Patch Detail
Show a patch.
GET /api/patches/26234/?format=api
{ "id": 26234, "url": "https://patchwork.libcamera.org/api/patches/26234/?format=api", "web_url": "https://patchwork.libcamera.org/patch/26234/", "project": { "id": 1, "url": "https://patchwork.libcamera.org/api/projects/1/?format=api", "name": "libcamera", "link_name": "libcamera", "list_id": "libcamera_core", "list_email": "libcamera-devel@lists.libcamera.org", "web_url": "", "scm_url": "", "webscm_url": "" }, "msgid": "<20260224193745.106186-3-johannes.goede@oss.qualcomm.com>", "date": "2026-02-24T19:37:43", "name": "[v3,2/4] software_isp: debayer_cpu: Add DebayerCpuThread class", "commit_ref": null, "pull_url": null, "state": "superseded", "archived": false, "hash": "eca36a2799375a0dd7f83f667f03f1efc0ffd2af", "submitter": { "id": 242, "url": "https://patchwork.libcamera.org/api/people/242/?format=api", "name": "Hans de Goede", "email": "johannes.goede@oss.qualcomm.com" }, "delegate": null, "mbox": "https://patchwork.libcamera.org/patch/26234/mbox/", "series": [ { "id": 5811, "url": "https://patchwork.libcamera.org/api/series/5811/?format=api", "web_url": "https://patchwork.libcamera.org/project/libcamera/list/?series=5811", "date": "2026-02-24T19:37:41", "name": "software_isp: debayer_cpu: Add multi-threading support", "version": 3, "mbox": "https://patchwork.libcamera.org/series/5811/mbox/" } ], "comments": "https://patchwork.libcamera.org/api/patches/26234/comments/", "check": "pending", "checks": "https://patchwork.libcamera.org/api/patches/26234/checks/", "tags": {}, "headers": { "Return-Path": "<libcamera-devel-bounces@lists.libcamera.org>", "X-Original-To": "parsemail@patchwork.libcamera.org", "Delivered-To": "parsemail@patchwork.libcamera.org", "Received": [ "from lancelot.ideasonboard.com (lancelot.ideasonboard.com\n\t[92.243.16.209])\n\tby patchwork.libcamera.org (Postfix) with ESMTPS id 8C8D5C32C8\n\tfor <parsemail@patchwork.libcamera.org>;\n\tTue, 24 Feb 2026 19:37:56 +0000 (UTC)", "from lancelot.ideasonboard.com (localhost [IPv6:::1])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTP id 93841622AD;\n\tTue, 24 Feb 2026 20:37:55 +0100 (CET)", "from mx0b-0031df01.pphosted.com (mx0b-0031df01.pphosted.com\n\t[205.220.180.131])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTPS id 513F9622B1\n\tfor <libcamera-devel@lists.libcamera.org>;\n\tTue, 24 Feb 2026 20:37:52 +0100 (CET)", "from pps.filterd (m0279868.ppops.net [127.0.0.1])\n\tby mx0a-0031df01.pphosted.com (8.18.1.11/8.18.1.11) with ESMTP id\n\t61OFQZ8P3177060 for <libcamera-devel@lists.libcamera.org>;\n\tTue, 24 Feb 2026 19:37:51 GMT", "from mail-qk1-f198.google.com (mail-qk1-f198.google.com\n\t[209.85.222.198])\n\tby mx0a-0031df01.pphosted.com (PPS) with ESMTPS id 4chemnry0k-1\n\t(version=TLSv1.3 cipher=TLS_AES_128_GCM_SHA256 bits=128 verify=NOT)\n\tfor <libcamera-devel@lists.libcamera.org>;\n\tTue, 24 Feb 2026 19:37:50 +0000 (GMT)", "by mail-qk1-f198.google.com with SMTP id\n\taf79cd13be357-8cb42f56c4aso5291949185a.3\n\tfor <libcamera-devel@lists.libcamera.org>;\n\tTue, 24 Feb 2026 11:37:50 -0800 (PST)", "from shalem\n\t(2001-1c00-0c32-7800-5bfa-a036-83f0-f9ec.cable.dynamic.v6.ziggo.nl.