From patchwork Sat Oct 14 08:39:50 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Logan.Lyu" X-Patchwork-Id: 44253 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:4b15:b0:15d:8365:d4b8 with SMTP id fp21csp1475038pzb; Sat, 14 Oct 2023 01:40:16 -0700 (PDT) X-Google-Smtp-Source: AGHT+IFob59pmd6q/akXSVLa8shJuOXSFjzAxpaaANhSMJoHp9QzTyP0GqU0yadmgZLweFpD0HK8 X-Received: by 2002:a17:907:2cef:b0:9ae:3d17:d5d0 with SMTP id hz15-20020a1709072cef00b009ae3d17d5d0mr24749049ejc.31.1697272815894; Sat, 14 Oct 2023 01:40:15 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1697272815; cv=none; d=google.com; s=arc-20160816; b=pRQpYbaW+H6l7bKdrPuGg7/r03uucGLKqwiNchqfF/8/h9epin3AsmcefZfdn91UU5 JudY/bi4aE6MbS7VmXsp3/14oA2F7uvQ+YgnMN4DapzbJzi3z8PYRi61D/770zZJQyr0 giYqJHp4vvJdS8voOT5jSP9JNE+sv/U5V8Q8djP5ZqkwkYFjhalUJonW88ecJtFVERpA Q9Ny1r4/pdjF0+c0IR/y357wOPQaOE+nUPWMWENduBzLOosCrOgCKvF1WTcj/YRa3dcP 3ktBqwoArTcJnsPhOQWgPbRQvagZ6IRwyYrVhEw6iPkWYkSRvlRczIXIOPyDtUA/6Skl aJag== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:reply-to:list-subscribe:list-help:list-post :list-archive:list-unsubscribe:list-id:precedence:subject :organization:to:from:user-agent:mime-version:date:message-id :delivered-to; bh=jAkGBZmBI9H/b16wvvfD36N2EdPcX8CH9tYGlOALJq0=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=tlmAQMyy+aY58BsMGRlfm7PEnHm7AC1K8llmoXdnN0PiRaoCd0hbU4/VZPUFM2WsE/ EBpjVXJzE7TK8XgoXCn4zar9VJlwi9D5rJXy7JbGkF2WNKNa+njOJNnNZFZPIAlgaD13 HVPLQXeMxcGY7xMOyubl2/bU5sOaOlIim560VAGTgZu+q6phPnasPyvFLaZXiVbkDdU/ 1tuAoFUkekuT7OTQ8W45AwwM+9bMlI4lOfrbP+09XHkdbr+koswMMQvLWgtke0MpldYI MS3LQbm7X2fNJlOJxe0VmXlMBOmm06p1JKNZO4ITAXWE0crRAsyFWkgwkfMl5NimZo9R 8Hiw== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id op27-20020a170906bcfb00b009b64b650210si573139ejb.710.2023.10.14.01.40.15; Sat, 14 Oct 2023 01:40:15 -0700 (PDT) Received-SPF: pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) client-ip=79.124.17.100; Authentication-Results: mx.google.com; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 30AC268C964; Sat, 14 Oct 2023 11:40:01 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from smtp-my3-01p11.yunyou.top (smtp-my3-01p11.yunyou.top [60.247.169.11]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 2508D68C94A for ; Sat, 14 Oct 2023 11:39:54 +0300 (EEST) Received: from [192.168.15.106] (unknown [125.121.27.199]) by smtp-my-01.yunyou.top (WestCloudMail) with ESMTPA id 39C0E1020F5 for ; Sat, 14 Oct 2023 16:39:50 +0800 (CST) Message-ID: <51ded552-9a6a-48d7-998e-ba14d737b29e@myais.com.cn> Date: Sat, 14 Oct 2023 16:39:50 +0800 MIME-Version: 1.0 User-Agent: Mozilla Thunderbird From: "Logan.Lyu" To: ffmpeg-devel@ffmpeg.org Organization: myais Subject: [FFmpeg-devel] (no