (CPUName.empty())
|
|
CPUName = "generic";
|
|
#if (defined(__APPLE__) || defined(__linux__)) && \
|
|
(defined(__ppc__) || defined(__powerpc__))
|
|
if (CPUName == "generic")
|
|
CPUName = sys::getHostCPUName();
|
|
#endif
|
|
|
|
// Initialize scheduling itinerary for the specified CPU.
|
|
InstrItins = getInstrItineraryForCPU(CPUName);
|
|
|
|
// Parse features string.
|
|
ParseSubtargetFeatures(CPUName, FS);
|
|
|
|
// If the user requested use of 64-bit regs, but the cpu selected doesn't
|
|
// support it, ignore.
|
|
if (IsPPC64 && has64BitSupport())
|
|
Use64BitRegs = true;
|
|
|
|
// Set up darwin-specific properties.
|
|
if (isDarwin())
|
|
HasLazyResolverStubs = true;
|
|
|
|
// QPX requires a 32-byte aligned stack. Note that we need to do this if
|
|
// we're compiling for a BG/Q system regardless of whether or not QPX
|
|
// is enabled because external functions will assume this alignment.
|
|
if (hasQPX() || isBGQ())
|
|
StackAlignment = 32;
|
|
|
|
// Determine endianness.
|
|
IsLittleEndian = (TargetTriple.getArch() == Triple::ppc64le);
|
|
|
|
// Determine default ABI.
|
|
if (TargetABI == PPC_ABI_UNKNOWN) {
|
|
if (!isDarwin() && IsPPC64) {
|
|
if (IsLittleEndian)
|
|
TargetABI = PPC_ABI_ELFv2;
|
|
else
|
|
TargetABI = PPC_ABI_ELFv1;
|
|
}
|
|
}
|
|
}
|
|
|
|
/// hasLazyResolverStub - Return true if accesses to the specified global have
|
|
/// to go through a dyld lazy resolution stub. This means that an extra load
|
|
/// is required to get the address of the global.
|
|
bool PPCSubtarget::hasLazyResolverStub(const GlobalValue *GV,
|
|
const TargetMachine &TM) const {
|
|
// We never have stubs if HasLazyResolverStubs=false or if in static mode.
|
|
if (!HasLazyResolverStubs || TM.getRelocationModel() == Reloc::Static)
|
|
return false;
|
|
bool isDecl = GV->isDeclaration();
|
|
if (GV->hasHiddenVisibility() && !isDecl && !GV->hasCommonLinkage())
|
|
return false;
|
|
return GV->hasWeakLinkage() || GV->hasLinkOnceLinkage() ||
|
|
GV->hasCommonLinkage() || isDecl;
|
|
}
|
|
|
|
// Embedded cores need aggressive scheduling (and some others also benefit).
|
|
static bool needsAggressiveScheduling(unsigned Directive) {
|
|
switch (Directive) {
|
|
default: return false;
|
|
case PPC::DIR_440:
|
|
case PPC::DIR_A2:
|
|
case PPC::DIR_E500mc:
|
|
case PPC::DIR_E5500:
|
|
case PPC::DIR_PWR7:
|
|
case PPC::DIR_PWR8:
|
|
return true;
|
|
}
|
|
}
|
|
|
|
bool PPCSubtarget::enableMachineScheduler() const {
|
|
// Enable MI scheduling for the embedded cores.
|
|
// FIXME: Enable this for all cores (some additional modeling
|
|
// may be necessary).
|
|
return needsAggressiveScheduling(DarwinDirective);
|
|
}
|
|
|
|
// This overrides the PostRAScheduler bit in the SchedModel for each CPU.
|
|
bool PPCSubtarget::enablePostMachineScheduler() const { return true; }
|
|
|
|
PPCGenSubtargetInfo::AntiDepBreakMode PPCSubtarget::getAntiDepBreakMode() const {
|
|
return TargetSubtargetInfo::ANTIDEP_ALL;
|
|
}
|
|
|
|
void PPCSubtarget::getCriticalPathRCs(RegClassVector &CriticalPathRCs) const {
|
|
CriticalPathRCs.clear();
|
|
CriticalPathRCs.push_back(isPPC64() ?
|
|
&PPC::G8RCRegClass : &PPC::GPRCRegClass);
|
|
}
|
|
|
|
void PPCSubtarget::overrideSchedPolicy(MachineSchedPolicy &Policy,
|
|
MachineInstr *begin,
|
|
MachineInstr *end,
|
|
unsigned NumRegionInstrs) const {
|
|
if (needsAggressiveScheduling(DarwinDirective)) {
|
|
Policy.OnlyTopDown = false;
|
|
Policy.OnlyBottomUp = false;
|
|
}
|
|
|
|
// Spilling is generally expensive on all PPC cores, so always enable
|
|
// register-pressure tracking.
|
|
Policy.ShouldTrackPressure = true;
|
|
}
|
|
|
|
bool PPCSubtarget::useAA() const {
|
|
// Use AA during code generation for the embedded cores.
|
|
return needsAggressiveScheduling(DarwinDirective);
|
|
}
|
|
|
|
bool PPCSubtarget::enableSubRegLiveness() const {
|
|
return UseSubRegLiveness;
|
|
}
|
|
|