Raptor/src/PIM/Compiler/PimMemoryLiveness.cpp

#include "mlir/Dialect/Bufferization/IR/BufferizableOpInterface.h"
#include "mlir/Dialect/MemRef/IR/MemRef.h"
#include "mlir/Dialect/SCF/IR/SCF.h"
#include "mlir/IR/Value.h"
#include "mlir/Interfaces/DestinationStyleOpInterface.h"

#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/Support/raw_ostream.h"

#include <numeric>
#include <string>
#include <tuple>
#include <utility>

#include "Common/Support/CheckedArithmetic.hpp"
#include "Common/Support/ReportUtils.hpp"
#include "src/Accelerators/PIM/Common/PimCommon.hpp"
#include "src/Accelerators/PIM/Compiler/PimMemoryLiveness.hpp"
#include "src/Accelerators/PIM/Dialect/Pim/PimOps.hpp"

using namespace llvm;
using namespace mlir;
using namespace onnx_mlir;

namespace {

static std::optional<unsigned> getLaneForMemoryValue(mlir::Value value, std::optional<unsigned> lane) {
  if (!lane)
    return std::nullopt;
  auto allocOp = value.getDefiningOp<memref::AllocOp>();
  if (!allocOp || !allocOp->getParentOfType<pim::PimCoreBatchOp>())
    return std::nullopt;
  return lane;
}

static MemoryValueKey getMemoryValueKey(mlir::Value value, std::optional<unsigned> lane = std::nullopt) {
  return {value, getLaneForMemoryValue(value, lane)};
}

struct MemoryTouchInterval {
  uint64_t start = 0;
  uint64_t end = 0;
  Operation* startOp = nullptr;
  Operation* endOp = nullptr;
  Operation* firstTouchOp = nullptr;
  Operation* lastTouchOp = nullptr;
  uint64_t firstTouchPosition = 0;
  uint64_t lastTouchPosition = 0;
  bool hasRuntimeUse = false;
  bool startUsedAllocFallback = false;
  bool endUsedFallback = false;
  bool escapesLoop = false;
  std::string fallbackReason;
  llvm::SmallVector<std::string, 8> aliasesFollowed;
};

struct OperationOrdering {
  llvm::DenseMap<Operation*, uint64_t> position;
  llvm::DenseMap<Operation*, uint64_t> subtreeEnd;
  uint64_t nextPosition = 0;
};

static std::string printValueToString(mlir::Value value) {
  std::string text;
  llvm::raw_string_ostream os(text);
  value.print(os);
  os.flush();
  return text;
}

static std::string printOperationToString(Operation* op) {
  if (!op)
    return "<none>";
  std::string text;
  llvm::raw_string_ostream os(text);
  op->print(os);
  os.flush();
  return text;
}

static std::string printLocationToString(Location loc) {
  std::string text;
  llvm::raw_string_ostream os(text);
  loc.print(os);
  os.flush();
  return text;
}

static std::string collapseWhitespace(StringRef text) {
  std::string out;
  out.reserve(text.size());
  bool lastWasSpace = false;
  for (char c : text) {
    bool isSpace = c == ' ' || c == '\n' || c == '\t' || c == '\r';
    if (isSpace) {
      if (!lastWasSpace && !out.empty())
        out.push_back(' ');
      lastWasSpace = true;
      continue;
    }
    out.push_back(c);
    lastWasSpace = false;
  }
  return out;
}

static std::string abbreviate(StringRef text, size_t maxLen) {
  if (text.size() <= maxLen)
    return text.str();
  return (text.take_front(maxLen - 3) + "...").str();
}

static std::string summarizeValue(mlir::Value value, size_t maxLen = 72) {
  return abbreviate(collapseWhitespace(printValueToString(value)), maxLen);
}

static std::string summarizeOperation(Operation* op, size_t maxLen = 96) {
  if (!op)
    return "<none>";
  std::string prefix = op->getName().getStringRef().str();
  std::string full = collapseWhitespace(printOperationToString(op));
  if (full == prefix)
    return prefix;
  return abbreviate(prefix + " :: " + full, maxLen);
}

