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 37F134286E for ; Mon, 3 Oct 2022 14:11:37 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 69C4268BBD7; Mon, 3 Oct 2022 17:10:50 +0300 (EEST) Received: from mail-lf1-f43.google.com (mail-lf1-f43.google.com [209.85.167.43]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id DD6EE68BBA4 for ; Mon, 3 Oct 2022 17:10:42 +0300 (EEST) Received: by mail-lf1-f43.google.com with SMTP id u26so8144019lfk.8 for ; Mon, 03 Oct 2022 07:10:42 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=semihalf.com; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date; bh=kai/emWzL6d1oU8idwAFA1gFjvQKCsNAiB3LnWuAjgo=; b=kL4j2yhy0lTHbARbBO9gPTdNwCTi1adKq0hN9pnFeBPy8Ewkwfkxhmt1MVGwYfMlxF sd8sbEwzEkMK8bL1W9xoMcVBTW30CPJl5U7mjKOAG4HwMbyXCvJCYq2xtjVgbsihMsZZ TIKlzAYsgToHQzs4t22GFM6rrP/bIgIrgLZnQAeWT/hKAbvnZ+CmQQmmcUQkT5jP+U5n UL//Y0aD2z5vzrh3JBUXH9w14DU2FjM9BsoMW6tpNtMmjry2SE13AnhhbGAy3pULe8pI mVwOQD0j2lmendwEnzW6IMp1m89ekmZrN/iI52DBKX8NPKGgFnpBN64XUbwsNjZSRDEf V01w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date; bh=kai/emWzL6d1oU8idwAFA1gFjvQKCsNAiB3LnWuAjgo=; b=qpLWpuPbLz8J4lEnNKavQk7KhXCtkfZOw2rYsBih+pPRIF7WG+9lsHWxpsTdM2yUA8 8cSAwS5NlqN+iuMeIM/y8Jnb3fmw9hozlfFOF8+QXwcUncKJX01FvgGn+vzhDDMZZpKZ wTdHLr8OocFA3HVrFDzPfmJns+hJFTRmnEFYDpio3VL724mI6crFPNdGYWQJq92EeyPV 4g7q2cO5V1QwkHwwlWPm5slgI5Z23Cm5PcyLxQUvijYH+yxoZ6fxRVabxYsVr/upe8XZ Ti0ox31WjH81b5f/TOY2kgXO7fK6DhhShTEvA1csB7a7SbPVZvGGok6gtxSJ8nCO4zCj TTJw== X-Gm-Message-State: ACrzQf1XxRzBCjpkdPqChpbEC137pg4c9QY9lCjTUuGI5JxjJggguwiK PDMA23nXwZKuik+PgPEs22a9G+QHQtkaaQ== X-Google-Smtp-Source: AMsMyM4oX8UWaGqCh78D1EfdFhNjM6kSp+WCmwAwilc9PBXRO/5Gg+4f8Dm8LHOE1UYIq+KrsBPMwQ== X-Received: by 2002:a05:6512:e9e:b0:4a2:1503:c2e7 with SMTP id bi30-20020a0565120e9e00b004a21503c2e7mr5081643lfb.476.1664806241859; Mon, 03 Oct 2022 07:10:41 -0700 (PDT) Received: from gilgamesh.lab.semihalf.net ([83.142.187.85]) by smtp.gmail.com with ESMTPSA id k15-20020a05651239cf00b00499b19f23e8sm1470610lfu.279.2022.10.03.07.10.41 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 03 Oct 2022 07:10:41 -0700 (PDT) From: Grzegorz Bernacki To: ffmpeg-devel@ffmpeg.org Date: Mon, 3 Oct 2022 16:10:18 +0200 Message-Id: <20221003141020.3564715-6-gjb@semihalf.com> X-Mailer: git-send-email 2.29.0 In-Reply-To: <20221003141020.3564715-1-gjb@semihalf.com> References: <20221003141020.3564715-1-gjb@semihalf.com> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH v2 5/7] lavc/aarch64: Provide optimized implementation of vsse8 for arm64. 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, hum@semihalf.com, 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 optimized implementation of vsse8 for arm64. Performance comparison tests are shown below. - vsse_1_c: 141.5 - vsse_1_neon: 32.5 Benchmarks and tests are run with checkasm tool on AWS Graviton 3. Signed-off-by: Grzegorz Bernacki --- libavcodec/aarch64/me_cmp_init_aarch64.c | 5 ++ libavcodec/aarch64/me_cmp_neon.S | 70 ++++++++++++++++++++++++ 2 files changed, 