llvm.org GIT mirror llvm / release_40 include / llvm / Target / TargetSchedule.td
release_40

Tree @release_40 (Download .tar.gz)

TargetSchedule.td @release_40raw · history · blame

  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
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
//===- TargetSchedule.td - Target Independent Scheduling ---*- tablegen -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the target-independent scheduling interfaces which should
// be implemented by each target which is using TableGen based scheduling.
//
// The SchedMachineModel is defined by subtargets for three categories of data:
// 1. Basic properties for coarse grained instruction cost model.
// 2. Scheduler Read/Write resources for simple per-opcode cost model.
// 3. Instruction itineraries for detailed reservation tables.
//
// (1) Basic properties are defined by the SchedMachineModel
// class. Target hooks allow subtargets to associate opcodes with
// those properties.
//
// (2) A per-operand machine model can be implemented in any
// combination of the following ways:
//
// A. Associate per-operand SchedReadWrite types with Instructions by
// modifying the Instruction definition to inherit from Sched. For
// each subtarget, define WriteRes and ReadAdvance to associate
// processor resources and latency with each SchedReadWrite type.
//
// B. In each instruction definition, name an ItineraryClass. For each
// subtarget, define ItinRW entries to map ItineraryClass to
// per-operand SchedReadWrite types. Unlike method A, these types may
// be subtarget specific and can be directly associated with resources
// by defining SchedWriteRes and SchedReadAdvance.
//
// C. In the subtarget, map SchedReadWrite types to specific
// opcodes. This overrides any SchedReadWrite types or
// ItineraryClasses defined by the Instruction. As in method B, the
// subtarget can directly associate resources with SchedReadWrite
// types by defining SchedWriteRes and SchedReadAdvance.
//
// D. In either the target or subtarget, define SchedWriteVariant or
// SchedReadVariant to map one SchedReadWrite type onto another
// sequence of SchedReadWrite types. This allows dynamic selection of
// an instruction's machine model via custom C++ code. It also allows
// a machine-independent SchedReadWrite type to map to a sequence of
// machine-dependent types.
//
// (3) A per-pipeline-stage machine model can be implemented by providing
// Itineraries in addition to mapping instructions to ItineraryClasses.
//===----------------------------------------------------------------------===//

// Include legacy support for instruction itineraries.
include "llvm/Target/TargetItinerary.td"

class Instruction; // Forward def

class Predicate; // Forward def

// DAG operator that interprets the DAG args as Instruction defs.
def instrs;

// DAG operator that interprets each DAG arg as a regex pattern for
// matching Instruction opcode names.
// The regex must match the beginning of the opcode (as in Python re.match).
// To avoid matching prefixes, append '$' to the pattern.
def instregex;

// Define the SchedMachineModel and provide basic properties for
// coarse grained instruction cost model. Default values for the
// properties are defined in MCSchedModel. A value of "-1" in the
// target description's SchedMachineModel indicates that the property
// is not overriden by the target.
//
// Target hooks allow subtargets to associate LoadLatency and
// HighLatency with groups of opcodes.
//
// See MCSchedule.h for detailed comments.
class SchedMachineModel {
  int IssueWidth = -1; // Max micro-ops that may be scheduled per cycle.
  int MicroOpBufferSize = -1; // Max micro-ops that can be buffered.
  int LoopMicroOpBufferSize = -1; // Max micro-ops that can be buffered for
                                  // optimized loop dispatch/execution.
  int LoadLatency = -1; // Cycles for loads to access the cache.
  int HighLatency = -1; // Approximation of cycles for "high latency" ops.
  int MispredictPenalty = -1; // Extra cycles for a mispredicted branch.

  // Per-cycle resources tables.
  ProcessorItineraries Itineraries = NoItineraries;

  bit PostRAScheduler = 0; // Enable Post RegAlloc Scheduler pass.

