[{"id":30025,"web_url":"https://patchwork.libcamera.org/comment/30025/","msgid":"<87iky6jewc.fsf@redhat.com>","date":"2024-06-18T18:15:47","subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","submitter":{"id":177,"url":"https://patchwork.libcamera.org/api/people/177/","name":"Milan Zamazal","email":"mzamazal@redhat.com"},"content":"Robert Mader writes:\n\n> In order to be more compatible with modern hardware and APIs. This\n> notably allows GL implementations to directly import the buffers more\n> often and seems to be required for Wayland.\n>\n> Further more, as we already enforce a 8 byte stride, these formats work\n> better for clients that don't support padding - such as libwebrtc at the\n> time of writing.\n>\n> Tested devices:\n> - Librem5\n> - PinePhone\n> - Thinkpad X13s\n>\n> Signed-off-by: Robert Mader \n> Tested-by: Kieran Bingham \n>\n> ---\n>\n> Changes in v3:\n> - Remove previously introduced variable again and use C++ templates\n> instead in order to avoid runtime costs\n> - Small cleanups and linting fixes\n>\n> Changes in v2:\n> - Reduce code duplication by using a runtime variable instead\n> - Small cleanups\n\nHi Robert,\n\nthis looks much better, thank you.\n\nReviewed-by: Milan Zamazal \n\n> ---\n> src/libcamera/software_isp/debayer_cpu.cpp | 75 +++++++++++++++++-----\n> src/libcamera/software_isp/debayer_cpu.h | 10 +++\n> 2 files changed, 69 insertions(+), 16 deletions(-)\n>\n> diff --git a/src/libcamera/software_isp/debayer_cpu.cpp b/src/libcamera/software_isp/debayer_cpu.cpp\n> index c038eed4..f8d2677d 100644\n> --- a/src/libcamera/software_isp/debayer_cpu.cpp\n> +++ b/src/libcamera/software_isp/debayer_cpu.cpp\n> @@ -74,6 +74,8 @@ DebayerCpu::~DebayerCpu()\n> \t*dst++ = blue_[curr[x] / (div)]; \\\n> \t*dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n> \t*dst++ = red_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n> +\tif constexpr (addAlphaByte) \\\n> +\t\t*dst++ = 255; \\\n> \tx++;\n> \n> /*\n> @@ -85,6 +87,8 @@ DebayerCpu::~DebayerCpu()\n> \t*dst++ = blue_[(prev[x] + next[x]) / (2 * (div))]; \\\n> \t*dst++ = green_[curr[x] / (div)]; \\\n> \t*dst++ = red_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n> +\tif constexpr (addAlphaByte) \\\n> +\t\t*dst++ = 255; \\\n> \tx++;\n> \n> /*\n> @@ -96,6 +100,8 @@ DebayerCpu::~DebayerCpu()\n> \t*dst++ = blue_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n> \t*dst++ = green_[curr[x] / (div)]; \\\n> \t*dst++ = red_[(prev[x] + next[x]) / (2 * (div))]; \\\n> +\tif constexpr (addAlphaByte) \\\n> +\t\t*dst++ = 255; \\\n> \tx++;\n> \n> /*\n> @@ -107,8 +113,11 @@ DebayerCpu::~DebayerCpu()\n> \t*dst++ = blue_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n> \t*dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n> \t*dst++ = red_[curr[x] / (div)]; \\\n> +\tif constexpr (addAlphaByte) \\\n> +\t\t*dst++ = 255; \\\n> \tx++;\n> \n> +template\n> void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint8_t)\n> @@ -119,6 +128,7 @@ void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint8_t)\n> @@ -129,6 +139,7 @@ void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint16_t)\n> @@ -140,6 +151,7 @@ void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint16_t)\n> @@ -151,6 +163,7 @@ void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint16_t)\n> @@ -162,6 +175,7 @@ void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint16_t)\n> @@ -173,6 +187,7 @@ void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tconst int widthInBytes = window_.width * 5 / 4;\n> @@ -198,6 +213,7 @@ void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tconst int widthInBytes = window_.width * 5 / 4;\n> @@ -218,6 +234,7 @@ void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tconst int widthInBytes = window_.width * 5 / 4;\n> @@ -238,6 +255,7 @@ void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tconst int widthInBytes = window_.width * 5 / 4;\n> @@ -280,7 +298,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n> \t\tconfig.bpp = (bayerFormat.bitDepth + 7) & ~7;\n> \t\tconfig.patternSize.width = 2;\n> \t\tconfig.patternSize.height = 2;\n> -\t\tconfig.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n> +\t\tconfig.outputFormats = std::vector({ formats::RGB888,\n> +\t\t\t\t\t\t\t\t formats::XRGB8888,\n> +\t\t\t\t\t\t\t\t formats::ARGB8888,\n> +\t\t\t\t\t\t\t\t formats::BGR888,\n> +\t\t\t\t\t\t\t\t formats::XBGR8888,\n> +\t\t\t\t\t\t\t\t formats::ABGR8888 });\n> \t\treturn 0;\n> \t}\n> \n> @@ -290,7 +313,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n> \t\tconfig.bpp = 10;\n> \t\tconfig.patternSize.width = 4; /* 5 bytes per *4* pixels */\n> \t\tconfig.patternSize.height = 2;\n> -\t\tconfig.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n> +\t\tconfig.outputFormats = std::vector({ formats::RGB888,\n> +\t\t\t\t\t\t\t\t formats::XRGB8888,\n> +\t\t\t\t\t\t\t\t formats::ARGB8888,\n> +\t\t\t\t\t\t\t\t formats::BGR888,\n> +\t\t\t\t\t\t\t\t formats::XBGR8888,\n> +\t\t\t\t\t\t\t\t formats::ABGR8888 });\n> \t\treturn 0;\n> \t}\n> \n> @@ -306,6 +334,12 @@ int DebayerCpu::getOutputConfig(PixelFormat outputFormat, DebayerOutputConfig &c\n> \t\treturn 0;\n> \t}\n> \n> +\tif (outputFormat == formats::XRGB8888 || outputFormat == formats::ARGB8888 ||\n> +\t outputFormat == formats::XBGR8888 || outputFormat == formats::ABGR8888) {\n> +\t\tconfig.bpp = 32;\n> +\t\treturn 0;\n> +\t}\n> +\n> \tLOG(Debayer, Info)\n> \t\t<< \"Unsupported output format \" << outputFormat.toString();\n> \treturn -EINVAL;\n> @@ -341,6 +375,7 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> {\n> \tBayerFormat bayerFormat =\n> \t\tBayerFormat::fromPixelFormat(inputFormat);\n> +\tbool addAlphaByte = false;\n> \n> \txShift_ = 0;\n> \tswapRedBlueGains_ = false;\n> @@ -351,8 +386,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> \t};\n> \n> \tswitch (outputFormat) {\n> +\tcase formats::XRGB8888:\n> +\tcase formats::ARGB8888:\n> +\t\taddAlphaByte = true;\n> +\t\t[[fallthrough]];\n> \tcase formats::RGB888:\n> \t\tbreak;\n> +\tcase formats::XBGR8888:\n> +\tcase formats::ABGR8888:\n> +\t\taddAlphaByte = true;\n> +\t\t[[fallthrough]];\n> \tcase formats::BGR888:\n> \t\t/* Swap R and B in bayer order to generate BGR888 instead of RGB888 */\n> \t\tswapRedBlueGains_ = true;\n> @@ -383,16 +426,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> \t isStandardBayerOrder(bayerFormat.order)) {\n> \t\tswitch (bayerFormat.bitDepth) {\n> \t\tcase 8:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer8_BGBG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer8_GRGR_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer8_BGBG_BGR888 : &DebayerCpu::debayer8_BGBG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer8_GRGR_BGR888 : &DebayerCpu::debayer8_GRGR_BGR888;\n> \t\t\tbreak;\n> \t\tcase 10:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10_BGBG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10_GRGR_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10_BGBG_BGR888 : &DebayerCpu::debayer10_BGBG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10_GRGR_BGR888 : &DebayerCpu::debayer10_GRGR_BGR888;\n> \t\t\tbreak;\n> \t\tcase 12:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer12_BGBG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer12_GRGR_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer12_BGBG_BGR888 : &DebayerCpu::debayer12_BGBG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer12_GRGR_BGR888 : &DebayerCpu::debayer12_GRGR_BGR888;\n> \t\t\tbreak;\n> \t\t}\n> \t\tsetupStandardBayerOrder(bayerFormat.order);\n> @@ -403,20 +446,20 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> \t bayerFormat.packing == BayerFormat::Packing::CSI2) {\n> \t\tswitch (bayerFormat.order) {\n> \t\tcase BayerFormat::BGGR:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n> \t\t\treturn 0;\n> \t\tcase BayerFormat::GBRG:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n> \t\t\treturn 0;\n> \t\tcase BayerFormat::GRBG:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n> \t\t\treturn 0;\n> \t\tcase BayerFormat::RGGB:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n> \t\t\treturn 0;\n> \t\tdefault:\n> \t\t\tbreak;\n> diff --git a/src/libcamera/software_isp/debayer_cpu.h b/src/libcamera/software_isp/debayer_cpu.h\n> index be7dcdca..1dac6435 100644\n> --- a/src/libcamera/software_isp/debayer_cpu.h\n> +++ b/src/libcamera/software_isp/debayer_cpu.h\n> @@ -85,18 +85,28 @@ private:\n> \tusing debayerFn = void (DebayerCpu::*)(uint8_t *dst, const uint8_t *src[]);\n> \n> \t/* 8-bit raw bayer format */\n> +\ttemplate\n> \tvoid debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> \t/* unpacked 10-bit raw bayer format */\n> +\ttemplate\n> \tvoid debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> \t/* unpacked 