llvm-project/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp

247 lines
8.2 KiB
C++
Raw Normal View History

//===-- PPCTargetMachine.cpp - Define TargetMachine for PowerPC -----------===//
//
2004-06-22 00:55:25 +08:00
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
2004-06-22 00:55:25 +08:00
//===----------------------------------------------------------------------===//
//
// Top-level implementation for the PowerPC target.
2004-06-22 00:55:25 +08:00
//
//===----------------------------------------------------------------------===//
#include "PPCTargetMachine.h"
#include "PPCTargetObjectFile.h"
#include "PPC.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/IR/Function.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/PassManager.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/FormattedStream.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Transforms/Scalar.h"
2004-06-22 00:55:25 +08:00
using namespace llvm;
static cl::
opt<bool> DisableCTRLoops("disable-ppc-ctrloops", cl::Hidden,
cl::desc("Disable CTR loops for PPC"));
[PowerPC] Select between VSX A-type and M-type FMA instructions just before RA The VSX instruction set has two types of FMA instructions: A-type (where the addend is taken from the output register) and M-type (where one of the product operands is taken from the output register). This adds a small pass that runs just after MI scheduling (and, thus, just before register allocation) that mutates A-type instructions (that are created during isel) into M-type instructions when: 1. This will eliminate an otherwise-necessary copy of the addend 2. One of the product operands is killed by the instruction The "right" moment to make this decision is in between scheduling and register allocation, because only there do we know whether or not one of the product operands is killed by any particular instruction. Unfortunately, this also makes the implementation somewhat complicated, because the MIs are not in SSA form and we need to preserve the LiveIntervals analysis. As a simple example, if we have: %vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9 %vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16, %RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16 ... %vreg9<def,tied1> = XSMADDADP %vreg9<tied0>, %vreg17, %vreg19, %RM<imp-use>; VSLRC:%vreg9,%vreg17,%vreg19 ... We can eliminate the copy by changing from the A-type to the M-type instruction. This means: %vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16, %RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16 is replaced by: %vreg16<def,tied1> = XSMADDMDP %vreg16<tied0>, %vreg18, %vreg9, %RM<imp-use>; VSLRC:%vreg16,%vreg18,%vreg9 and we remove: %vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9 llvm-svn: 204768
2014-03-26 07:29:21 +08:00
static cl::opt<bool>
VSXFMAMutateEarly("schedule-ppc-vsx-fma-mutation-early",
cl::Hidden, cl::desc("Schedule VSX FMA instruction mutation early"));
static cl::opt<bool>
EnableGEPOpt("ppc-gep-opt", cl::Hidden,
cl::desc("Enable optimizations on complex GEPs"),
cl::init(true));
extern "C" void LLVMInitializePowerPCTarget() {
// Register the targets
2012-02-03 13:12:30 +08:00
RegisterTargetMachine<PPC32TargetMachine> A(ThePPC32Target);
RegisterTargetMachine<PPC64TargetMachine> B(ThePPC64Target);
RegisterTargetMachine<PPC64TargetMachine> C(ThePPC64LETarget);
}
static std::string computeFSAdditions(StringRef FS, CodeGenOpt::Level OL, StringRef TT) {
std::string FullFS = FS;
Triple TargetTriple(TT);
// Make sure 64-bit features are available when CPUname is generic
if (TargetTriple.getArch() == Triple::ppc64 ||
TargetTriple.getArch() == Triple::ppc64le) {
if (!FullFS.empty())
FullFS = "+64bit," + FullFS;
else
FullFS = "+64bit";
}
if (OL >= CodeGenOpt::Default) {
if (!FullFS.empty())
FullFS = "+crbits," + FullFS;
else
FullFS = "+crbits";
}
return FullFS;
}
static std::unique_ptr<TargetLoweringObjectFile> createTLOF(const Triple &TT) {
// If it isn't a Mach-O file then it's going to be a linux ELF
// object file.
if (TT.isOSDarwin())
return make_unique<TargetLoweringObjectFileMachO>();
return make_unique<PPC64LinuxTargetObjectFile>();
}
// The FeatureString here is a little subtle. We are modifying the feature string
// with what are (currently) non-function specific overrides as it goes into the
// LLVMTargetMachine constructor and then using the stored value in the
// Subtarget constructor below it.
