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 97E6D4A94B for ; Mon, 6 May 2024 03:38:35 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 4720B68D51E; Mon, 6 May 2024 06:38:32 +0300 (EEST) Received: from out203-205-221-191.mail.qq.com (out203-205-221-191.mail.qq.com [203.205.221.191]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 9741B68D469 for ; Mon, 6 May 2024 06:38:24 +0300 (EEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=foxmail.com; s=s201512; t=1714966694; bh=TjL2BoJt1aJwB9AkpI9Dq4yUNpt6o7lRKqiPVLHWE1U=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=rUo9uBMN4cm9ZLpvEvMij91eR8FbqBuoAoO/Xjv8DLeZ1KCEkAe/SYsstbcx903uj jGhM2gfwDWY05rpyqHeyEEXbIsOt7viTCYS8ZPZ2ssZNtcr32wfHGDF1ZOTFrD2wyP TqkLI7rxV/WIFoZd8AglZyNFPF7gcPMX1bwqeemM= Received: from localhost.localdomain ([42.56.223.122]) by newxmesmtplogicsvrsza15-1.qq.com (NewEsmtp) with SMTP id 98B83073; Mon, 06 May 2024 11:38:11 +0800 X-QQ-mid: xmsmtpt1714966693tkd70582r Message-ID: X-QQ-XMAILINFO: N7WYGs5jwDno8n7+G9Bjj9EdOYmuCT5D8dHt8yLO3VWDgGo9CglAag0h0x2dOR yda2TRJa9YOP3bHzHSpKZaL3vQI5UJjGoY8EsBZK4XR0nq0akUL9HNKSe2Nj9xcu6yVinXCO9/oU gfmcI1nBNvvUJ116747MMpP0N/xYX7gY0+eWWKDTnPO1HOz6OA5yDIn8Pz+46bkmFuZD6rdsS5ST yU8loGigynoDNRA7SgYYFbZ2rUoKM5MK0c/6iKgtC1KRRmCGFbdbJTDv6xmkKajjI/MYViTYWwF6 q4AFvB/7QFU1SCGkQXuRNxdFVAtkGgaJFX2axTl/m3NY2x5XfmkDowynfM2DUj4RrZElkSGiqWHL IV+4x+qswf+aAMRfxFqQZ5cCUbXhW9Nsu9N5B2/Q/a22xcgfgzyP7jZlF7QJ48bIjpOeOf5Gy0iM g6TSwC6KCw7C5DMLp/AXSRxiMcD2YUKf0oMl9ALAaIlhMuknl9FUFPTieUx0KUzoFqMt/1l2bMOt bTtdQ0UyZrb8vBIWsDTQQg2LLYo1kKmAKPvUhQwjDvZywDxrF1tcrs9E8fPja3cIzsi335t0VUHW Fw1HNshTl7nUe9iX0bLs3yt2s/XoZLefWzJfk9WhH32BiFPChz04AIdJu41xx8Fl4QPWaD2g7LX1 k3a9uJstr4wI55RuVRdxkNW5jFlxWn6zGJwzT5/GcF5Ki2Vnt0Wq0vEKQeuoBupJeeKROO8M4xk/ RiFG+HQKvrfm581vGQBt9nXWrEYHcTUcMVRlRR43Jf2r2TBssclU4DrzmaL74hWnD1ypJ2M7wYqK WahjpC88cVaNGk8jqhlGDV3a7MafCMhu9UNpjBdZj9ofPYaiJBvwkiVCBX4RCeEHLFkxgy1A8FeP IsOlE53ely2F/1KQ/S+tVAfs01J9GxSUM9Uvb1B1WnRdpaMNs+oQDb+7RzGLjByZAVtRi4ANy+ X-QQ-XMRINFO: NS+P29fieYNw95Bth2bWPxk= From: uk7b@foxmail.com To: ffmpeg-devel@ffmpeg.org Date: Mon, 6 May 2024 11:38:02 +0800 X-OQ-MSGID: <20240506033809.3790245-2-uk7b@foxmail.com> X-Mailer: git-send-email 2.45.0 In-Reply-To: <20240506033809.3790245-1-uk7b@foxmail.com> References: <20240506033809.3790245-1-uk7b@foxmail.com> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH v3 2/9] lavc/vp8dsp: R-V V put_bilin_h v 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: sunyuechi 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: From: sunyuechi C908: vp8_put_bilin4_h_c: 367.0 vp8_put_bilin4_h_rvv_i32: 137.7 vp8_put_bilin4_v_c: 377.0 vp8_put_bilin4_v_rvv_i32: 137.7 vp8_put_bilin8_h_c: 1431.0 vp8_put_bilin8_h_rvv_i32: 297.5 vp8_put_bilin8_v_c: 1449.0 vp8_put_bilin8_v_rvv_i32: 297.5 vp8_put_bilin16_h_c: 2839.0 vp8_put_bilin16_h_rvv_i32: 344.7 vp8_put_bilin16_v_c: 2857.0 vp8_put_bilin16_v_rvv_i32: 344.7 --- libavcodec/riscv/vp8dsp_init.c | 21 +++++++++++++++ libavcodec/riscv/vp8dsp_rvv.S | 