12-bit raw bayer format */\n> +\ttemplate\n> \tvoid debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> \t/* CSI-2 packed 10-bit raw bayer format (all the 4 orders) */\n> +\ttemplate\n> \tvoid debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> \n> \tstruct DebayerInputConfig {","headers":{"Return-Path":"","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 24898BD87C\n\tfor ;\n\tTue, 18 Jun 2024 18:15:56 +0000 (UTC)","from lancelot.ideasonboard.com (localhost [IPv6:::1])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTP id 2D327654A4;\n\tTue, 18 Jun 2024 20:15:55 +0200 (CEST)","from us-smtp-delivery-124.mimecast.com\n\t(us-smtp-delivery-124.mimecast.com [170.10.129.124])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTPS id 65DA661A1F\n\tfor ;\n\tTue, 18 Jun 2024 20:15:53 +0200 (CEST)","from mail-lj1-f198.google.com (mail-lj1-f198.google.com\n\t[209.85.208.198]) by relay.mimecast.com with ESMTP with STARTTLS\n\t(version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id\n\tus-mta-549-wwKUEFPuNQG9u8qO5-LcRQ-1; Tue, 18 Jun 2024 14:15:50 -0400","by mail-lj1-f198.google.com with SMTP id\n\t38308e7fff4ca-2ec0397ff31so45377361fa.3\n\tfor ;\n\tTue, 18 Jun 2024 11:15:50 -0700 (PDT)","from nuthatch (ip-77-48-47-2.net.vodafone.cz. [77.48.47.2])\n\tby smtp.gmail.com with ESMTPSA id\n\t5b1f17b1804b1-422f6320bfdsm196840125e9.37.2024.06.18.11.15.47\n\t(version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n\tTue, 18 Jun 2024 11:15:47 -0700 (PDT)"],"Authentication-Results":"lancelot.ideasonboard.com; dkim=pass (1024-bit key;\n\tunprotected) header.d=redhat.com header.i=@redhat.com\n\theader.b=\"K0Vx7KHZ\"; dkim-atps=neutral","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com;\n\ts=mimecast20190719; t=1718734552;\n\th=from:from:reply-to:subject:subject:date:date:message-id:message-id:\n\tto:to:cc:cc:mime-version:mime-version:content-type:content-type:\n\tin-reply-to:in-reply-to:references:references;\n\tbh=Q43ArtLNCa1m27UCJV0bxyh4sy0f86fZPMX7oYkEFk8=;\n\tb=K0Vx7KHZ9SHP8wl7rmQrsKxk2SUmbk0TkayRVlh1ZbnHPuGU7srHy4TUc/t2A8KYPPkLmm\n\tHVWMONVAoisv8gNxkzj161mlnHtszu0go08k6UKcYFwZTQVl6bfz6JW4aQtuQ+2OoR6/7u\n\tF2754LqQH/qjQBAaC4Aucnbs/1tQVY8=","X-MC-Unique":"wwKUEFPuNQG9u8qO5-LcRQ-1","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20230601; t=1718734549; x=1719339349;\n\th=mime-version:user-agent:message-id:date:references:in-reply-to\n\t:subject:cc:to:from:x-gm-message-state:from:to:cc:subject:date\n\t:message-id:reply-to;\n\tbh=Q43ArtLNCa1m27UCJV0bxyh4sy0f86fZPMX7oYkEFk8=;\n\tb=A9vASMCY8PUVpK3dhGBgvoonyXEBN2Q/j4Y97syf+3LFujeFa3YLp8oocNz/4uB4iS\n\tVfKb5NiQG2Pnt5isLMHaNS6KLeJXt7xFNlz/88deAsHVuXtGbEoH3lSJI0lmnnIh+tGO\n\txh46jSzi4d4U4z3OmJCiSolkDCwQkISy0YhOAxEeZhz73mWZKJeYWM8Y+qnCTgKuNUz9\n\ta4hNby6n/DRrUv2ph3CvJCVfHajeW4zkr1j+n91DLLtKcpBwI2NeZK6BeQ/D7jE+K/Jz\n\tbSXWo6ddLE0Wou4I/ozAXYzx/8I2l9rgZl/wmqdn+h/J1d8DCc0FgT4oqvvMJjdexYTb\n\teZIQ==","X-Gm-Message-State":"AOJu0YwW7toGQyNo8k97q5ohAs4/a1dtDrbiVaS0ajDD/pQIV91Jn2Tc\n\toET0QtWlFHGRkHYlbFkE6KtL6Q6gseiQ6dE67OgsSrhODm58pPokLkCx9f+p0mVM9RrXAE59eXW\n\tU+ElwJxIt0ZzDg5KXvCXKMMVE08ycffGvsH7yX+yfCpOD1eDFqz8SYlelZhfVadLkh5lMsUs=","X-Received":["by 2002:a2e:8904:0:b0:2ec:1dfc:45cd with SMTP id\n\t38308e7fff4ca-2ec3cea476cmr4054111fa.4.1718734549070; \n\tTue, 18 Jun 2024 11:15:49 -0700 (PDT)","by 2002:a2e:8904:0:b0:2ec:1dfc:45cd with SMTP id\n\t38308e7fff4ca-2ec3cea476cmr4053911fa.4.1718734548607; \n\tTue, 18 Jun 2024 11:15:48 -0700 (PDT)"],"X-Google-Smtp-Source":"AGHT+IFo4G6nUdhv6qWqilVZ7CmSiFjt8LooWunQgu0nkxqIW4fuXpnsuWjyGenr81bO9tgcO//Yig==","From":"Milan Zamazal ","To":"Robert Mader ","Cc":"libcamera-devel@lists.libcamera.org, Kieran Bingham\n\t","Subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","In-Reply-To":"<20240618063227.197989-1-robert.mader@collabora.com> (Robert\n\tMader's message of \"Tue, 18 Jun 2024 08:31:59 +0200\")","References":"<20240618063227.197989-1-robert.mader@collabora.com>","Date":"Tue, 18 Jun 2024 20:15:47 +0200","Message-ID":"<87iky6jewc.fsf@redhat.com>","User-Agent":"Gnus/5.13 (Gnus v5.13)","MIME-Version":"1.0","X-Mimecast-Spam-Score":"0","X-Mimecast-Originator":"redhat.com","Content-Type":"text/plain","X-BeenThere":"libcamera-devel@lists.libcamera.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Errors-To":"libcamera-devel-bounces@lists.libcamera.org","Sender":"\"libcamera-devel\" "}},{"id":30026,"web_url":"https://patchwork.libcamera.org/comment/30026/","msgid":"<171879106746.804094.663439147425782768@ping.linuxembedded.co.uk>","date":"2024-06-19T09:57:47","subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","submitter":{"id":4,"url":"https://patchwork.libcamera.org/api/people/4/","name":"Kieran Bingham","email":"kieran.bingham@ideasonboard.com"},"content":"Quoting Robert Mader (2024-06-18 07:31:59)\n> In order to be more compatible with modern hardware and APIs. This\n> notably allows GL implementations to directly import the buffers more\n> often and seems to be required for Wayland.\n> \n> Further more, as we already enforce a 8 byte stride, these formats work\n> better for clients that don't support padding - such as libwebrtc at the\n> time of writing.\n> \n> Tested devices:\n> - Librem5\n> - PinePhone\n> - Thinkpad X13s\n> \n> Signed-off-by: Robert Mader \n> Tested-by: Kieran Bingham \n\nRe-tested again on the x13s, and firefox-nightly.\n\nReviewed-by: Kieran Bingham \n\n\n> \n> ---\n> \n> Changes in v3:\n> - Remove previously introduced variable again and use C++ templates\n> instead in order to avoid runtime costs\n> - Small cleanups and linting fixes\n> \n> Changes in v2:\n> - Reduce code duplication by using a runtime variable instead\n> - Small cleanups\n> ---\n> src/libcamera/software_isp/debayer_cpu.cpp | 75 +++++++++++++++++-----\n> src/libcamera/software_isp/debayer_cpu.h | 10 +++\n> 2 files changed, 69 insertions(+), 16 deletions(-)\n> \n> diff --git a/src/libcamera/software_isp/debayer_cpu.cpp b/src/libcamera/software_isp/debayer_cpu.cpp\n> index c038eed4..f8d2677d 100644\n> --- a/src/libcamera/software_isp/debayer_cpu.cpp\n> +++ b/src/libcamera/software_isp/debayer_cpu.cpp\n> @@ -74,6 +74,8 @@ DebayerCpu::~DebayerCpu()\n> *dst++ = blue_[curr[x] / (div)]; \\\n> *dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n> *dst++ = red_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n> + if constexpr (addAlphaByte) \\\n> + *dst++ = 255; \\\n> x++;\n> \n> /*\n> @@ -85,6 +87,8 @@ DebayerCpu::~DebayerCpu()\n> *dst++ = blue_[(prev[x] + next[x]) / (2 * (div))]; \\\n> *dst++ = green_[curr[x] / (div)]; \\\n> *dst++ = red_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n> + if constexpr (addAlphaByte) \\\n> + *dst++ = 255; \\\n> x++;\n> \n> /*\n> @@ -96,6 +100,8 @@ DebayerCpu::~DebayerCpu()\n> *dst++ = blue_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n> *dst++ = green_[curr[x] / (div)]; \\\n> *dst++ = red_[(prev[x] + next[x]) / (2 * (div))]; \\\n> + if constexpr (addAlphaByte) \\\n> + *dst++ = 255; \\\n> x++;\n> \n> /*\n> @@ -107,8 +113,11 @@ DebayerCpu::~DebayerCpu()\n> *dst++ = blue_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n> *dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n> *dst++ = red_[curr[x] / (div)]; \\\n> + if constexpr (addAlphaByte) \\\n> + *dst++ = 255; \\\n> x++;\n> \n> +template\n> void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> DECLARE_SRC_POINTERS(uint8_t)\n> @@ -119,6 +128,7 @@ void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> }\n> }\n> \n> +template\n> void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> DECLARE_SRC_POINTERS(uint8_t)\n> @@ -129,6 +139,7 @@ void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> }\n> }\n> \n> +template\n> void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> DECLARE_SRC_POINTERS(uint16_t)\n> @@ -140,6 +151,7 @@ void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> }\n> }\n> \n> +template\n> void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> DECLARE_SRC_POINTERS(uint16_t)\n> @@ -151,6 +163,7 @@ void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> }\n> }\n> \n> +template\n> void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> DECLARE_SRC_POINTERS(uint16_t)\n> @@ -162,6 +175,7 @@ void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> }\n> }\n> \n> +template\n> void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> DECLARE_SRC_POINTERS(uint16_t)\n> @@ -173,6 +187,7 @@ void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> }\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> const int widthInBytes = window_.width * 5 / 4;\n> @@ -198,6 +213,7 @@ void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> }\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> const int widthInBytes = window_.width * 5 / 4;\n> @@ -218,6 +234,7 @@ void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> }\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> const int widthInBytes = window_.width * 5 / 4;\n> @@ -238,6 +255,7 @@ void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n> }\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> const int widthInBytes = window_.width * 5 / 4;\n> @@ -280,7 +298,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n> config.bpp = (bayerFormat.bitDepth + 7) & ~7;\n> config.patternSize.width = 2;\n> config.patternSize.height = 2;\n> - config.