PPCTargetMachine::PPCTargetMachine(const Target &T, StringRef TT, StringRef CPU,
StringRef FS, const TargetOptions &Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: LLVMTargetMachine(T, TT, CPU, computeFSAdditions(FS, OL, TT), Options, RM,
CM, OL),
TLOF(createTLOF(Triple(getTargetTriple()))),
Subtarget(TT, CPU, TargetFS, *this) {
initAsmInfo();
}
PPCTargetMachine::~PPCTargetMachine() {}
void PPC32TargetMachine::anchor() { }
2012-02-03 13:12:30 +08:00
PPC32TargetMachine::PPC32TargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
const TargetOptions &Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: PPCTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL) {
}
void PPC64TargetMachine::anchor() { }
2012-02-03 13:12:30 +08:00
PPC64TargetMachine::PPC64TargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
const TargetOptions &Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: PPCTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL) {
}
const PPCSubtarget *
PPCTargetMachine::getSubtargetImpl(const Function &F) const {
AttributeSet FnAttrs = F.getAttributes();
Attribute CPUAttr =
FnAttrs.getAttribute(AttributeSet::FunctionIndex, "target-cpu");
Attribute FSAttr =
FnAttrs.getAttribute(AttributeSet::FunctionIndex, "target-features");
std::string CPU = !CPUAttr.hasAttribute(Attribute::None)
? CPUAttr.getValueAsString().str()
: TargetCPU;
std::string FS = !FSAttr.hasAttribute(Attribute::None)
? FSAttr.getValueAsString().str()
: TargetFS;
auto &I = SubtargetMap[CPU + FS];
if (!I) {
// This needs to be done before we create a new subtarget since any
// creation will depend on the TM and the code generation flags on the
// function that reside in TargetOptions.
resetTargetOptions(F);
I = llvm::make_unique<PPCSubtarget>(TargetTriple, CPU, FS, *this);
}
return I.get();
}
//===----------------------------------------------------------------------===//
// Pass Pipeline Configuration
//===----------------------------------------------------------------------===//
namespace {
/// PPC Code Generator Pass Configuration Options.
class PPCPassConfig : public TargetPassConfig {
public:
PPCPassConfig(PPCTargetMachine *TM, PassManagerBase &PM)
: TargetPassConfig(TM, PM) {}
PPCTargetMachine &getPPCTargetMachine() const {
return getTM<PPCTargetMachine>();
}
const PPCSubtarget &getPPCSubtarget() const {
return *getPPCTargetMachine().getSubtargetImpl();
}
void addIRPasses() override;
bool addPreISel() override;
bool addILPOpts() override;
bool addInstSelector() override;
void addPreRegAlloc() override;
void addPreSched2() override;
void addPreEmitPass() override;
};
} // namespace
TargetPassConfig *PPCTargetMachine::createPassConfig(PassManagerBase &PM) {
return new PPCPassConfig(this, PM);
}
void PPCPassConfig::addIRPasses() {
addPass(createAtomicExpandPass(&getPPCTargetMachine()));
if (TM->getOptLevel() == CodeGenOpt::Aggressive && EnableGEPOpt) {
// Call SeparateConstOffsetFromGEP pass to extract constants within indices
// and lower a GEP with multiple indices to either arithmetic operations or
// multiple GEPs with single index.
addPass(createSeparateConstOffsetFromGEPPass(TM, true));
// Call EarlyCSE pass to find and remove subexpressions in the lowered
// result.
addPass(createEarlyCSEPass());
// Do loop invariant code motion in case part of the lowered result is
// invariant.
