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 3625A43445 for ; Tue, 12 Jul 2022 09:16:12 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 98A4968B842; Tue, 12 Jul 2022 12:16:00 +0300 (EEST) Received: from mail-lj1-f175.google.com (mail-lj1-f175.google.com [209.85.208.175]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id D842768B823 for ; Tue, 12 Jul 2022 12:15:53 +0300 (EEST) Received: by mail-lj1-f175.google.com with SMTP id a10so7327221ljj.5 for ; Tue, 12 Jul 2022 02:15:53 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=semihalf.com; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=dCs3buVB/GTjq4HkLbiB7hD0kMb+WbwEg2zN71KrXQ8=; b=Y1DA+Mrma/oP+1katza4HigKUMbfLjotFEvFIvlH40eQsGH8rDGUppSsGJs8J4hEEs Ass/WSuWq6vPxEl29nww5uGIoKFtLVMsotipXRWVRwEicAmleXGD9FvqBYtVbQQ8VDVu ovuz2mHE0QtxQHD5UpyVNSze8ly36FeT5T/+VHitzYpWcJhFA4yY6d81VoC/4Ci2JtWE HJ4rjCHhdec8jQSlNbbyavBx/FTGTahmTMYhcrcJrabk6dHfdeBsoB5WF02IysPLv8yk /3peXWd0RlYxDOdjmSAE7KtibJgQpUnOFeW2aL1PYaDXO+aTTEZMHLA3Ze/SExFzqHWR bz6Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=dCs3buVB/GTjq4HkLbiB7hD0kMb+WbwEg2zN71KrXQ8=; b=zMACreaTjm2Qr/gakGofCpUhJH0RaHFfr2+SIvXLHrdNDv9gFUzdhZv55t5cpFc9Fy +vBzkA09fEnrHIQzB5plUQzEGGWHR/M4U/wXCHtEvXyycwU4+Pv8jVcpuxXuJsFmb5qT ne/IjXLeGWSSXGEZ0Ysl8TIgaQh2tz0LJSzYtfwECDpsZEU3FkeXOZmmXaLJpwlHRpDM mi+K4Y2zvbKJXGY6TLJKlwMRJXdKxSFwrIO7Xe7KdpXdBmuXkYXLKxwx4QMxbBYXIFJs 5aVmf+LlwxeewmJjBGHbBrm3OK3IDh3IgsWfcHvd20b0Vwg2wcpKisaQ43TxwDuZHw8U e9Bg== X-Gm-Message-State: AJIora/q4k5t40D/+y2QVUF4MpuJw+fO2QN7jjxPwPHZEmk5+PWa27Sl 9nghJXH/gJtVsN39qFoAI7aeBYl1VdaP2j3B X-Google-Smtp-Source: AGRyM1vooMU48RPFAB4RuPWRRoOit3w5Z0mD6EvCXo9ljSzYhrCbil3mXSXq1aWbvm80OP/jR6iNWQ== X-Received: by 2002:a2e:504:0:b0:25d:529a:3852 with SMTP id 4-20020a2e0504000000b0025d529a3852mr11877715ljf.179.1657617352935; Tue, 12 Jul 2022 02:15:52 -0700 (PDT) Received: from hum-HP-ProBook-440-G7.semihalf.net ([83.142.187.84]) by smtp.gmail.com with ESMTPSA id d9-20020a19e609000000b0048355942defsm2067241lfh.249.2022.07.12.02.15.52 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 12 Jul 2022 02:15:52 -0700 (PDT) From: Hubert Mazur To: ffmpeg-devel@ffmpeg.org Date: Tue, 12 Jul 2022 11:15:33 +0200 Message-Id: <20220712091533.429382-2-hum@semihalf.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20220712091533.429382-1-hum@semihalf.com> References: <20220629082440.119841-3-hum@semihalf.com> <20220712091533.429382-1-hum@semihalf.com> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH] lavc/aarch64: Add pix_abs16_x2 neon implementation 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 Cc: gjb@semihalf.com, upstream@semihalf.com, jswinney@amazon.com, Hubert Mazur , martin@martin.st, mw@semihalf.com, spop@amazon.com 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: Provide neon implementation for pix_abs16_x2 function. Performance tests of implementation are below. - pix_abs_0_1_c: 283.5 - pix_abs_0_1_neon: 39.0 Benchmarks