1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
|
//===--------------------- Scheduler.cpp ------------------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// A scheduler for processor resource units and processor resource groups.
//
//===----------------------------------------------------------------------===//
#include "llvm/MCA/HardwareUnits/Scheduler.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
namespace llvm {
namespace mca {
#define DEBUG_TYPE "llvm-mca"
void Scheduler::initializeStrategy(std::unique_ptr<SchedulerStrategy> S) {
// Ensure we have a valid (non-null) strategy object.
Strategy = S ? std::move(S) : std::make_unique<DefaultSchedulerStrategy>();
}
// Anchor the vtable of SchedulerStrategy and DefaultSchedulerStrategy.
SchedulerStrategy::~SchedulerStrategy() = default;
DefaultSchedulerStrategy::~DefaultSchedulerStrategy() = default;
#ifndef NDEBUG
void Scheduler::dump() const {
dbgs() << "[SCHEDULER]: WaitSet size is: " << WaitSet.size() << '\n';
dbgs() << "[SCHEDULER]: ReadySet size is: " << ReadySet.size() << '\n';
dbgs() << "[SCHEDULER]: IssuedSet size is: " << IssuedSet.size() << '\n';
Resources->dump();
}
#endif
Scheduler::Status Scheduler::isAvailable(const InstRef &IR) {
ResourceStateEvent RSE =
Resources->canBeDispatched(IR.getInstruction()->getUsedBuffers());
HadTokenStall = RSE != RS_BUFFER_AVAILABLE;
switch (RSE) {
case ResourceStateEvent::RS_BUFFER_UNAVAILABLE:
return Scheduler::SC_BUFFERS_FULL;
case ResourceStateEvent::RS_RESERVED:
return Scheduler::SC_DISPATCH_GROUP_STALL;
case ResourceStateEvent::RS_BUFFER_AVAILABLE:
break;
}
// Give lower priority to LSUnit stall events.
LSUnit::Status LSS = LSU.isAvailable(IR);
HadTokenStall = LSS != LSUnit::LSU_AVAILABLE;
switch (LSS) {
case LSUnit::LSU_LQUEUE_FULL:
return Scheduler::SC_LOAD_QUEUE_FULL;
case LSUnit::LSU_SQUEUE_FULL:
return Scheduler::SC_STORE_QUEUE_FULL;
case LSUnit::LSU_AVAILABLE:
return Scheduler::SC_AVAILABLE;
}
llvm_unreachable("Don't know how to process this LSU state result!");
}
void Scheduler::issueInstructionImpl(
InstRef &IR,
SmallVectorImpl<std::pair<ResourceRef, ResourceCycles>> &UsedResources) {
Instruction *IS = IR.getInstruction();
const InstrDesc &D = IS->getDesc();
// Issue the instruction and collect all the consumed resources
// into a vector. That vector is then used to notify the listener.
Resources->issueInstruction(D, UsedResources);
// Notify the instruction that it started executing.
// This updates the internal state of each write.
IS->execute(IR.getSourceIndex());
IS->computeCriticalRegDep();
if (IS->isMemOp()) {
LSU.onInstructionIssued(IR);
const MemoryGroup &Group = LSU.getGroup(IS->getLSUTokenID());
IS->setCriticalMemDep(Group.getCriticalPredecessor());
}
if (IS->isExecuting())
IssuedSet.emplace_back(IR);
else if (IS->isExecuted())
LSU.onInstructionExecuted(IR);
}
// Release the buffered resources and issue the instruction.
void Scheduler::issueInstruction(
InstRef &IR,
SmallVectorImpl<std::pair<ResourceRef, ResourceCycles>> &UsedResources,
SmallVectorImpl<InstRef> &PendingInstructions,
SmallVectorImpl<InstRef> &ReadyInstructions) {
const Instruction &Inst = *IR.getInstruction();
bool HasDependentUsers = Inst.hasDependentUsers();
HasDependentUsers |= Inst.isMemOp() && LSU.hasDependentUsers(IR);
Resources->releaseBuffers(Inst.getUsedBuffers());
issueInstructionImpl(IR, UsedResources);
// Instructions that have been issued during this cycle might have unblocked
// other dependent instructions. Dependent instructions may be issued during
// this same cycle if operands have ReadAdvance entries. Promote those
// instructions to the ReadySet and notify the caller that those are ready.