  // Subtargets that define a model for only a subset of instructions
  // that have a scheduling class (itinerary class or SchedRW list)
  // and may actually be generated for that subtarget must clear this
  // bit. Otherwise, the scheduler considers an unmodelled opcode to
  // be an error. This should only be set during initial bringup,
  // or there will be no way to catch simple errors in the model
  // resulting from changes to the instruction definitions.
  bit CompleteModel = 1;

  // A processor may only implement part of published ISA, due to either new ISA
  // extensions, (e.g. Pentium 4 doesn't have AVX) or implementation
  // (ARM/MIPS/PowerPC/SPARC soft float cores).
  //
  // For a processor which doesn't support some feature(s), the schedule model
  // can use:
  //
  // let<Predicate> UnsupportedFeatures = [HaveA,..,HaveY];
  //
  // to skip the checks for scheduling information when building LLVM for
  // instructions which have any of the listed predicates in their Predicates
  // field.
  list<Predicate> UnsupportedFeatures = [];

  bit NoModel = 0; // Special tag to indicate missing machine model.
}

def NoSchedModel : SchedMachineModel {
  let NoModel = 1;
  let CompleteModel = 0;
}

// Define a kind of processor resource that may be common across
// similar subtargets.
class ProcResourceKind;

// Define a number of interchangeable processor resources. NumUnits
// determines the throughput of instructions that require the resource.
//
// An optional Super resource may be given to model these resources as
// a subset of the more general super resources. Using one of these
// resources implies using one of the super resoruces.
//
// ProcResourceUnits normally model a few buffered resources within an
// out-of-order engine. Buffered resources may be held for multiple
// clock cycles, but the scheduler does not pin them to a particular
// clock cycle relative to instruction dispatch. Setting BufferSize=0
// changes this to an in-order issue/dispatch resource. In this case,
// the scheduler counts down from the cycle that the instruction
// issues in-order, forcing a stall whenever a subsequent instruction
// requires the same resource until the number of ResourceCyles
// specified in WriteRes expire. Setting BufferSize=1 changes this to
// an in-order latency resource. In this case, the scheduler models
// producer/consumer stalls between instructions that use the
// resource.
//
// Examples (all assume an out-of-order engine):
//
// Use BufferSize = -1 for "issue ports" fed by a unified reservation
// station. Here the size of the reservation station is modeled by
// MicroOpBufferSize, which should be the minimum size of either the
// register rename pool, unified reservation station, or reorder
// buffer.
//
// Use BufferSize = 0 for resources that force "dispatch/issue
// groups". (Different processors define dispath/issue
// differently. Here we refer to stage between decoding into micro-ops
// and moving them into a reservation station.) Normally NumMicroOps
// is sufficient to limit dispatch/issue groups. However, some
// processors can form groups of with only certain combinitions of
// instruction types. e.g. POWER7.
//
// Use BufferSize = 1 for in-order execution units. This is used for
// an in-order pipeline within an out-of-order core where scheduling
// dependent operations back-to-back is guaranteed to cause a
// bubble. e.g. Cortex-a9 floating-point.
//
// Use BufferSize > 1 for out-of-order executions units with a
// separate reservation station. This simply models the size of the
// reservation station.
//
// To model both dispatch/issue groups and in-order execution units,
// create two types of units, one with BufferSize=0 and one with
// BufferSize=1.
//
// SchedModel ties these units to a processor for any stand-alone defs
// of this class. Instances of subclass ProcResource will be automatically
// attached to a processor, so SchedModel is not needed.
class ProcResourceUnits<ProcResourceKind kind, int num> {
  ProcResourceKind Kind = kind;
  int NumUnits = num;
  ProcResourceKind Super = ?;
  int BufferSize = -1;
  SchedMachineModel SchedModel = ?;
}

// EponymousProcResourceKind helps implement ProcResourceUnits by
// allowing a ProcResourceUnits definition to reference itself. It
// should not be referenced anywhere else.
def EponymousProcResourceKind : ProcResourceKind;

// Subtargets typically define processor resource kind and number of
// units in one place.
class ProcResource<int num> : ProcResourceKind,
  ProcResourceUnits<EponymousProcResourceKind, num>;

class ProcResGroup<list<ProcResource> resources> : ProcResourceKind {
  list<ProcResource> Resources = resources;
  SchedMachineModel SchedModel = ?;
  int BufferSize = -1;
}

// A target architecture may define SchedReadWrite types and associate
// them with instruction operands.
class SchedReadWrite;

// List the per-operand types that map to the machine model of an
// instruction. One SchedWrite type must be listed for each explicit
// def operand in order. Additional SchedWrite types may optionally be
// listed for implicit def operands.  SchedRead types may optionally
// be listed for use operands in order. The order of defs relative to
// uses is insignificant. This way, the same SchedReadWrite list may
// be used for multiple forms of an operation. For example, a
// two-address instruction could have two tied operands or single
// operand that both reads and writes a reg. In both cases we have a
// single SchedWrite and single SchedRead in any order.
class Sched<list<SchedReadWrite> schedrw> {
  list<SchedReadWrite> SchedRW = schedrw;
}