\n\t[2001:1c00:c32:7800:5bfa:a036:83f0:f9ec])\n\tby smtp.gmail.com with ESMTPSA id\n\ta640c23a62f3a-b9084e8cb3fsm458232866b.48.2026.02.24.11.37.48\n\t(version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n\tTue, 24 Feb 2026 11:37:48 -0800 (PST)" ], "Authentication-Results": "lancelot.ideasonboard.com; dkim=pass (2048-bit key;\n\tunprotected) header.d=qualcomm.com header.i=@qualcomm.com\n\theader.b=\"bC9KGrlC\"; dkim=pass (2048-bit key;\n\tunprotected) header.d=oss.qualcomm.com header.i=@oss.qualcomm.com\n\theader.b=\"Zyv8KsDt\"; dkim-atps=neutral", "DKIM-Signature": [ "v=1; a=rsa-sha256; c=relaxed/relaxed; d=qualcomm.com; h=\n\tcc:content-transfer-encoding:date:from:in-reply-to:message-id\n\t:mime-version:references:subject:to; s=qcppdkim1; bh=me+HBKUkDgV\n\tdYQngZuHh24uEVJQAqxiMU3chL38HdgA=; b=bC9KGrlCv3XOaXOJl07CrWb8q6E\n\tg1S9MpMrEnbO1HIGDJcDPz59GLCBvnCnaRl6JZWaxtd0GKe6Zmkcmu6i4XhmI1N5\n\tp/2L1/GT1hhBvLQZZfVklsFXuG9kQXd9JxBNPJZ5WbY3MjPx0g7r399DFkB7qAGC\n\tJkWjlqJwCh9JaipObsObg+uD9fLTSt/Lx0OZdq5P5kt4JCb4rvcmeBWs9SdCRr7B\n\tyoy4h8fG1NsJL1Tx8kMPVukSeckLf7LGRUWw4fCMhgtCV92eMRk/+DjCAwA4oQI0\n\trH4hnFMeYsheq3J60A6h8tdpPS+4mzT/imri7R8xiyHvI1GnvbqujniAIXQ==", "v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=oss.qualcomm.com; s=google; t=1771961870; x=1772566670;\n\tdarn=lists.libcamera.org; \n\th=content-transfer-encoding:mime-version:references:in-reply-to\n\t:message-id:date:subject:cc:to:from:from:to:cc:subject:date\n\t:message-id:reply-to;\n\tbh=me+HBKUkDgVdYQngZuHh24uEVJQAqxiMU3chL38HdgA=;\n\tb=Zyv8KsDtnyu+320MNNR8lQsdx6IDr/JEzx74xqpc8DNfyU6HC7isSJ5piNd33gOM5G\n\tFPDvgBavTDKs8B40YTNjlhD0I7Lcrc71mBPVE82DEMrXN/BtuE07d+bk73P8CJtozIU2\n\txXrngx1W6VXgBrlWKW2Mj1tpOPnslvhRs2ZAmqlvmCrlpQFPR7XoWilihjZ+lmb1MNbP\n\tI2F/PDflHFM0cLdADvsOhjOX7bXni7IzNZSatePJKApFoCEO/OSe8zURGh393NAObWUf\n\t73gI8xI0Uo1mUt+X68GNyWOv553zVp33AIW/vJA/KXZU7hrz7320CgtpRhOgQqRhMWqj\n\tMj2w==" ], "X-Google-DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20230601; t=1771961870; x=1772566670;\n\th=content-transfer-encoding:mime-version:references:in-reply-to\n\t:message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from\n\t:to:cc:subject:date:message-id:reply-to;\n\tbh=me+HBKUkDgVdYQngZuHh24uEVJQAqxiMU3chL38HdgA=;\n\tb=eoZ7stHzWJvuBMHZJNqhggnZxIExm4now6fODZbxWIIQO6O3/OxGgoifZCoZHpDk5/\n\tgkA4cei9klnrjop0zkqC0lk76n5wiLS+s1Nb7V2FBo8FZZEbR6J+5Z4MzOE5yCfOr8IH\n\tz2bF3VWlOr7u4ap7CQ7up/a2wBHNmGo9/kSphjqe/kFdVGI/ab0RJdDYjATfV3dx9KFj\n\tIQHBMHk99kBH3UHteiaS9W0HiFOVP3KB/SVJzx5/BHikljbg3c8dVTXglPXQoZjkoTLo\n\tshbm1i0DXDs+zkRQahAZQYSqPB3auCdc7Wtqhb1ZSGAj+FYVKKBHlYOZterxrj2UzWzo\n\tJqAA==", "X-Gm-Message-State": "AOJu0YyjMhH56lywqpL9Mm1uEK1prqmoGzub+qHdVyQF2JoPurK7Wf05\n\tVygm+2gHdQsY4XD2g8LyGDKwy0rkAJZ0qtmHUVcG/lyVaix4Ey+XFVHBQKwP6itQri4Z/OacRYv\n\t06aNQEErJxOCV4Xy5giZIYsmYU4SCrisgpYOBt4pkomxgGst1AmK9ZOUqnUomN8Ku/HFNjK+GWp\n\tKbYIWuLMIr", "X-Gm-Gg": "AZuq6aKVO8+6uASheRkNOdn//2a3G8p6OPkKQGIb+ZShOBzq9aivcNuYXamLuu0yQ5z\n\tFfXnYRySU3QsHEIPB+yfvu5wlquM+6Y2+7B5DEFf3O8DIk8R51LugvWzCzxPHckRHPLYBGFLAoX\n\tzcbzlhvAtGAEHC2dgqO9teLnpMOWW2ulBXPg3nLTRcE4np04VDQtayKJPnv4/8rbORLtzGsHhh0\n\t4HXCdExC0XtQ2CpQzgOBbO9hua58NbBmIViuQGEyqwkgCYF9k4W+NUAaAKWDvXKY++b/3tLK7r7\n\tsvj4U8b/CTEky2ln6Fu2vhVqXosRh89uTVWQMi89GiiRmLqMW34JU9BMW94ftDUtATRNUrAmF5r\n\tMhIoOpZn71YIUmJwi34XwNNfcknUWB8pCi+HSTbZo1vLJAqyFM4pat7+qShK6OxpHkbITR7H3gJ\n\tq5sdcdYipYVVV+4MWfrV9nO7/Fts+/szMfSvtx", "X-Received": [ "by 2002:a05:620a:f0d:b0:8ca:2a04:3ff3 with SMTP id\n\taf79cd13be357-8cb8ca03fe5mr1726073185a.30.1771961869804; \n\tTue, 24 Feb 2026 11:37:49 -0800 (PST)", "by 2002:a05:620a:f0d:b0:8ca:2a04:3ff3 with SMTP id\n\taf79cd13be357-8cb8ca03fe5mr1726068185a.30.1771961869063; \n\tTue, 24 Feb 2026 11:37:49 -0800 (PST)" ], "From": "Hans de Goede <johannes.goede@oss.qualcomm.com>", "To": "libcamera-devel@lists.libcamera.org, Milan Zamazal <mzamazal@redhat.com>", "Cc": "Hans de Goede <johannes.goede@oss.qualcomm.com>", "Subject": "[PATCH v3 2/4] software_isp: debayer_cpu: Add DebayerCpuThread class", "Date": "Tue, 24 Feb 2026 20:37:43 +0100", "Message-ID": "<20260224193745.106186-3-johannes.goede@oss.qualcomm.com>", "X-Mailer": "git-send-email 2.52.0", "In-Reply-To": "<20260224193745.106186-1-johannes.goede@oss.qualcomm.com>", "References": "<20260224193745.106186-1-johannes.goede@oss.qualcomm.com>", "MIME-Version": "1.0", "Content-Transfer-Encoding": "8bit", "X-Proofpoint-Spam-Details-Enc": "AW1haW4tMjYwMjI0MDE2OCBTYWx0ZWRfX0xfvC0eBxnbf\n\tfATYZNK0GSo2SCm5R4DidTEqSPOhRUqc3GDqxngo54jucTR9BgZOVHtlTZl+5pczhO0UOzrLq5k\n\tQvSStBNWE5UOh426Q8jTtF0jVYqIwPuo8ALrvt/qZJ+YD4vIbKGBDBPwL9+ekDFi+5Kt/5RCkmZ\n\tAa8zbgjJ/CYlxo48lbzrJ3GaY8j9ZASxFP0y4eI2cxASD9d0s33wlDCViKBOJ5DHA5TnsD+7XDl\n\tMRtXmcBkzkQvbFmjcwm3I1JqGF9ndwOMMmf/IMkr5doU2rwamJrF9C2EcUiXyHYWNJczfOF37Wj\n\th0CIP1xKpmaeQumMqbjcpEKcBDRFxALd8CqEJ3rn5MqHNlXhbSu6YuYRRa7l60CfGZsB7sQkKlQ\n\tmQDWQKIVuDrmsI75dvPzRN7bRXdzAGFgvHOpFvyzUC70FGb/kQLZFlanoYPWcf1ohwItaVidXwz\n\tj1g1ZFWespV2BflEYvg==", "X-Proofpoint-ORIG-GUID": "UJCy6G2eL79Q09R1KrjsvfUNMsml0xzc", "X-Authority-Analysis": "v=2.4 cv=Ro7I7SmK c=1 sm=1 tr=0 ts=699dfe0e cx=c_pps\n\ta=qKBjSQ1v91RyAK45QCPf5w==:117 a=xqWC_Br6kY4A:10 a=HzLeVaNsDn8A:10\n\ta=s4-Qcg_JpJYA:10 a=VkNPw1HP01LnGYTKEx00:22 a=u7WPNUs3qKkmUXheDGA7:22\n\ta=ZpdpYltYx_vBUK5n70dp:22 a=EUspDBNiAAAA:8 a=Chkswc9nKTKKIei3T8UA:9\n\ta=NFOGd7dJGGMPyQGDc5-O:22", "X-Proofpoint-GUID": "UJCy6G2eL79Q09R1KrjsvfUNMsml0xzc", "X-Proofpoint-Virus-Version": "vendor=baseguard\n\tengine=ICAP:2.0.293, Aquarius:18.0.1121, Hydra:6.1.51,\n\tFMLib:17.12.100.49\n\tdefinitions=2026-02-24_02,2026-02-23_03,2025-10-01_01", "X-Proofpoint-Spam-Details": "rule=outbound_notspam policy=outbound score=0\n\tmalwarescore=0 clxscore=1015 spamscore=0 bulkscore=0 adultscore=0\n\timpostorscore=0 phishscore=0 lowpriorityscore=0 priorityscore=1501\n\tsuspectscore=0 classifier=typeunknown authscore=0 authtc= authcc=\n\troute=outbound adjust=0 reason=mlx scancount=1\n\tengine=8.22.0-2602130000\n\tdefinitions=main-2602240168", "X-BeenThere": "libcamera-devel@lists.libcamera.org", "X-Mailman-Version": "2.1.29", "Precedence": "list", "List-Id": "<libcamera-devel.lists.libcamera.org>", "List-Unsubscribe": "<https://lists.libcamera.org/options/libcamera-devel>,\n\t<mailto:libcamera-devel-request@lists.libcamera.org?subject=unsubscribe>", "List-Archive": "<https://lists.libcamera.org/pipermail/libcamera-devel/>", "List-Post": "<mailto:libcamera-devel@lists.libcamera.org>", "List-Help": "<mailto:libcamera-devel-request@lists.libcamera.org?subject=help>", "List-Subscribe": "<https://lists.libcamera.org/listinfo/libcamera-devel>,\n\t<mailto:libcamera-devel-request@lists.libcamera.org?subject=subscribe>", "Errors-To": "libcamera-devel-bounces@lists.libcamera.org", "Sender": "\"libcamera-devel\" <libcamera-devel-bounces@lists.libcamera.org>" }, "content": "Add a DebayerCpuThreadclass and use this in the inner render loop.\nThis contains data which needs to be separate per thread.\n\nThis is a preparation patch for making DebayerCpu support multi-threading.\n\nBenchmarking on the Arduino Uno-Q with a weak CPU which is good for\nperformance testing, shows 146-147ms per 3272x2464 frame both before and\nafter this change, with things maybe being 0.5 ms slower after this change.