Currently we do nothing RISC-V specific in this scheduler. This is a part of vtype-based scheduling. Reviewers: BeMg, mshockwave, lukel97, preames, topperc Pull Request: https://github.com/llvm/llvm-project/pull/172613
123 lines
5.2 KiB
C++
123 lines
5.2 KiB
C++
//===- RISCVMachineScheduler.cpp - MI Scheduler for RISC-V ----------------===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "RISCVMachineScheduler.h"
|
|
#include "llvm/CodeGen/ScheduleDAG.h"
|
|
|
|
using namespace llvm;
|
|
|
|
#define DEBUG_TYPE "riscv-prera-sched-strategy"
|
|
|
|
bool RISCVPreRAMachineSchedStrategy::tryCandidate(SchedCandidate &Cand,
|
|
SchedCandidate &TryCand,
|
|
SchedBoundary *Zone) const {
|
|
//-------------------------------------------------------------------------//
|
|
// Below is copied from `GenericScheduler::tryCandidate`.
|
|
// FIXME: Is there a way to not replicate this?
|
|
//-------------------------------------------------------------------------//
|
|
// Initialize the candidate if needed.
|
|
if (!Cand.isValid()) {
|
|
TryCand.Reason = FirstValid;
|
|
return true;
|
|
}
|
|
|
|
// Bias PhysReg Defs and copies to their uses and defined respectively.
|
|
if (tryGreater(biasPhysReg(TryCand.SU, TryCand.AtTop),
|
|
biasPhysReg(Cand.SU, Cand.AtTop), TryCand, Cand, PhysReg))
|
|
return TryCand.Reason != NoCand;
|
|
|
|
// Avoid exceeding the target's limit.
|
|
if (DAG->isTrackingPressure() &&
|
|
tryPressure(TryCand.RPDelta.Excess, Cand.RPDelta.Excess, TryCand, Cand,
|
|
RegExcess, TRI, DAG->MF))
|
|
return TryCand.Reason != NoCand;
|
|
|
|
// Avoid increasing the max critical pressure in the scheduled region.
|
|
if (DAG->isTrackingPressure() &&
|
|
tryPressure(TryCand.RPDelta.CriticalMax, Cand.RPDelta.CriticalMax,
|
|
TryCand, Cand, RegCritical, TRI, DAG->MF))
|
|
return TryCand.Reason != NoCand;
|
|
|
|
// We only compare a subset of features when comparing nodes between
|
|
// Top and Bottom boundary. Some properties are simply incomparable, in many
|
|
// other instances we should only override the other boundary if something
|
|
// is a clear good pick on one boundary. Skip heuristics that are more
|
|
// "tie-breaking" in nature.
|
|
bool SameBoundary = Zone != nullptr;
|
|
if (SameBoundary) {
|
|
// For loops that are acyclic path limited, aggressively schedule for
|
|
// latency. Within an single cycle, whenever CurrMOps > 0, allow normal
|
|
// heuristics to take precedence.
|
|
if (Rem.IsAcyclicLatencyLimited && !Zone->getCurrMOps() &&
|
|
tryLatency(TryCand, Cand, *Zone))
|
|
return TryCand.Reason != NoCand;
|
|
|
|
// Prioritize instructions that read unbuffered resources by stall cycles.
|
|
if (tryLess(Zone->getLatencyStallCycles(TryCand.SU),
|
|
Zone->getLatencyStallCycles(Cand.SU), TryCand, Cand, Stall))
|
|
return TryCand.Reason != NoCand;
|
|
}
|
|
|
|
// Keep clustered nodes together to encourage downstream peephole
|
|
// optimizations which may reduce resource requirements.
|
|
//
|
|
// This is a best effort to set things up for a post-RA pass. Optimizations
|
|
// like generating loads of multiple registers should ideally be done within
|
|
// the scheduler pass by combining the loads during DAG postprocessing.
|
|
unsigned CandZoneCluster = Cand.AtTop ? TopClusterID : BotClusterID;
|
|
unsigned TryCandZoneCluster = TryCand.AtTop ? TopClusterID : BotClusterID;
|
|
bool CandIsClusterSucc =
|
|
isTheSameCluster(CandZoneCluster, Cand.SU->ParentClusterIdx);
|
|
bool TryCandIsClusterSucc =
|
|
isTheSameCluster(TryCandZoneCluster, TryCand.SU->ParentClusterIdx);
|
|
|
|
if (tryGreater(TryCandIsClusterSucc, CandIsClusterSucc, TryCand, Cand,
|
|
Cluster))
|
|
return TryCand.Reason != NoCand;
|
|
|
|
if (SameBoundary) {
|
|
// Weak edges are for clustering and other constraints.
|
|
if (tryLess(getWeakLeft(TryCand.SU, TryCand.AtTop),
|
|
getWeakLeft(Cand.SU, Cand.AtTop), TryCand, Cand, Weak))
|
|
return TryCand.Reason != NoCand;
|
|
}
|
|
|
|
// Avoid increasing the max pressure of the entire region.
|
|
if (DAG->isTrackingPressure() &&
|
|
tryPressure(TryCand.RPDelta.CurrentMax, Cand.RPDelta.CurrentMax, TryCand,
|
|
Cand, RegMax, TRI, DAG->MF))
|
|
return TryCand.Reason != NoCand;
|
|
|
|
if (SameBoundary) {
|
|
// Avoid critical resource consumption and balance the schedule.
|
|
TryCand.initResourceDelta(DAG, SchedModel);
|
|
if (tryLess(TryCand.ResDelta.CritResources, Cand.ResDelta.CritResources,
|
|
TryCand, Cand, ResourceReduce))
|
|
return TryCand.Reason != NoCand;
|
|
if (tryGreater(TryCand.ResDelta.DemandedResources,
|
|
Cand.ResDelta.DemandedResources, TryCand, Cand,
|
|
ResourceDemand))
|
|
return TryCand.Reason != NoCand;
|
|
|
|
// Avoid serializing long latency dependence chains.
|
|
// For acyclic path limited loops, latency was already checked above.
|
|
if (!RegionPolicy.DisableLatencyHeuristic && TryCand.Policy.ReduceLatency &&
|
|
!Rem.IsAcyclicLatencyLimited && tryLatency(TryCand, Cand, *Zone))
|
|
return TryCand.Reason != NoCand;
|
|
|
|
// Fall through to original instruction order.
|
|
if ((Zone->isTop() && TryCand.SU->NodeNum < Cand.SU->NodeNum) ||
|
|
(!Zone->isTop() && TryCand.SU->NodeNum > Cand.SU->NodeNum)) {
|
|
TryCand.Reason = NodeOrder;
|
|
return true;
|
|
}
|
|
}
|
|
|
|
return false;
|
|
}
|