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n> + config.outputFormats = std::vector({ formats::RGB888,\n> + formats::XRGB8888,\n> + formats::ARGB8888,\n> + formats::BGR888,\n> + formats::XBGR8888,\n> + formats::ABGR8888 });\n> return 0;\n> }\n> \n> @@ -290,7 +313,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n> config.bpp = 10;\n> config.patternSize.width = 4; /* 5 bytes per *4* pixels */\n> config.patternSize.height = 2;\n> - config.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n> + config.outputFormats = std::vector({ formats::RGB888,\n> + formats::XRGB8888,\n> + formats::ARGB8888,\n> + formats::BGR888,\n> + formats::XBGR8888,\n> + formats::ABGR8888 });\n> return 0;\n> }\n> \n> @@ -306,6 +334,12 @@ int DebayerCpu::getOutputConfig(PixelFormat outputFormat, DebayerOutputConfig &c\n> return 0;\n> }\n> \n> + if (outputFormat == formats::XRGB8888 || outputFormat == formats::ARGB8888 ||\n> + outputFormat == formats::XBGR8888 || outputFormat == formats::ABGR8888) {\n> + config.bpp = 32;\n> + return 0;\n> + }\n> +\n> LOG(Debayer, Info)\n> << \"Unsupported output format \" << outputFormat.toString();\n> return -EINVAL;\n> @@ -341,6 +375,7 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> {\n> BayerFormat bayerFormat =\n> BayerFormat::fromPixelFormat(inputFormat);\n> + bool addAlphaByte = false;\n> \n> xShift_ = 0;\n> swapRedBlueGains_ = false;\n> @@ -351,8 +386,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> };\n> \n> switch (outputFormat) {\n> + case formats::XRGB8888:\n> + case formats::ARGB8888:\n> + addAlphaByte = true;\n> + [[fallthrough]];\n> case formats::RGB888:\n> break;\n> + case formats::XBGR8888:\n> + case formats::ABGR8888:\n> + addAlphaByte = true;\n> + [[fallthrough]];\n> case formats::BGR888:\n> /* Swap R and B in bayer order to generate BGR888 instead of RGB888 */\n> swapRedBlueGains_ = true;\n> @@ -383,16 +426,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> isStandardBayerOrder(bayerFormat.order)) {\n> switch (bayerFormat.bitDepth) {\n> case 8:\n> - debayer0_ = &DebayerCpu::debayer8_BGBG_BGR888;\n> - debayer1_ = &DebayerCpu::debayer8_GRGR_BGR888;\n> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer8_BGBG_BGR888 : &DebayerCpu::debayer8_BGBG_BGR888;\n> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer8_GRGR_BGR888 : &DebayerCpu::debayer8_GRGR_BGR888;\n> break;\n> case 10:\n> - debayer0_ = &DebayerCpu::debayer10_BGBG_BGR888;\n> - debayer1_ = &DebayerCpu::debayer10_GRGR_BGR888;\n> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10_BGBG_BGR888 : &DebayerCpu::debayer10_BGBG_BGR888;\n> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10_GRGR_BGR888 : &DebayerCpu::debayer10_GRGR_BGR888;\n> break;\n> case 12:\n> - debayer0_ = &DebayerCpu::debayer12_BGBG_BGR888;\n> - debayer1_ = &DebayerCpu::debayer12_GRGR_BGR888;\n> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer12_BGBG_BGR888 : &DebayerCpu::debayer12_BGBG_BGR888;\n> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer12_GRGR_BGR888 : &DebayerCpu::debayer12_GRGR_BGR888;\n> break;\n> }\n> setupStandardBayerOrder(bayerFormat.order);\n> @@ -403,20 +446,20 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> bayerFormat.packing == BayerFormat::Packing::CSI2) {\n> switch (bayerFormat.order) {\n> case BayerFormat::BGGR:\n> - debayer0_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n> - debayer1_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n> return 0;\n> case BayerFormat::GBRG:\n> - debayer0_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n> - debayer1_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n> return 0;\n> case BayerFormat::GRBG:\n> - debayer0_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n> - debayer1_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n> return 0;\n> case BayerFormat::RGGB:\n> - debayer0_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n> - debayer1_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n> return 0;\n> default:\n> break;\n> diff --git a/src/libcamera/software_isp/debayer_cpu.h b/src/libcamera/software_isp/debayer_cpu.h\n> index be7dcdca..1dac6435 100644\n> --- a/src/libcamera/software_isp/debayer_cpu.h\n> +++ b/src/libcamera/software_isp/debayer_cpu.h\n> @@ -85,18 +85,28 @@ private:\n> using debayerFn = void (DebayerCpu::*)(uint8_t *dst, const uint8_t *src[]);\n> \n> /* 8-bit raw bayer format */\n> + template\n> void debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> + template\n> void debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> /* unpacked 10-bit raw bayer format */\n> + template\n> void debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> + template\n> void debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> /* unpacked 12-bit raw bayer format */\n> + template\n> void debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> + template\n> void debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> /* CSI-2 packed 10-bit raw bayer format (all the 4 orders) */\n> + template\n> void debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> + template\n> void debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> + template\n> void debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[]);\n> + template\n> void debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> \n> struct DebayerInputConfig {\n> -- \n> 2.45.2\n>","headers":{"Return-Path":"","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 A6841BD87C\n\tfor ;\n\tWed, 19 Jun 2024 09:57:53 +0000 (UTC)","from lancelot.ideasonboard.com (localhost [IPv6:::1])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTP id A3D0B654A4;\n\tWed, 19 Jun 2024 11:57:52 +0200 (CEST)","from perceval.ideasonboard.com (perceval.ideasonboard.com\n\t[213.167.242.64])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTPS id 940D561A0F\n\tfor ;\n\tWed, 19 Jun 2024 11:57:50 +0200 (CEST)","from pendragon.ideasonboard.com\n\t(cpc89244-aztw30-2-0-cust6594.18-1.cable.virginm.net [86.31.185.195])\n\tby perceval.ideasonboard.com (Postfix) with ESMTPSA id 0CCE9F89;\n\tWed, 19 Jun 2024 11:57:32 +0200 (CEST)"],"Authentication-Results":"lancelot.ideasonboard.com; dkim=pass (1024-bit key;\n\tunprotected) header.d=ideasonboard.com header.i=@ideasonboard.com\n\theader.b=\"FtZlhUPO\"; dkim-atps=neutral","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/simple; d=ideasonboard.com;\n\ts=mail; t=1718791052;\n\tbh=MstAyhsyk9Lf01xNC9HFKfFBdNfRPJ94mSqcZmCYLAg=;\n\th=In-Reply-To:References:Subject:From:Cc:To:Date:From;\n\tb=FtZlhUPOEO53tVZCJLvg4GDapacibTArgOszEeSyTE5HVvNX/FK4W5GdMIHKM0jH5\n\tQYTbd1oiZGA/yO8Apqjl0hXdA/MJ9uxVa2xznAoyDk4Pu4czN1NZiAa6Kz2ZSU8uH3\n\t+xlVz3kEjqdIoLxsNvOn3OoyEuyGvnLUC1ub02H8=","Content-Type":"text/plain; charset=\"utf-8\"","MIME-Version":"1.0","Content-Transfer-Encoding":"quoted-printable","In-Reply-To":"<20240618063227.197989-1-robert.mader@collabora.com>","References":"<20240618063227.197989-1-robert.mader@collabora.com>","Subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","From":"Kieran Bingham ","Cc":"Robert Mader ","To":"Robert Mader ,\n\tlibcamera-devel@lists.libcamera.org","Date":"Wed, 19 Jun 2024 10:57:47 +0100","Message-ID":"<171879106746.804094.663439147425782768@ping.linuxembedded.co.uk>","User-Agent":"alot/0.10","X-BeenThere":"libcamera-devel@lists.libcamera.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Errors-To":"libcamera-devel-bounces@lists.libcamera.org","Sender":"\"libcamera-devel\" "}},{"id":30045,"web_url":"https://patchwork.libcamera.org/comment/30045/","msgid":"<3048b066-a927-4602-a783-e3f660ff018c@redhat.com>","date":"2024-06-24T09:37:52","subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","submitter":{"id":102,"url":"https://patchwork.libcamera.org/api/people/102/","name":"Hans de Goede","email":"hdegoede@redhat.com"},"content":"Hi,\n\nOn 6/18/24 8:31 AM, Robert Mader wrote:\n> In order to be more compatible with modern hardware and APIs. This\n> notably allows GL implementations to directly import the buffers more\n> often and seems to be required for Wayland.\n> \n> Further more, as we already enforce a 8 byte stride, these formats work\n> better for clients that don't support padding - such as libwebrtc at the\n> time of writing.