static std::string summarizeLocation(Location loc, size_t maxLen = 88) {
  return abbreviate(collapseWhitespace(printLocationToString(loc)), maxLen);
}

static void assignOperationOrdering(Operation* op, OperationOrdering& ordering) {
  uint64_t position = ordering.nextPosition++;
  ordering.position[op] = position;
  uint64_t end = position;
  for (Region& region : op->getRegions())
    for (Block& block : region)
      for (Operation& nestedOp : block) {
        assignOperationOrdering(&nestedOp, ordering);
        end = std::max(end, ordering.subtreeEnd.lookup(&nestedOp));
      }
  ordering.subtreeEnd[op] = end;
}

static OperationOrdering buildOperationOrdering(Operation* coreLikeOp) {
  OperationOrdering ordering;
  if (!coreLikeOp || coreLikeOp->getNumRegions() != 1 || coreLikeOp->getRegion(0).empty())
    return ordering;

  for (Operation& op : coreLikeOp->getRegion(0).front())
    assignOperationOrdering(&op, ordering);
  return ordering;
}

static bool isSupportedAliasOp(Operation* op) {
  return isa<memref::SubViewOp, memref::CastOp, memref::CollapseShapeOp, memref::ExpandShapeOp>(op);
}

static bool isRuntimeMemoryTouchOp(Operation* op) {
  return isa<pim::PimMemCopyHostToDevOp,
             pim::PimMemCopyDevToHostOp,
             pim::PimMemCopyOp,
             pim::PimReceiveOp,
             pim::PimSendOp,
             pim::PimConcatOp,
             pim::PimVMMOp,
             pim::PimTransposeOp,
             pim::PimVVAddOp,
             pim::PimVVSubOp,
             pim::PimVVMulOp,
             pim::PimVVMaxOp,
             pim::PimVVDMulOp,
             pim::PimVAvgOp,
             pim::PimVReluOp,
             pim::PimVTanhOp,
             pim::PimVSigmOp,
             pim::PimVSoftmaxOp>(op);
}

static bool isIgnoredLivenessUser(Operation* op) {
  return isSupportedAliasOp(op) || isa<scf::ForOp, scf::YieldOp, memref::DeallocOp>(op) || isCoreStaticAddressOp(op);
}

static bool isWithin(mlir::Value value, Region* region) {
  if (!region)
    return false;
  if (auto blockArg = dyn_cast<BlockArgument>(value))
    return blockArg.getOwner()->getParent() == region;
  if (Operation* definingOp = value.getDefiningOp())
    return definingOp->getParentRegion() == region || region->isAncestor(definingOp->getParentRegion());
  return false;
}

static bool isNestedAllocation(Operation* coreLikeOp, memref::AllocOp allocOp) {
  if (!coreLikeOp || coreLikeOp->getNumRegions() != 1 || coreLikeOp->getRegion(0).empty())
    return false;
  return allocOp->getBlock() != &coreLikeOp->getRegion(0).front();
}

static void addFallbackReason(std::string& reason, StringRef newReason) {
  if (newReason.empty())
    return;
  if (!reason.empty())
    reason += "; ";
  reason += newReason.str();
}

static void appendAliasDescription(llvm::SmallVectorImpl<std::string>& aliases, mlir::Value value) {
  std::string text = printValueToString(value);
  if (!llvm::is_contained(aliases, text))
    aliases.push_back(std::move(text));
}

struct OrderedTouchRange {
  uint64_t start = 0;
  uint64_t end = 0;
  Operation* startOp = nullptr;
  Operation* endOp = nullptr;
  bool escapedLoop = false;
};

static OrderedTouchRange
getEffectiveTouchRange(mlir::Value definingValue, Operation* user, const OperationOrdering& ordering) {
  OrderedTouchRange range {ordering.position.lookup(user), ordering.position.lookup(user), user, user, false};
  for (Operation* current = user; current; current = current->getParentOp()) {
    auto forOp = dyn_cast<scf::ForOp>(current);
    if (!forOp || isWithin(definingValue, &forOp.getRegion()))
      continue;
    range.start = std::min(range.start, ordering.position.lookup(forOp));
    range.end = std::max(range.end, ordering.subtreeEnd.lookup(forOp));
    range.startOp = forOp;
    range.endOp = forOp;
    range.escapedLoop = true;
  }
  return range;
}

