PawletOS/external_libcamera
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

software_isp: swstats_cpu: Prepare for multi-threading support

Browse Source 
Make the storage used to accumulate the RGB sums and the Y histogram
value a vector of SwIspStats objects instead of a single object so
that when using multi-threading every thread can use its own storage to
collect intermediate stats to avoid cache-line bouncing.

Benchmarking with the GPU-ISP which does separate swstats benchmarking,
on the Arduino Uno-Q which has a weak CPU which is good for performance
testing, shows 20ms to generate stats for a 3272x2464 frame both before
and after this change.

Reviewed-by: Milan Zamazal <mzamazal@redhat.com>
Signed-off-by: Hans de Goede <johannes.goede@oss.qualcomm.com>
Signed-off-by: Kieran Bingham <kieran.bingham@ideasonboard.com>
This commit is contained in:
Hans de Goede
2026-03-10 13:01:02 +01:00
committed by Kieran Bingham
parent 2a1c75504c
commit 6e53e72e96
2 changed files with 54 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/libcamera/internal/software_isp/swstats_cpu.h
+13 -12
View File
@@ -12,6 +12,7 @@
#pragma once
#include <stdint.h>
#include <vector>
#include <libcamera/base/signal.h>
@@ -51,13 +52,13 @@ public:
const Size &patternSize() { return patternSize_; }
int configure(const StreamConfiguration &inputCfg);
int configure(const StreamConfiguration &inputCfg, unsigned int statsBufferCount = 1);
void setWindow(const Rectangle &window);
void startFrame(uint32_t frame);
void finishFrame(uint32_t frame, uint32_t bufferId);
void processFrame(uint32_t frame, uint32_t bufferId, FrameBuffer *input);
void processLine0(uint32_t frame, unsigned int y, const uint8_t *src[])
void processLine0(uint32_t frame, unsigned int y, const uint8_t *src[], unsigned int statsBufferIndex = 0)
{
if (frame % kStatPerNumFrames)
return;
@@ -66,10 +67,10 @@ public:
y >= (window_.y + window_.height))
return;
(this->*stats0_)(src);
(this->*stats0_)(src, stats_[statsBufferIndex]);
}
void processLine2(uint32_t frame, unsigned int y, const uint8_t *src[])
void processLine2(uint32_t frame, unsigned int y, const uint8_t *src[], unsigned int statsBufferIndex = 0)
{
if (frame % kStatPerNumFrames)
return;
@@ -78,25 +79,25 @@ public:
y >= (window_.y + window_.height))
return;
(this->*stats2_)(src);
(this->*stats2_)(src, stats_[statsBufferIndex]);
}
Signal<uint32_t, uint32_t> statsReady;
private:
using statsProcessFn = void (SwStatsCpu::*)(const uint8_t *src[]);
using statsProcessFn = void (SwStatsCpu::*)(const uint8_t *src[], SwIspStats &stats);
using processFrameFn = void (SwStatsCpu::*)(MappedFrameBuffer &in);
int setupStandardBayerOrder(BayerFormat::Order order);
/* Bayer 8 bpp unpacked */
void statsBGGR8Line0(const uint8_t *src[]);
void statsBGGR8Line0(const uint8_t *src[], SwIspStats &stats);
/* Bayer 10 bpp unpacked */
void statsBGGR10Line0(const uint8_t *src[]);
void statsBGGR10Line0(const uint8_t *src[], SwIspStats &stats);
/* Bayer 12 bpp unpacked */
void statsBGGR12Line0(const uint8_t *src[]);
void statsBGGR12Line0(const uint8_t *src[], SwIspStats &stats);
/* Bayer 10 bpp packed */
void statsBGGR10PLine0(const uint8_t *src[]);
void statsGBRG10PLine0(const uint8_t *src[]);
void statsBGGR10PLine0(const uint8_t *src[], SwIspStats &stats);
void statsGBRG10PLine0(const uint8_t *src[], SwIspStats &stats);
void processBayerFrame2(MappedFrameBuffer &in);
@@ -116,8 +117,8 @@ private:
unsigned int xShift_;
unsigned int stride_;
std::vector<SwIspStats> stats_;
SharedMemObject<SwIspStats> sharedStats_;
SwIspStats stats_;
Benchmark bench_;
};