\n> \n> Tested devices:\n> - Librem5\n> - PinePhone\n> - Thinkpad X13s\n> \n> Signed-off-by: Robert Mader \n> Tested-by: Kieran Bingham \n\nThanks, patch looks good to me:\n\nReviewed-by: Hans de Goede \n\nRegards,\n\nHans\n\n\n\n\n> \n> ---\n> \n> Changes in v3:\n> - Remove previously introduced variable again and use C++ templates\n> instead in order to avoid runtime costs\n> - Small cleanups and linting fixes\n> \n> Changes in v2:\n> - Reduce code duplication by using a runtime variable instead\n> - Small cleanups\n> ---\n> src/libcamera/software_isp/debayer_cpu.cpp | 75 +++++++++++++++++-----\n> src/libcamera/software_isp/debayer_cpu.h | 10 +++\n> 2 files changed, 69 insertions(+), 16 deletions(-)\n> \n> diff --git a/src/libcamera/software_isp/debayer_cpu.cpp b/src/libcamera/software_isp/debayer_cpu.cpp\n> index c038eed4..f8d2677d 100644\n> --- a/src/libcamera/software_isp/debayer_cpu.cpp\n> +++ b/src/libcamera/software_isp/debayer_cpu.cpp\n> @@ -74,6 +74,8 @@ DebayerCpu::~DebayerCpu()\n> \t*dst++ = blue_[curr[x] / (div)]; \\\n> \t*dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n> \t*dst++ = red_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n> +\tif constexpr (addAlphaByte) \\\n> +\t\t*dst++ = 255; \\\n> \tx++;\n> \n> /*\n> @@ -85,6 +87,8 @@ DebayerCpu::~DebayerCpu()\n> \t*dst++ = blue_[(prev[x] + next[x]) / (2 * (div))]; \\\n> \t*dst++ = green_[curr[x] / (div)]; \\\n> \t*dst++ = red_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n> +\tif constexpr (addAlphaByte) \\\n> +\t\t*dst++ = 255; \\\n> \tx++;\n> \n> /*\n> @@ -96,6 +100,8 @@ DebayerCpu::~DebayerCpu()\n> \t*dst++ = blue_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n> \t*dst++ = green_[curr[x] / (div)]; \\\n> \t*dst++ = red_[(prev[x] + next[x]) / (2 * (div))]; \\\n> +\tif constexpr (addAlphaByte) \\\n> +\t\t*dst++ = 255; \\\n> \tx++;\n> \n> /*\n> @@ -107,8 +113,11 @@ DebayerCpu::~DebayerCpu()\n> \t*dst++ = blue_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n> \t*dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n> \t*dst++ = red_[curr[x] / (div)]; \\\n> +\tif constexpr (addAlphaByte) \\\n> +\t\t*dst++ = 255; \\\n> \tx++;\n> \n> +template\n> void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint8_t)\n> @@ -119,6 +128,7 @@ void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint8_t)\n> @@ -129,6 +139,7 @@ void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint16_t)\n> @@ -140,6 +151,7 @@ void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint16_t)\n> @@ -151,6 +163,7 @@ void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint16_t)\n> @@ -162,6 +175,7 @@ void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tDECLARE_SRC_POINTERS(uint16_t)\n> @@ -173,6 +187,7 @@ void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tconst int widthInBytes = window_.width * 5 / 4;\n> @@ -198,6 +213,7 @@ void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tconst int widthInBytes = window_.width * 5 / 4;\n> @@ -218,6 +234,7 @@ void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tconst int widthInBytes = window_.width * 5 / 4;\n> @@ -238,6 +255,7 @@ void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n> \t}\n> }\n> \n> +template\n> void DebayerCpu::debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[])\n> {\n> \tconst int widthInBytes = window_.width * 5 / 4;\n> @@ -280,7 +298,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n> \t\tconfig.bpp = (bayerFormat.bitDepth + 7) & ~7;\n> \t\tconfig.patternSize.width = 2;\n> \t\tconfig.patternSize.height = 2;\n> -\t\tconfig.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n> +\t\tconfig.outputFormats = std::vector({ formats::RGB888,\n> +\t\t\t\t\t\t\t\t formats::XRGB8888,\n> +\t\t\t\t\t\t\t\t formats::ARGB8888,\n> +\t\t\t\t\t\t\t\t formats::BGR888,\n> +\t\t\t\t\t\t\t\t formats::XBGR8888,\n> +\t\t\t\t\t\t\t\t formats::ABGR8888 });\n> \t\treturn 0;\n> \t}\n> \n> @@ -290,7 +313,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n> \t\tconfig.bpp = 10;\n> \t\tconfig.patternSize.width = 4; /* 5 bytes per *4* pixels */\n> \t\tconfig.patternSize.height = 2;\n> -\t\tconfig.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n> +\t\tconfig.outputFormats = std::vector({ formats::RGB888,\n> +\t\t\t\t\t\t\t\t formats::XRGB8888,\n> +\t\t\t\t\t\t\t\t formats::ARGB8888,\n> +\t\t\t\t\t\t\t\t formats::BGR888,\n> +\t\t\t\t\t\t\t\t formats::XBGR8888,\n> +\t\t\t\t\t\t\t\t formats::ABGR8888 });\n> \t\treturn 0;\n> \t}\n> \n> @@ -306,6 +334,12 @@ int DebayerCpu::getOutputConfig(PixelFormat outputFormat, DebayerOutputConfig &c\n> \t\treturn 0;\n> \t}\n> \n> +\tif (outputFormat == formats::XRGB8888 || outputFormat == formats::ARGB8888 ||\n> +\t outputFormat == formats::XBGR8888 || outputFormat == formats::ABGR8888) {\n> +\t\tconfig.bpp = 32;\n> +\t\treturn 0;\n> +\t}\n> +\n> \tLOG(Debayer, Info)\n> \t\t<< \"Unsupported output format \" << outputFormat.toString();\n> \treturn -EINVAL;\n> @@ -341,6 +375,7 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> {\n> \tBayerFormat bayerFormat =\n> \t\tBayerFormat::fromPixelFormat(inputFormat);\n> +\tbool addAlphaByte = false;\n> \n> \txShift_ = 0;\n> \tswapRedBlueGains_ = false;\n> @@ -351,8 +386,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> \t};\n> \n> \tswitch (outputFormat) {\n> +\tcase formats::XRGB8888:\n> +\tcase formats::ARGB8888:\n> +\t\taddAlphaByte = true;\n> +\t\t[[fallthrough]];\n> \tcase formats::RGB888:\n> \t\tbreak;\n> +\tcase formats::XBGR8888:\n> +\tcase formats::ABGR8888:\n> +\t\taddAlphaByte = true;\n> +\t\t[[fallthrough]];\n> \tcase formats::BGR888:\n> \t\t/* Swap R and B in bayer order to generate BGR888 instead of RGB888 */\n> \t\tswapRedBlueGains_ = true;\n> @@ -383,16 +426,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> \t isStandardBayerOrder(bayerFormat.order)) {\n> \t\tswitch (bayerFormat.bitDepth) {\n> \t\tcase 8:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer8_BGBG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer8_GRGR_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer8_BGBG_BGR888 : &DebayerCpu::debayer8_BGBG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer8_GRGR_BGR888 : &DebayerCpu::debayer8_GRGR_BGR888;\n> \t\t\tbreak;\n> \t\tcase 10:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10_BGBG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10_GRGR_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10_BGBG_BGR888 : &DebayerCpu::debayer10_BGBG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10_GRGR_BGR888 : &DebayerCpu::debayer10_GRGR_BGR888;\n> \t\t\tbreak;\n> \t\tcase 12:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer12_BGBG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer12_GRGR_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer12_BGBG_BGR888 : &DebayerCpu::debayer12_BGBG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer12_GRGR_BGR888 : &DebayerCpu::debayer12_GRGR_BGR888;\n> \t\t\tbreak;\n> \t\t}\n> \t\tsetupStandardBayerOrder(bayerFormat.order);\n> @@ -403,20 +446,20 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> \t bayerFormat.packing == BayerFormat::Packing::CSI2) {\n> \t\tswitch (bayerFormat.order) {\n> \t\tcase BayerFormat::BGGR:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n> \t\t\treturn 0;\n> \t\tcase BayerFormat::GBRG:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n> \t\t\treturn 0;\n> \t\tcase BayerFormat::GRBG:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n> \t\t\treturn 0;\n> \t\tcase BayerFormat::RGGB:\n> -\t\t\tdebayer0_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n> -\t\t\tdebayer1_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n> +\t\t\tdebayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n> +\t\t\tdebayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n> \t\t\treturn 0;\n> \t\tdefault:\n> \t\t\tbreak;\n> diff --git a/src/libcamera/software_isp/debayer_cpu.h b/src/libcamera/software_isp/debayer_cpu.h\n> index be7dcdca..1dac6435 100644\n> --- a/src/libcamera/software_isp/debayer_cpu.h\n> +++ b/src/libcamera/software_isp/debayer_cpu.h\n> @@ -85,18 +85,28 @@ private:\n> \tusing debayerFn = void (DebayerCpu::*)(uint8_t *dst, const uint8_t *src[]);\n> \n> \t/* 8-bit raw bayer format */\n> +\ttemplate\n> \tvoid debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> \t/* unpacked 10-bit raw bayer format */\n> +\ttemplate\n> \tvoid debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> \t/* unpacked 12-bit raw bayer format */\n> +\ttemplate\n> \tvoid debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> \t/* CSI-2 packed 10-bit raw bayer format (all the 4 orders) */\n> +\ttemplate\n> \tvoid debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[]);\n> +\ttemplate\n> \tvoid debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> \n> \tstruct