llvm-6502/lib/Target/PowerPC/PPCTargetMachine.cpp

169 lines
5.3 KiB
C++
Raw Normal View History

//===-- PPCTargetMachine.cpp - Define TargetMachine for PowerPC -----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// Top-level implementation for the PowerPC target.
//
//===----------------------------------------------------------------------===//
#include "PPCTargetMachine.h"
#include "PPC.h"
#include "llvm/CodeGen/Passes.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"
using namespace llvm;
static cl::
opt<bool> DisableCTRLoops("disable-ppc-ctrloops", cl::Hidden,
cl::desc("Disable CTR loops for PPC"));
extern "C" void LLVMInitializePowerPCTarget() {
// Register the targets
RegisterTargetMachine<PPC32TargetMachine> A(ThePPC32Target);
RegisterTargetMachine<PPC64TargetMachine> B(ThePPC64Target);
}
PPCTargetMachine::PPCTargetMachine(const Target &T, StringRef TT,
StringRef CPU, StringRef FS,
const TargetOptions &Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL,
bool is64Bit)
: LLVMTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL),
Subtarget(TT, CPU, FS, is64Bit),
DL(Subtarget.getDataLayoutString()), InstrInfo(*this),
FrameLowering(Subtarget), JITInfo(*this, is64Bit),
TLInfo(*this), TSInfo(*this),
Switch TargetTransformInfo from an immutable analysis pass that requires a TargetMachine to construct (and thus isn't always available), to an analysis group that supports layered implementations much like AliasAnalysis does. This is a pretty massive change, with a few parts that I was unable to easily separate (sorry), so I'll walk through it. The first step of this conversion was to make TargetTransformInfo an analysis group, and to sink the nonce implementations in ScalarTargetTransformInfo and VectorTargetTranformInfo into a NoTargetTransformInfo pass. This allows other passes to add a hard requirement on TTI, and assume they will always get at least on implementation. The TargetTransformInfo analysis group leverages the delegation chaining trick that AliasAnalysis uses, where the base class for the analysis group delegates to the previous analysis *pass*, allowing all but tho NoFoo analysis passes to only implement the parts of the interfaces they support. It also introduces a new trick where each pass in the group retains a pointer to the top-most pass that has been initialized. This allows passes to implement one API in terms of another API and benefit when some other pass above them in the stack has more precise results for the second API. The second step of this conversion is to create a pass that implements the TargetTransformInfo analysis using the target-independent abstractions in the code generator. This replaces the ScalarTargetTransformImpl and VectorTargetTransformImpl classes in lib/Target with a single pass in lib/CodeGen called BasicTargetTransformInfo. This class actually provides most of the TTI functionality, basing it upon the TargetLowering abstraction and other information in the target independent code generator. The third step of the conversion adds support to all TargetMachines to register custom analysis passes. This allows building those passes with access to TargetLowering or other target-specific classes, and it also allows each target to customize the set of analysis passes desired in the pass manager. The baseline LLVMTargetMachine implements this interface to add the BasicTTI pass to the pass manager, and all of the tools that want to support target-aware TTI passes call this routine on whatever target machine they end up with to add the appropriate passes. The fourth step of the conversion created target-specific TTI analysis passes for the X86 and ARM backends. These passes contain the custom logic that was previously in their extensions of the ScalarTargetTransformInfo and VectorTargetTransformInfo interfaces. I separated them into their own file, as now all of the interface bits are private and they just expose a function to create the pass itself. Then I extended these target machines to set up a custom set of analysis passes, first adding BasicTTI as a fallback, and then adding their customized TTI implementations. The fourth step required logic that was shared between the target independent layer and the specific targets to move to a different interface, as they no longer derive from each other. As a consequence, a helper functions were added to TargetLowering representing the common logic needed both in the target implementation and the codegen implementation of the TTI pass. While technically this is the only change that could have been committed separately, it would have been a nightmare to extract. The final step of the conversion was just to delete all the old boilerplate. This got rid of the ScalarTargetTransformInfo and VectorTargetTransformInfo classes, all of the support in all of the targets for producing instances of them, and all of the support in the tools for manually constructing a pass based around them. Now that TTI is a relatively normal analysis group, two things become straightforward. First, we can sink it into lib/Analysis which is a more natural layer for it to live. Second, clients of this interface can depend on it *always* being available which will simplify their code and behavior. These (and other) simplifications will follow in subsequent commits, this one is clearly big enough. Finally, I'm very aware that much of the comments and documentation needs to be updated. As soon as I had this working, and plausibly well commented, I wanted to get it committed and in front of the build bots. I'll be doing a few passes over documentation later if it sticks. Commits to update DragonEgg and Clang will be made presently. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171681 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-07 01:37:14 +00:00
InstrItins(Subtarget.getInstrItineraryData()) {
// The binutils for the BG/P are too old for CFI.
if (Subtarget.isBGP())
setMCUseCFI(false);
initAsmInfo();
}
void PPC32TargetMachine::anchor() { }
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, false) {
}
void PPC64TargetMachine::anchor() { }
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, true) {
}
//===----------------------------------------------------------------------===//
// 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();
}
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). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181927 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-15 21:37:41 +00:00
virtual bool addPreISel();
virtual bool addILPOpts();
virtual bool addInstSelector();
virtual bool addPreSched2();
virtual bool addPreEmitPass();
};
} // namespace
TargetPassConfig *PPCTargetMachine::createPassConfig(PassManagerBase &PM) {
return new PPCPassConfig(this, PM);
}
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). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181927 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-15 21:37:41 +00:00
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). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181927 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-15 21:37:41 +00:00
addPass(createPPCCTRLoops(getPPCTargetMachine()));
return false;
}
bool PPCPassConfig::addILPOpts() {
if (getPPCSubtarget().hasISEL()) {
addPass(&EarlyIfConverterID);
return true;
}
return false;
}
bool PPCPassConfig::addInstSelector() {
// Install an instruction selector.
addPass(createPPCISelDag(getPPCTargetMachine()));
#ifndef NDEBUG
if (!DisableCTRLoops && getOptLevel() != CodeGenOpt::None)
addPass(createPPCCTRLoopsVerify());
#endif
return false;
}
bool PPCPassConfig::addPreSched2() {
if (getOptLevel() != CodeGenOpt::None)
addPass(&IfConverterID);
return true;
}
bool PPCPassConfig::addPreEmitPass() {
if (getOptLevel() != CodeGenOpt::None)
addPass(createPPCEarlyReturnPass());
// Must run branch selection immediately preceding the asm printer.
addPass(createPPCBranchSelectionPass());
return false;
}
bool PPCTargetMachine::addCodeEmitter(PassManagerBase &PM,
JITCodeEmitter &JCE) {
// Inform the subtarget that we are in JIT mode. FIXME: does this break macho
// writing?
Subtarget.SetJITMode();
// Machine code emitter pass for PowerPC.
PM.add(createPPCJITCodeEmitterPass(*this, JCE));
return 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(getTargetLowering()));
PM.add(createPPCTargetTransformInfoPass(this));
}