From patchwork Tue Jun 4 18:59:05 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= X-Patchwork-Id: 49557 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a59:d153:0:b0:460:55fa:d5ed with SMTP id bt19csp96381vqb; Tue, 4 Jun 2024 11:59:19 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCW4tsJrB2KjUooCusfXXT+M9Gnb2yeiqoT0psZQo4VoavhQ1MU8Le89U6W5xNGOGFdZyI9tEJqEs9xDcPQNetD0QJonbYsfNgaY3Q== X-Google-Smtp-Source: AGHT+IGopu9GltfstxMtrg67htR6xfoDr+z7LagryhIcv44A3pYIdkh+JSepax6h1nYo0V37o8BD X-Received: by 2002:a50:d75b:0:b0:572:9b20:fa with SMTP id 4fb4d7f45d1cf-57a8bc918a9mr283183a12.33.1717527559292; Tue, 04 Jun 2024 11:59:19 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1717527559; cv=none; d=google.com; s=arc-20160816; b=X4TxP3rsnRzN6vipdpOVUiOdrifRpo7ekZ3DvWLtAP3q5QIYDsoxhwVaqsHsrP9Sj+ x649BXFGqz99bZwr3dI0TN8fU4irgMcIebmd3cMKEpbLtUMrn/ECP7EBV/a1boC6fVfs RfTlKMLmAZkRTAimWyJjjvGHa5h/4y4sbeq8bfV8a+tDwSFUEZ9sThteq4FM7w/lDSIG gVCX8NZnywWrF6R10+TnFt0uEpES2Cr+4zgkFpEn3BnjVO4TfP4dDsSd/RC1qi1QYqUr GwX4kCCf3MwvD7ljcoSiqGZipdL6AnMk67sywGP4yRpWykrSAd5C6MX02qtKoYXv8FDY vhRQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:reply-to:list-subscribe :list-help:list-post:list-archive:list-unsubscribe:list-id :precedence:subject:mime-version:message-id:date:to:from :delivered-to; bh=ZHFWvoodgETTazr/vCvpRUBI8umL118w6VQxCl4/6Yg=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=PImfMiRShIKaDqn5r6QQX/T08b30ZW4dV805++Pzvn1Em70EAm/IqVy4lzQYmdSPJs MTbWBqq4PP6M7FkJcK6fcK4Gk3U/Ev4VlIojbYSzEoV7Xo93hlqocmLo5HN9zX070f2G hnxrk7m5uZTkWAqGCgQzk5qt/OLDWKT2octkGR6FRU7MvB58lVTf6vTN1EWfyK90lkJa hbHhLEBB7on8VzO8rtpL/wQUUs2NMSNFI7E5SuW39dEdGkX4ld6WuoX2xrCBUh5uUcf+ IeFO6OJF/hSRnwVRx4ufSWF5/0W+/b5kSrQW36UQxjLul18io6s0RkGEN4lq1GNTJkMU CLoQ==; dara=google.com 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 4fb4d7f45d1cf-57a31b80387si5318490a12.134.2024.06.04.11.59.18; Tue, 04 Jun 2024 11:59:19 -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 7633268D6FD; Tue, 4 Jun 2024 21:59:16 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from ursule.remlab.net (vps-a2bccee9.vps.ovh.net [51.75.19.47]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 647E268D47D for ; Tue, 4 Jun 2024 21:59:09 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id 900C8C0138 for ; Tue, 4 Jun 2024 21:59:08 +0300 (EEST) From: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Tue, 4 Jun 2024 21:59:05 +0300 Message-ID: <20240604185908.22309-1-remi@remlab.net> X-Mailer: git-send-email 2.45.1 MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCHv2 1/4] lavc/vc1dsp: R-V V vc1_inv_trans_8x8 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: aNzr7ctPJQIU T-Head C908 (cycles): vc1dsp.vc1_inv_trans_8x8_c: 871.7 vc1dsp.vc1_inv_trans_8x8_rvv_i32: 286.7 --- Changes since version 1: - Use fixed-point rounding instead of adding 4 or 64 explicitly. --- libavcodec/riscv/vc1dsp_init.c | 2 + libavcodec/riscv/vc1dsp_rvv.S | 110 +++++++++++++++++++++++++++++++++ 2 files changed, 112 insertions(+) diff --git a/libavcodec/riscv/vc1dsp_init.c b/libavcodec/riscv/vc1dsp_init.c index e4838fb347..b8a1015ce5 100644 --- a/libavcodec/riscv/vc1dsp_init.c +++ b/libavcodec/riscv/vc1dsp_init.c @@ -26,6 +26,7 @@ #include "libavcodec/vc1.h" void ff_vc1_inv_trans_8x8_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); +void ff_vc1_inv_trans_8x8_rvv(int16_t block[64]); void ff_vc1_inv_trans_4x8_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_8x4_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_4x4_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); @@ -53,6 +54,7 @@ av_cold void ff_vc1dsp_init_riscv(VC1DSPContext *dsp) # if HAVE_RVV if (flags & AV_CPU_FLAG_RVV_I32) { if (ff_rv_vlen_least(128)) { + dsp->vc1_inv_trans_8x8 = ff_vc1_inv_trans_8x8_rvv; dsp->vc1_inv_trans_4x8_dc = ff_vc1_inv_trans_4x8_dc_rvv; dsp->vc1_inv_trans_4x4_dc = ff_vc1_inv_trans_4x4_dc_rvv; dsp->avg_vc1_mspel_pixels_tab[0][0] = ff_avg_pixels16x16_rvv; diff --git a/libavcodec/riscv/vc1dsp_rvv.S b/libavcodec/riscv/vc1dsp_rvv.S index 8b3a830a4a..e15783d113 100644 --- a/libavcodec/riscv/vc1dsp_rvv.S +++ b/libavcodec/riscv/vc1dsp_rvv.S @@ -113,6 +113,116 @@ func ff_vc1_inv_trans_4x4_dc_rvv, zve32x ret endfunc + .variant_cc ff_vc1_inv_trans_8_rvv +func ff_vc1_inv_trans_8_rvv, zve32x + li t4, 12 + vsll.vi v18, v6, 4 + li t2, 6 + vmul.vx v8, v0, t4 + li t5, 15 + vmul.vx v10, v4, t4 + li t3, 9 + # t[2..5] = [6 9 12 15] + vsll.vi v12, v2, 4 + vmul.vx v14, v6, t2 + vmul.vx v16, v2, t2 + vadd.vv v26, v12, v14 # t3 + vadd.vv v24, v8, v10 # t1 + vsub.vv v25, v8, v10 # t2 + vsub.vv v27, v16, v18 # t4 + vadd.vv v28, v24, v26 # t5 + vsub.vv v31, v24, v26 # t8 + vadd.vv v29, v25, v27 # t6 + vsub.vv v30, v25, v27 # t7 + vsll.vi v20, v1, 4 + vmul.vx v21, v3, t5 + vmul.vx v22, v5, t3 + vsll.vi v23, v7, 2 + vadd.vv v20, v20, v21 + vadd.vv v22, v22, v23 + vsll.vi v21, v3, 2 + vadd.vv v16, v20, v22 # t1 + vmul.vx v20, v1, t5 + vsll.vi v22, v5, 4 + vmul.vx v23, v7, t3 + vsub.vv v20, v20, v21 + vadd.vv v22, v22, v23 + vsll.vi v21, v3, 4 + vsub.vv v17, v20, v22 # t2 + vmul.vx v20, v1, t3 + vsll.vi v22, v5, 2 + vmul.vx v23, v7, t5 + vsub.vv v20, v20, v21 + vadd.vv v22, v22, v23 + vmul.vx v21, v3, t3 + vadd.vv v18, v20, v22 # t3 + vsll.vi v20, v1, 2 + vmul.vx v22, v5, t5 + vsll.vi v23, v7, 4 + vsub.vv v20, v20, v21 + vsub.vv v22, v22, v23 + vadd.vv v0, v28, v16 + vadd.vv v19, v20, v22 # t4 + vadd.vv v1, v29, v17 + vadd.vv v2, v30, v18 + vadd.vv v3, v31, v19 + vsub.vv v4, v31, v19 + vsub.vv v5, v30, v18 + vsub.vv v6, v29, v17 + vsub.vv v7, v28, v16 + jr t0 +endfunc + +func ff_vc1_inv_trans_8x8_rvv, zve32x + csrwi vxrm, 0 + vsetivli zero, 8, e16, m1, ta, ma + addi a1, a0, 1 * 8 * 2 + vle16.v v0, (a0) + addi a2, a0, 2 * 8 * 2 + vle16.v v1, (a1) + addi a3, a0, 3 * 8 * 2 + vle16.v v2, (a2) + addi a4, a0, 4 * 8 * 2 + vle16.v v3, (a3) + addi a5, a0, 5 * 8 * 2 + vle16.v v4, (a4) + addi a6, a0, 6 * 8 * 2 + vle16.v v5, (a5) + addi a7, a0, 7 * 8 * 2 + vle16.v v6, (a6) + vle16.v v7, (a7) + jal t0, ff_vc1_inv_trans_8_rvv + .irp n,0,1,2,3,4,5,6,7 + vssra.vi v\n, v\n, 3 + .endr + vsseg8e16.v v0, (a0) + .irp n,0,1,2,3,4,5,6,7 + vle16.v v\n, (a\n) + .endr + jal t0, ff_vc1_inv_trans_8_rvv + vadd.vi v4, v4, 1 + vadd.vi v5, v5, 1 + vssra.vi v4, v4, 7 + vssra.vi v5, v5, 7 + vse16.v v4, (a4) + vadd.vi v6, v6, 1 + vse16.v