DebayerInputConfig {","headers":{"Return-Path":"","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 19B84BD87C\n\tfor ;\n\tMon, 24 Jun 2024 09:38:01 +0000 (UTC)","from lancelot.ideasonboard.com (localhost [IPv6:::1])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTP id C6ED0654A9;\n\tMon, 24 Jun 2024 11:37:59 +0200 (CEST)","from us-smtp-delivery-124.mimecast.com\n\t(us-smtp-delivery-124.mimecast.com [170.10.129.124])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTPS id 0E97F619EA\n\tfor ;\n\tMon, 24 Jun 2024 11:37:57 +0200 (CEST)","from mail-ed1-f72.google.com (mail-ed1-f72.google.com\n\t[209.85.208.72]) by relay.mimecast.com with ESMTP with STARTTLS\n\t(version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id\n\tus-mta-161-jCBSEf8gMUG8lb6cSo6piQ-1; Mon, 24 Jun 2024 05:37:55 -0400","by mail-ed1-f72.google.com with SMTP id\n\t4fb4d7f45d1cf-57d24c8f338so1831371a12.3\n\tfor ;\n\tMon, 24 Jun 2024 02:37:55 -0700 (PDT)","from [10.40.98.157] ([78.108.130.194])\n\tby smtp.gmail.com with ESMTPSA id\n\t4fb4d7f45d1cf-57d303d80f7sm4514583a12.8.2024.06.24.02.37.52\n\t(version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128);\n\tMon, 24 Jun 2024 02:37:52 -0700 (PDT)"],"Authentication-Results":"lancelot.ideasonboard.com; dkim=pass (1024-bit key;\n\tunprotected) header.d=redhat.com header.i=@redhat.com\n\theader.b=\"JgspyNTh\"; dkim-atps=neutral","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com;\n\ts=mimecast20190719; t=1719221876;\n\th=from:from:reply-to:subject:subject:date:date:message-id:message-id:\n\tto:to:cc:cc:mime-version:mime-version:content-type:content-type:\n\tcontent-transfer-encoding:content-transfer-encoding:\n\tin-reply-to:in-reply-to:references:references;\n\tbh=4QafEBwodfJ3jTBOf6LG6pKeH4Gi39+7IdEPgFCdl0w=;\n\tb=JgspyNThBk3ynCwaTMZeLA9acSsAYu+o9bX5mGSArbArQ6zRQm6G9mxOsXPf3HaQUcH00z\n\tERuTUOqCRqQxuVc20MxjfL6c9UNTUNIYWIRbO2/CWE00Qk4RBIt/HW+N4UqdS43VyfNM6D\n\tgPAMGFkZtoPfMUHmdVJOkMs+pvw7s/8=","X-MC-Unique":"jCBSEf8gMUG8lb6cSo6piQ-1","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20230601; t=1719221874; x=1719826674;\n\th=content-transfer-encoding:in-reply-to:from:content-language\n\t:references:cc:to:subject:user-agent:mime-version:date:message-id\n\t:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to;\n\tbh=4QafEBwodfJ3jTBOf6LG6pKeH4Gi39+7IdEPgFCdl0w=;\n\tb=Cgk7clljUTHGEJ8BrmMj8OcL5I/GIm0O1kRJj8l1hp3EJ3Me7+MwasII8HeI9XJitM\n\tKoTh/e98xnZy20RXzy8vDZH1WNT0fhHIWdIkr6DMZ4l20JDsXVsIvukDphDHX6ekM/j+\n\twLUNxIew2G3jCA6CowyDBbKmFefhHPuPy71ez6ll4r2AR4FlLc28iimZa233TcVOnJVv\n\tJeY4f431v3pmHaqF1d5Gjokxd0zrCkRJyqYux7jybEGDWTmIxl2tP7tM6Zfb7htWdbdR\n\tcCKU2WRra3yoT78qUySG/rNkH+D3Cr/jyBs93T5WpJA/OPf5wChu+foiVHR0gnr2J5nd\n\tn1mg==","X-Forwarded-Encrypted":"i=1;\n\tAJvYcCXYtCXloa/pY7NcJKxRTm92Gc0poo0rVYz/eVMw2FysJOKBAimflGek+vADmum20fP1hEYtLSd3I7uskS7QWb5gDqE9+beb4LqueIApkCHnJwvBxw==","X-Gm-Message-State":"AOJu0YwwTxygIYK6kkKPQSNqiFnJuJvIFTJ7dppptMc6cyQMcDZhMgXQ\n\tO1JP+9BrWfaJz5HHBKKxqzSSU7QnI/qxsuxObapXTBnvuN7JQaef+zmp29saNcyz1ePx5iUyWbg\n\tINik3Fd1GtT3vOJ+qRLO73C/GXEEheXu3FkGQC3kFpVC+M3OBnAm5ii8k5i5Tpu+PohDVFyxhqG\n\tCVZm8=","X-Received":["by 2002:a50:cd84:0:b0:57c:61a2:ed47 with SMTP id\n\t4fb4d7f45d1cf-57d4bd83130mr2316592a12.24.1719221873925; \n\tMon, 24 Jun 2024 02:37:53 -0700 (PDT)","by 2002:a50:cd84:0:b0:57c:61a2:ed47 with SMTP id\n\t4fb4d7f45d1cf-57d4bd83130mr2316583a12.24.1719221873396; \n\tMon, 24 Jun 2024 02:37:53 -0700 (PDT)"],"X-Google-Smtp-Source":"AGHT+IESaa/oAP9N3eyJaenlT6MvxiaG9EUr4B54s0avFWwzrQOD9AmjzghApKqa9lOhTGsEw0a33A==","Message-ID":"<3048b066-a927-4602-a783-e3f660ff018c@redhat.com>","Date":"Mon, 24 Jun 2024 11:37:52 +0200","MIME-Version":"1.0","User-Agent":"Mozilla Thunderbird","Subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","To":"Robert Mader ,\n\tlibcamera-devel@lists.libcamera.org","Cc":"Kieran Bingham ","References":"<20240618063227.197989-1-robert.mader@collabora.com>","From":"Hans de Goede ","In-Reply-To":"<20240618063227.197989-1-robert.mader@collabora.com>","X-Mimecast-Spam-Score":"0","X-Mimecast-Originator":"redhat.com","Content-Language":"en-US","Content-Type":"text/plain; charset=UTF-8","Content-Transfer-Encoding":"7bit","X-BeenThere":"libcamera-devel@lists.libcamera.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Errors-To":"libcamera-devel-bounces@lists.libcamera.org","Sender":"\"libcamera-devel\" "}},{"id":30049,"web_url":"https://patchwork.libcamera.org/comment/30049/","msgid":"<171922977962.341316.6814845742008517299@ping.linuxembedded.co.uk>","date":"2024-06-24T11:49:39","subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","submitter":{"id":4,"url":"https://patchwork.libcamera.org/api/people/4/","name":"Kieran Bingham","email":"kieran.bingham@ideasonboard.com"},"content":"Quoting Hans de Goede (2024-06-24 10:37:52)\n> Hi,\n> \n> On 6/18/24 8:31 AM, Robert Mader wrote:\n> > In order to be more compatible with modern hardware and APIs. This\n> > notably allows GL implementations to directly import the buffers more\n> > often and seems to be required for Wayland.\n> > \n> > Further more, as we already enforce a 8 byte stride, these formats work\n> > better for clients that don't support padding - such as libwebrtc at the\n> > time of writing.\n> > \n> > Tested devices:\n> > - Librem5\n> > - PinePhone\n> > - Thinkpad X13s\n> > \n> > Signed-off-by: Robert Mader \n> > Tested-by: Kieran Bingham \n> \n> Thanks, patch looks good to me:\n> \n> Reviewed-by: Hans de Goede \n\nThanks Hans,\n\nI'm sorry I can't add your tag though as I merged this last week.\n- https://git.libcamera.org/libcamera/libcamera.git/commit/?id=437e601653e69c82f5396979d99e7b9b5bb6086b\n\n--\nKieran\n\n\n> \n> Regards,\n> \n> Hans\n> \n> \n> \n> \n> > \n> > ---\n> > \n> > Changes in v3:\n> > - Remove previously introduced variable again and use C++ templates\n> > instead in order to avoid runtime costs\n> > - Small cleanups and linting fixes\n> > \n> > Changes in v2:\n> > - Reduce code duplication by using a runtime variable instead\n> > - Small cleanups\n> > ---\n> > src/libcamera/software_isp/debayer_cpu.cpp | 75 +++++++++++++++++-----\n> > src/libcamera/software_isp/debayer_cpu.h | 10 +++\n> > 2 files changed, 69 insertions(+), 16 deletions(-)\n> > \n> > diff --git a/src/libcamera/software_isp/debayer_cpu.cpp b/src/libcamera/software_isp/debayer_cpu.cpp\n> > index c038eed4..f8d2677d 100644\n> > --- a/src/libcamera/software_isp/debayer_cpu.cpp\n> > +++ b/src/libcamera/software_isp/debayer_cpu.cpp\n> > @@ -74,6 +74,8 @@ DebayerCpu::~DebayerCpu()\n> > *dst++ = blue_[curr[x] / (div)]; \\\n> > *dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n> > *dst++ = red_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n> > + if constexpr (addAlphaByte) \\\n> > + *dst++ = 255; \\\n> > x++;\n> > \n> > /*\n> > @@ -85,6 +87,8 @@ DebayerCpu::~DebayerCpu()\n> > *dst++ = blue_[(prev[x] + next[x]) / (2 * (div))]; \\\n> > *dst++ = green_[curr[x] / (div)]; \\\n> > *dst++ = red_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n> > + if constexpr (addAlphaByte) \\\n> > + *dst++ = 255; \\\n> > x++;\n> > \n> > /*\n> > @@ -96,6 +100,8 @@ DebayerCpu::~DebayerCpu()\n> > *dst++ = blue_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n> > *dst++ = green_[curr[x] / (div)]; \\\n> > *dst++ = red_[(prev[x] + next[x]) / (2 * (div))]; \\\n> > + if constexpr (addAlphaByte) \\\n> > + *dst++ = 255; \\\n> > x++;\n> > \n> > /*\n> > @@ -107,8 +113,11 @@ DebayerCpu::~DebayerCpu()\n> > *dst++ = blue_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n> > *dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n> > *dst++ = red_[curr[x] / (div)]; \\\n> > + if constexpr (addAlphaByte) \\\n> > + *dst++ = 255; \\\n> > x++;\n> > \n> > +template\n> > void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > DECLARE_SRC_POINTERS(uint8_t)\n> > @@ -119,6 +128,7 @@ void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> > }\n> > }\n> > \n> > +template\n> > void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > DECLARE_SRC_POINTERS(uint8_t)\n> > @@ -129,6 +139,7 @@ void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> > }\n> > }\n> > \n> > +template\n> > void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > DECLARE_SRC_POINTERS(uint16_t)\n> > @@ -140,6 +151,7 @@ void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> > }\n> > }\n> > \n> > +template\n> > void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > DECLARE_SRC_POINTERS(uint16_t)\n> > @@ -151,6 +163,7 @@ void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> > }\n> > }\n> > \n> > +template\n> > void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > DECLARE_SRC_POINTERS(uint16_t)\n> > @@ -162,6 +175,7 @@ void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> > }\n> > }\n> > \n> > +template\n> > void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > DECLARE_SRC_POINTERS(uint16_t)\n> > @@ -173,6 +187,7 @@ void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> > }\n> > }\n> > \n> > +template\n> > void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > const int widthInBytes = window_.width * 5 / 4;\n> > @@ -198,6 +213,7 @@ void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n> > }\n> > }\n> > \n> > +template\n> > void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > const int widthInBytes = window_.width * 5 / 4;\n> > @@ -218,6 +234,7 @@ void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n> > }\n> > }\n> > \n> > +template\n> > void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > const int widthInBytes = window_.width * 5 / 4;\n> > @@ -238,6 +255,7 @@ void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n> > }\n> > }\n> > \n> > +template\n> > void DebayerCpu::debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[])\n> > {\n> > const int widthInBytes = window_.width * 5 / 4;\n> > @@ -280,7 +298,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n> > config.bpp = (bayerFormat.bitDepth + 7) & ~7;\n> > config.patternSize.width = 2;\n> > config.patternSize.height = 2;\n> > - config.