diag: passage vs boundary-band ceiling split (L88); coarse passage cache rejected
Verified ablations (zero passage work / zero band calls). LOD0-2 @W12: exact FI 2.27 / TN 2.25 s; passages off FI 0.81 / TN 0.85; bands off FI 2.11 / TN 2.06. Passages cost ~1.4-1.6 s of near readiness, bands ~0.1-0.2 s. A tile-local 4-voxel trilinear passage-delta cache increased carve segment visits (FI 34.5M -> 56.2M) and slowed LOD0-2 (FI 2.58 -> 3.77 s); removed. No world change. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016dhxM43dnWvUu2B5Ph1iG1
This commit is contained in:
1 parent
0fe7f371f7
commit
fa78192c86
5 files changed
+285
-15
No files matched your search
@@ -138,6 +138,7 @@ namespace VoxelForgeCore
|
|||||||
std::uint64_t passageTileFeatureCount = 0;
|
std::uint64_t passageTileFeatureCount = 0;
|
||||||
std::uint64_t passageTileRouteSegmentCandidates = 0;
|
std::uint64_t passageTileRouteSegmentCandidates = 0;
|
||||||
std::uint64_t passageTileMouthSegmentCandidates = 0;
|
std::uint64_t passageTileMouthSegmentCandidates = 0;
|
||||||
|
std::uint64_t resolvedBoundaryBandQueries = 0;
|
||||||
std::uint64_t passageComposerQueries = 0;
|
std::uint64_t passageComposerQueries = 0;
|
||||||
std::uint64_t passageIterations = 0;
|
std::uint64_t passageIterations = 0;
|
||||||
std::uint64_t passageTileBoundChecks = 0;
|
std::uint64_t passageTileBoundChecks = 0;
|
||||||
|
|||||||
@@ -31,19 +31,37 @@
|
|||||||
#include <variant>
|
#include <variant>
|
||||||
#include <vector>
|
#include <vector>
|
||||||
|
|
||||||
// L86-only ceiling measurement. This removes passage carving/support and the transition-mouth
|
// L88-only composition split. These switches let the timing harness remove passage work and
|
||||||
// passage fade so timing can measure the best possible passage-representation gain. Never ship
|
// resolved boundary-band work independently. They are diagnostic only, never world settings.
|
||||||
// or expose this diagnostic as a world setting.
|
static bool VF_IsL88DiagnosticSwitchEnabled(const char* Name)
|
||||||
static bool VF_IsL86PassageCompositionDisabled()
|
|
||||||
{
|
{
|
||||||
static const bool bDisabled = []()
|
const char* Value=std::getenv(Name);
|
||||||
{
|
return Value&&Value[0]=='1'&&Value[1]=='\0';
|
||||||
const char* Value = std::getenv("VOXELFORGE_L86_DISABLE_PASSAGE_COMPOSITION");
|
}
|
||||||
return Value && Value[0] == '1' && Value[1] == '\0';
|
|
||||||
}();
|
static bool VF_IsL88PassageCompositionDisabled()
|
||||||
|
{
|
||||||
|
static const bool bDisabled=VF_IsL88DiagnosticSwitchEnabled(
|
||||||
|
"VOXELFORGE_L88_DISABLE_PASSAGES")
|
||||||
|
||VF_IsL88DiagnosticSwitchEnabled("VOXELFORGE_L86_DISABLE_PASSAGE_COMPOSITION");
|
||||||
return bDisabled;
|
return bDisabled;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static bool VF_IsL88BoundaryBandsDisabled()
|
||||||
|
{
|
||||||
|
static const bool bDisabled=VF_IsL88DiagnosticSwitchEnabled(
|
||||||
|
"VOXELFORGE_L88_DISABLE_BOUNDARY_BANDS")
|
||||||
|
||VF_IsL88DiagnosticSwitchEnabled("VOXELFORGE_L86_DISABLE_PASSAGE_COMPOSITION");
|
||||||
|
return bDisabled;
|
||||||
|
}
|
||||||
|
|
||||||
|
static bool VF_IsL88AllowPassageAblationWalkabilityFailure()
|
||||||
|
{
|
||||||
|
static const bool bEnabled=VF_IsL88DiagnosticSwitchEnabled(
|
||||||
|
"VOXELFORGE_L88_ALLOW_PASSAGE_ABLATION_WALKABILITY_FAILURE");
|
||||||
|
return bEnabled;
|
||||||
|
}
|
||||||
|
|
||||||
// Standalone-only world compiler. It compiles the runtime room/tunnel/passages into
|
// Standalone-only world compiler. It compiles the runtime room/tunnel/passages into
|
||||||
// axis-line intervals, composes rock/cave signs into packed Z-column words, then displaces
|
// axis-line intervals, composes rock/cave signs into packed Z-column words, then displaces
|
||||||
// only the conservative surface band. The copied Unreal generator remains the A/B reference.
|
// only the conservative surface band. The copied Unreal generator remains the A/B reference.
|
||||||
@@ -197,7 +215,6 @@ public:
|
|||||||
std::ptrdiff_t first=-1,end=-1;
|
std::ptrdiff_t first=-1,end=-1;
|
||||||
std::vector<std::uint8_t> activeNodes;
|
std::vector<std::uint8_t> activeNodes;
|
||||||
};
|
};
|
||||||
|
|
||||||
FScopedPassageTileQueries(const FStandaloneShapeWorld& shape,
|
FScopedPassageTileQueries(const FStandaloneShapeWorld& shape,
|
||||||
const std::array<std::int64_t,3>& minimumSubvoxels,
|
const std::array<std::int64_t,3>& minimumSubvoxels,
|
||||||
const std::array<std::int64_t,3>& maximumSubvoxels,
|
const std::array<std::int64_t,3>& maximumSubvoxels,
|
||||||
@@ -208,7 +225,9 @@ public:
|
|||||||
{
|
{
|
||||||
mayContainResolvedBoundaryBand_=shape.ResolvedBoundaryBandsIntersectSubvoxelRange(
|
mayContainResolvedBoundaryBand_=shape.ResolvedBoundaryBandsIntersectSubvoxelRange(
|
||||||
minimumSubvoxels_[2],maximumSubvoxels_[2]);
|
minimumSubvoxels_[2],maximumSubvoxels_[2]);
|
||||||
const bool disablePassageComposition = VF_IsL86PassageCompositionDisabled();
|
const bool disablePassageComposition=VF_IsL88PassageCompositionDisabled();
|
||||||
|
const bool disableBoundaryBands=VF_IsL88BoundaryBandsDisabled();
|
||||||
|
if(disableBoundaryBands)mayContainResolvedBoundaryBand_=false;
|
||||||
mayContainTransitionPassageFade_ = !disablePassageComposition
|
mayContainTransitionPassageFade_ = !disablePassageComposition
|
||||||
&& shape.ResolvedTransitionPassageFadeIntersectsTileXY(
|
&& shape.ResolvedTransitionPassageFadeIntersectsTileXY(
|
||||||
minimumSubvoxels_, maximumSubvoxels_);
|
minimumSubvoxels_, maximumSubvoxels_);
|
||||||
@@ -930,6 +949,9 @@ public:
|
|||||||
#endif
|
#endif
|
||||||
(void)X;(void)Y;
|
(void)X;(void)Y;
|
||||||
const auto* tileQueries=ActivePassageTileQueries;
|
const auto* tileQueries=ActivePassageTileQueries;
|
||||||
|
if(tileQueries&&tileQueries->matches(*this))
|
||||||
|
if(auto* profile=tileQueries->profileStats())
|
||||||
|
++profile->resolvedBoundaryBandQueries;
|
||||||
if(tileQueries&&tileQueries->matches(*this))
|
if(tileQueries&&tileQueries->matches(*this))
|
||||||
{
|
{
|
||||||
if(!tileQueries->mayContainResolvedBoundaryBand())
|
if(!tileQueries->mayContainResolvedBoundaryBand())
|
||||||
@@ -2256,9 +2278,11 @@ public:
|
|||||||
// mouth that crosses a wide transition band. Keep that opt-in field whole;
|
// mouth that crosses a wide transition band. Keep that opt-in field whole;
|
||||||
// its host-rock value already supplies the ceiling and bedrock.
|
// its host-rock value already supplies the ceiling and bedrock.
|
||||||
const bool disablePassageComposition=!nativeLattice
|
const bool disablePassageComposition=!nativeLattice
|
||||||
&&VF_IsL86PassageCompositionDisabled();
|
&&VF_IsL88PassageCompositionDisabled();
|
||||||
|
const bool disableBoundaryBands=!nativeLattice
|
||||||
|
&&VF_IsL88BoundaryBandsDisabled();
|
||||||
float boundary=graphDensity;
|
float boundary=graphDensity;
|
||||||
if(!nativeLattice&&!disablePassageComposition)
|
if(!nativeLattice&&!disableBoundaryBands)
|
||||||
{
|
{
|
||||||
VoxelForgeCore::Linux77Profiler::FScopedPhase l77BandsPhase(
|
VoxelForgeCore::Linux77Profiler::FScopedPhase l77BandsPhase(
|
||||||
VoxelForgeCore::Linux77Profiler::EPhase::Bands);
|
VoxelForgeCore::Linux77Profiler::EPhase::Bands);
|
||||||
@@ -3019,11 +3043,22 @@ public:
|
|||||||
// Route validation is world-wide. Detail regions reuse the same authored route data and
|
// Route validation is world-wide. Detail regions reuse the same authored route data and
|
||||||
// do not need to repeat the 5,642-point world audit for every entering tile group.
|
// do not need to repeat the 5,642-point world audit for every entering tile group.
|
||||||
Substage=Clock::now();
|
Substage=Clock::now();
|
||||||
if(bValidatePassageRoutes&&!ValidatePassageRoutes())
|
const bool bPassageRoutesValid=!bValidatePassageRoutes||ValidatePassageRoutes();
|
||||||
|
if(!bPassageRoutesValid)
|
||||||
|
{
|
||||||
|
if(VF_IsL88PassageCompositionDisabled()
|
||||||
|
&&!VF_IsL88BoundaryBandsDisabled()
|
||||||
|
&&VF_IsL88AllowPassageAblationWalkabilityFailure())
|
||||||
|
{
|
||||||
|
std::printf("[L88PassageAblation] route walkability failed as expected; "
|
||||||
|
"continuing only to measure passage-off/bands-on readiness\n");
|
||||||
|
}
|
||||||
|
else
|
||||||
{
|
{
|
||||||
Error="compiled shape world contains a solid passage centreline sample";
|
Error="compiled shape world contains a solid passage centreline sample";
|
||||||
return false;
|
return false;
|
||||||
}
|
}
|
||||||
|
}
|
||||||
Stats.PassageValidationSeconds=std::chrono::duration<double>(Clock::now()-Substage).count();
|
Stats.PassageValidationSeconds=std::chrono::duration<double>(Clock::now()-Substage).count();
|
||||||
Built=true;
|
Built=true;
|
||||||
if(bIncludeFarWorld)BuildFarWorld();
|
if(bIncludeFarWorld)BuildFarWorld();
|
||||||
|
|||||||
@@ -0,0 +1,35 @@
|
|||||||
|
# Linux 88 — passage and boundary cost
|
||||||
|
|
||||||
|
## Ceiling split
|
||||||
|
|
||||||
|
L80 protocol: one warmup, then three interleaved measured runs per mode, worker count and stratum. Values are median seconds to LOD0–2 ready / whole view ready.
|
||||||
|
|
||||||
|
| Stratum | Workers | Exact | Passages off, bands on | Bands off, passages on |
|
||||||
|
|---|---:|---:|---:|---:|
|
||||||
|
| FI | 8 | 2.419 / 3.696 | 0.808 / 1.738 | 2.306 / 3.556 |
|
||||||
|
| FI | 12 | 2.273 / 3.463 | 0.812 / 1.683 | 2.114 / 3.290 |
|
||||||
|
| TN | 8 | 2.458 / 3.624 | 0.912 / 1.814 | 2.222 / 3.308 |
|
||||||
|
| TN | 12 | 2.253 / 3.294 | 0.851 / 1.683 | 2.056 / 3.061 |
|
||||||
|
|
||||||
|
Passage composition costs about 1.40–1.61 s of FI/TN LOD0–2 readiness. Boundary bands cost about 0.11–0.24 s. The split counters confirmed the ablations: passages-off had zero passage queries, iterations, carve/support visits and relief calls, while retaining 11.39M FI / 7.72M TN band calls in profiled tiles. Bands-off had zero band calls while passage iterations remained 14.06M FI / 12.43M TN. The profile covered 629 FI and 614 TN near tiles. Passage-off intentionally failed the route walkability check because the remaining bands close an authored mouth; a split-only diagnostic continued the timing run.
|
||||||
|
|
||||||
|
Exact-field readiness across all four strates:
|
||||||
|
|
||||||
|
| Stratum | W8 LOD0–2 / whole | W12 LOD0–2 / whole |
|
||||||
|
|---|---:|---:|
|
||||||
|
| SurfaceWorld | 1.093 / 2.340 | 1.024 / 2.157 |
|
||||||
|
| FloatingIslands | 2.419 / 3.696 | 2.273 / 3.463 |
|
||||||
|
| TunnelNetwork | 2.458 / 3.624 | 2.253 / 3.294 |
|
||||||
|
| VerticalShafts | 1.312 / 2.386 | 1.128 / 2.080 |
|
||||||
|
|
||||||
|
## Prototype and decision
|
||||||
|
|
||||||
|
I tested a tile-local 4-voxel trilinear cache of passage-composition deltas, with exact evaluation near or across the zero surface. It did not remove enough route work: instrumented FI/TN runs recorded 4.75M / 7.71M exact coarse-node evaluations, and carve-segment visits increased from 34.5M / 33.1M to 56.2M / 76.5M.
|
||||||
|
|
||||||
|
Two unprofiled interleaved W8 pairs confirmed the regression. FI LOD0–2 median rose from 2.583 s exact to 3.765 s coarse; TN rose from 2.646 s to 4.649 s. Whole-view medians rose from 3.957 to 8.708 s for FI and 3.735 to 7.976 s for TN. The prototype was removed from source.
|
||||||
|
|
||||||
|
The pre-measurement acceptance bar was max displacement ≤5 cm, mean ≤1 cm per stratum, and zero sign flips on canonical walk-floor samples. Displacement was not measured. The prototype stopped at the speed gate, so post-prototype passage audits, captures, and Clang/GCC W1/W8/W12 comparisons were not run. No evaluator version bump or hash re-pins were made; version remains 214. The fast tier passed on the cleaned exact-field source: 274 checks in 311.3 s, stamp `81a934b80ed90d2ab0137345d15688a9bd201e4ec6ce7af94b08f4cb4e77c1a3`.
|
||||||
|
|
||||||
|
## Runs
|
||||||
|
|
||||||
|
All benchmark and verification jobs used CPUs 0–11; headless jobs were capped at 6 GiB. No run exceeded 30 minutes. The timing and per-tile work logs are under `Saved/Linux/l88/ceiling-split/` and `Saved/Linux/l88/coarse-prototype/`; the fast-tier log and summary are under `Saved/Linux/l88/logs/fast-tier.log` and `Saved/Linux/l88/verify-fast/fast-summary.json`. No Unreal `Source/` files changed, so no UE build was needed. No commit, push, or stash was made.
|
||||||
@@ -0,0 +1,198 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Measure passage and boundary-band ceilings independently under the L80 protocol."""
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import json
|
||||||
|
import re
|
||||||
|
import statistics
|
||||||
|
import subprocess
|
||||||
|
import time
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
ROOT = Path(__file__).resolve().parents[4]
|
||||||
|
OUT = ROOT / "Saved/Linux/l88/ceiling-split"
|
||||||
|
DATA = ROOT / "Standalone/data/owner_world.json"
|
||||||
|
BINARY = ROOT / "Saved/Linux/l88/bin/VoxelForgeCoreHeadless-l88-clang19"
|
||||||
|
STRATA = {
|
||||||
|
"S0": {"id": 0, "camera": (8.0, 16.0, -372.2626953125), "near": 1408, "whole": 2850},
|
||||||
|
"FI": {"id": 1, "camera": (25.8369140625, 3.19921875, -737.0), "near": 1216, "whole": 2249},
|
||||||
|
"TN": {"id": 2, "camera": (19.166015625, -14.2001953125, -753.3740234375), "near": 1344, "whole": 2233},
|
||||||
|
"S3": {"id": 3, "camera": (-20.0625, -5.068359375, -900.353515625), "near": 1344, "whole": 2329},
|
||||||
|
}
|
||||||
|
WORKERS = (8, 12)
|
||||||
|
MODES = ("direct", "passages_off", "bands_off")
|
||||||
|
PIPELINE = re.compile(r"^\[StreamPipeline\] (.*)$", re.M)
|
||||||
|
FIELDS = re.compile(r"([a-zA-Z0-9_]+)=([^ ]+)")
|
||||||
|
NEAR = re.compile(
|
||||||
|
r"^\[WorldAssemblerNearLODReady\] lods=0-2 tiles=(\d+)/(\d+) cold_ready_s=([0-9.]+)$", re.M)
|
||||||
|
PASSAGE_TILE = re.compile(r"^\[PassageComposerTile\] (.*)$", re.M)
|
||||||
|
STAMP = re.compile(r"^\[VoxelForgeSourceStamp\] sha256=(\S+)$", re.M)
|
||||||
|
|
||||||
|
|
||||||
|
def base_command(stratum: str, workers: int, mode: str, profile: bool = False) -> list[str]:
|
||||||
|
spec = STRATA[stratum]
|
||||||
|
camera = ",".join(f"{value:.12f}" for value in spec["camera"]) + ",0,0"
|
||||||
|
child = [
|
||||||
|
str(BINARY), str(DATA), "--world-assembler-prototype", "--stream-benchmark",
|
||||||
|
"--stream-pipeline", f"--workers={workers}", "--clip-radius=3",
|
||||||
|
"--max-clip-level=8", "--max-level=8", f"--camera={camera}",
|
||||||
|
"--profile-lod-work", "--stream-scheduler-policy=3",
|
||||||
|
]
|
||||||
|
if profile:
|
||||||
|
child.append("--profile-passage-composer")
|
||||||
|
env = ["VOXELFORGE_L81_PASSAGE_BOUND_PADDING_VOXELS=0"]
|
||||||
|
if mode == "passages_off":
|
||||||
|
env.extend(("VOXELFORGE_L88_DISABLE_PASSAGES=1",
|
||||||
|
"VOXELFORGE_L88_ALLOW_PASSAGE_ABLATION_WALKABILITY_FAILURE=1"))
|
||||||
|
elif mode == "bands_off":
|
||||||
|
env.append("VOXELFORGE_L88_DISABLE_BOUNDARY_BANDS=1")
|
||||||
|
return [
|
||||||
|
"taskset", "-c", "0-11", "prlimit", "--as=6442450944", "--", "env",
|
||||||
|
*env, "timeout", "1740s", *child,
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
def execute(stratum: str, workers: int, mode: str, phase: str,
|
||||||
|
replicate: int = 0, profile: bool = False) -> dict:
|
||||||
|
OUT.mkdir(parents=True, exist_ok=True)
|
||||||
|
label = f"{stratum.lower()}-w{workers}-{mode}-{phase}"
|
||||||
|
if replicate:
|
||||||
|
label += f"-r{replicate}"
|
||||||
|
if profile:
|
||||||
|
label += "-profile"
|
||||||
|
log = OUT / f"{label}.log"
|
||||||
|
started = time.monotonic()
|
||||||
|
with log.open("w", encoding="utf-8") as stream:
|
||||||
|
result = subprocess.run(base_command(stratum, workers, mode, profile), cwd=ROOT,
|
||||||
|
stdout=stream, stderr=subprocess.STDOUT,
|
||||||
|
check=False, timeout=1750)
|
||||||
|
output = log.read_text(encoding="utf-8", errors="replace")
|
||||||
|
pipeline, near, stamp = PIPELINE.search(output), NEAR.search(output), STAMP.search(output)
|
||||||
|
if result.returncode or pipeline is None or near is None or stamp is None:
|
||||||
|
raise RuntimeError(f"run failed or required output is missing: {log}; exit={result.returncode}")
|
||||||
|
spec = STRATA[stratum]
|
||||||
|
near_counts = (int(near.group(1)), int(near.group(2)))
|
||||||
|
if near_counts != (spec["near"], spec["near"]):
|
||||||
|
raise RuntimeError(f"incomplete near set in {log}: {near_counts}")
|
||||||
|
fields = dict(FIELDS.findall(pipeline.group(1)))
|
||||||
|
whole_counts = tuple(int(value) for value in fields["whole_tiles"].split("/"))
|
||||||
|
if whole_counts != (spec["whole"], spec["whole"]):
|
||||||
|
raise RuntimeError(f"incomplete whole view in {log}: {whole_counts}")
|
||||||
|
ablation_walkability = "[L88PassageAblation]" in output
|
||||||
|
if (mode == "passages_off") != ablation_walkability:
|
||||||
|
raise RuntimeError(f"passage ablation walkability marker unexpected in {log}")
|
||||||
|
row = {
|
||||||
|
"stratum": stratum, "workers": workers, "mode": mode, "phase": phase,
|
||||||
|
"replicate": replicate, "profile": profile, "exit_code": result.returncode,
|
||||||
|
"wall_s": round(time.monotonic() - started, 3), "source_stamp": stamp.group(1),
|
||||||
|
"lod02_ready_s": float(near.group(3)),
|
||||||
|
"whole_view_ready_s": float(fields["whole_view_ready"].removesuffix("s")),
|
||||||
|
"shape_s": float(fields["shape"].removesuffix("s")),
|
||||||
|
"far_shape_s": float(fields["far_shape"].removesuffix("s")),
|
||||||
|
"ablation_walkability_failed": ablation_walkability,
|
||||||
|
"near_tiles": spec["near"], "whole_tiles": spec["whole"],
|
||||||
|
"log": str(log.relative_to(ROOT)),
|
||||||
|
}
|
||||||
|
if profile:
|
||||||
|
total = {name: 0 for name in (
|
||||||
|
"boundary_band_queries", "queries", "passage_iterations",
|
||||||
|
"carve_segment_visits", "support_segment_visits", "relief_field_calls",
|
||||||
|
)}
|
||||||
|
profiled_tiles = 0
|
||||||
|
for match in PASSAGE_TILE.finditer(output):
|
||||||
|
fields = dict(FIELDS.findall(match.group(1)))
|
||||||
|
if int(fields["key"].rsplit("lod", 1)[1].rstrip(")")) > 2:
|
||||||
|
continue
|
||||||
|
profiled_tiles += 1
|
||||||
|
for name in total:
|
||||||
|
total[name] += int(fields[name])
|
||||||
|
if not profiled_tiles:
|
||||||
|
raise RuntimeError(f"passage/band profile rows missing in {log}")
|
||||||
|
row.update({f"profile_{name}": value for name, value in total.items()})
|
||||||
|
row["profiled_near_tiles"] = profiled_tiles
|
||||||
|
print("[L88CeilingSplitRun] " + json.dumps(row, sort_keys=True), flush=True)
|
||||||
|
return row
|
||||||
|
|
||||||
|
|
||||||
|
def profile_modes() -> list[dict]:
|
||||||
|
rows = [execute(stratum, 8, mode, "profile", profile=True)
|
||||||
|
for stratum in ("FI", "TN") for mode in MODES]
|
||||||
|
for stratum in ("FI", "TN"):
|
||||||
|
subset = {row["mode"]: row for row in rows if row["stratum"] == stratum}
|
||||||
|
direct, passages, bands = (subset[name] for name in MODES)
|
||||||
|
if direct["profile_boundary_band_queries"] == 0 or direct["profile_queries"] == 0:
|
||||||
|
raise RuntimeError(f"direct profile did not exercise both paths for {stratum}")
|
||||||
|
if passages["profile_boundary_band_queries"] == 0 or any(
|
||||||
|
passages[f"profile_{name}"] != 0
|
||||||
|
for name in ("queries", "passage_iterations", "carve_segment_visits",
|
||||||
|
"support_segment_visits", "relief_field_calls")
|
||||||
|
):
|
||||||
|
raise RuntimeError(f"passages-off profile did not isolate the band path for {stratum}")
|
||||||
|
if bands["profile_boundary_band_queries"] != 0 or any(
|
||||||
|
bands[f"profile_{name}"] == 0
|
||||||
|
for name in ("queries", "passage_iterations", "carve_segment_visits")
|
||||||
|
):
|
||||||
|
raise RuntimeError(f"bands-off profile did not preserve passage work for {stratum}")
|
||||||
|
(OUT / "profile-summary.json").write_text(json.dumps(rows, indent=2) + "\n", encoding="utf-8")
|
||||||
|
return rows
|
||||||
|
|
||||||
|
|
||||||
|
def timing_matrix() -> list[dict]:
|
||||||
|
# One warmup for each complete stratum/worker/mode window.
|
||||||
|
for stratum in STRATA:
|
||||||
|
for workers in WORKERS:
|
||||||
|
for mode in MODES:
|
||||||
|
execute(stratum, workers, mode, "warmup")
|
||||||
|
orders = (
|
||||||
|
((8, "direct"), (8, "passages_off"), (8, "bands_off"),
|
||||||
|
(12, "bands_off"), (12, "passages_off"), (12, "direct")),
|
||||||
|
((12, "passages_off"), (12, "direct"), (12, "bands_off"),
|
||||||
|
(8, "bands_off"), (8, "direct"), (8, "passages_off")),
|
||||||
|
((8, "bands_off"), (8, "direct"), (8, "passages_off"),
|
||||||
|
(12, "direct"), (12, "passages_off"), (12, "bands_off")),
|
||||||
|
)
|
||||||
|
measured = []
|
||||||
|
for stratum in STRATA:
|
||||||
|
for replicate, order in enumerate(orders, 1):
|
||||||
|
for workers, mode in order:
|
||||||
|
measured.append(execute(stratum, workers, mode, "measured", replicate))
|
||||||
|
(OUT / "runs-partial.json").write_text(
|
||||||
|
json.dumps(measured, indent=2) + "\n", encoding="utf-8")
|
||||||
|
summary = []
|
||||||
|
for stratum in STRATA:
|
||||||
|
for workers in WORKERS:
|
||||||
|
for mode in MODES:
|
||||||
|
subset = [r for r in measured if r["stratum"] == stratum
|
||||||
|
and r["workers"] == workers and r["mode"] == mode]
|
||||||
|
if len(subset) != 3:
|
||||||
|
raise RuntimeError(f"expected 3 measured runs for {stratum} W{workers} {mode}")
|
||||||
|
item = {"stratum": stratum, "workers": workers, "mode": mode,
|
||||||
|
"measured_runs": len(subset)}
|
||||||
|
for metric in ("lod02_ready_s", "whole_view_ready_s", "shape_s", "far_shape_s"):
|
||||||
|
values = [r[metric] for r in subset]
|
||||||
|
item[metric] = values
|
||||||
|
item[f"{metric}_median"] = statistics.median(values)
|
||||||
|
summary.append(item)
|
||||||
|
(OUT / "summary.json").write_text(
|
||||||
|
json.dumps({"runs": measured, "summary": summary}, indent=2) + "\n",
|
||||||
|
encoding="utf-8")
|
||||||
|
return measured
|
||||||
|
|
||||||
|
|
||||||
|
def main() -> int:
|
||||||
|
parser = argparse.ArgumentParser()
|
||||||
|
parser.add_argument("--profiles-only", action="store_true")
|
||||||
|
parser.add_argument("--timing-only", action="store_true")
|
||||||
|
args = parser.parse_args()
|
||||||
|
if not BINARY.is_file() or not DATA.is_file():
|
||||||
|
raise SystemExit(f"missing input: {BINARY} or {DATA}")
|
||||||
|
if not args.timing_only:
|
||||||
|
profile_modes()
|
||||||
|
if not args.profiles_only:
|
||||||
|
timing_matrix()
|
||||||
|
return 0
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
raise SystemExit(main())
|
||||||
@@ -1493,13 +1493,14 @@ private:
|
|||||||
static_cast<unsigned long long>(D.islandSharedCacheConflictReplacements),
|
static_cast<unsigned long long>(D.islandSharedCacheConflictReplacements),
|
||||||
static_cast<double>(D.islandSharedCacheLockWaitNanoseconds)/1000.0);
|
static_cast<double>(D.islandSharedCacheLockWaitNanoseconds)/1000.0);
|
||||||