subject) 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 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: blPXz6GNICYI checkasm bench: put_hevc_epel_v4_8_c: 79.9 put_hevc_epel_v4_8_neon: 25.7 put_hevc_epel_v6_8_c: 151.4 put_hevc_epel_v6_8_neon: 46.4 put_hevc_epel_v8_8_c: 250.9 put_hevc_epel_v8_8_neon: 41.7 put_hevc_epel_v12_8_c: 542.7 put_hevc_epel_v12_8_neon: 108.7 put_hevc_epel_v16_8_c: 939.4 put_hevc_epel_v16_8_neon: 169.2 put_hevc_epel_v24_8_c: 2104.9 put_hevc_epel_v24_8_neon: 307.9 put_hevc_epel_v32_8_c: 3713.9 put_hevc_epel_v32_8_neon: 524.2 put_hevc_epel_v48_8_c: 8175.2 put_hevc_epel_v48_8_neon: 1197.2 put_hevc_epel_v64_8_c: 16049.4 put_hevc_epel_v64_8_neon: 2094.9 Co-Authored-By: J. Dekker Signed-off-by: Logan Lyu --- libavcodec/aarch64/hevcdsp_epel_neon.S | 223 ++++++++++++++++++++++ libavcodec/aarch64/hevcdsp_init_aarch64.c | 5 + 2 files changed, 228 insertions(+) *c, const int bit_depth) c->put_hevc_qpel_bi[9][0][1] = ff_hevc_put_hevc_qpel_bi_h16_8_neon; NEON8_FNASSIGN(c->put_hevc_epel, 0, 0, pel_pixels,); + NEON8_FNASSIGN(c->put_hevc_epel, 1, 0, epel_v,); NEON8_FNASSIGN(c->put_hevc_qpel, 0, 0, pel_pixels,); NEON8_FNASSIGN(c->put_hevc_epel_uni, 0, 0, pel_uni_pixels,); NEON8_FNASSIGN(c->put_hevc_epel_uni, 1, 0, epel_uni_v,); diff --git a/libavcodec/aarch64/hevcdsp_epel_neon.S b/libavcodec/aarch64/hevcdsp_epel_neon.S index b4ca1e4c20..e541db5430 100644 --- a/libavcodec/aarch64/hevcdsp_epel_neon.S +++ b/libavcodec/aarch64/hevcdsp_epel_neon.S @@ -243,6 +243,229 @@ function ff_hevc_put_hevc_pel_pixels64_8_neon, export=1 ret endfunc + +function ff_hevc_put_hevc_epel_v4_8_neon, export=1 + load_epel_filterb x5, x4 + sub x1, x1, x2 + mov x10, #(MAX_PB_SIZE * 2) + ldr s16, [x1] + ldr s17, [x1 ,x2] + add x1, x1, x2, lsl #1 + ld1 {v18.s}[0], [x1], x2 +.macro calc src0, src1, src2, src3 + ld1 {\src3\().s}[0], [x1], x2 + movi v4.8h, #0 + calc_epelb v4, \src0, \src1, \src2, \src3 + subs w3, w3, #1 + st1 {v4.4h}, [x0], x10 +.endm +1: calc_all4 +.purgem calc +2: ret +endfunc + +function ff_hevc_put_hevc_epel_v6_8_neon, export=1 + load_epel_filterb x5, x4 + sub x1, x1, x2 + mov x10, #(MAX_PB_SIZE * 2 - 8) + ldr d16, [x1] + ldr d17, [x1, x2] + add x1, x1, x2, lsl #1 + ld1 {v18.8b}, [x1], x2 +.macro calc src0, src1, src2, src3 + ld1 {\src3\().8b}, [x1], x2 + movi v4.8h, #0 + calc_epelb v4, \src0, \src1, \src2, \src3 + st1 {v4.d}[0], [x0], #8 + subs w3, w3, #1 + st1 {v4.s}[2], [x0], x10 +.endm +1: calc_all4 +.purgem calc +2: ret +endfunc + +function ff_hevc_put_hevc_epel_v8_8_neon, export=1 + load_epel_filterb x5, x4 + sub x1, x1, x2 + mov x10, #(MAX_PB_SIZE * 2) + ldr d16, [x1] + ldr d17, [x1, x2] + add x1, x1, x2, lsl #1 + ld1 {v18.8b}, [x1], x2 +.macro calc