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n> > + config.outputFormats = std::vector({ formats::RGB888,\n> > + formats::XRGB8888,\n> > + formats::ARGB8888,\n> > + formats::BGR888,\n> > + formats::XBGR8888,\n> > + formats::ABGR8888 });\n> > return 0;\n> > }\n> > \n> > @@ -290,7 +313,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n> > config.bpp = 10;\n> > config.patternSize.width = 4; /* 5 bytes per *4* pixels */\n> > config.patternSize.height = 2;\n> > - config.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n> > + config.outputFormats = std::vector({ formats::RGB888,\n> > + formats::XRGB8888,\n> > + formats::ARGB8888,\n> > + formats::BGR888,\n> > + formats::XBGR8888,\n> > + formats::ABGR8888 });\n> > return 0;\n> > }\n> > \n> > @@ -306,6 +334,12 @@ int DebayerCpu::getOutputConfig(PixelFormat outputFormat, DebayerOutputConfig &c\n> > return 0;\n> > }\n> > \n> > + if (outputFormat == formats::XRGB8888 || outputFormat == formats::ARGB8888 ||\n> > + outputFormat == formats::XBGR8888 || outputFormat == formats::ABGR8888) {\n> > + config.bpp = 32;\n> > + return 0;\n> > + }\n> > +\n> > LOG(Debayer, Info)\n> > << \"Unsupported output format \" << outputFormat.toString();\n> > return -EINVAL;\n> > @@ -341,6 +375,7 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> > {\n> > BayerFormat bayerFormat =\n> > BayerFormat::fromPixelFormat(inputFormat);\n> > + bool addAlphaByte = false;\n> > \n> > xShift_ = 0;\n> > swapRedBlueGains_ = false;\n> > @@ -351,8 +386,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> > };\n> > \n> > switch (outputFormat) {\n> > + case formats::XRGB8888:\n> > + case formats::ARGB8888:\n> > + addAlphaByte = true;\n> > + [[fallthrough]];\n> > case formats::RGB888:\n> > break;\n> > + case formats::XBGR8888:\n> > + case formats::ABGR8888:\n> > + addAlphaByte = true;\n> > + [[fallthrough]];\n> > case formats::BGR888:\n> > /* Swap R and B in bayer order to generate BGR888 instead of RGB888 */\n> > swapRedBlueGains_ = true;\n> > @@ -383,16 +426,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> > isStandardBayerOrder(bayerFormat.order)) {\n> > switch (bayerFormat.bitDepth) {\n> > case 8:\n> > - debayer0_ = &DebayerCpu::debayer8_BGBG_BGR888;\n> > - debayer1_ = &DebayerCpu::debayer8_GRGR_BGR888;\n> > + debayer0_ = addAlphaByte ? &DebayerCpu::debayer8_BGBG_BGR888 : &DebayerCpu::debayer8_BGBG_BGR888;\n> > + debayer1_ = addAlphaByte ? &DebayerCpu::debayer8_GRGR_BGR888 : &DebayerCpu::debayer8_GRGR_BGR888;\n> > break;\n> > case 10:\n> > - debayer0_ = &DebayerCpu::debayer10_BGBG_BGR888;\n> > - debayer1_ = &DebayerCpu::debayer10_GRGR_BGR888;\n> > + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10_BGBG_BGR888 : &DebayerCpu::debayer10_BGBG_BGR888;\n> > + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10_GRGR_BGR888 : &DebayerCpu::debayer10_GRGR_BGR888;\n> > break;\n> > case 12:\n> > - debayer0_ = &DebayerCpu::debayer12_BGBG_BGR888;\n> > - debayer1_ = &DebayerCpu::debayer12_GRGR_BGR888;\n> > + debayer0_ = addAlphaByte ? &DebayerCpu::debayer12_BGBG_BGR888 : &DebayerCpu::debayer12_BGBG_BGR888;\n> > + debayer1_ = addAlphaByte ? &DebayerCpu::debayer12_GRGR_BGR888 : &DebayerCpu::debayer12_GRGR_BGR888;\n> > break;\n> > }\n> > setupStandardBayerOrder(bayerFormat.order);\n> > @@ -403,20 +446,20 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n> > bayerFormat.packing == BayerFormat::Packing::CSI2) {\n> > switch (bayerFormat.order) {\n> > case BayerFormat::BGGR:\n> > - debayer0_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n> > - debayer1_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n> > + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n> > + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n> > return 0;\n> > case BayerFormat::GBRG:\n> > - debayer0_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n> > - debayer1_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n> > + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n> > + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n> > return 0;\n> > case BayerFormat::GRBG:\n> > - debayer0_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n> > - debayer1_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n> > + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n> > + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n> > return 0;\n> > case BayerFormat::RGGB:\n> > - debayer0_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n> > - debayer1_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n> > + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n> > + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n> > return 0;\n> > default:\n> > break;\n> > diff --git a/src/libcamera/software_isp/debayer_cpu.h b/src/libcamera/software_isp/debayer_cpu.h\n> > index be7dcdca..1dac6435 100644\n> > --- a/src/libcamera/software_isp/debayer_cpu.h\n> > +++ b/src/libcamera/software_isp/debayer_cpu.h\n> > @@ -85,18 +85,28 @@ private:\n> > using debayerFn = void (DebayerCpu::*)(uint8_t *dst, const uint8_t *src[]);\n> > \n> > /* 8-bit raw bayer format */\n> > + template\n> > void debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > + template\n> > void debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > /* unpacked 10-bit raw bayer format */\n> > + template\n> > void debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > + template\n> > void debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > /* unpacked 12-bit raw bayer format */\n> > + template\n> > void debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > + template\n> > void debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > /* CSI-2 packed 10-bit raw bayer format (all the 4 orders) */\n> > + template\n> > void debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > + template\n> > void debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > + template\n> > void debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > + template\n> > void debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[]);\n> > \n> > struct DebayerInputConfig {\n>","headers":{"Return-Path":"","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 88A49BDB1D\n\tfor ;\n\tMon, 24 Jun 2024 11:49:43 +0000 (UTC)","from lancelot.ideasonboard.com (localhost [IPv6:::1])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTP id 2ABAC654A9;\n\tMon, 24 Jun 2024 13:49:43 +0200 (CEST)","from perceval.ideasonboard.com (perceval.ideasonboard.com\n\t[IPv6:2001:4b98:dc2:55:216:3eff:fef7:d647])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTPS id 3E553654A1\n\tfor ;\n\tMon, 24 Jun 2024 13:49:42 +0200 (CEST)","from pendragon.ideasonboard.com\n\t(cpc89244-aztw30-2-0-cust6594.18-1.cable.virginm.net [86.31.185.195])\n\tby perceval.ideasonboard.com (Postfix) with ESMTPSA id 8824D7E0;\n\tMon, 24 Jun 2024 13:49:20 +0200 (CEST)"],"Authentication-Results":"lancelot.ideasonboard.com; dkim=pass (1024-bit key;\n\tunprotected) header.d=ideasonboard.com header.i=@ideasonboard.com\n\theader.b=\"RKUnXCGU\"; dkim-atps=neutral","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/simple; d=ideasonboard.com;\n\ts=mail; t=1719229760;\n\tbh=26vpuvYRdxNE1QUKZmbnm4lN6FOF14c2/r2qrd27qSI=;\n\th=In-Reply-To:References:Subject:From:Cc:To:Date:From;\n\tb=RKUnXCGUV5FWj4l9pChxqxsPtl4j9a150shKs8kroTgUdtfI+EboHvEEa+eoUgNqk\n\tQzemeRiJvnFL5X8B20dKr9NLUJE57/Id4+kcSlCeopi2CZhE/9iOXeANMjb6GgY2Sm\n\tWuLxoIM/z53/lkusoDo23yZFfXAXvhKbAI/Bz9iE=","Content-Type":"text/plain; charset=\"utf-8\"","MIME-Version":"1.0","Content-Transfer-Encoding":"quoted-printable","In-Reply-To":"<3048b066-a927-4602-a783-e3f660ff018c@redhat.com>","References":"<20240618063227.197989-1-robert.mader@collabora.com>\n\t<3048b066-a927-4602-a783-e3f660ff018c@redhat.com>","Subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","From":"Kieran Bingham ","Cc":"","To":"Hans de Goede ,\n\tRobert Mader ,\n\tlibcamera-devel@lists.libcamera.org","Date":"Mon, 24 Jun 2024 12:49:39 +0100","Message-ID":"<171922977962.341316.6814845742008517299@ping.linuxembedded.co.uk>","User-Agent":"alot/0.10","X-BeenThere":"libcamera-devel@lists.libcamera.