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 599F146A3E for ; Sun, 2 Jul 2023 12:33:59 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id C01BA68C304; Sun, 2 Jul 2023 15:33:17 +0300 (EEST) Received: from mail-wm1-f48.google.com (mail-wm1-f48.google.com [209.85.128.48]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id E11F368C2A4 for ; Sun, 2 Jul 2023 15:33:15 +0300 (EEST) Received: by mail-wm1-f48.google.com with SMTP id 5b1f17b1804b1-3fbc244d386so34989575e9.2 for ; Sun, 02 Jul 2023 05:33:15 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kynesim-co-uk.20221208.gappssmtp.com; s=20221208; t=1688301195; x=1690893195; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=7Tpsu4kxZcEgdtrcUU/5U8eHJmmUuqwH5IGld1D0XAA=; b=3Lhv/t4YJIsOCjtA9TugDbf0SVzmCuq8tXMJhAHxQSAQNXQxiO+LGza+ftZgNOVD6H 6VUM3bVCL2wRCFeqEGKQBJN5Ah8lQ3fEaNWt42k3oTSxFAa/85Wq7FokbRpAGdpSRsco VS6zDvVpN1mMCRXJPliNXe7pxv6vbwUXwc+JkHnOVKdgzF7IymsvEgwgvIH4wvJWgN9b 0/A3lGMYKuf+9YBFLygbQE0PYXkptjXRMtlQAlY+U+TXNN/gJM1HZ79rADFQE4tX7XZK cQk+uvp5pIOrD4NLn4/xzvhd9KzoosYi3qZy8qdTSnAemAsEDjVsfQUgToea/0HMQdib NIZw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1688301195; x=1690893195; 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:message-id:reply-to; bh=7Tpsu4kxZcEgdtrcUU/5U8eHJmmUuqwH5IGld1D0XAA=; b=FbZqi5OCFND5b7ggv1aT8U9Z5RqivD3D0pZ/hffUrMwkKXo4hTGcelKLtcjEv+6XMe BBzG5yKA6UjVPtI03E26/v3BJ5xcUlKJRI8a0SXbkvBXXJHtgHmVDm6RHVD4eecv5/cZ GR7KGIiI13biKdubwbKb3d055k0uaQYKXUOowXwBwMtwSwAtuyfHHkcKtvt3MKK32hLg YflyMr1GjWANNYJnXAGA1yhhcPSuKFCMj/3UMGfz9CFinpc2w9rWJ8eBYivjYeWY5ifH n0YYKbMZ0/3hQ5oJYCumwKh3ifxxZ06DXIJUP9q337FWqdA1l5GHV9cN988LwPgmLjX9 +vEw== X-Gm-Message-State: AC+VfDxiDnweb0jtaO09ynbx99hxuJ7BeIYKyZ4jiG2vwRffVJZCcNnE fKVfMtsGK2JiqWfTZxhXxCf8CxnoGHQL9mzKkg4= X-Google-Smtp-Source: ACHHUZ7yG7bB0uYi6PeUXVeqxuTif1Ud7c0THC87rKceLN21MJH9WX/KHICh2oSp8mueogQ3GpKdsg== X-Received: by 2002:a05:600c:24d:b0:3f7:f884:7be3 with SMTP id 13-20020a05600c024d00b003f7f8847be3mr5931845wmj.4.1688301195076; Sun, 02 Jul 2023 05:33:15 -0700 (PDT) Received: from sucnaath.outer.uphall.net (cpc1-cmbg20-2-0-cust759.5-4.cable.virginm.net. [86.21.218.248]) by smtp.gmail.com with ESMTPSA id f12-20020a7bc8cc000000b003fbbe41fd78sm8816167wml.10.2023.07.02.05.33.13 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sun, 02 Jul 2023 05:33:14 -0700 (PDT) From: John Cox To: ffmpeg-devel@ffmpeg.org Date: Sun, 2 Jul 2023 12:32:35 +0000 Message-Id: <20230702123242.232484-9-jc@kynesim.co.uk> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20230702123242.232484-1-jc@kynesim.co.uk> References: <20230702123242.232484-1-jc@kynesim.co.uk> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH v2 08/15] avfilter/vf_bwdif: Add neon for filter_edge 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: thomas.mundt@hr.de, John Cox , martin@martin.st 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: John Cox --- libavfilter/aarch64/vf_bwdif_init_aarch64.c | 20 ++++ libavfilter/aarch64/vf_bwdif_neon.S | 104 ++++++++++++++++++++ 2 files changed, 124 insertions(+) diff --git a/libavfilter/aarch64/vf_bwdif_init_aarch64.c b/libavfilter/aarch64/vf_bwdif_init_aarch64.c index 3ffaa07ab3..e75cf2f204 100644 --- a/libavfilter/aarch64/vf_bwdif_init_aarch64.c +++ b/libavfilter/aarch64/vf_bwdif_init_aarch64.c @@ -24,10 +24,29 @@ #include "libavfilter/bwdif.h" #include "libavutil/aarch64/cpu.h" +void ff_bwdif_filter_edge_neon(void *dst1, void *prev1, void *cur1, void *next1, + int w, int prefs, int mrefs, int prefs2, int mrefs2, + int parity, int clip_max, int spat); + void ff_bwdif_filter_intra_neon(void *dst1, void *cur1, int w, int prefs, int mrefs, int prefs3, int mrefs3, int parity, int clip_max); +static void filter_edge_helper(void *dst1, void *prev1, void *cur1, void *next1, + int w, int prefs, int mrefs, int prefs2, int mrefs2, + int parity, int clip_max, int spat) +{ + const int w0 = clip_max != 255 ? 