\n\nSigned-off-by: Hans de Goede <johannes.goede@oss.qualcomm.com>\n---\nChanges in v3:\n- Use std::unique_ptr for the DebayerCpuThread pointers\n- Document new DebayerCpuThread class\n- Make DebayerCpuThread inherit from both Thread and Object\n\nChanges in v2:\n- Replace the DebayerCpuThreadData struct from v1 with a DebayerCpuThread\n class, derived from Object to allow calling invokeMethod for thread re-use\n in followup patches\n- As part of this also move a bunch of methods which primarily deal with\n per thread data: setupInputMemcpy(), shiftLinePointers(), memcpyNextLine(),\n process*() to the new DebayerCpuThread class\n---\n src/libcamera/software_isp/debayer_cpu.cpp | 244 +++++++++++++++------\n src/libcamera/software_isp/debayer_cpu.h | 20 +-\n 2 files changed, 188 insertions(+), 76 deletions(-)", "diff": "diff --git a/src/libcamera/software_isp/debayer_cpu.cpp b/src/libcamera/software_isp/debayer_cpu.cpp\nindex e7b01210..36b7881b 100644\n--- a/src/libcamera/software_isp/debayer_cpu.cpp\n+++ b/src/libcamera/software_isp/debayer_cpu.cpp\n@@ -18,6 +18,8 @@\n \n #include <linux/dma-buf.h>\n \n+#include <libcamera/base/thread.h>\n+\n #include <libcamera/formats.h>\n \n #include \"libcamera/internal/bayer_format.h\"\n@@ -27,6 +29,52 @@\n \n namespace libcamera {\n \n+/**\n+ * \\brief Class representing one CPU debayering thread\n+ *\n+ * Implementation for CPU based debayering threads.\n+ */\n+class DebayerCpuThread : public Thread, public Object\n+{\n+public:\n+\tDebayerCpuThread(DebayerCpu *debayer, unsigned int threadIndex,\n+\t\t\t bool enableInputMemcpy);\n+\n+\tvoid configure(unsigned int yStart, unsigned int yEnd);\n+\tvoid process(uint32_t frame, const uint8_t *src, uint8_t *dst);\n+\n+private:\n+\tvoid setupInputMemcpy(const uint8_t *linePointers[]);\n+\tvoid shiftLinePointers(const uint8_t *linePointers[], const uint8_t *src);\n+\tvoid memcpyNextLine(const uint8_t *linePointers[]);\n+\tvoid process2(uint32_t frame, const uint8_t *src, uint8_t *dst);\n+\tvoid process4(uint32_t frame, const uint8_t *src, uint8_t *dst);\n+\n+\tDebayerCpu *debayer_;\n+\tunsigned int threadIndex_;\n+\tunsigned int yStart_;\n+\tunsigned int yEnd_;\n+\tunsigned int lineBufferLength_;\n+\tunsigned int lineBufferPadding_;\n+\tunsigned int lineBufferIndex_;\n+\tstd::vector<uint8_t> lineBuffers_[DebayerCpu::kMaxLineBuffers];\n+\tbool enableInputMemcpy_;\n+};\n+\n+/**\n+ * \\brief Construct a DebayerCpuThread object\n+ * \\param[in] debayer pointer back to the DebayerCpuObject this thread belongs to\n+ * \\param[in] threadIndex 0 .. n thread-index value for the thread\n+ * \\param[in] enableInputMemcpy when set copy input data to a heap buffer before use\n+ */\n+DebayerCpuThread::DebayerCpuThread(DebayerCpu *debayer, unsigned int threadIndex,\n+\t\t\t\t bool enableInputMemcpy)\n+\t: Thread(\"DebayerCpu:\" + std::to_string(threadIndex)),\n+\t debayer_(debayer), threadIndex_(threadIndex),\n+\t enableInputMemcpy_(enableInputMemcpy)\n+{\n+}\n+\n /**\n * \\class DebayerCpu\n * \\brief Class for debayering on the CPU\n@@ -53,8 +101,14 @@ DebayerCpu::DebayerCpu(std::unique_ptr<SwStatsCpu> stats, const GlobalConfigurat\n \t * \\todo Make memcpy automatic based on runtime detection of platform\n \t * capabilities.