From 6c509a3d144d46a11454d32d128d16e16602b50f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 11 Mar 2024 15:15:20 +0100 Subject: [PATCH 17/21] libcamera: Add "Software ISP benchmarking" documentation Add a "Software ISP benchmarking" documentation section which describes the performance/power consumption measurements used during the Software ISP's development. Reviewed-by: Milan Zamazal Signed-off-by: Hans de Goede Reviewed-by: Stefan Klug --- Documentation/index.rst | 1 + Documentation/meson.build | 1 + Documentation/software-isp-benchmarking.rst | 82 +++++++++++++++++++++ 3 files changed, 84 insertions(+) create mode 100644 Documentation/software-isp-benchmarking.rst diff --git a/Documentation/index.rst b/Documentation/index.rst index 63fac72d..5442ae75 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -24,3 +24,4 @@ Lens driver requirements Python Bindings Camera Sensor Model + SoftwareISP Benchmarking diff --git a/Documentation/meson.build b/Documentation/meson.build index 7a58fec8..3872e0a8 100644 --- a/Documentation/meson.build +++ b/Documentation/meson.build @@ -80,6 +80,7 @@ if sphinx.found() 'lens_driver_requirements.rst', 'python-bindings.rst', 'sensor_driver_requirements.rst', + 'software-isp-benchmarking.rst', '../README.rst', ] diff --git a/Documentation/software-isp-benchmarking.rst b/Documentation/software-isp-benchmarking.rst new file mode 100644 index 00000000..b2803953 --- /dev/null +++ b/Documentation/software-isp-benchmarking.rst @@ -0,0 +1,82 @@ +.. SPDX-License-Identifier: CC-BY-SA-4.0 + +.. _software-isp-benchmarking: + +Software ISP benchmarking +========================= + +The Software ISP is particularly sensitive to performance regressions +therefore it is a good idea to always benchmark the Software ISP +before and after making changes to it and ensure that there are +no performance regressions. + +DebayerCpu class builtin benchmark +---------------------------------- + +The DebayerCpu class has a builtin benchmark. This benchmark +measures the time spent on processing (collecting statistics +and debayering) only, it does not measure the time spent on +capturing or outputting the frames. + +The builtin benchmark always runs. So this can be used by simply +running "cam" or "qcam" with a pipeline using the Software ISP. + +When it runs it will skip measuring the first 30 frames to +allow the caches and the CPU temperature (turbo-ing) to warm-up +and then it measures 30 fps and shows the total and per frame +processing time using an info level log message: + +.. code-block:: text + + INFO Debayer debayer_cpu.cpp:907 Processed 30 frames in 244317us, 8143 us/frame + +To get stable measurements it is advised to disable any other processes which +may cause significant CPU usage (e.g. disable wifi, bluetooth and browsers). +When possible it is also advisable to disable CPU turbo-ing and +frequency-scaling. + +For example when benchmarking on a Lenovo ThinkPad X1 Yoga Gen 8, with +the charger plugged in, the CPU can be fixed to run at 2 GHz using: + +.. code-block:: shell + + sudo x86_energy_perf_policy --turbo-enable 0 + sudo cpupower frequency-set -d 2GHz -u 2GHz + +with these settings the builtin bench reports a processing time of ~7.8ms/frame +on this laptop for FHD SGRBG10 (unpacked) bayer data. + +Measuring power consumption +--------------------------- + +Since the Software ISP is often used on mobile devices it is also +important to measure power consumption and ensure that that does +not regress. + +For example to measure power consumption on a Lenovo ThinkPad X1 Yoga Gen 8 +it needs to be running on battery and it should be configured with its +platform-profile (/sys/firmware/acpi/platform_profile) set to balanced and +with its default turbo and frequency-scaling behavior to match real world usage. + +Then start qcam to capture a FHD picture at 30 fps and position the qcam window +so that it is fully visible. After this run the following command to monitor +the power consumption: + +.. code-block:: shell + + watch -n 10 cat /sys/class/power_supply/BAT0/power_now /sys/class/hwmon/hwmon6/fan?_input + +Note this not only measures the power consumption in µW it also monitors +the speed of this laptop's 2 fans. This is important because depending on +the ambient temperature the 2 fans may spin up while testing and this +will cause an additional power consumption of approx. 0.5 W messing up +the measurement. + +After starting qcam + the watch command let the laptop sit without using +it for 2 minutes for the readings to stabilize. Then check that the fans +have not turned on and manually take a couple of consecutive power readings +and avarage these. + +On the example Lenovo ThinkPad X1 Yoga Gen 8 laptop this results in +a measured power consumption of approx. 13 W while running qcam versus +approx. 4-5 W while setting idle with its OLED panel on. -- 2.43.2