if (HasDependentUsers)
if (promoteToPendingSet(PendingInstructions))
promoteToReadySet(ReadyInstructions);
}
bool Scheduler::promoteToReadySet(SmallVectorImpl<InstRef> &Ready) {
// Scan the set of waiting instructions and promote them to the
// ready set if operands are all ready.
unsigned PromotedElements = 0;
for (auto I = PendingSet.begin(), E = PendingSet.end(); I != E;) {
InstRef &IR = *I;
if (!IR)
break;
// Check if there are unsolved register dependencies.
Instruction &IS = *IR.getInstruction();
if (!IS.isReady() && !IS.updatePending()) {
++I;
continue;
}
// Check if there are unsolved memory dependencies.
if (IS.isMemOp() && !LSU.isReady(IR)) {
++I;
continue;
}
LLVM_DEBUG(dbgs() << "[SCHEDULER]: Instruction #" << IR
<< " promoted to the READY set.\n");
Ready.emplace_back(IR);
ReadySet.emplace_back(IR);
IR.invalidate();
++PromotedElements;
std::iter_swap(I, E - PromotedElements);
}
PendingSet.resize(PendingSet.size() - PromotedElements);
return PromotedElements;
}
bool Scheduler::promoteToPendingSet(SmallVectorImpl<InstRef> &Pending) {
// Scan the set of waiting instructions and promote them to the
// pending set if operands are all ready.
unsigned RemovedElements = 0;
for (auto I = WaitSet.begin(), E = WaitSet.end(); I != E;) {
InstRef &IR = *I;
if (!IR)
break;
// Check if this instruction is now ready. In case, force
// a transition in state using method 'updateDispatched()'.
Instruction &IS = *IR.getInstruction();
if (IS.isDispatched() && !IS.updateDispatched()) {
++I;
continue;
}
if (IS.isMemOp() && LSU.isWaiting(IR)) {
++I;
continue;
}
LLVM_DEBUG(dbgs() << "[SCHEDULER]: Instruction #" << IR
<< " promoted to the PENDING set.\n");
Pending.emplace_back(IR);
PendingSet.emplace_back(IR);
IR.invalidate();
++RemovedElements;
std::iter_swap(I, E - RemovedElements);
}
WaitSet.resize(WaitSet.size() - RemovedElements);
return RemovedElements;
}
InstRef Scheduler::select() {
unsigned QueueIndex = ReadySet.size();
for (unsigned I = 0, E = ReadySet.size(); I != E; ++I) {
InstRef &IR = ReadySet[I];
if (QueueIndex == ReadySet.size() ||
Strategy->compare(IR, ReadySet[QueueIndex])) {
Instruction &IS = *IR.getInstruction();
uint64_t BusyResourceMask = Resources->checkAvailability(IS.getDesc());
if (BusyResourceMask)
IS.setCriticalResourceMask(BusyResourceMask);
BusyResourceUnits |= BusyResourceMask;
if (!BusyResourceMask)
QueueIndex = I;
}
}
if (QueueIndex == ReadySet.size())
return InstRef();
// We found an instruction to issue.
InstRef IR = ReadySet[QueueIndex];
std::swap(ReadySet[QueueIndex], ReadySet[ReadySet.size() - 1]);
ReadySet.pop_back();
return IR;
}
void Scheduler::updateIssuedSet(SmallVectorImpl<InstRef> &Executed) {
unsigned RemovedElements = 0;
for (auto I = IssuedSet.begin(), E = IssuedSet.end(); I != E;) {
InstRef &IR = *I;
if (!IR)
break;
Instruction &IS = *IR.getInstruction();
if (!IS.isExecuted()) {
LLVM_DEBUG(dbgs() << "[SCHEDULER]: Instruction #" << IR
<< " is still executing.\n");
++I;
continue;
}
// Instruction IR has completed execution.