src0, src1, src2, src3 + ld1 {\src3\().8b}, [x1], x2 + movi v4.8h, #0 + calc_epelb v4, \src0, \src1, \src2, \src3 + subs w3, w3, #1 + st1 {v4.8h}, [x0], x10 +.endm +1: calc_all4 +.purgem calc +2: ret +endfunc + +function ff_hevc_put_hevc_epel_v12_8_neon, export=1 + load_epel_filterb x5, x4 + sub x1, x1, x2 + mov x10, #(MAX_PB_SIZE * 2) + ldr q16, [x1] + ldr q17, [x1, x2] + add x1, x1, x2, lsl #1 + ld1 {v18.16b}, [x1], x2 +.macro calc src0, src1, src2, src3 + ld1 {\src3\().16b}, [x1], x2 + movi v4.8h, #0 + movi v5.8h, #0 + calc_epelb v4, \src0, \src1, \src2, \src3 + calc_epelb2 v5, \src0, \src1, \src2, \src3 + str q4, [x0] + subs w3, w3, #1 + str d5, [x0, #16] + add x0, x0, x10 +.endm +1: calc_all4 +.purgem calc +2: ret +endfunc + +function ff_hevc_put_hevc_epel_v16_8_neon, export=1 + load_epel_filterb x5, x4 + sub x1, x1, x2 + mov x10, #(MAX_PB_SIZE * 2) + ldr q16, [x1] + ldr q17, [x1, x2] + add x1, x1, x2, lsl #1 + ld1 {v18.16b}, [x1], x2 +.macro calc src0, src1, src2, src3 + ld1 {\src3\().16b}, [x1], x2 + movi v4.8h, #0 + movi v5.8h, #0 + calc_epelb v4, \src0, \src1, \src2, \src3 + calc_epelb2 v5, \src0, \src1, \src2, \src3 + subs w3, w3, #1 + st1 {v4.8h, v5.8h}, [x0], x10 +.endm +1: calc_all4 +.purgem calc +2: ret +endfunc + +function ff_hevc_put_hevc_epel_v24_8_neon, export=1 + load_epel_filterb x5, x4 + sub x1, x1, x2 + mov x10, #(MAX_PB_SIZE * 2) + ld1 {v16.8b, v17.8b, v18.8b}, [x1], x2 + ld1 {v19.8b, v20.8b, v21.8b}, [x1], x2 + ld1 {v22.8b, v23.8b, v24.8b}, [x1], x2 +.macro calc src0, src1, src2, src3, src4, src5, src6, src7, src8, src9, src10, src11 + ld1 {\src9\().8b, \src10\().8b, \src11\().8b}, [x1], x2 + movi v4.8h, #0 + movi v5.8h, #0 + movi v6.8h, #0 + calc_epelb v4, \src0, \src3, \src6, \src9 + calc_epelb v5, \src1, \src4, \src7, \src10 + calc_epelb v6, \src2, \src5, \src8, \src11 + subs w3, w3, #1 + st1 {v4.8h-v6.8h}, [x0], x10 +.endm +1: calc_all12 +.purgem calc +2: ret +endfunc + +function ff_hevc_put_hevc_epel_v32_8_neon, export=1 + load_epel_filterb x5, x4 + sub x1, x1, x2 + mov x10, #(MAX_PB_SIZE * 2) + ld1 {v16.16b, v17.16b}, [x1], x2 + ld1 {v18.16b, v19.16b}, [x1], x2 + ld1 {v20.16b, v21.16b}, [x1], x2 +.macro calc src0, src1, src2, src3, src4, src5, src6, src7 + ld1 {\src6\().16b, \src7\().16b}, [x1], x2 + movi v4.8h, #0 + movi v5.8h, #0 + movi v6.8h, #0 + movi v7.8h, #0 + calc_epelb v4, \src0, \src2, \src4, \src6 + calc_epelb2 v5, \src0, \src2, \src4, \src6 + calc_epelb v6, \src1, \src3, \src5, \src7 + calc_epelb2 v7, \src1, \src3, \src5, \src7 + subs w3, w3, #1 + st1 {v4.8h-v7.8h}, [x0], x10 +.endm +1: calc_all8 +.purgem calc +2: ret +endfunc + +function ff_hevc_put_hevc_epel_v48_8_neon, export=1 + load_epel_filterb x5, x4 + sub x1, x1, x2 + mov