addPass(createLICMPass());
}
TargetPassConfig::addIRPasses();
}
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
bool PPCPassConfig::addPreISel() {
if (!DisableCTRLoops && getOptLevel() != CodeGenOpt::None)
Implement PPC counter loops as a late IR-level pass The old PPCCTRLoops pass, like the Hexagon pass version from which it was derived, could only handle some simple loops in canonical form. We cannot directly adapt the new Hexagon hardware loops pass, however, because the Hexagon pass contains a fundamental assumption that non-constant-trip-count loops will contain a guard, and this is not always true (the result being that incorrect negative counts can be generated). With this commit, we replace the pass with a late IR-level pass which makes use of SE to calculate the backedge-taken counts and safely generate the loop-count expressions (including any necessary max() parts). This IR level pass inserts custom intrinsics that are lowered into the desired decrement-and-branch instructions. The most fragile part of this new implementation is that interfering uses of the counter register must be detected on the IR level (and, on PPC, this also includes any indirect branches in addition to function calls). Also, to make all of this work, we need a variant of the mtctr instruction that is marked as having side effects. Without this, machine-code level CSE, DCE, etc. illegally transform the resulting code. Hopefully, this can be improved in the future. This new pass is smaller than the original (and much smaller than the new Hexagon hardware loops pass), and can handle many additional cases correctly. In addition, the preheader-creation code has been copied from LoopSimplify, and after we decide on where it belongs, this code will be refactored so that it can be explicitly shared (making this implementation even smaller). The new test-case files ctrloop-{le,lt,ne}.ll have been adapted from tests for the new Hexagon pass. There are a few classes of loops that this pass does not transform (noted by FIXMEs in the files), but these deficiencies can be addressed within the SE infrastructure (thus helping many other passes as well). llvm-svn: 181927
2013-05-16 05:37:41 +08:00
addPass(createPPCCTRLoops(getPPCTargetMachine()));
return false;
}
bool PPCPassConfig::addILPOpts() {
addPass(&EarlyIfConverterID);
return true;
}
bool PPCPassConfig::addInstSelector() {
// Install an instruction selector.
addPass(createPPCISelDag(getPPCTargetMachine()));
#ifndef NDEBUG
if (!DisableCTRLoops && getOptLevel() != CodeGenOpt::None)
addPass(createPPCCTRLoopsVerify());
#endif
addPass(createPPCVSXCopyPass());
return false;
}
void PPCPassConfig::addPreRegAlloc() {
initializePPCVSXFMAMutatePass(*PassRegistry::getPassRegistry());
insertPass(VSXFMAMutateEarly ? &RegisterCoalescerID : &MachineSchedulerID,
&PPCVSXFMAMutateID);
[PowerPC] Select between VSX A-type and M-type FMA instructions just before RA The VSX instruction set has two types of FMA instructions: A-type (where the addend is taken from the output register) and M-type (where one of the product operands is taken from the output register). This adds a small pass that runs just after MI scheduling (and, thus, just before register allocation) that mutates A-type instructions (that are created during isel) into M-type instructions when: 1. This will eliminate an otherwise-necessary copy of the addend 2. One of the product operands is killed by the instruction The "right" moment to make this decision is in between scheduling and register allocation, because only there do we know whether or not one of the product operands is killed by any particular instruction. Unfortunately, this also makes the implementation somewhat complicated, because the MIs are not in SSA form and we need to preserve the LiveIntervals analysis. As a simple example, if we have: %vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9 %vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16, %RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16 ... %vreg9<def,tied1> = XSMADDADP %vreg9<tied0>, %vreg17, %vreg19, %RM<imp-use>; VSLRC:%vreg9,%vreg17,%vreg19 ... We can eliminate the copy by changing from the A-type to the M-type instruction. This means: %vreg5<def,tied1> = XSMADDADP %vreg5<tied0>, %vreg17, %vreg16, %RM<imp-use>; VSLRC:%vreg5,%vreg17,%vreg16 is replaced by: %vreg16<def,tied1> = XSMADDMDP %vreg16<tied0>, %vreg18, %vreg9, %RM<imp-use>; VSLRC:%vreg16,%vreg18,%vreg9 and we remove: %vreg5<def> = COPY %vreg9; VSLRC:%vreg5,%vreg9 llvm-svn: 204768
2014-03-26 07:29:21 +08:00
}
void PPCPassConfig::addPreSched2() {
addPass(createPPCVSXCopyCleanupPass(), false);
if (getOptLevel() != CodeGenOpt::None)
addPass(&IfConverterID);
}
void PPCPassConfig::addPreEmitPass() {
if (getOptLevel() != CodeGenOpt::None)
addPass(createPPCEarlyReturnPass(), false);
// Must run branch selection immediately preceding the asm printer.
addPass(createPPCBranchSelectionPass(), false);
}
void PPCTargetMachine::addAnalysisPasses(PassManagerBase &PM) {
// Add first the target-independent BasicTTI pass, then our PPC pass. This
// allows the PPC pass to delegate to the target independent layer when
// appropriate.
PM.add(createBasicTargetTransformInfoPass(this));
PM.add(createPPCTargetTransformInfoPass(this));
}