49 ++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+) diff --git a/libavcodec/riscv/vp8dsp_init.c b/libavcodec/riscv/vp8dsp_init.c index fa3feeacf7..afffa6de2f 100644 --- a/libavcodec/riscv/vp8dsp_init.c +++ b/libavcodec/riscv/vp8dsp_init.c @@ -34,6 +34,10 @@ VP8_EPEL(16, rvi); VP8_EPEL(8, rvi); VP8_EPEL(4, rvi); +VP8_BILIN(16, rvv); +VP8_BILIN(8, rvv); +VP8_BILIN(4, rvv); + av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c) { #if HAVE_RV @@ -48,6 +52,23 @@ av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c) c->put_vp8_epel_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvi; c->put_vp8_bilinear_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvi; } +#if HAVE_RVV + if (flags & AV_CPU_FLAG_RVV_I32 && ff_get_rv_vlenb() >= 16) { + c->put_vp8_bilinear_pixels_tab[0][0][1] = ff_put_vp8_bilin16_h_rvv; + c->put_vp8_bilinear_pixels_tab[0][0][2] = ff_put_vp8_bilin16_h_rvv; + c->put_vp8_bilinear_pixels_tab[1][0][1] = ff_put_vp8_bilin8_h_rvv; + c->put_vp8_bilinear_pixels_tab[1][0][2] = ff_put_vp8_bilin8_h_rvv; + c->put_vp8_bilinear_pixels_tab[2][0][1] = ff_put_vp8_bilin4_h_rvv; + c->put_vp8_bilinear_pixels_tab[2][0][2] = ff_put_vp8_bilin4_h_rvv; + + c->put_vp8_bilinear_pixels_tab[0][1][0] = ff_put_vp8_bilin16_v_rvv; + c->put_vp8_bilinear_pixels_tab[0][2][0] = ff_put_vp8_bilin16_v_rvv; + c->put_vp8_bilinear_pixels_tab[1][1][0] = ff_put_vp8_bilin8_v_rvv; + c->put_vp8_bilinear_pixels_tab[1][2][0] = ff_put_vp8_bilin8_v_rvv; + c->put_vp8_bilinear_pixels_tab[2][1][0] = ff_put_vp8_bilin4_v_rvv; + c->put_vp8_bilinear_pixels_tab[2][2][0] = ff_put_vp8_bilin4_v_rvv; + } +#endif #endif } diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S index 8a0773f964..9bf969d794 100644 --- a/libavcodec/riscv/vp8dsp_rvv.S +++ b/libavcodec/riscv/vp8dsp_rvv.S @@ -20,6 +20,18 @@ #include "libavutil/riscv/asm.S" +.macro vsetvlstatic8 len +.if \len <= 4 + vsetivli zero, \len, e8, mf4, ta, ma +.elseif \len <= 8 + vsetivli zero, \len, e8, mf2, ta, ma +.elseif \len <= 16 + vsetivli zero, \len, e8, m1, ta, ma +.elseif \len <= 31 + vsetivli zero, \len, e8, m2, ta, ma +.endif +.endm + .macro vp8_idct_dc_add vlse32.v v0, (a0), a2 lh a5, 0(a1) @@ -71,3 +83,40 @@ func ff_vp8_idct_dc_add4uv_rvv, zve32x ret endfunc + +.macro bilin_load dst len type mn +.ifc \type,v + add t5, a2, a3 +.elseif \type == h + addi t5, a2, 1 +.endif + vle8.v \dst, (a2) + vle8.v v2, (t5) + vwmulu.vx v28, \dst, t1 + vwmaccu.vx v28, \mn, v2 + vwaddu.wx v24, v28, t4 + vnsra.wi \dst, v24, 3 +.endm + +.macro put_vp8_bilin_h_v len type mn +func ff_put_vp8_bilin\len\()_\type\()_rvv, zve32x + vsetvlstatic8 \len + li t1, 8 + li t4, 4 + sub t1, t1, \mn +1: + addi a4, a4, -1 + bilin_load v0, \len, \type, \mn + vse8.v v0, (a0) + add a2, a2, a3 + add a0, a0, a1 + bnez a4, 1b + + ret +endfunc +.endm + +.irp len 16,8,4 +put_vp8_bilin_h_v \len h a5 +put_vp8_bilin_h_v \len v a6 +.endr -- 2.45.0 _______________________________________________ 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".