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Errors-To":"libcamera-devel-bounces@lists.libcamera.org","Sender":"\"libcamera-devel\" "}},{"id":30050,"web_url":"https://patchwork.libcamera.org/comment/30050/","msgid":"<7d34e67f-79f9-4bb7-b336-9f856ef41f12@redhat.com>","date":"2024-06-24T12:33:44","subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","submitter":{"id":102,"url":"https://patchwork.libcamera.org/api/people/102/","name":"Hans de Goede","email":"hdegoede@redhat.com"},"content":"Hi,\n\nOn 6/24/24 1:49 PM, Kieran Bingham wrote:\n> Quoting Hans de Goede (2024-06-24 10:37:52)\n>> Hi,\n>>\n>> On 6/18/24 8:31 AM, Robert Mader wrote:\n>>> In order to be more compatible with modern hardware and APIs. This\n>>> notably allows GL implementations to directly import the buffers more\n>>> often and seems to be required for Wayland.\n>>>\n>>> Further more, as we already enforce a 8 byte stride, these formats work\n>>> better for clients that don't support padding - such as libwebrtc at the\n>>> time of writing.\n>>>\n>>> Tested devices:\n>>> - Librem5\n>>> - PinePhone\n>>> - Thinkpad X13s\n>>>\n>>> Signed-off-by: Robert Mader \n>>> Tested-by: Kieran Bingham \n>>\n>> Thanks, patch looks good to me:\n>>\n>> Reviewed-by: Hans de Goede \n> \n> Thanks Hans,\n> \n> I'm sorry I can't add your tag though as I merged this last week.\n> - https://git.libcamera.org/libcamera/libcamera.git/commit/?id=437e601653e69c82f5396979d99e7b9b5bb6086b\n\nNo worries, good that it is already merged :)\n\nRegards,\n\nHans\n\n\n\n\n>>> ---\n>>>\n>>> Changes in v3:\n>>> - Remove previously introduced variable again and use C++ templates\n>>> instead in order to avoid runtime costs\n>>> - Small cleanups and linting fixes\n>>>\n>>> Changes in v2:\n>>> - Reduce code duplication by using a runtime variable instead\n>>> - Small cleanups\n>>> ---\n>>> src/libcamera/software_isp/debayer_cpu.cpp | 75 +++++++++++++++++-----\n>>> src/libcamera/software_isp/debayer_cpu.h | 10 +++\n>>> 2 files changed, 69 insertions(+), 16 deletions(-)\n>>>\n>>> diff --git a/src/libcamera/software_isp/debayer_cpu.cpp b/src/libcamera/software_isp/debayer_cpu.cpp\n>>> index c038eed4..f8d2677d 100644\n>>> --- a/src/libcamera/software_isp/debayer_cpu.cpp\n>>> +++ b/src/libcamera/software_isp/debayer_cpu.cpp\n>>> @@ -74,6 +74,8 @@ DebayerCpu::~DebayerCpu()\n>>> *dst++ = blue_[curr[x] / (div)]; \\\n>>> *dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n>>> *dst++ = red_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n>>> + if constexpr (addAlphaByte) \\\n>>> + *dst++ = 255; \\\n>>> x++;\n>>> \n>>> /*\n>>> @@ -85,6 +87,8 @@ DebayerCpu::~DebayerCpu()\n>>> *dst++ = blue_[(prev[x] + next[x]) / (2 * (div))]; \\\n>>> *dst++ = green_[curr[x] / (div)]; \\\n>>> *dst++ = red_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n>>> + if constexpr (addAlphaByte) \\\n>>> + *dst++ = 255; \\\n>>> x++;\n>>> \n>>> /*\n>>> @@ -96,6 +100,8 @@ DebayerCpu::~DebayerCpu()\n>>> *dst++ = blue_[(curr[x - p] + curr[x + n]) / (2 * (div))]; \\\n>>> *dst++ = green_[curr[x] / (div)]; \\\n>>> *dst++ = red_[(prev[x] + next[x]) / (2 * (div))]; \\\n>>> + if constexpr (addAlphaByte) \\\n>>> + *dst++ = 255; \\\n>>> x++;\n>>> \n>>> /*\n>>> @@ -107,8 +113,11 @@ DebayerCpu::~DebayerCpu()\n>>> *dst++ = blue_[(prev[x - p] + prev[x + n] + next[x - p] + next[x + n]) / (4 * (div))]; \\\n>>> *dst++ = green_[(prev[x] + curr[x - p] + curr[x + n] + next[x]) / (4 * (div))]; \\\n>>> *dst++ = red_[curr[x] / (div)]; \\\n>>> + if constexpr (addAlphaByte) \\\n>>> + *dst++ = 255; \\\n>>> x++;\n>>> \n>>> +template\n>>> void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> DECLARE_SRC_POINTERS(uint8_t)\n>>> @@ -119,6 +128,7 @@ void DebayerCpu::debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> }\n>>> }\n>>> \n>>> +template\n>>> void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> DECLARE_SRC_POINTERS(uint8_t)\n>>> @@ -129,6 +139,7 @@ void DebayerCpu::debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> }\n>>> }\n>>> \n>>> +template\n>>> void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> DECLARE_SRC_POINTERS(uint16_t)\n>>> @@ -140,6 +151,7 @@ void DebayerCpu::debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> }\n>>> }\n>>> \n>>> +template\n>>> void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> DECLARE_SRC_POINTERS(uint16_t)\n>>> @@ -151,6 +163,7 @@ void DebayerCpu::debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> }\n>>> }\n>>> \n>>> +template\n>>> void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> DECLARE_SRC_POINTERS(uint16_t)\n>>> @@ -162,6 +175,7 @@ void DebayerCpu::debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> }\n>>> }\n>>> \n>>> +template\n>>> void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> DECLARE_SRC_POINTERS(uint16_t)\n>>> @@ -173,6 +187,7 @@ void DebayerCpu::debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> }\n>>> }\n>>> \n>>> +template\n>>> void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> const int widthInBytes = window_.width * 5 / 4;\n>>> @@ -198,6 +213,7 @@ void DebayerCpu::debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> }\n>>> }\n>>> \n>>> +template\n>>> void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> const int widthInBytes = window_.width * 5 / 4;\n>>> @@ -218,6 +234,7 @@ void DebayerCpu::debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> }\n>>> }\n>>> \n>>> +template\n>>> void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> const int widthInBytes = window_.width * 5 / 4;\n>>> @@ -238,6 +255,7 @@ void DebayerCpu::debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> }\n>>> }\n>>> \n>>> +template\n>>> void DebayerCpu::debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[])\n>>> {\n>>> const int widthInBytes = window_.width * 5 / 4;\n>>> @@ -280,7 +298,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n>>> config.bpp = (bayerFormat.bitDepth + 7) & ~7;\n>>> config.patternSize.width = 2;\n>>> config.patternSize.height = 2;\n>>> - config.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n>>> + config.outputFormats = std::vector({ formats::RGB888,\n>>> + formats::XRGB8888,\n>>> + formats::ARGB8888,\n>>> + formats::BGR888,\n>>> + formats::XBGR8888,\n>>> + formats::ABGR8888 });\n>>> return 0;\n>>> }\n>>> \n>>> @@ -290,7 +313,12 @@ int DebayerCpu::getInputConfig(PixelFormat inputFormat, DebayerInputConfig &conf\n>>> config.bpp = 10;\n>>> config.patternSize.width = 4; /* 5 bytes per *4* pixels */\n>>> config.patternSize.height = 2;\n>>> - config.outputFormats = std::vector({ formats::RGB888, formats::BGR888 });\n>>> + config.outputFormats = std::vector({ formats::RGB888,\n>>> + formats::XRGB8888,\n>>> + formats::ARGB8888,\n>>> + formats::BGR888,\n>>> + formats::XBGR8888,\n>>> + formats::ABGR8888 });\n>>> return 0;\n>>> }\n>>> \n>>> @@ -306,6 +334,12 @@ int DebayerCpu::getOutputConfig(PixelFormat outputFormat, DebayerOutputConfig &c\n>>> return 0;\n>>> }\n>>> \n>>> + if (outputFormat == formats::XRGB8888 || outputFormat == formats::ARGB8888 ||\n>>> + outputFormat == formats::XBGR8888 || outputFormat == formats::ABGR8888) {\n>>> + config.bpp = 32;\n>>> + return 0;\n>>> + }\n>>> +\n>>> LOG(Debayer, Info)\n>>> << \"Unsupported output format \" << outputFormat.toString();\n>>> return -EINVAL;\n>>> @@ -341,6 +375,7 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n>>> {\n>>> BayerFormat bayerFormat =\n>>> BayerFormat::fromPixelFormat(inputFormat);\n>>> + bool addAlphaByte = false;\n>>> \n>>> xShift_ = 0;\n>>> swapRedBlueGains_ = false;\n>>> @@ -351,8 +386,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n>>> };\n>>> \n>>> switch (outputFormat) {\n>>> + case formats::XRGB8888:\n>>> + case formats::ARGB8888:\n>>> + addAlphaByte = true;\n>>> + [[fallthrough]];\n>>> case formats::RGB888:\n>>> break;\n>>> + case formats::XBGR8888:\n>>> + case formats::ABGR8888:\n>>> + addAlphaByte = true;\n>>> + [[fallthrough]];\n>>> case formats::BGR888:\n>>> /* Swap R and B in bayer order to generate BGR888 instead of RGB888 */\n>>> swapRedBlueGains_ = true;\n>>> @@ -383,16 +426,16 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n>>> isStandardBayerOrder(bayerFormat.order)) {\n>>> switch (bayerFormat.bitDepth) {\n>>> case 8:\n>>> - debayer0_ = &DebayerCpu::debayer8_BGBG_BGR888;\n>>> - debayer1_ = &DebayerCpu::debayer8_GRGR_BGR888;\n>>> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer8_BGBG_BGR888 : &DebayerCpu::debayer8_BGBG_BGR888;\n>>> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer8_GRGR_BGR888 : &DebayerCpu::debayer8_GRGR_BGR888;\n>>> break;\n>>> case 10:\n>>> - debayer0_ = &DebayerCpu::debayer10_BGBG_BGR888;\n>>> - debayer1_ = &DebayerCpu::debayer10_GRGR_BGR888;\n>>> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10_BGBG_BGR888 : &DebayerCpu::debayer10_BGBG_BGR888;\n>>> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10_GRGR_BGR888 : &DebayerCpu::debayer10_GRGR_BGR888;\n>>> break;\n>>> case 12:\n>>> - debayer0_ = &DebayerCpu::debayer12_BGBG_BGR888;\n>>> - debayer1_ = &DebayerCpu::debayer12_GRGR_BGR888;\n>>> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer12_BGBG_BGR888 : &DebayerCpu::debayer12_BGBG_BGR888;\n>>> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer12_GRGR_BGR888 : &DebayerCpu::debayer12_GRGR_BGR888;\n>>> break;\n>>> }\n>>> setupStandardBayerOrder(bayerFormat.order);\n>>> @@ -403,20 +446,20 @@ int DebayerCpu::setDebayerFunctions(PixelFormat inputFormat, PixelFormat outputF\n>>> bayerFormat.packing == BayerFormat::Packing::CSI2) {\n>>> switch (bayerFormat.order) {\n>>> case BayerFormat::BGGR:\n>>> - debayer0_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n>>> - debayer1_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n>>> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n>>> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n>>> return 0;\n>>> case BayerFormat::GBRG:\n>>> - debayer0_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n>>> - debayer1_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n>>> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n>>> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n>>> return 0;\n>>> case BayerFormat::GRBG:\n>>> - debayer0_ = &DebayerCpu::debayer10P_GRGR_BGR888;\n>>> - debayer1_ = &DebayerCpu::debayer10P_BGBG_BGR888;\n>>> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_GRGR_BGR888 : &DebayerCpu::debayer10P_GRGR_BGR888;\n>>> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_BGBG_BGR888 : &DebayerCpu::debayer10P_BGBG_BGR888;\n>>> return 0;\n>>> case BayerFormat::RGGB:\n>>> - debayer0_ = &DebayerCpu::debayer10P_RGRG_BGR888;\n>>> - debayer1_ = &DebayerCpu::debayer10P_GBGB_BGR888;\n>>> + debayer0_ = addAlphaByte ? &DebayerCpu::debayer10P_RGRG_BGR888 : &DebayerCpu::debayer10P_RGRG_BGR888;\n>>> + debayer1_ = addAlphaByte ? &DebayerCpu::debayer10P_GBGB_BGR888 : &DebayerCpu::debayer10P_GBGB_BGR888;\n>>> return 0;\n>>> default:\n>>> break;\n>>> diff --git a/src/libcamera/software_isp/debayer_cpu.h b/src/libcamera/software_isp/debayer_cpu.h\n>>> index be7dcdca..1dac6435 100644\n>>> --- a/src/libcamera/software_isp/debayer_cpu.h\n>>> +++ b/src/libcamera/software_isp/debayer_cpu.h\n>>> @@ -85,18 +85,28 @@ private:\n>>> using debayerFn = void (DebayerCpu::*)(uint8_t *dst, const uint8_t *src[]);\n>>> \n>>> /* 8-bit raw bayer format */\n>>> + template\n>>> void debayer8_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> + template\n>>> void debayer8_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> /* unpacked 10-bit raw bayer format */\n>>> + template\n>>> void debayer10_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> + template\n>>> void debayer10_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> /* unpacked 12-bit raw bayer format */\n>>> + template\n>>> void debayer12_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> + template\n>>> void debayer12_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> /* CSI-2 packed 10-bit raw bayer format (all the 4 orders) */\n>>> + template\n>>> void debayer10P_BGBG_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> + template\n>>> void debayer10P_GRGR_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> + template\n>>> void debayer10P_GBGB_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> + template\n>>> void debayer10P_RGRG_BGR888(uint8_t *dst, const uint8_t *src[]);\n>>> \n>>> struct DebayerInputConfig {\n>>\n>","headers":{"Return-Path":"","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 22383BD87C\n\tfor ;\n\tMon, 24 Jun 2024 12:33:56 +0000 (UTC)","from lancelot.ideasonboard.com (localhost [IPv6:::1])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTP id 3D5C9654A9;\n\tMon, 24 Jun 2024 14:33:55 +0200 (CEST)","from us-smtp-delivery-124.mimecast.com\n\t(us-smtp-delivery-124.mimecast.com [170.10.129.124])\n\tby lancelot.ideasonboard.com (Postfix) with ESMTPS id 6AE04654A1\n\tfor ;\n\tMon, 24 Jun 2024 14:33:52 +0200 (CEST)","from mail-ej1-f69.google.com (mail-ej1-f69.google.com\n\t[209.85.218.69]) by relay.mimecast.com with ESMTP with STARTTLS\n\t(version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id\n\tus-mta-147-n6UEvP7IPb2JbhaxzsYKgQ-1; Mon, 24 Jun 2024 08:33:47 -0400","by mail-ej1-f69.google.com with SMTP id\n\ta640c23a62f3a-a725c45ab1dso41109366b.0\n\tfor ;\n\tMon, 24 Jun 2024 05:33:47 -0700 (PDT)","from [10.40.98.157] ([78.108.130.194])\n\tby smtp.gmail.com with ESMTPSA id\n\ta640c23a62f3a-a6fcf56033asm405781466b.157.2024.06.24.05.33.44\n\t(version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128);\n\tMon, 24 Jun 2024 05:33:44 -0700 (PDT)"],"Authentication-Results":"lancelot.ideasonboard.com; dkim=pass (1024-bit key;\n\tunprotected) header.d=redhat.com header.i=@redhat.com\n\theader.b=\"cyItTb3s\"; dkim-atps=neutral","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com;\n\ts=mimecast20190719; t=1719232431;\n\th=from:from:reply-to:subject:subject:date:date:message-id:message-id:\n\tto:to:cc:mime-version:mime-version:content-type:content-type:\n\tcontent-transfer-encoding:content-transfer-encoding:\n\tin-reply-to:in-reply-to:references:references;\n\tbh=UEl4vOXiVKxlcjuUa0xMCTdp8uXGcn2rypSuoasasIc=;\n\tb=cyItTb3sr9pdEpKDQuVqzSZL6W7Jgkyi5OeK89ih7i6sOYD4+RAt36h9kAezFqgJSCqIOn\n\tvM/Q6U5jYRx0rNW6EfJWTCUsIa9OYqT0wtmB5X2XAojm5dqW3cyXYZdEAXuqwpcAFxHZHU\n\tvWZO3jqLox/0RpPQJuSdmctahvjnVaU=","X-MC-Unique":"n6UEvP7IPb2JbhaxzsYKgQ-1","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20230601; t=1719232425; x=1719837225;\n\th=content-transfer-encoding:in-reply-to:from:content-language\n\t:references:to:subject:user-agent:mime-version:date:message-id\n\t:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to;\n\tbh=UEl4vOXiVKxlcjuUa0xMCTdp8uXGcn2rypSuoasasIc=;\n\tb=JyWndK7OPz09oxdSEaXpGuYk0D00xChngD+zHMw5ZP5P1h5WCTQ8nHfLJQdM1F3vCu\n\tCBU2QLphkImUiMnANnMndRE7WXXZInuNkNKpCAC/Ru1EOg/NF7Vv7FOJKIrxFDbszZmS\n\tyM3mOW3LLNp13PIU+MoL2aZg/DMOlNCCULiZSHO76Q0MURSniCJNRpuUK/pwRszTsiY2\n\tfi50gjyo6N65joB2ekzMn4rTShQVuddTGQ52V1NbuptkqaJ3c7xAq9ki3EgOPIq8/hw8\n\tKkHdOMglt89u/Y0a/oKRZHdxPxE+JtqnI3r8D9YLoqNxVPAQm418wgqi5cN3H6JV65rh\n\t+W1Q==","X-Forwarded-Encrypted":"i=1;\n\tAJvYcCX8te/aXwbXD+cG2nxOXV74B3f9TeUxLwIJjbMUrby9VyngP2mg0sXGO1pgmFlJAuAYEIkyyHm8vykN9b4QflRJTzqLXQVDVXMfC62CmitDXH9zIA==","X-Gm-Message-State":"AOJu0YyjQvnLJasZWda4Vn3ayK+j3xxdapoSp8vzRaj80fpfsjXpzjVH\n\tcoZQineGvm8Z0ZnvweEmB1JnDcSzrPg5ahItkVo/lcdNdhEXeRkJ7+1/iBgpVCEn4FiYsgHrlDs\n\tOeKRfPA9Z24s2mWhSMNiAL0dP/3GixvZRPXNxFNKf6GBQOW3ginDx2FhPbJhb/A9B/GBLE7OpL+\n\t68dbc=","X-Received":["by 2002:a17:907:7649:b0:a6f:e5f7:e966 with SMTP id\n\ta640c23a62f3a-a7242c4d33amr387798066b.45.1719232425510; \n\tMon, 24 Jun 2024 05:33:45 -0700 (PDT)","by 2002:a17:907:7649:b0:a6f:e5f7:e966 with SMTP id\n\ta640c23a62f3a-a7242c4d33amr387796266b.45.1719232425011; \n\tMon, 24 Jun 2024 05:33:45 -0700 (PDT)"],"X-Google-Smtp-Source":"AGHT+IE/fXBfaiCTIFUXg/auvUJPpd9o2MTdyuWgzOZ0hF3x1hBaalTvTLh3Dx/JHPVSdn9RlacEsQ==","Message-ID":"<7d34e67f-79f9-4bb7-b336-9f856ef41f12@redhat.com>","Date":"Mon, 24 Jun 2024 14:33:44 +0200","MIME-Version":"1.0","User-Agent":"Mozilla Thunderbird","Subject":"Re: [PATCH v3] libcamera: debayer_cpu: Add 32bits/aligned output\n\tformats","To":"Kieran Bingham ,\n\tRobert Mader ,\n\tlibcamera-devel@lists.libcamera.org","References":"<20240618063227.197989-1-robert.mader@collabora.com>\n\t<3048b066-a927-4602-a783-e3f660ff018c@redhat.com>\n\t<171922977962.341316.6814845742008517299@ping.linuxembedded.co.uk>","From":"Hans de Goede ","In-Reply-To":"<171922977962.341316.6814845742008517299@ping.linuxembedded.co.uk>","X-Mimecast-Spam-Score":"0","X-Mimecast-Originator":"redhat.com","Content-Language":"en-US","Content-Type":"text/plain; charset=UTF-8","Content-Transfer-Encoding":"7bit","X-BeenThere":"libcamera-devel@lists.libcamera.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"","List-Unsubscribe":",\n\t","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n\t","Errors-To":"libcamera-devel-bounces@lists.libcamera.org","Sender":"\"libcamera-devel\" "}}]