From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org [79.124.17.100]) by master.gitmailbox.com (Postfix) with ESMTP id 7B945411C3 for ; Tue, 4 Jan 2022 05:21:20 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id E663868B229; Tue, 4 Jan 2022 07:20:38 +0200 (EET) Received: from wnew1-smtp.messagingengine.com (wnew1-smtp.messagingengine.com [64.147.123.26]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 2662768B231 for ; Tue, 4 Jan 2022 07:20:32 +0200 (EET) Received: from compute1.internal (compute1.nyi.internal [10.202.2.41]) by mailnew.west.internal (Postfix) with ESMTP id 24E732B001E9 for ; Tue, 4 Jan 2022 00:20:30 -0500 (EST) Received: from mailfrontend1 ([10.202.2.162]) by compute1.internal (MEProxy); Tue, 04 Jan 2022 00:20:30 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=itanimul.li; h= from:to:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; s=fm3; bh=rasbJDbUwmLnu Ucw7VlaM7OWrPXWw0MkyX4u3tCrllg=; b=l34GYrCkxfDr15igAgiD27pF4J8f9 FE23K8lU1vU3hOTT1wlQa9CTDEOhl0deo7+KbE54gbWQCa95Mrj4fzNb3inGcRPM 31CKIbWlWjCDk0EzTk9vgP3f0VUJLKl3z7/MEna6hFx/n1XgFSPrgqYTx9rLewT0 UX/2EHwg/4j8uXOI2EbwkroP/COWE+FSOEGtZPUaPM76ix4qRa8cRVdN2lCBJRfx LQneZ6+fxyhjC7P+/nEV9umh0Lpvb98QFu//uupCGb0J4HSyZI/KwS0+tFcYW/1T TUZC8yL3aQEdeOkekBOcY9jp0UjjjLpycRsPH1W2xEZZWwjt67m9/n/MA== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=content-transfer-encoding:date:from :in-reply-to:message-id:mime-version:references:subject:to :x-me-proxy:x-me-proxy:x-me-sender:x-me-sender:x-sasl-enc; s= fm1; bh=rasbJDbUwmLnuUcw7VlaM7OWrPXWw0MkyX4u3tCrllg=; b=awpLJb0O Zz8ZPCUwrBkh3J5lrnTNflnJRn7XXB7MUIi935D3pITbFuQClyoekw5V17XMFgVP OFmhppViQgwRqnmO2Wz3Btu7qtv32xpVIkzhPHavtQJNsMso4N/x97Dw85EJOAR+ BXkzDwvnaYxV3KbpSdhS/LhRWncaMEP4VMa7PhdmJYETrIy0Q2MODHITp5cEpPRh 3OhRBQmDfIiwVTj1Ooogt4K/m3YcNwyI8ZWbN6wbqsYUEm1K5Y8RMclVz+pk4Puc b8e7EVSc+DGAvHKSpLHjqhfmlI5bjDoyoOMdowoEmdBfW0bZ96Vrs0FiQWsGtNVz RJaLZCxfW6la5Q== X-ME-Sender: X-ME-Received: X-ME-Proxy-Cause: gggruggvucftvghtrhhoucdtuddrgedvuddrudefvddgjeelucetufdoteggodetrfdotf fvucfrrhhofhhilhgvmecuhfgrshhtofgrihhlpdfqfgfvpdfurfetoffkrfgpnffqhgen uceurghilhhouhhtmecufedttdenucgovfgvgihtqfhnlhihqddqufhprghmsghothdqkg egvdduqdehudculdeftddtmdenucfjughrpefhvffufffkofgjfhgggfestdekredtredt tdenucfhrhhomhepfdflrdcuffgvkhhkvghrfdcuoehjuggvkhesihhtrghnihhmuhhlrd hliheqnecuggftrfgrthhtvghrnhephfdvfeejffegffefieefvefgheeuudelhefhffev tddthfehudeitdetfeehieetnecuffhomhgrihhnpehnvghonhdrshgsnecuvehluhhsth gvrhfuihiivgeptdenucfrrghrrghmpehmrghilhhfrhhomhepjhguvghksehithgrnhhi mhhulhdrlhhi X-ME-Proxy: Received: by mail.messagingengine.com (Postfix) with ESMTPA for ; Tue, 4 Jan 2022 00:20:28 -0500 (EST) From: "J. Dekker" To: ffmpeg-devel@ffmpeg.org Date: Tue, 4 Jan 2022 06:20:17 +0100 Message-Id: <20220104052018.9541-5-jdek@itanimul.li> X-Mailer: git-send-email 2.32.0 (Apple Git-132) In-Reply-To: <20220104052018.9541-1-jdek@itanimul.li> References: <20220104052018.9541-1-jdek@itanimul.li> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH v3 5/6] lavc/aarch64: clean-up sao band 8x8 