LSU.onInstructionExecuted(IR);
Executed.emplace_back(IR);
++RemovedElements;
IR.invalidate();
std::iter_swap(I, E - RemovedElements);
}
IssuedSet.resize(IssuedSet.size() - RemovedElements);
}
uint64_t Scheduler::analyzeResourcePressure(SmallVectorImpl<InstRef> &Insts) {
llvm::append_range(Insts, ReadySet);
return BusyResourceUnits;
}
void Scheduler::analyzeDataDependencies(SmallVectorImpl<InstRef> &RegDeps,
SmallVectorImpl<InstRef> &MemDeps) {
const auto EndIt = PendingSet.end() - NumDispatchedToThePendingSet;
for (const InstRef &IR : make_range(PendingSet.begin(), EndIt)) {
const Instruction &IS = *IR.getInstruction();
if (Resources->checkAvailability(IS.getDesc()))
continue;
if (IS.isMemOp() && LSU.isPending(IR))
MemDeps.emplace_back(IR);
if (IS.isPending())
RegDeps.emplace_back(IR);
}
}
void Scheduler::cycleEvent(SmallVectorImpl<ResourceRef> &Freed,
SmallVectorImpl<InstRef> &Executed,
SmallVectorImpl<InstRef> &Pending,
SmallVectorImpl<InstRef> &Ready) {
LSU.cycleEvent();
// Release consumed resources.
Resources->cycleEvent(Freed);
for (InstRef &IR : IssuedSet)
IR.getInstruction()->cycleEvent();
updateIssuedSet(Executed);
for (InstRef &IR : PendingSet)
IR.getInstruction()->cycleEvent();
for (InstRef &IR : WaitSet)
IR.getInstruction()->cycleEvent();
promoteToPendingSet(Pending);
promoteToReadySet(Ready);
NumDispatchedToThePendingSet = 0;
BusyResourceUnits = 0;
}
bool Scheduler::mustIssueImmediately(const InstRef &IR) const {
const InstrDesc &Desc = IR.getInstruction()->getDesc();
if (Desc.isZeroLatency())
return true;
// Instructions that use an in-order dispatch/issue processor resource must be
// issued immediately to the pipeline(s). Any other in-order buffered
// resources (i.e. BufferSize=1) is consumed.
return Desc.MustIssueImmediately;
}
bool Scheduler::dispatch(InstRef &IR) {
Instruction &IS = *IR.getInstruction();
Resources->reserveBuffers(IS.getUsedBuffers());
// If necessary, reserve queue entries in the load-store unit (LSU).
if (IS.isMemOp())
IS.setLSUTokenID(LSU.dispatch(IR));
if (IS.isDispatched() || (IS.isMemOp() && LSU.isWaiting(IR))) {
LLVM_DEBUG(dbgs() << "[SCHEDULER] Adding #" << IR << " to the WaitSet\n");
WaitSet.push_back(IR);
return false;
}
if (IS.isPending() || (IS.isMemOp() && LSU.isPending(IR))) {
LLVM_DEBUG(dbgs() << "[SCHEDULER] Adding #" << IR
<< " to the PendingSet\n");
PendingSet.push_back(IR);
++NumDispatchedToThePendingSet;
return false;
}
assert(IS.isReady() && (!IS.isMemOp() || LSU.isReady(IR)) &&
"Unexpected internal state found!");
// Don't add a zero-latency instruction to the Ready queue.
// A zero-latency instruction doesn't consume any scheduler resources. That is
// because it doesn't need to be executed, and it is often removed at register
// renaming stage. For example, register-register moves are often optimized at
// register renaming stage by simply updating register aliases. On some
// targets, zero-idiom instructions (for example: a xor that clears the value
// of a register) are treated specially, and are often eliminated at register
// renaming stage.
if (!mustIssueImmediately(IR)) {
LLVM_DEBUG(dbgs() << "[SCHEDULER] Adding #" << IR << " to the ReadySet\n");
ReadySet.push_back(IR);
}
return true;
}
} // namespace mca
} // namespace llvm
|