// Define a scheduler resource associated with a def operand.
class SchedWrite : SchedReadWrite;
def NoWrite : SchedWrite;

// Define a scheduler resource associated with a use operand.
class SchedRead  : SchedReadWrite;

// Define a SchedWrite that is modeled as a sequence of other
// SchedWrites with additive latency. This allows a single operand to
// be mapped the resources composed from a set of previously defined
// SchedWrites.
//
// If the final write in this sequence is a SchedWriteVariant marked
// Variadic, then the list of prior writes are distributed across all
// operands after resolving the predicate for the final write.
//
// SchedModel silences warnings but is ignored.
class WriteSequence<list<SchedWrite> writes, int rep = 1> : SchedWrite {
  list<SchedWrite> Writes = writes;
  int Repeat = rep;
  SchedMachineModel SchedModel = ?;
}

// Define values common to WriteRes and SchedWriteRes.
//
// SchedModel ties these resources to a processor.
class ProcWriteResources<list<ProcResourceKind> resources> {
  list<ProcResourceKind> ProcResources = resources;
  list<int> ResourceCycles = [];
  int Latency = 1;
  int NumMicroOps = 1;
  bit BeginGroup = 0;
  bit EndGroup = 0;
  // Allow a processor to mark some scheduling classes as unsupported
  // for stronger verification.
  bit Unsupported = 0;
  SchedMachineModel SchedModel = ?;
}

// Define the resources and latency of a SchedWrite. This will be used
// directly by targets that have no itinerary classes. In this case,
// SchedWrite is defined by the target, while WriteResources is
// defined by the subtarget, and maps the SchedWrite to processor
// resources.
//
// If a target already has itinerary classes, SchedWriteResources can
// be used instead to define subtarget specific SchedWrites and map
// them to processor resources in one place. Then ItinRW can map
// itinerary classes to the subtarget's SchedWrites.
//
// ProcResources indicates the set of resources consumed by the write.
// Optionally, ResourceCycles indicates the number of cycles the
// resource is consumed. Each ResourceCycles item is paired with the
// ProcResource item at the same position in its list. Since
// ResourceCycles are rarely specialized, the list may be
// incomplete. By default, resources are consumed for a single cycle,
// regardless of latency, which models a fully pipelined processing
// unit. A value of 0 for ResourceCycles means that the resource must
// be available but is not consumed, which is only relevant for
// unbuffered resources.
//
// By default, each SchedWrite takes one micro-op, which is counted
// against the processor's IssueWidth limit. If an instruction can
// write multiple registers with a single micro-op, the subtarget
// should define one of the writes to be zero micro-ops. If a
// subtarget requires multiple micro-ops to write a single result, it
// should either override the write's NumMicroOps to be greater than 1
// or require additional writes. Extra writes can be required either
// by defining a WriteSequence, or simply listing extra writes in the
// instruction's list of writers beyond the number of "def"
// operands. The scheduler assumes that all micro-ops must be
// dispatched in the same cycle. These micro-ops may be required to
// begin or end the current dispatch group.
class WriteRes<SchedWrite write, list<ProcResourceKind> resources>
  : ProcWriteResources<resources> {
  SchedWrite WriteType = write;
}

// Directly name a set of WriteResources defining a new SchedWrite
// type at the same time. This class is unaware of its SchedModel so
// must be referenced by InstRW or ItinRW.
class SchedWriteRes<list<ProcResourceKind> resources> : SchedWrite,
  ProcWriteResources<resources>;

// Define values common to ReadAdvance and SchedReadAdvance.
//
// SchedModel ties these resources to a processor.
class ProcReadAdvance<int cycles, list<SchedWrite> writes = []> {
  int Cycles = cycles;
  list<SchedWrite> ValidWrites = writes;
  // Allow a processor to mark some scheduling classes as unsupported
  // for stronger verification.
  bit Unsupported = 0;
  SchedMachineModel SchedModel = ?;
}

// A processor may define a ReadAdvance associated with a SchedRead
// to reduce latency of a prior write by N cycles. A negative advance
// effectively increases latency, which may be used for cross-domain
// stalls.
//
// A ReadAdvance may be associated with a list of SchedWrites
// to implement pipeline bypass. The Writes list may be empty to
// indicate operands that are always read this number of Cycles later
// than a normal register read, allowing the read's parent instruction
// to issue earlier relative to the writer.
class ReadAdvance<SchedRead read, int cycles, list<SchedWrite> writes = []>
  : ProcReadAdvance<cycles, writes> {
  SchedRead ReadType = read;
}

