summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/AMDGPU/GCNSchedStrategy.h
blob: dd687a930c79a41bb9078e06d31429d32948a6be (plain)
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
//===-- GCNSchedStrategy.h - GCN Scheduler Strategy -*- 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
//
//===----------------------------------------------------------------------===//
//
/// \file
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_AMDGPU_GCNSCHEDSTRATEGY_H
#define LLVM_LIB_TARGET_AMDGPU_GCNSCHEDSTRATEGY_H

#include "GCNRegPressure.h"
#include "llvm/CodeGen/MachineScheduler.h"

namespace llvm {

class SIMachineFunctionInfo;
class SIRegisterInfo;
class GCNSubtarget;

/// This is a minimal scheduler strategy.  The main difference between this
/// and the GenericScheduler is that GCNSchedStrategy uses different
/// heuristics to determine excess/critical pressure sets.  Its goal is to
/// maximize kernel occupancy (i.e. maximum number of waves per simd).
class GCNMaxOccupancySchedStrategy final : public GenericScheduler {
  friend class GCNScheduleDAGMILive;

  SUnit *pickNodeBidirectional(bool &IsTopNode);

  void pickNodeFromQueue(SchedBoundary &Zone, const CandPolicy &ZonePolicy,
                         const RegPressureTracker &RPTracker,
                         SchedCandidate &Cand);

  void initCandidate(SchedCandidate &Cand, SUnit *SU,
                     bool AtTop, const RegPressureTracker &RPTracker,
                     const SIRegisterInfo *SRI,
                     unsigned SGPRPressure, unsigned VGPRPressure);

  std::vector<unsigned> Pressure;
  std::vector<unsigned> MaxPressure;

  unsigned SGPRExcessLimit;
  unsigned VGPRExcessLimit;
  unsigned SGPRCriticalLimit;
  unsigned VGPRCriticalLimit;

  unsigned TargetOccupancy;

  MachineFunction *MF;

public:
  GCNMaxOccupancySchedStrategy(const MachineSchedContext *C);

  SUnit *pickNode(bool &IsTopNode) override;

  void initialize(ScheduleDAGMI *DAG) override;

  void setTargetOccupancy(unsigned Occ) { TargetOccupancy = Occ; }
};

class GCNScheduleDAGMILive final : public ScheduleDAGMILive {

  const GCNSubtarget &ST;

  SIMachineFunctionInfo &MFI;

  // Occupancy target at the beginning of function scheduling cycle.
  unsigned StartingOccupancy;

  // Minimal real occupancy recorder for the function.
  unsigned MinOccupancy;

  // Scheduling stage number.
  unsigned Stage;

  // Current region index.
  size_t RegionIdx;

  // Vector of regions recorder for later rescheduling
  SmallVector<std::pair<MachineBasicBlock::iterator,
                        MachineBasicBlock::iterator>, 32> Regions;

  // Region live-in cache.
  SmallVector<GCNRPTracker::LiveRegSet, 32> LiveIns;

  // Region pressure cache.
  SmallVector<GCNRegPressure, 32> Pressure;

  // Temporary basic block live-in cache.
  DenseMap<const MachineBasicBlock*, GCNRPTracker::LiveRegSet> MBBLiveIns;

  DenseMap<MachineInstr *, GCNRPTracker::LiveRegSet> BBLiveInMap;
  DenseMap<MachineInstr *, GCNRPTracker::LiveRegSet> getBBLiveInMap() const;

  // Return current region pressure.
  GCNRegPressure getRealRegPressure() const;

  // Compute and cache live-ins and pressure for all regions in block.
  void computeBlockPressure(const MachineBasicBlock *MBB);


public:
  GCNScheduleDAGMILive(MachineSchedContext *C,
                       std::unique_ptr<MachineSchedStrategy> S);

  void schedule() override;

  void finalizeSchedule() override;
};

} // End namespace llvm

#endif // GCNSCHEDSTRATEGY_H
OpenPOWER on IntegriCloud