llvm-6502/lib/Target/PowerPC/PPCSubtarget.cpp
Hal Finkel f8d179ba76 [PowerPC] Add support for the QPX vector instruction set
This adds support for the QPX vector instruction set, which is used by the
enhanced A2 cores on the IBM BG/Q supercomputers. QPX vectors are 256 bytes
wide, holding 4 double-precision floating-point values. Boolean values, modeled
here as <4 x i1> are actually also represented as floating-point values
(essentially  { -1, 1 } for { false, true }). QPX shares many features with
Altivec and VSX, but is distinct from both of them. One major difference is
that, instead of adding completely-separate vector registers, QPX vector
registers are extensions of the scalar floating-point registers (lane 0 is the
corresponding scalar floating-point value). The operations supported on QPX
vectors mirrors that supported on the scalar floating-point values (with some
additional ones for permutations and logical/comparison operations).

I've been maintaining this support out-of-tree, as part of the bgclang project,
for several years. This is not the entire bgclang patch set, but is most of the
subset that can be cleanly integrated into LLVM proper at this time. Adding
this to the LLVM backend is part of my efforts to rebase bgclang to the current
LLVM trunk, but is independently useful (especially for codes that use LLVM as
a JIT in library form).

The assembler/disassembler test coverage is complete. The CodeGen test coverage
is not, but I've included some tests, and more will be added as follow-up work.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230413 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-25 01:06:45 +00:00

215 lines
6.9 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 "PPCTargetMachine.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);
static cl::opt<bool> QPXStackUnaligned("qpx-stack-unaligned",
cl::desc("Even when QPX is enabled the stack is not 32-byte aligned"),
cl::Hidden);
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),
IsPPC64(TargetTriple.getArch() == Triple::ppc64 ||
TargetTriple.getArch() == Triple::ppc64le),
TM(TM), FrameLowering(initializeSubtargetDependencies(CPU, FS)),
InstrInfo(*this), TLInfo(TM, *this), TSInfo(TM.getDataLayout()) {}
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;
HasP8Altivec = 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;
IsQPXStackUnaligned = false;
}
void PPCSubtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
// Determine default and user specified characteristics
std::string CPUName = CPU;
if (CPUName.empty()) {
// If cross-compiling with -march=ppc64le without -mcpu
if (TargetTriple.getArch() == Triple::ppc64le)
CPUName = "ppc64le";
else
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.
IsQPXStackUnaligned = QPXStackUnaligned;
StackAlignment = getPlatformStackAlignment();
// Determine endianness.
// FIXME: Part of the TargetMachine.
IsLittleEndian = (TargetTriple.getArch() == Triple::ppc64le);
}
/// 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 {
// 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;
}
bool PPCSubtarget::isELFv2ABI() const { return TM.isELFv2ABI(); }
bool PPCSubtarget::isPPC64() const { return TM.isPPC64(); }