// Directly associate a new SchedRead type with a delay and optional
// pipeline bypess. For use with InstRW or ItinRW.
class SchedReadAdvance<int cycles, list<SchedWrite> writes = []> : SchedRead,
  ProcReadAdvance<cycles, writes>;

// Define SchedRead defaults. Reads seldom need special treatment.
def ReadDefault : SchedRead;
def NoReadAdvance : SchedReadAdvance<0>;

// Define shared code that will be in the same scope as all
// SchedPredicates. Available variables are:
// (const MachineInstr *MI, const TargetSchedModel *SchedModel)
class PredicateProlog<code c> {
  code Code = c;
}

// Define a predicate to determine which SchedVariant applies to a
// particular MachineInstr. The code snippet is used as an
// if-statement's expression. Available variables are MI, SchedModel,
// and anything defined in a PredicateProlog.
//
// SchedModel silences warnings but is ignored.
class SchedPredicate<code pred> {
  SchedMachineModel SchedModel = ?;
  code Predicate = pred;
}
def NoSchedPred : SchedPredicate<[{true}]>;

// Associate a predicate with a list of SchedReadWrites. By default,
// the selected SchedReadWrites are still associated with a single
// operand and assumed to execute sequentially with additive
// latency. However, if the parent SchedWriteVariant or
// SchedReadVariant is marked "Variadic", then each Selected
// SchedReadWrite is mapped in place to the instruction's variadic
// operands. In this case, latency is not additive. If the current Variant
// is already part of a Sequence, then that entire chain leading up to
// the Variant is distributed over the variadic operands.
class SchedVar<SchedPredicate pred, list<SchedReadWrite> selected> {
  SchedPredicate Predicate = pred;
  list<SchedReadWrite> Selected = selected;
}

// SchedModel silences warnings but is ignored.
class SchedVariant<list<SchedVar> variants> {
  list<SchedVar> Variants = variants;
  bit Variadic = 0;
  SchedMachineModel SchedModel = ?;
}

// A SchedWriteVariant is a single SchedWrite type that maps to a list
// of SchedWrite types under the conditions defined by its predicates.
//
// A Variadic write is expanded to cover multiple "def" operands. The
// SchedVariant's Expansion list is then interpreted as one write
// per-operand instead of the usual sequential writes feeding a single
// operand.
class SchedWriteVariant<list<SchedVar> variants> : SchedWrite,
  SchedVariant<variants> {
}

// A SchedReadVariant is a single SchedRead type that maps to a list
// of SchedRead types under the conditions defined by its predicates.
//
// A Variadic write is expanded to cover multiple "readsReg" operands as
// explained above.
class SchedReadVariant<list<SchedVar> variants> : SchedRead,
  SchedVariant<variants> {
}

// Map a set of opcodes to a list of SchedReadWrite types. This allows
// the subtarget to easily override specific operations.
//
// SchedModel ties this opcode mapping to a processor.
class InstRW<list<SchedReadWrite> rw, dag instrlist> {
  list<SchedReadWrite> OperandReadWrites = rw;
  dag Instrs = instrlist;
  SchedMachineModel SchedModel = ?;
  // Allow a subtarget to mark some instructions as unsupported.
  bit Unsupported = 0;
}

// Map a set of itinerary classes to SchedReadWrite resources. This is
// used to bootstrap a target (e.g. ARM) when itineraries already
// exist and changing InstrInfo is undesirable.
//
// SchedModel ties this ItineraryClass mapping to a processor.
class ItinRW<list<SchedReadWrite> rw, list<InstrItinClass> iic> {
  list<InstrItinClass> MatchedItinClasses = iic;
  list<SchedReadWrite> OperandReadWrites = rw;
  SchedMachineModel SchedModel = ?;
}

// Alias a target-defined SchedReadWrite to a processor specific
// SchedReadWrite. This allows a subtarget to easily map a
// SchedReadWrite type onto a WriteSequence, SchedWriteVariant, or
// SchedReadVariant.
//
// SchedModel will usually be provided by surrounding let statement
// and ties this SchedAlias mapping to a processor.
class SchedAlias<SchedReadWrite match, SchedReadWrite alias> {
  SchedReadWrite MatchRW = match;
  SchedReadWrite AliasRW = alias;
  SchedMachineModel SchedModel = ?;
}