static MemoryTouchInterval
computeMemoryTouchInterval(memref::AllocOp allocOp, const OperationOrdering& ordering, uint64_t fallbackEnd) {
  MemoryTouchInterval interval;
  interval.start = ordering.position.lookup(allocOp);
  interval.end = interval.start;
  interval.startOp = allocOp;
  interval.endOp = allocOp;

  SmallPtrSet<mlir::Value, 16> visitedValues;
  SmallPtrSet<Operation*, 32> visitedUsers;
  SmallVector<mlir::Value> pendingValues;
  pendingValues.push_back(allocOp.getResult());
  auto parentLoop = allocOp->getParentOfType<scf::ForOp>();

  while (!pendingValues.empty()) {
    mlir::Value value = pendingValues.pop_back_val();
    if (!visitedValues.insert(value).second)
      continue;

    for (Operation* user : value.getUsers()) {
      if (!visitedUsers.insert(user).second)
        continue;

      if (isSupportedAliasOp(user)) {
        for (mlir::Value result : user->getResults()) {
          pendingValues.push_back(result);
          appendAliasDescription(interval.aliasesFollowed, result);
        }
      }

      if (auto dpsOp = dyn_cast<DestinationStyleOpInterface>(user)) {
        for (OpResult result : user->getResults()) {
          OpOperand* tiedOperand = dpsOp.getTiedOpOperand(result);
          if (!tiedOperand || tiedOperand->get() != value)
            continue;
          pendingValues.push_back(result);
          appendAliasDescription(interval.aliasesFollowed, result);
        }
      }

      if (auto forOp = dyn_cast<scf::ForOp>(user)) {
        for (auto [index, initArg] : llvm::enumerate(forOp.getInitArgs())) {
          if (initArg != value)
            continue;
          pendingValues.push_back(forOp.getRegionIterArgs()[index]);
          pendingValues.push_back(forOp.getResult(index));
          appendAliasDescription(interval.aliasesFollowed, forOp.getRegionIterArgs()[index]);
          appendAliasDescription(interval.aliasesFollowed, forOp.getResult(index));
          if (parentLoop && forOp != parentLoop)
            interval.escapesLoop = true;
        }
      }

      if (auto yieldOp = dyn_cast<scf::YieldOp>(user)) {
        auto forOp = dyn_cast<scf::ForOp>(yieldOp->getParentOp());
        if (!forOp) {
          addFallbackReason(interval.fallbackReason, "yield without scf.for parent");
        }
        else {
          for (auto [index, operand] : llvm::enumerate(yieldOp.getOperands())) {
            if (operand != value)
              continue;
            pendingValues.push_back(forOp.getResult(index));
            appendAliasDescription(interval.aliasesFollowed, forOp.getResult(index));
            if (parentLoop && forOp == parentLoop)
              interval.escapesLoop = true;
          }
        }
      }

      if (isRuntimeMemoryTouchOp(user)) {
        uint64_t touchPosition = ordering.position.lookup(user);
        if (!interval.hasRuntimeUse || touchPosition < interval.firstTouchPosition) {
          interval.firstTouchPosition = touchPosition;
          interval.firstTouchOp = user;
        }
        if (!interval.hasRuntimeUse || touchPosition > interval.lastTouchPosition) {
          interval.lastTouchPosition = touchPosition;
          interval.lastTouchOp = user;
        }

        OrderedTouchRange range = getEffectiveTouchRange(allocOp.getResult(), user, ordering);
        interval.escapesLoop |= range.escapedLoop;
        if (!interval.hasRuntimeUse) {
          interval.start = range.start;
          interval.end = range.end;
          interval.startOp = range.startOp;
          interval.endOp = range.endOp;
          interval.hasRuntimeUse = true;
        }
        else {
          if (range.start < interval.start) {
            interval.start = range.start;
            interval.startOp = range.startOp;
          }
          if (range.end > interval.end) {
            interval.end = range.end;
            interval.endOp = range.endOp;
          }
        }
        continue;
      }

      if (isIgnoredLivenessUser(user))
        continue;

      addFallbackReason(interval.fallbackReason, "unhandled user op");
      interval.endUsedFallback = true;
    }
  }

  if (!interval.hasRuntimeUse) {
    interval.startUsedAllocFallback = true;
    interval.endUsedFallback = true;
    interval.start = ordering.position.lookup(allocOp);
    interval.end = fallbackEnd;
    interval.startOp = allocOp;
    interval.endOp = allocOp->getParentOp();
    interval.firstTouchPosition = interval.start;
    interval.lastTouchPosition = interval.end;
    addFallbackReason(interval.fallbackReason, "no runtime memory touch");
    return interval;
  }

  if (interval.endUsedFallback) {
    interval.end = std::max(interval.end, fallbackEnd);
    interval.endOp = allocOp->getParentOp();
  }

  return interval;
}

static FailureOr<size_t> getAllocSizeBytes(memref::AllocOp allocOp) {
  auto type = dyn_cast<ShapedType>(allocOp.getType());
  if (!type)
    return failure();
  auto checkedBytes = pim::getCheckedShapedTypeSizeInBytes(type, allocOp, "memory allocation byte size");
  if (failed(checkedBytes))
    return failure();
  return pim::checkedSize(*checkedBytes, allocOp, "memory allocation byte size");
}

static bool intervalsOverlap(const LocalAllocInterval& lhs, const LocalAllocInterval& rhs) {
  return !(lhs.end < rhs.start || rhs.end < lhs.start);
}

static uint64_t getSlotLogicalBytes(const PlannedPhysicalSlot& slot, ArrayRef<LocalAllocInterval> intervals) {
  uint64_t slotLogicalBytes = 0;
  for (size_t intervalIndex : slot.intervalIndices)
    slotLogicalBytes += intervals[intervalIndex].size;
  return slotLogicalBytes;
}

} // namespace

SmallVector<LocalAllocInterval, 0> onnx_mlir::buildLocalAllocIntervals(Operation* coreLikeOp,
                                                                       std::optional<unsigned> lane) {
  SmallVector<LocalAllocInterval, 0> intervals;
  OperationOrdering ordering = buildOperationOrdering(coreLikeOp);
  if (ordering.position.empty())
    return intervals;

  uint64_t fallbackEnd = ordering.nextPosition == 0 ? 0 : ordering.nextPosition - 1;
  size_t nextIntervalId = 0;
  coreLikeOp->walk([&](memref::AllocOp allocOp) {
    auto checkedSize = getAllocSizeBytes(allocOp);
    if (failed(checkedSize)) {
      llvm::errs() << "Failed to compute local allocation size for value: ";
      allocOp.getResult().print(llvm::errs());
      llvm::errs() << "\n";
      llvm_unreachable("Failed to compute local allocation size");
    }

    MemoryTouchInterval touchInterval = computeMemoryTouchInterval(allocOp, ordering, fallbackEnd);
    LocalAllocInterval interval;
    interval.id = nextIntervalId++;
    interval.alloc = allocOp;
    interval.key = getMemoryValueKey(allocOp.getResult(), lane);
    interval.start = touchInterval.start;
    interval.end = touchInterval.end;
    interval.size = *checkedSize;
    interval.startOp = touchInterval.startOp;
    interval.endOp = touchInterval.endOp;
    interval.firstTouchOp = touchInterval.firstTouchOp;
    interval.lastTouchOp = touchInterval.lastTouchOp;
    interval.firstTouchPosition = touchInterval.firstTouchPosition;
    interval.lastTouchPosition = touchInterval.lastTouchPosition;
    interval.startUsedAllocFallback = touchInterval.startUsedAllocFallback;
    interval.endUsedFallback = touchInterval.endUsedFallback;
    interval.hasRuntimeUse = touchInterval.hasRuntimeUse;
    interval.insideNestedRegion = isNestedAllocation(coreLikeOp, allocOp);
    interval.escapesLoop = touchInterval.escapesLoop;
    interval.fallbackReason = std::move(touchInterval.fallbackReason);
    interval.aliasesFollowed = std::move(touchInterval.aliasesFollowed);
    intervals.push_back(std::move(interval));
  });

  return intervals;
}

SmallVector<PlannedPhysicalSlot, 0> onnx_mlir::planPhysicalSlots(MutableArrayRef<LocalAllocInterval> intervals) {
  SmallVector<PlannedPhysicalSlot, 0> slots;
  SmallVector<size_t> intervalOrder(intervals.size());
  std::iota(intervalOrder.begin(), intervalOrder.end(), 0);
  llvm::stable_sort(intervalOrder, [&](size_t lhsIndex, size_t rhsIndex) {
    const LocalAllocInterval& lhs = intervals[lhsIndex];
    const LocalAllocInterval& rhs = intervals[rhsIndex];
    if (lhs.size != rhs.size)
      return lhs.size > rhs.size;
    if (lhs.start != rhs.start)
      return lhs.start < rhs.start;
    if (lhs.end != rhs.end)
      return lhs.end < rhs.end;
    return lhs.id < rhs.id;
  });

  for (size_t intervalIndex : intervalOrder) {
    LocalAllocInterval& interval = intervals[intervalIndex];
    PlannedPhysicalSlot* bestSlot = nullptr;
    auto bestKey = std::tuple<size_t, size_t, size_t, size_t>(std::numeric_limits<size_t>::max(),
                                                              std::numeric_limits<size_t>::max(),
                                                              std::numeric_limits<size_t>::max(),
                                                              std::numeric_limits<size_t>::max());

    for (size_t slotIndex = 0; slotIndex < slots.size(); ++slotIndex) {
      PlannedPhysicalSlot& slot = slots[slotIndex];
      bool compatible = true;
      for (size_t otherIndex : slot.intervalIndices) {
        if (intervalsOverlap(interval, intervals[otherIndex])) {
          compatible = false;
          break;
        }
      }
      if (!compatible)
        continue;

      size_t resultingSize = std::max(slot.requiredSize, interval.size);
      size_t growth = resultingSize - slot.requiredSize;
      auto candidateKey =
        std::tuple<size_t, size_t, size_t, size_t>(growth, resultingSize, slot.intervalIndices.size(), slot.id);
      if (candidateKey < bestKey) {
        bestKey = candidateKey;
        bestSlot = &slot;
      }
    }

    if (!bestSlot) {
      slots.push_back({slots.size(), interval.size, interval.size, 0, {intervalIndex}});
      interval.slotPlanIndex = slots.size() - 1;
      interval.physicalSlotId = slots.back().id;
      interval.physicalSlotSize = slots.back().requiredSize;
      continue;
    }

    bestSlot->requiredSize = std::max(bestSlot->requiredSize, interval.size);
    bestSlot->size = bestSlot->requiredSize;
    bestSlot->intervalIndices.push_back(intervalIndex);
    interval.slotPlanIndex = static_cast<size_t>(bestSlot - slots.data());
    interval.physicalSlotId = bestSlot->id;
    interval.physicalSlotSize = bestSlot->requiredSize;
  }

  return slots;
}

MemoryPlanArtifacts onnx_mlir::buildMemoryPlanArtifacts(Operation* coreLikeOp,
                                                        std::optional<unsigned> lane,
                                                        ArrayRef<LocalAllocInterval> intervals,
                                                        ArrayRef<PlannedPhysicalSlot> slots,
                                                        size_t addressLimit,
                                                        PimMemoryReportLevel reportLevel) {
  MemoryPlanArtifacts artifacts;

  uint64_t totalLogicalBytes = 0;
  uint64_t totalPhysicalBytes = 0;
  uint64_t fallbackIntervals = 0;
  uint64_t noRuntimeTouchIntervals = 0;
  uint64_t reusedAllocations = 0;
  uint64_t nestedIntervals = 0;
  uint64_t loopEscapingIntervals = 0;
  size_t largestLogicalAllocation = 0;
  size_t largestPhysicalSlot = 0;
  size_t maximumAssignedAddress = 0;

  for (const LocalAllocInterval& interval : intervals) {
    totalLogicalBytes += interval.size;
    largestLogicalAllocation = std::max(largestLogicalAllocation, interval.size);
    maximumAssignedAddress = std::max(maximumAssignedAddress, interval.assignedAddress + interval.physicalSlotSize);
    if (interval.startUsedAllocFallback || interval.endUsedFallback)
      ++fallbackIntervals;
    if (!interval.hasRuntimeUse)
      ++noRuntimeTouchIntervals;
    if (interval.insideNestedRegion)
      ++nestedIntervals;
    if (interval.escapesLoop)
      ++loopEscapingIntervals;
  }
  for (const PlannedPhysicalSlot& slot : slots) {
    totalPhysicalBytes += slot.size;
    largestPhysicalSlot = std::max(largestPhysicalSlot, slot.size);
    if (slot.intervalIndices.size() > 1)
      reusedAllocations += slot.intervalIndices.size() - 1;
  }

  uint64_t savedBytes = totalLogicalBytes >= totalPhysicalBytes ? totalLogicalBytes - totalPhysicalBytes : 0;
  double savedPercent =
    totalLogicalBytes == 0 ? 0.0 : 100.0 * static_cast<double>(savedBytes) / static_cast<double>(totalLogicalBytes);

  raw_string_ostream os(artifacts.textReport);
  os << "=== PIM Memory Liveness Report ===\n";
  os << "Op: " << coreLikeOp->getName() << "\n";
  if (lane)
    os << "Lane: " << *lane << "\n";
  os << "Summary:\n";
  os << "  logical allocation bytes:  " << formatReportMemory(totalLogicalBytes) << " (" << totalLogicalBytes << ")\n";
  os << "  physical allocation bytes: " << formatReportMemory(totalPhysicalBytes) << " (" << totalPhysicalBytes
     << ")\n";
  os << "  saved bytes:               " << formatReportMemory(savedBytes) << " (" << savedBytes << ")\n";
  os << "  saved percent: " << format("%.2f%%", savedPercent) << "\n";
  os << "  intervals: " << intervals.size() << "\n";
  os << "  physical slots: " << slots.size() << "\n";
  os << "  reused allocations: " << reusedAllocations << "\n";
  os << "  fallback intervals: " << fallbackIntervals << "\n";
  os << "  intervals with no runtime memory touch: " << noRuntimeTouchIntervals << "\n";
  os << "  nested allocations: " << nestedIntervals << "\n";
  os << "  loop-escaping allocations: " << loopEscapingIntervals << "\n";
  os << "  largest logical allocation: " << largestLogicalAllocation << "\n";
  os << "  largest physical slot: " << largestPhysicalSlot << "\n";
  os << "  address limit: " << addressLimit << "\n";
  os << "  peak physical memory: " << formatReportMemory(maximumAssignedAddress) << " (" << maximumAssignedAddress
     << ")\n";
  os << "  maximum assigned address: " << maximumAssignedAddress << "\n";

  os << "\nHow To Read:\n";
  os << "  `summary` only shows the strongest reuse cases and the worst offenders.\n";
  os << "  Use `--pim-memory-report=full` when you need the complete slot-by-slot and interval-by-interval dump.\n";
  os << "  Large single-use slots, fallback intervals, and nested single-use allocations are the best places\n";
  os << "  to inspect if allocations should be moved, sunk, or made easier to coalesce earlier in the pipeline.\n";

  SmallVector<const PlannedPhysicalSlot*> reusedSlots;
  SmallVector<const PlannedPhysicalSlot*> singleUseSlots;
  for (const PlannedPhysicalSlot& slot : slots)
    if (slot.intervalIndices.size() > 1)
      reusedSlots.push_back(&slot);
    else
      singleUseSlots.push_back(&slot);

  llvm::stable_sort(reusedSlots, [&](const PlannedPhysicalSlot* lhs, const PlannedPhysicalSlot* rhs) {
    uint64_t lhsLogicalBytes = getSlotLogicalBytes(*lhs, intervals);
    uint64_t rhsLogicalBytes = getSlotLogicalBytes(*rhs, intervals);
    if (lhs->intervalIndices.size() != rhs->intervalIndices.size())
      return lhs->intervalIndices.size() > rhs->intervalIndices.size();
    if (lhsLogicalBytes != rhsLogicalBytes)
      return lhsLogicalBytes > rhsLogicalBytes;
    if (lhs->size != rhs->size)
      return lhs->size > rhs->size;
    return lhs->id < rhs->id;
  });
  llvm::stable_sort(singleUseSlots, [&](const PlannedPhysicalSlot* lhs, const PlannedPhysicalSlot* rhs) {
    if (lhs->size != rhs->size)
      return lhs->size > rhs->size;
    return lhs->id < rhs->id;
  });

  constexpr size_t kSummaryReuseLimit = 6;
  constexpr size_t kSummaryOffenderLimit = 10;

  os << "\nBest Reuse:\n";
  if (reusedSlots.empty()) {
    os << "  no slots were shared by multiple intervals\n";
  }
  else {
    for (const PlannedPhysicalSlot* slot : ArrayRef(reusedSlots).take_front(kSummaryReuseLimit)) {
      uint64_t slotLogicalBytes = getSlotLogicalBytes(*slot, intervals);
      os << "  slot #" << slot->id << "  addr=" << slot->address << "  size=" << formatReportMemory(slot->size)
         << "  intervals=" << slot->intervalIndices.size() << "  logical_sum=" << formatReportMemory(slotLogicalBytes)
         << "\n";
      for (size_t intervalIndex : slot->intervalIndices) {
        const LocalAllocInterval& interval = intervals[intervalIndex];
        os << "    #" << interval.id << "  [" << interval.start << "," << interval.end << "]"
           << "  logical=" << formatReportMemory(interval.size)
           << "  first=" << summarizeOperation(interval.firstTouchOp, 40)
           << "  last=" << summarizeOperation(interval.lastTouchOp, 40) << "\n";
      }
    }
  }

  os << "\nTop Offenders:\n";
  bool printedAttention = false;
  for (const PlannedPhysicalSlot* slot : ArrayRef(singleUseSlots).take_front(kSummaryOffenderLimit)) {
    const LocalAllocInterval& interval = intervals[slot->intervalIndices.front()];
    printedAttention = true;
    os << "  slot #" << slot->id << " is single-use"
       << "  size=" << formatReportMemory(slot->size) << "  interval=#" << interval.id
       << "  value=" << summarizeValue(interval.key.value, 56) << "\n";
    os << "    first=" << summarizeOperation(interval.firstTouchOp, 40)
       << "  last=" << summarizeOperation(interval.lastTouchOp, 40)
       << "  nested=" << (interval.insideNestedRegion ? "yes" : "no")
       << "  escapes_loop=" << (interval.escapesLoop ? "yes" : "no") << "\n";
  }
  size_t fallbackPrinted = 0;
  for (const LocalAllocInterval& interval : intervals) {
    if (!(interval.startUsedAllocFallback || interval.endUsedFallback) || fallbackPrinted >= kSummaryOffenderLimit)
      continue;
    printedAttention = true;
    ++fallbackPrinted;
    os << "  fallback interval #" << interval.id << "  size=" << formatReportMemory(interval.size)
       << "  value=" << summarizeValue(interval.key.value, 56) << "\n";
    os << "    reason: " << (interval.fallbackReason.empty() ? "<none>" : interval.fallbackReason) << "\n";
  }
  size_t nestedPrinted = 0;
  for (const LocalAllocInterval& interval : intervals) {
    if (nestedPrinted >= kSummaryOffenderLimit)
      break;
    if (!(interval.insideNestedRegion && slots[interval.slotPlanIndex].intervalIndices.size() == 1))
      continue;
    printedAttention = true;
    ++nestedPrinted;
    os << "  nested single-use interval #" << interval.id << "  slot #" << interval.physicalSlotId
       << "  size=" << formatReportMemory(interval.size) << "  value=" << summarizeValue(interval.key.value, 56)
       << "\n";
    os << "    hint: move or sink this alloc inside the nested region if the IR allows it.\n";
  }
  if (!printedAttention)
    os << "  no obvious blockers detected in this core\n";

  if (reportLevel == PimMemoryReportFull) {
    os << "\nSlot Reuse:\n";
    for (const PlannedPhysicalSlot& slot : slots) {
      uint64_t slotLogicalBytes = getSlotLogicalBytes(slot, intervals);
      os << "  slot #" << slot.id << "  addr=" << slot.address << "  size=" << formatReportMemory(slot.size) << " ("
         << slot.size << ")"
         << "  intervals=" << slot.intervalIndices.size() << "  logical_sum=" << formatReportMemory(slotLogicalBytes)
         << "\n";
      for (size_t intervalIndex : slot.intervalIndices) {
        const LocalAllocInterval& interval = intervals[intervalIndex];
        mlir::Value allocValue = interval.key.value;
        os << "    [" << interval.start << "," << interval.end << "]"
           << "  #" << interval.id << "  logical=" << formatReportMemory(interval.size)
           << "  nested=" << (interval.insideNestedRegion ? "yes" : "no")
           << "  escapes_loop=" << (interval.escapesLoop ? "yes" : "no")
           << "  first=" << summarizeOperation(interval.firstTouchOp, 48)
           << "  last=" << summarizeOperation(interval.lastTouchOp, 48) << "\n";
        os << "      value=" << summarizeValue(allocValue) << "\n";
      }
    }
  }

  if (reportLevel == PimMemoryReportFull) {
    os << "\nInterval Details:\n";
    for (const LocalAllocInterval& interval : intervals) {
      const PlannedPhysicalSlot& slot = slots[interval.slotPlanIndex];
      mlir::Value allocValue = interval.key.value;
      Operation* definingOp = allocValue.getDefiningOp();
      os << "  #" << interval.id << "  slot=" << slot.id << "  live=[" << interval.start << "," << interval.end << "]"
         << "  logical=" << formatReportMemory(interval.size)
         << "  slot_size=" << formatReportMemory(interval.physicalSlotSize) << "  addr=" << interval.assignedAddress
         << "\n";
      os << "    value=" << summarizeValue(allocValue, 88) << "\n";
      os << "    type=" << allocValue.getType() << "\n";
      os << "    loc="
         << summarizeLocation(definingOp ? definingOp->getLoc() : UnknownLoc::get(coreLikeOp->getContext())) << "\n";
      os << "    nested=" << (interval.insideNestedRegion ? "yes" : "no")
         << "  escapes_loop=" << (interval.escapesLoop ? "yes" : "no")
         << "  start_fallback=" << (interval.startUsedAllocFallback ? "yes" : "no")
         << "  end_fallback=" << (interval.endUsedFallback ? "yes" : "no") << "\n";
      os << "    first_use=" << summarizeOperation(interval.firstTouchOp) << " @" << interval.firstTouchPosition
         << "\n";
      os << "    last_use=" << summarizeOperation(interval.lastTouchOp) << " @" << interval.lastTouchPosition << "\n";
      os << "    slot_peers=";
      bool first = true;
      for (size_t otherIndex : slot.intervalIndices) {
        if (intervals[otherIndex].id == interval.id)
          continue;
        if (!first)
          os << ", ";
        os << "#" << intervals[otherIndex].id;
        first = false;
      }
      if (first)
        os << "<none>";
      os << "\n";
      if (!interval.fallbackReason.empty())
        os << "    fallback_reason=" << interval.fallbackReason << "\n";
      if (!interval.aliasesFollowed.empty()) {
        os << "    aliases_followed=" << interval.aliasesFollowed.size() << "\n";
        for (const std::string& alias : interval.aliasesFollowed)
          os << "      - " << abbreviate(collapseWhitespace(alias), 108) << "\n";
      }
    }
  }
  os.flush();

  return artifacts;
}