\n \t */\n-\tenableInputMemcpy_ =\n+\tbool enableInputMemcpy =\n \t\tconfiguration.option<bool>({ \"software_isp\", \"copy_input_buffer\" }).value_or(true);\n+\n+\t/* Just one thread object for now, which will be called inline rather than async */\n+\tthreads_.resize(1);\n+\n+\tfor (unsigned int i = 0; i < threads_.size(); i++)\n+\t\tthreads_[i] = std::make_unique<DebayerCpuThread>(this, i, enableInputMemcpy);\n }\n \n DebayerCpu::~DebayerCpu() = default;\n@@ -484,7 +538,7 @@ int DebayerCpu::configure(const StreamConfiguration &inputCfg,\n \tif (getInputConfig(inputCfg.pixelFormat, inputConfig_) != 0)\n \t\treturn -EINVAL;\n \n-\tif (stats_->configure(inputCfg) != 0)\n+\tif (stats_->configure(inputCfg, threads_.size()) != 0)\n \t\treturn -EINVAL;\n \n \tconst Size &statsPatternSize = stats_->patternSize();\n@@ -548,17 +602,43 @@ int DebayerCpu::configure(const StreamConfiguration &inputCfg,\n \t */\n \tstats_->setWindow(Rectangle(window_.size()));\n \n+\tunsigned int yStart = 0;\n+\tunsigned int linesPerThread = (window_.height / threads_.size()) &\n+\t\t\t\t ~(inputConfig_.patternSize.height - 1);\n+\tunsigned int i;\n+\n+\tfor (i = 0; i < (threads_.size() - 1); i++) {\n+\t\tthreads_[i]->configure(yStart, yStart + linesPerThread);\n+\t\tyStart += linesPerThread;\n+\t}\n+\tthreads_[i]->configure(yStart, window_.height);\n+\n+\treturn 0;\n+}\n+\n+/**\n+ * \\brief Configure thread to process a specific part of the image\n+ * \\param[in] yStart y coordinate of first line to process\n+ * \\param[in] yEnd y coordinate of the line at which to stop processing\n+ *\n+ * Configure the thread to process lines yStart - (yEnd - 1).\n+ */\n+void DebayerCpuThread::configure(unsigned int yStart, unsigned int yEnd)\n+{\n+\tDebayer::DebayerInputConfig &inputConfig = debayer_->inputConfig_;\n+\n+\tyStart_ = yStart;\n+\tyEnd_ = yEnd;\n+\n \t/* pad with patternSize.Width on both left and right side */\n-\tlineBufferPadding_ = inputConfig_.patternSize.width * inputConfig_.bpp / 8;\n-\tlineBufferLength_ = window_.width * inputConfig_.bpp / 8 +\n+\tlineBufferPadding_ = inputConfig.patternSize.width * inputConfig.bpp / 8;\n+\tlineBufferLength_ = debayer_->window_.width * inputConfig.bpp / 8 +\n \t\t\t 2 * lineBufferPadding_;\n \n \tif (enableInputMemcpy_) {\n-\t\tfor (unsigned int i = 0; i <= inputConfig_.patternSize.height; i++)\n+\t\tfor (unsigned int i = 0; i <= inputConfig.patternSize.height; i++)\n \t\t\tlineBuffers_[i].resize(lineBufferLength_);\n \t}\n-\n-\treturn 0;\n }\n \n /*\n@@ -599,9 +679,9 @@ DebayerCpu::strideAndFrameSize(const PixelFormat &outputFormat, const Size &size\n \treturn std::make_tuple(stride, stride * size.height);\n }\n \n-void DebayerCpu::setupInputMemcpy(const uint8_t *linePointers[])\n+void DebayerCpuThread::setupInputMemcpy(const uint8_t *linePointers[])\n {\n-\tconst unsigned int patternHeight = inputConfig_.patternSize.height;\n+\tconst unsigned int patternHeight = debayer_->inputConfig_.patternSize.height;\n \n \tif (!enableInputMemcpy_)\n \t\treturn;\n@@ -617,20 +697,20 @@ void DebayerCpu::setupInputMemcpy(const uint8_t *linePointers[])\n \tlineBufferIndex_ = patternHeight;\n }\n \n-void DebayerCpu::shiftLinePointers(const uint8_t *linePointers[], const uint8_t *src)\n+void DebayerCpuThread::shiftLinePointers(const uint8_t *linePointers[], const uint8_t *src)\n {\n-\tconst unsigned int patternHeight = inputConfig_.patternSize.height;\n+\tconst unsigned int patternHeight = debayer_->inputConfig_.patternSize.height;\n \n \tfor (unsigned int i = 0; i < patternHeight; i++)\n \t\tlinePointers[i] = linePointers[i + 1];\n \n-\tlinePointers[patternHeight] = src +\n-\t\t\t\t (patternHeight / 