slightly faster codegen
This commit is contained in:
@@ -42,8 +42,6 @@ static MemoryValueKey getMemoryValueKey(mlir::Value value, std::optional<unsigne
|
||||
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;
|
||||
@@ -218,22 +216,18 @@ static void appendAliasDescription(llvm::SmallVectorImpl<std::string>& aliases,
|
||||
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};
|
||||
OrderedTouchRange range {ordering.position.lookup(user), ordering.position.lookup(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;
|
||||
@@ -247,8 +241,6 @@ computeMemoryTouchInterval(memref::AllocOp allocOp,
|
||||
MemoryTouchInterval interval;
|
||||
interval.start = ordering.position.lookup(allocOp);
|
||||
interval.end = interval.start;
|
||||
interval.startOp = allocOp;
|
||||
interval.endOp = allocOp;
|
||||
auto recordAlias = [&](mlir::Value value) {
|
||||
if (includeAliasDescriptions)
|
||||
appendAliasDescription(interval.aliasesFollowed, value);
|
||||
@@ -350,18 +342,14 @@ computeMemoryTouchInterval(memref::AllocOp allocOp,
|
||||
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;
|
||||
@@ -380,8 +368,6 @@ computeMemoryTouchInterval(memref::AllocOp allocOp,
|
||||
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");
|
||||
@@ -390,7 +376,6 @@ computeMemoryTouchInterval(memref::AllocOp allocOp,
|
||||
|
||||
if (interval.endUsedFallback) {
|
||||
interval.end = std::max(interval.end, fallbackEnd);
|
||||
interval.endOp = allocOp->getParentOp();
|
||||
}
|
||||
|
||||
return interval;
|
||||
@@ -447,8 +432,6 @@ SmallVector<LocalAllocInterval, 0> onnx_mlir::buildLocalAllocIntervals(Operation
|
||||
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;
|
||||
@@ -574,7 +557,7 @@ MemoryPlanArtifacts onnx_mlir::buildMemoryPlanArtifacts(Operation* coreLikeOp,
|
||||
double savedPercent =
|
||||
totalLogicalBytes == 0 ? 0.0 : 100.0 * static_cast<double>(savedBytes) / static_cast<double>(totalLogicalBytes);
|
||||
|
||||
raw_string_ostream os(artifacts.textReport);
|
||||
raw_string_ostream os(artifacts);
|
||||
os << "=== PIM Memory Liveness Report ===\n";
|
||||
os << "Op: " << coreLikeOp->getName() << "\n";
|
||||
if (lane)
|
||||
|
||||
Reference in New Issue
Block a user