x10, #64 + ld1 {v16.16b, v17.16b, v18.16b}, [x1], x2 + ld1 {v19.16b, v20.16b, v21.16b}, [x1], x2 + ld1 {v22.16b, v23.16b, v24.16b}, [x1], x2 +.macro calc src0, src1, src2, src3, src4, src5, src6, src7, src8, src9, src10, src11 + ld1 {\src9\().16b, \src10\().16b, \src11\().16b}, [x1], x2 + movi v4.8h, #0 + movi v5.8h, #0 + movi v6.8h, #0 + movi v7.8h, #0 + movi v28.8h, #0 + movi v29.8h, #0 + calc_epelb v4, \src0, \src3, \src6, \src9 + calc_epelb2 v5, \src0, \src3, \src6, \src9 + calc_epelb v6, \src1, \src4, \src7, \src10 + calc_epelb2 v7, \src1, \src4, \src7, \src10 + calc_epelb v28, \src2, \src5, \src8, \src11 + calc_epelb2 v29, \src2, \src5, \src8, \src11 + st1 {v4.8h-v7.8h}, [x0], #64 + subs w3, w3, #1 + st1 {v28.8h-v29.8h}, [x0], x10 +.endm +1: calc_all12 +.purgem calc +2: ret +endfunc + +function ff_hevc_put_hevc_epel_v64_8_neon, export=1 + load_epel_filterb x5, x4 + sub sp, sp, #32 + st1 {v8.8b-v11.8b}, [sp] + sub x1, x1, x2 + ld1 {v16.16b, v17.16b, v18.16b, v19.16b}, [x1], x2 + ld1 {v20.16b, v21.16b, v22.16b, v23.16b}, [x1], x2 + ld1 {v24.16b, v25.16b, v26.16b, v27.16b}, [x1], x2 +.macro calc src0, src1, src2, src3, src4, src5, src6, src7, src8, src9, src10, src11, src12, src13, src14, src15 + ld1 {\src12\().16b-\src15\().16b}, [x1], x2 + movi v4.8h, #0 + movi v5.8h, #0 + movi v6.8h, #0 + movi v7.8h, #0 + movi v8.8h, #0 + movi v9.8h, #0 + movi v10.8h, #0 + movi v11.8h, #0 + calc_epelb v4, \src0, \src4, \src8, \src12 + calc_epelb2 v5, \src0, \src4, \src8, \src12 + calc_epelb v6, \src1, \src5, \src9, \src13 + calc_epelb2 v7, \src1, \src5, \src9, \src13 + calc_epelb v8, \src2, \src6, \src10, \src14 + calc_epelb2 v9, \src2, \src6, \src10, \src14 + calc_epelb v10, \src3, \src7, \src11, \src15 + calc_epelb2 v11, \src3, \src7, \src11, \src15 + st1 {v4.8h-v7.8h}, [x0], #64 + subs w3, w3, #1 + st1 {v8.8h-v11.8h}, [x0], #64 +.endm +1: calc_all16 +.purgem calc +2: ld1 {v8.8b-v11.8b}, [sp] + add sp, sp, #32 + ret +endfunc + function ff_hevc_put_hevc_epel_uni_v4_8_neon, export=1 load_epel_filterb x6, x5 sub x2, x2, x3 diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c index 4c377a7940..82e1623a67 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -156,6 +156,10 @@ NEON8_FNPROTO(pel_pixels, (int16_t *dst, const uint8_t *src, ptrdiff_t srcstride, int height, intptr_t mx, intptr_t my, int width),); +NEON8_FNPROTO(epel_v, (int16_t *dst, + const uint8_t *src, ptrdiff_t srcstride, + int height, intptr_t mx, intptr_t my, int width),); + NEON8_FNPROTO(pel_uni_pixels, (uint8_t *_dst, ptrdiff_t _dststride, const uint8_t *_src, ptrdiff_t _srcstride, int height, intptr_t mx, intptr_t my, int width),); @@ -305,6 +309,7 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext