mirror of
https://github.com/slsdetectorgroup/aare.git
synced 2026-11-01 00:21:29 +01:00
kferjaouiandClaude Opus 5.5
e80e552497
perf/hist/ mirrors perf/cf/: a driver that runs each config under nsys, the traced process, settings and a README. The fill (H2D + fill_bin_major per frame) and the readout (bin_to_pixel_major + one D2H per values()) are reported separately. Only one chunk of frames is held in host memory and re-queued until the requested frame count. gpu_span.analyze() takes an optional engines subset, so the one-off readout D2H doesn't count towards the fill window or roofline. Default output is unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
28 lines
862 B
Python
28 lines
862 B
Python
"""PixelHistogramCUDA-specific settings for the probes in this folder.
|
|
|
|
Importing this module also makes ../common.py and ../gpu_span.py importable.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
HERE = Path(__file__).resolve().parent
|
|
sys.path.insert(0, str(HERE.parent))
|
|
import common # noqa: E402
|
|
|
|
# Rebuild-guard: the extension must be newer than all of these.
|
|
HEADERS = ["include/aare/hist/PixelHistogramCUDA.hpp",
|
|
"include/aare/hist/pixelhistogram_kernel.cuh",
|
|
"include/aare/RAII_device.hpp"]
|
|
|
|
# Kernel short names in the trace. The fill kernel runs once per batch; the
|
|
# readout kernel once per values() call.
|
|
FILL_KERNEL = "fill_bin_major"
|
|
READOUT_KERNEL = "bin_to_pixel_major"
|
|
|
|
|
|
def results_dir(tag: str = "") -> Path:
|
|
"""hist/results/<date>[_tag]/"""
|
|
return common.results_dir(HERE, "", tag)
|