function formatting X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Archived-At: List-Archive: List-Post: Signed-off-by: J. Dekker --- libavcodec/aarch64/hevcdsp_sao_neon.S | 65 +++++++++++---------------- 1 file changed, 25 insertions(+), 40 deletions(-) diff --git a/libavcodec/aarch64/hevcdsp_sao_neon.S b/libavcodec/aarch64/hevcdsp_sao_neon.S index 167b9676d8..73b0b3b056 100644 --- a/libavcodec/aarch64/hevcdsp_sao_neon.S +++ b/libavcodec/aarch64/hevcdsp_sao_neon.S @@ -30,24 +30,21 @@ // int width, int height) function ff_hevc_sao_band_filter_8x8_8_neon, export=1 sub sp, sp, #64 - stp xzr, xzr, [sp] - stp xzr, xzr, [sp, #16] - stp xzr, xzr, [sp, #32] - stp xzr, xzr, [sp, #48] + stp xzr, xzr, [sp] + stp xzr, xzr, [sp, #16] + stp xzr, xzr, [sp, #32] + stp xzr, xzr, [sp, #48] mov w8, #4 -0: - ldrsh x9, [x4, x8, lsl #1] // x9 = sao_offset_val[k+1] +0: ldrsh x9, [x4, x8, lsl #1] // sao_offset_val[k+1] subs w8, w8, #1 - add w10, w8, w5 // x10 = k + sao_left_class - and w10, w10, #0x1F + add w10, w8, w5 // k + sao_left_class + and w10, w10, #0x1F strh w9, [sp, x10, lsl #1] bne 0b - ld1 {v16.16b-v19.16b}, [sp], #64 - movi v20.8h, #1 -1: // beginning of line - mov w8, w6 -2: - // Simple layout for accessing 16bit values + ld1 {v16.16b-v19.16b}, [sp], #64 + movi v20.8h, #1 +1: mov w8, w6 // beginning of line +2: // Simple layout for accessing 16bit values // with 8bit LUT. // // 00 01 02 03 04 05 06 07 @@ -55,33 +52,21 @@ function ff_hevc_sao_band_filter_8x8_8_neon, export=1 // |xDE#xAD|xCA#xFE|xBE#xEF|xFE#xED|.... // +-----------------------------------> // i-0 i-1 i-2 i-3 - // dst[x] = av_clip_pixel(src[x] + offset_table[src[x] >> shift]); - ld1 {v2.8b}, [x1] - // load src[x] - uxtl v0.8h, v2.8b - // >> shift - ushr v2.8h, v0.8h, #3 // BIT_DEPTH - 3 - // x2 (access lower short) - shl v1.8h, v2.8h, #1 // low (x2, accessing short) - // +1 access upper short - add v3.8h, v1.8h, v20.8h - // shift insert index to upper byte - sli v1.8h, v3.8h, #8 - // table - tbx v2.16b, {v16.16b-v19.16b}, v1.16b - // src[x] + table - add v1.8h, v0.8h, v2.8h - // clip + narrow - sqxtun v4.8b, v1.8h - // store - st1 {v4.8b}, [x0] - // done 8 pixels - subs w8, w8, #8 + ld1 {v2.8b}, [x1] // dst[x] = av_clip_pixel(src[x] + offset_table[src[x] >> shift]); + uxtl v0.8h, v2.8b // load src[x] + ushr v2.8h, v0.8h, #3 // >> BIT_DEPTH - 3 + shl v1.8h, v2.8h, #1 // low (x2, accessing short) + add v3.8h, v1.8h, v20.8h // +1 access upper short + sli v1.8h, v3.8h, #8 // shift insert index to upper byte + tbx v2.16b, {v16.16b-v19.16b}, v1.16b // table + add v1.8h, v0.8h, v2.8h // src[x] + table + sqxtun v4.8b, v1.8h // clip + narrow + st1 {v4.8b}, [x0] // store + subs w8, w8, #8 // done 8 pixels bne 2b - // finished line - subs w7, w7, #1 - add x0, x0, x2 // dst += stride_dst - add x1, x1, x3 // src += stride_src + subs w7, w7, #1 // finished line, prep. new + add x0, x0, x2 // dst += stride_dst + add x1, x1, x3 // src += stride_src bne 1b ret endfunc -- 2.32.0 (Apple Git-132) _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".