and tests run with checkasm tool on AWS Graviton 3. Signed-off-by: Hubert Mazur --- libavcodec/aarch64/me_cmp_init_aarch64.c | 3 + libavcodec/aarch64/me_cmp_neon.S | 75 ++++++++++++++++++++++++ 2 files changed, 78 insertions(+) diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c index bec9148a1a..136b008eb7 100644 --- a/libavcodec/aarch64/me_cmp_init_aarch64.c +++ b/libavcodec/aarch64/me_cmp_init_aarch64.c @@ -27,6 +27,8 @@ int ff_pix_abs16_neon(MpegEncContext *s, uint8_t *blk1, uint8_t *blk2, ptrdiff_t stride, int h); int ff_pix_abs16_xy2_neon(MpegEncContext *s, uint8_t *blk1, uint8_t *blk2, ptrdiff_t stride, int h); +int ff_pix_abs16_x2_neon(MpegEncContext *v, uint8_t *pix1, uint8_t *pix2, + ptrdiff_t stride, int h); av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx) { @@ -34,6 +36,7 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx) if (have_neon(cpu_flags)) { c->pix_abs[0][0] = ff_pix_abs16_neon; + c->pix_abs[0][1] = ff_pix_abs16_x2_neon; c->pix_abs[0][3] = ff_pix_abs16_xy2_neon; c->sad[0] = ff_pix_abs16_neon; diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S index a7937bd8be..e49d049fc2 100644 --- a/libavcodec/aarch64/me_cmp_neon.S +++ b/libavcodec/aarch64/me_cmp_neon.S @@ -203,3 +203,78 @@ function ff_pix_abs16_xy2_neon, export=1 fmov w0, s0 // copy result to general purpose register ret endfunc + +function ff_pix_abs16_x2_neon, export=1 + // x0 unused + // x1 uint8_t *pix1 + // x2 uint8_t *pix2 + // x3 ptrdiff_t stride + // w4 int h + + cmp w4, #4 + // initialize buffers + movi d20, #0 + add x5, x2, #1 // pix2 + 1 + b.lt 2f + +// make 4 iterations at once +1: + + // abs(pix1[0] - avg2(pix2[0], pix2[1])) + // avg2(a,b) = (((a) + (b) + 1) >> 1) + // abs(x) = (x < 0 ? -x : x) + + ld1 {v1.16b}, [x2], x3 + ld1 {v2.16b}, [x5], x3 + urhadd v30.16b, v1.16b, v2.16b + ld1 {v0.16b}, [x1], x3 + uabdl v16.8h, v0.8b, v30.8b + ld1 {v4.16b}, [x2], x3 + uabdl2 v17.8h, v0.16b, v30.16b + ld1 {v5.16b}, [x5], x3 + urhadd v29.16b, v4.16b, v5.16b + ld1 {v3.16b}, [x1], x3 + uabal v16.8h, v3.8b, v29.8b + ld1 {v7.16b}, [x2], x3 + uabal2 v17.8h, v3.16b, v29.16b + ld1 {v22.16b}, [x5], x3 + urhadd v28.16b, v7.16b, v22.16b + ld1 {v6.16b}, [x1], x3 + uabal v16.8h, v6.8b, v28.8b + ld1 {v24.16b}, [x2], x3 + uabal2 v17.8h, v6.16b, v28.16b + ld1 {v25.16b}, [x5], x3 + urhadd v27.16b, v24.16b, v25.16b + ld1 {v23.16b}, [x1], x3 + uabal v16.8h, v23.8b, v27.8b + uabal2 v17.8h, v23.16b, v27.16b + + sub w4, w4, #4 + + add v16.8h, v16.8h, v17.8h + uaddlv s16, v16.8h + cmp w4, #4 + add d20, d20, d16 + + b.ge 1b + cbz w4, 3f + +// iterate by one +2: + ld1 {v1.16b}, [x2], x3 + ld1 {v2.16b}, [x5], x3 + urhadd v29.16b, v1.16b, v2.16b + ld1 {v0.16b}, [x1], x3 + uabd v28.16b, v0.16b, v29.16b + + uaddlv h28, v28.16b + subs w4, w4, #1 + + add d20, d20, d28 + b.ne 2b + +3: + fmov w0, s20 + + ret +endfunc -- 2.34.1 _______________________________________________ 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".