if(D.passageComposerProfiled)
|
if(D.passageComposerProfiled)
|
||||||
std::printf("[PassageComposerTile] key=(%d,%d,%d,lod%d) worker_ms=%.3f samples=%llu native_field_calls=%llu features=%llu route_candidates=%llu mouth_candidates=%llu queries=%llu passage_iterations=%llu tile_bound_checks=%llu tile_bound_rejects=%llu tile_bound_skipped_iterations=%llu upper_mouth_checks=%llu column_candidates=%llu column_distance_calls=%llu negative_bounds=%llu negative_rejects=%llu positive_bounds=%llu positive_rejects=%llu carve_segment_visits=%llu smooth_carve_joins=%llu support_segment_visits=%llu smooth_support_joins=%llu support_capsule_checks=%llu later_bore_checks=%llu other_capsule_checks=%llu mouth_support_calls=%llu mouth_route_segment_checks=%llu relief_field_calls=%llu smoothstep_evaluations=%llu\n",
|
std::printf("[PassageComposerTile] key=(%d,%d,%d,lod%d) worker_ms=%.3f samples=%llu native_field_calls=%llu features=%llu route_candidates=%llu mouth_candidates=%llu boundary_band_queries=%llu queries=%llu passage_iterations=%llu tile_bound_checks=%llu tile_bound_rejects=%llu tile_bound_skipped_iterations=%llu upper_mouth_checks=%llu column_candidates=%llu column_distance_calls=%llu negative_bounds=%llu negative_rejects=%llu positive_bounds=%llu positive_rejects=%llu carve_segment_visits=%llu smooth_carve_joins=%llu support_segment_visits=%llu smooth_support_joins=%llu support_capsule_checks=%llu later_bore_checks=%llu other_capsule_checks=%llu mouth_support_calls=%llu mouth_route_segment_checks=%llu relief_field_calls=%llu smoothstep_evaluations=%llu\n",
|
||||||
Event.Key.Coord.X,Event.Key.Coord.Y,Event.Key.Coord.Z,Event.Key.Level,
|
Event.Key.Coord.X,Event.Key.Coord.Y,Event.Key.Coord.Z,Event.Key.Level,
|
||||||
Event.WorkerMilliseconds,static_cast<unsigned long long>(Event.DensitySamples),
|
Event.WorkerMilliseconds,static_cast<unsigned long long>(Event.DensitySamples),
|
||||||
static_cast<unsigned long long>(D.fieldCalls),
|
static_cast<unsigned long long>(D.fieldCalls),
|
||||||
static_cast<unsigned long long>(D.passageTileFeatureCount),
|
static_cast<unsigned long long>(D.passageTileFeatureCount),
|
||||||
static_cast<unsigned long long>(D.passageTileRouteSegmentCandidates),
|
static_cast<unsigned long long>(D.passageTileRouteSegmentCandidates),
|
||||||
static_cast<unsigned long long>(D.passageTileMouthSegmentCandidates),
|
static_cast<unsigned long long>(D.passageTileMouthSegmentCandidates),
|
||||||
|
static_cast<unsigned long long>(D.resolvedBoundaryBandQueries),
|
||||||
static_cast<unsigned long long>(D.passageComposerQueries),
|
static_cast<unsigned long long>(D.passageComposerQueries),
|
||||||
static_cast<unsigned long long>(D.passageIterations),
|
static_cast<unsigned long long>(D.passageIterations),
|
||||||
static_cast<unsigned long long>(D.passageTileBoundChecks),
|
static_cast<unsigned long long>(D.passageTileBoundChecks),
|
||||||
|
|||||||
Reference in new issue
Block a user