2) * (int)inputConfig_.stride;\n+\tlinePointers[patternHeight] =\n+\t\tsrc + (patternHeight / 2) * (int)debayer_->inputConfig_.stride;\n }\n \n-void DebayerCpu::memcpyNextLine(const uint8_t *linePointers[])\n+void DebayerCpuThread::memcpyNextLine(const uint8_t *linePointers[])\n {\n-\tconst unsigned int patternHeight = inputConfig_.patternSize.height;\n+\tconst unsigned int patternHeight = debayer_->inputConfig_.patternSize.height;\n \n \tif (!enableInputMemcpy_)\n \t\treturn;\n@@ -643,23 +723,48 @@ void DebayerCpu::memcpyNextLine(const uint8_t *linePointers[])\n \tlineBufferIndex_ = (lineBufferIndex_ + 1) % (patternHeight + 1);\n }\n \n-void DebayerCpu::process2(uint32_t frame, const uint8_t *src, uint8_t *dst)\n+/**\n+ * \\brief Process part of the image assigned to this debayer thread\n+ * \\param[in] frame The frame number\n+ * \\param[in] src The source buffer\n+ * \\param[in] dst The destination buffer\n+ */\n+void DebayerCpuThread::process(uint32_t frame, const uint8_t *src, uint8_t *dst)\n {\n-\tunsigned int yEnd = window_.height;\n+\tRectangle &window = debayer_->window_;\n+\n+\t/* Adjust src to top left corner of the window */\n+\tsrc += (window.y + yStart_) * debayer_->inputConfig_.stride +\n+\t window.x * debayer_->inputConfig_.bpp / 8;\n+\t/* Adjust dst for yStart_ */\n+\tdst += yStart_ * debayer_->outputConfig_.stride;\n+\n+\tif (debayer_->inputConfig_.patternSize.height == 2)\n+\t\tprocess2(frame, src, dst);\n+\telse\n+\t\tprocess4(frame, src, dst);\n+}\n+\n+void DebayerCpuThread::process2(uint32_t frame, const uint8_t *src, uint8_t *dst)\n+{\n+\tunsigned int outputStride = debayer_->outputConfig_.stride;\n+\tunsigned int inputStride = debayer_->inputConfig_.stride;\n+\tRectangle &window = debayer_->window_;\n+\tunsigned int yEnd = yEnd_;\n \t/* Holds [0] previous- [1] current- [2] next-line */\n \tconst uint8_t *linePointers[3];\n \n-\t/* Adjust src to top left corner of the window */\n-\tsrc += window_.y * inputConfig_.stride + window_.x * inputConfig_.bpp / 8;\n-\n \t/* [x] becomes [x - 1] after initial shiftLinePointers() call */\n-\tif (window_.y) {\n-\t\tlinePointers[1] = src - inputConfig_.stride; /* previous-line */\n+\tif (window.y + yStart_) {\n+\t\tlinePointers[1] = src - inputStride; /* previous-line */\n \t\tlinePointers[2] = src;\n \t} else {\n-\t\t/* window_.y == 0, use the next line as prev line */\n-\t\tlinePointers[1] = src + inputConfig_.stride;\n+\t\t/* Top line, use the next line as prev line */\n+\t\tlinePointers[1] = src + inputStride;\n \t\tlinePointers[2] = src;\n+\t}\n+\n+\tif (window.y == 0 && yEnd_ == window.height) {\n \t\t/*\n \t\t * Last 2 lines also need special handling.\n \t\t * (And configure() ensures that yEnd >= 2.)\n@@ -669,83 +774,93 @@ void DebayerCpu::process2(uint32_t frame, const uint8_t *src, uint8_t *dst)\n \n \tsetupInputMemcpy(linePointers);\n \n-\tfor (unsigned int y = 0; y < yEnd; y += 2) {\n+\t/*\n+\t * Note y is the line-number *inside* the window, since stats_' window\n+\t * is the stats window inside/relative to the debayer window. IOW for\n+\t * single thread rendering y goes from 0 to window.height.