0 : w & ~15; + + ff_bwdif_filter_edge_neon(dst1, prev1, cur1, next1, w0, prefs, mrefs, prefs2, mrefs2, + parity, clip_max, spat); + + if (w0 < w) + ff_bwdif_filter_edge_c((char *)dst1 + w0, (char *)prev1 + w0, (char *)cur1 + w0, (char *)next1 + w0, + w - w0, prefs, mrefs, prefs2, mrefs2, + parity, clip_max, spat); +} + static void filter_intra_helper(void *dst1, void *cur1, int w, int prefs, int mrefs, int prefs3, int mrefs3, int parity, int clip_max) { @@ -52,5 +71,6 @@ ff_bwdif_init_aarch64(BWDIFContext *s, int bit_depth) return; s->filter_intra = filter_intra_helper; + s->filter_edge = filter_edge_helper; } diff --git a/libavfilter/aarch64/vf_bwdif_neon.S b/libavfilter/aarch64/vf_bwdif_neon.S index 48dc7bcd9d..d6e7d109f5 100644 --- a/libavfilter/aarch64/vf_bwdif_neon.S +++ b/libavfilter/aarch64/vf_bwdif_neon.S @@ -149,6 +149,110 @@ coeffs: .hword 5570, 3801, 1016, -3801 // hf[0] = v0.h[2], -hf[1] = v0.h[5] .hword 5077, 981 // sp[0] = v0.h[6] +// ============================================================================ +// +// void ff_bwdif_filter_edge_neon( +// void *dst1, // x0 +// void *prev1, // x1 +// void *cur1, // x2 +// void *next1, // x3 +// int w, // w4 +// int prefs, // w5 +// int mrefs, // w6 +// int prefs2, // w7 +// int mrefs2, // [sp, #0] +// int parity, // [sp, #SP_INT] +// int clip_max, // [sp, #SP_INT*2] unused +// int spat); // [sp, #SP_INT*3] + +function ff_bwdif_filter_edge_neon, export=1 + // Sanity check w + cmp w4, #0 + ble 99f + +// #define prev2 cur +// const uint8_t * restrict next2 = parity ? prev : next; + + ldr w8, [sp, #0] // mrefs2 + + ldr w17, [sp, #SP_INT] // parity + ldr w16, [sp, #SP_INT*3] // spat + cmp w17, #0 + csel x17, x1, x3, ne + +// for (x = 0; x < w; x++) { + +10: +// int m1 = cur[mrefs]; +// int d = (prev2[0] + next2[0]) >> 1; +// int p1 = cur[prefs]; +// int temporal_diff0 = FFABS(prev2[0] - next2[0]); +// int temporal_diff1 =(FFABS(prev[mrefs] - m1) + FFABS(prev[prefs] - p1)) >> 1; +// int temporal_diff2 =(FFABS(next[mrefs] - m1) + FFABS(next[prefs] - p1)) >> 1; +// int diff = FFMAX3(temporal_diff0 >> 1, temporal_diff1, temporal_diff2); + ldr q31, [x2] + ldr q21, [x17] + uhadd v16.16b, v31.16b, v21.16b // d0 = v16 + uabd v17.16b, v31.16b, v21.16b // td0 = v17 + ldr q24, [x2, w6, sxtw] // m1 = v24 + ldr q22, [x2, w5, sxtw] // p1 = v22 + + ldr q0, [x1, w6, sxtw] // prev[mrefs] + ldr q2, [x1, w5, sxtw] // prev[prefs] + ldr q1, [x3, w6, sxtw] // next[mrefs] + ldr q3, [x3, w5, sxtw] // next[prefs] + + ushr v29.16b, v17.16b, #1 + + uabd v31.16b, v0.16b, v24.16b + uabd v30.16b, v2.16b, v22.16b + uhadd v0.16b, v31.16b, v30.16b // td1 = q0 + + uabd v31.16b, v1.16b, v24.16b + uabd v30.16b, v3.16b, v22.16b + uhadd v1.16b, v31.16b, v30.16b // td2 = q1 + + umax v0.16b, v0.16b, v29.16b + umax v0.16b, v0.16b, v1.16b // diff = v0 + +// if (spat) { +// SPAT_CHECK() +// } +// i0 = (m1 + p1) >> 1; + cbz w16, 1f + + ldr q31, [x2, w8, sxtw] + ldr q18, [x17, w8, sxtw] + ldr q30, [x2, w7, sxtw] + ldr q19, [x17, w7, sxtw] + uhadd v18.16b, v18.16b, v31.16b + uhadd v19.16b, v19.16b, v30.16b + + SPAT_CHECK v0, v18, v24, v16, v22, v19, v31, v30, v29, v28 + +1: + uhadd v2.16b, v22.16b, v24.16b + + // i0 = v2, s0 = v2, d0 = v16, diff = v0, t0 = v31, t1 = v30 + DIFF_CLIP v2, v2, v16, v0, v31, v30 + +// dst[0] = av_clip(interpol, 0, clip_max); + str q2, [x0], #16 + +// dst++; +// cur++; +// } + subs w4, w4, #16 + add x1, x1, #16 + add x2, x2, #16 + add x3, x3, #16 + add x17, x17, #16 + bgt 10b + +99: + ret +endfunc + // ============================================================================ // // void ff_bwdif_filter_intra_neon( -- 2.39.2 _______________________________________________ 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".