75 insertions(+) diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c index 05156627fa..1a0c3e90bb 100644 --- a/libavcodec/aarch64/me_cmp_init_aarch64.c +++ b/libavcodec/aarch64/me_cmp_init_aarch64.c @@ -71,6 +71,9 @@ int nsse8_neon(int multiplier, const uint8_t *s, const uint8_t *s2, int nsse8_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2, ptrdiff_t stride, int h); +int vsse8_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2, + ptrdiff_t stride, int h); + av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx) { int cpu_flags = av_get_cpu_flags(); @@ -96,6 +99,8 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx) c->vsad[5] = vsad_intra8_neon; c->vsse[0] = vsse16_neon; + c->vsse[1] = vsse8_neon; + c->vsse[4] = vsse_intra16_neon; c->nsse[0] = nsse16_neon_wrapper; diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S index 24be05dd18..104e02f495 100644 --- a/libavcodec/aarch64/me_cmp_neon.S +++ b/libavcodec/aarch64/me_cmp_neon.S @@ -838,6 +838,76 @@ function vsad16_neon, export=1 ret endfunc +function vsse8_neon, export=1 + // x0 unused + // x1 uint8_t *pix1 + // x2 uint8_t *pix2 + // x3 ptrdiff_t stride + // w4 int h + + ld1 {v0.8b}, [x1], x3 // Load pix1[0], first iteration + ld1 {v1.8b}, [x2], x3 // Load pix2[0], first iteration + + sub w4, w4, #1 // we need to make h-1 iterations + movi v16.4s, #0 + movi v17.4s, #0 + + cmp w4, #3 // check if we can make 3 iterations at once + usubl v31.8h, v0.8b, v1.8b // Signed difference of pix1[0] - pix2[0], first iteration + b.lt 2f + + +1: + // x = abs(pix1[0] - pix2[0] - pix1[0 + stride] + pix2[0 + stride]) + // res = (x) * (x) + ld1 {v0.8b}, [x1], x3 // Load pix1[0 + stride], first iteration + ld1 {v1.8b}, [x2], x3 // Load pix2[0 + stride], first iteration + ld1 {v2.8b}, [x1], x3 // Load pix1[0 + stride], second iteration + ld1 {v3.8b}, [x2], x3 // Load pix2[0 + stride], second iteration + usubl v29.8h, v0.8b, v1.8b + usubl2 v28.8h, v0.16b, v1.16b + ld1 {v4.8b}, [x1], x3 // Load pix1[0 + stride], third iteration + ld1 {v5.8b}, [x2], x3 // Load pix1[0 + stride], third iteration + sabd v31.8h, v31.8h, v29.8h + usubl v27.8h, v2.8b, v3.8b + usubl v25.8h, v4.8b, v5.8b + sabd v29.8h, v29.8h, v27.8h + sabd v27.8h, v27.8h, v25.8h + umlal v16.4s, v31.4h, v31.4h + umlal2 v17.4s, v31.8h, v31.8h + mov v31.16b, v25.16b + umlal v16.4s, v29.4h, v29.4h + umlal2 v17.4s, v29.8h, v29.8h + sub w4, w4, #3 + umlal v16.4s, v27.4h, v27.4h + umlal2 v17.4s, v27.8h, v27.8h + cmp w4, #3 + + b.ge 1b + + cbz w4, 3f + +// iterate by once +2: + ld1 {v0.8b}, [x1], x3 + ld1 {v1.8b}, [x2], x3 + subs w4, w4, #1 + usubl v29.8h, v0.8b, v1.8b + sabd v31.8h, v31.8h, v29.8h + umlal v16.4s, v31.4h, v31.4h + umlal2 v17.4s, v31.8h, v31.8h + mov v31.16b, v29.16b + b.ne 2b + +3: + add v16.4s, v16.4s, v17.4s + uaddlv d17, v16.4s + fmov w0, s17 + + ret +endfunc + + function vsse16_neon, export=1 // x0 unused // x1 uint8_t *pix1 -- 2.37.1 _______________________________________________ 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".