\n+\t */\n+\tfor (unsigned int y = yStart_; y < yEnd; y += 2) {\n \t\tshiftLinePointers(linePointers, src);\n \t\tmemcpyNextLine(linePointers);\n-\t\tstats_->processLine0(frame, y, linePointers);\n-\t\t(this->*debayer0_)(dst, linePointers);\n-\t\tsrc += inputConfig_.stride;\n-\t\tdst += outputConfig_.stride;\n+\t\tdebayer_->stats_->processLine0(frame, y, linePointers, threadIndex_);\n+\t\tdebayer_->debayer0(dst, linePointers);\n+\t\tsrc += inputStride;\n+\t\tdst += outputStride;\n \n \t\tshiftLinePointers(linePointers, src);\n \t\tmemcpyNextLine(linePointers);\n-\t\t(this->*debayer1_)(dst, linePointers);\n-\t\tsrc += inputConfig_.stride;\n-\t\tdst += outputConfig_.stride;\n+\t\tdebayer_->debayer1(dst, linePointers);\n+\t\tsrc += inputStride;\n+\t\tdst += outputStride;\n \t}\n \n-\tif (window_.y == 0) {\n+\tif (window.y == 0 && yEnd_ == window.height) {\n \t\tshiftLinePointers(linePointers, src);\n \t\tmemcpyNextLine(linePointers);\n-\t\tstats_->processLine0(frame, yEnd, linePointers);\n-\t\t(this->*debayer0_)(dst, linePointers);\n-\t\tsrc += inputConfig_.stride;\n-\t\tdst += outputConfig_.stride;\n+\t\tdebayer_->stats_->processLine0(frame, yEnd, linePointers, threadIndex_);\n+\t\tdebayer_->debayer0(dst, linePointers);\n+\t\tsrc += inputStride;\n+\t\tdst += outputStride;\n \n \t\tshiftLinePointers(linePointers, src);\n \t\t/* next line may point outside of src, use prev. */\n \t\tlinePointers[2] = linePointers[0];\n-\t\t(this->*debayer1_)(dst, linePointers);\n-\t\tsrc += inputConfig_.stride;\n-\t\tdst += outputConfig_.stride;\n+\t\tdebayer_->debayer1(dst, linePointers);\n+\t\tsrc += inputStride;\n+\t\tdst += outputStride;\n \t}\n }\n \n-void DebayerCpu::process4(uint32_t frame, const uint8_t *src, uint8_t *dst)\n+void DebayerCpuThread::process4(uint32_t frame, const uint8_t *src, uint8_t *dst)\n {\n+\tunsigned int outputStride = debayer_->outputConfig_.stride;\n+\tunsigned int inputStride = debayer_->inputConfig_.stride;\n+\n \t/*\n \t * This holds pointers to [0] 2-lines-up [1] 1-line-up [2] current-line\n \t * [3] 1-line-down [4] 2-lines-down.\n \t */\n \tconst uint8_t *linePointers[5];\n \n-\t/* Adjust src to top left corner of the window */\n-\tsrc += window_.y * inputConfig_.stride + window_.x * inputConfig_.bpp / 8;\n-\n \t/* [x] becomes [x - 1] after initial shiftLinePointers() call */\n-\tlinePointers[1] = src - 2 * inputConfig_.stride;\n-\tlinePointers[2] = src - inputConfig_.stride;\n+\tlinePointers[1] = src - 2 * inputStride;\n+\tlinePointers[2] = src - inputStride;\n \tlinePointers[3] = src;\n-\tlinePointers[4] = src + inputConfig_.stride;\n+\tlinePointers[4] = src + inputStride;\n \n \tsetupInputMemcpy(linePointers);\n \n-\tfor (unsigned int y = 0; y < window_.height; y += 4) {\n+\t/*\n+\t * Note y is the line-number *inside* the window, since stats_' window\n+\t * is the stats window inside/relative to the debayer window. IOW for\n+\t * single thread rendering y goes from 0 to window.height.\n+\t */\n+\tfor (unsigned int y = yStart_; y < yEnd_; y += 4) {\n \t\tshiftLinePointers(linePointers, src);\n \t\tmemcpyNextLine(linePointers);\n-\t\tstats_->processLine0(frame, y, linePointers);\n-\t\t(this->*debayer0_)(dst, linePointers);\n-\t\tsrc += inputConfig_.stride;\n-\t\tdst += outputConfig_.stride;\n+\t\tdebayer_->stats_->processLine0(frame, y, linePointers, threadIndex_);\n+\t\tdebayer_->debayer0(dst, linePointers);\n+\t\tsrc += inputStride;\n+\t\tdst += outputStride;\n \n \t\tshiftLinePointers(linePointers, src);\n \t\tmemcpyNextLine(linePointers);\n-\t\t(this->*debayer1_)(dst, linePointers);\n-\t\tsrc += inputConfig_.stride;\n-\t\tdst += outputConfig_.stride;\n+\t\tdebayer_->debayer1(dst, linePointers);\n+\t\tsrc += inputStride;\n+\t\tdst += outputStride;\n \n \t\tshiftLinePointers(linePointers, src);\n \t\tmemcpyNextLine(linePointers);\n-\t\tstats_->processLine2(frame, y, linePointers);\n-\t\t(this->*debayer2_)(dst, linePointers);\n-\t\tsrc += inputConfig_.stride;\n-\t\tdst += outputConfig_.stride;\n+\t\tdebayer_->stats_->processLine2(frame, y, linePointers, threadIndex_);\n+\t\tdebayer_->debayer2(dst, linePointers);\n+\t\tsrc += inputStride;\n+\t\tdst += outputStride;\n \n \t\tshiftLinePointers(linePointers, src);\n \t\tmemcpyNextLine(linePointers);\n-\t\t(this->*debayer3_)(dst, linePointers);\n-\t\tsrc += inputConfig_.stride;\n-\t\tdst += outputConfig_.stride;\n+\t\tdebayer_->debayer3(dst, linePointers);\n+\t\tsrc += inputStride;\n+\t\tdst += outputStride;\n \t}\n }\n \n@@ -867,10 +982,7 @@ void DebayerCpu::process(uint32_t frame, FrameBuffer *input, FrameBuffer *output\n \n \tstats_->startFrame(frame);\n \n-\tif (inputConfig_.patternSize.height == 2)\n-\t\tprocess2(frame, in.planes()[0].data(), out.planes()[0].data());\n-\telse\n-\t\tprocess4(frame, in.planes()[0].data(), out.planes()[0].data());\n+\tthreads_[0]->process(frame, in.planes()[0].data(), out.planes()[0].data());\n \n \tmetadata.planes()[0].bytesused = out.planes()[0].size();\n \ndiff --git a/src/libcamera/software_isp/debayer_cpu.h b/src/libcamera/software_isp/debayer_cpu.h\nindex 7a651746..1074bc9c 100644\n--- a/src/libcamera/software_isp/debayer_cpu.h\n+++ b/src/libcamera/software_isp/debayer_cpu.h\n@@ -26,6 +26,7 @@\n \n namespace libcamera {\n \n+class DebayerCpuThread;\n class DebayerCpu : public Debayer\n {\n public:\n@@ -44,6 +45,8 @@ public:\n \tconst SharedFD &getStatsFD() { return stats_->getStatsFD(); }\n \n private:\n+\tfriend class DebayerCpuThread;\n+\n \t/**\n \t * \\brief Called to debayer 1 line of Bayer input data to output format\n \t * \\param[out] dst Pointer to the start of the output line to write\n@@ -74,6 +77,11 @@ private:\n \t */\n \tusing debayerFn = void (DebayerCpu::*)(uint8_t *dst, const uint8_t *src[]);\n \n+\tvoid debayer0(uint8_t *dst, const uint8_t *src[]) { (this->*debayer0_)(dst, src); }\n+\tvoid debayer1(uint8_t *dst, const uint8_t *src[]) { (this->*debayer1_)(dst, src); }\n+\tvoid debayer2(uint8_t *dst, const uint8_t *src[]) { (this->*debayer2_)(dst, src); }\n+\tvoid debayer3(uint8_t *dst, const uint8_t *src[]) { (this->*debayer3_)(dst, src); }\n+\n \t/* 8-bit raw bayer format */\n \ttemplate<bool addAlphaByte, bool ccmEnabled>\n \tvoid debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n@@ -105,11 +113,6 @@ private:\n \tint setDebayerFunctions(PixelFormat inputFormat,\n \t\t\t\tPixelFormat outputFormat,\n \t\t\t\tbool ccmEnabled);\n-\tvoid setupInputMemcpy(const uint8_t *linePointers[]);\n-\tvoid shiftLinePointers(const uint8_t *linePointers[], const uint8_t *src);\n-\tvoid memcpyNextLine(const uint8_t *linePointers[]);\n-\tvoid process2(uint32_t frame, const uint8_t *src, uint8_t *dst);\n-\tvoid process4(uint32_t frame, const uint8_t *src, uint8_t *dst);\n \tvoid updateGammaTable(const DebayerParams ¶ms);\n \tvoid updateLookupTables(const DebayerParams ¶ms);\n \n@@ -142,12 +145,9 @@ private:\n \tdebayerFn debayer3_;\n \tRectangle window_;\n \tstd::unique_ptr<SwStatsCpu> stats_;\n-\tstd::vector<uint8_t> lineBuffers_[kMaxLineBuffers];\n-\tunsigned int lineBufferLength_;\n-\tunsigned int lineBufferPadding_;\n-\tunsigned int lineBufferIndex_;\n \tunsigned int xShift_; /* Offset of 0/1 applied to window_.x */\n-\tbool enableInputMemcpy_;\n+\n+\tstd::vector<std::unique_ptr<DebayerCpuThread>>threads_;\n };\n \n } /* namespace libcamera */\n", "prefixes": [ "v3", "2/4" ] }