v5, (a5) + vadd.vi v7, v7, 1 + vssra.vi v6, v6, 7 + vssra.vi v7, v7, 7 + vse16.v v6, (a6) + vssra.vi v0, v0, 7 + vse16.v v7, (a7) + vssra.vi v1, v1, 7 + vse16.v v0, (a0) + vssra.vi v2, v2, 7 + vse16.v v1, (a1) + vssra.vi v3, v3, 7 + vse16.v v2, (a2) + vse16.v v3, (a3) + ret +endfunc + .macro mspel_op op pos n1 n2 add t1, \pos, a2 v\op\()e8.v v\n1, (\pos) From patchwork Tue Jun 4 18:59:06 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= X-Patchwork-Id: 49558 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a59:d153:0:b0:460:55fa:d5ed with SMTP id bt19csp96437vqb; Tue, 4 Jun 2024 11:59:28 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWfsqC3yUZmRB7JVSqEgy3XbUixucIB5I6kcKLwHFTflU/qQbGUo8IlpVjVtDXpdnAN0QxwLeGUhVXk1QEAkebGu9VFv5ZSgryjMQ== X-Google-Smtp-Source: AGHT+IHz8mrCKq4Do88lu+97cI5+Q0KQIbaVdSieovjwTBncBKxDgVfmlvUbin5b+p3vZ+SCOrxY X-Received: by 2002:a50:aa93:0:b0:578:5d4c:9401 with SMTP id 4fb4d7f45d1cf-57a8b7c612amr331124a12.28.1717527568103; Tue, 04 Jun 2024 11:59:28 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1717527568; cv=none; d=google.com; s=arc-20160816; b=SksY6KNPVVQglb2qVWvHnRRCgqpoYUwvde8idtwq0qh1o62+Jm0F4G+qYWBTamllE7 njJDt7UVJOtLdjuysRGcqUb8pIcG/io6vfvHxCE9m+amIaUm3Ez6U5svoH6dceeTgz/V XAzuNJdrgQ69iuIgdWKz3Kf1JHgB5/e2Ttldx0GbsMoDcNgN1PXWM1yeUOSI9waZY4kU rx0L/pYqTLGjSyvZRa0ZEdQMjsd+lgbvsM4Y+GucfK00plHEv1jMCFxgGK2mrRVmVppX ++0hQ223QkFQSieHGAU1Tm4QKdszKgEUA0ZsuCodfRSgnnjJLXpcgdX7I0Pqs+RBLL6H W5zA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:reply-to:list-subscribe :list-help:list-post:list-archive:list-unsubscribe:list-id :precedence:subject:mime-version:references:in-reply-to:message-id :date:to:from:delivered-to; bh=7GjEs9I/1/k32Mnx3opNJMFVR18Ns3HcrXUX+Hx+oww=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=u8/u8bXbWiXgIlh5m7Wb04L3rog7Yt6h/Je77y62ltcnTS0OtRG6B8VEh6hnQNeEeZ CjYiTZsTiLfu6DZGqcb4ZBWytWALqBLKyl9ViK9oYCVZzMegCK/pOBfF1XHHW+mVA56g rrrtScIFxYvWkF9AOe8ssbrUNLEIMW2Fr/uvyjArbXhwd7fgOcJt8KG6jo+vRDCEfumD IZMUylAosvjRMYww9fjqgAeCuk4rU8VCJdX4GGs5rqxyC1oB4u4lIajP9gL4qbVACmu3 fhtFs4EO0UMgVOxGQwbT3I/2LqOfS6GY9jHxAfvf0lIttJ/baqPk3weoSdVRJlmdZtQ5 x6QQ==; dara=google.com 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 4fb4d7f45d1cf-57a31ca5f11si5392096a12.574.2024.06.04.11.59.27; Tue, 04 Jun 2024 11:59:28 -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 65B8268D6FE; Tue, 4 Jun 2024 21:59:17 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from ursule.remlab.net (vps-a2bccee9.vps.ovh.net [51.75.19.47]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 598E868D2C1 for ; Tue, 4 Jun 2024 21:59:09 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id C1F53C018B for ; Tue, 4 Jun 2024 21:59:08 +0300 (EEST) From: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Tue, 4 Jun 2024 21:59:06 +0300 Message-ID: <20240604185908.22309-2-remi@remlab.net> X-Mailer: git-send-email 2.45.1 In-Reply-To: <20240604185908.22309-1-remi@remlab.net> References: <20240604185908.22309-1-remi@remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCHv2 2/4] lavc/vc1dsp: R-V V vc1_inv_trans_8x4 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: DicZ1MNy4Gyd T-Head C908 (cycles): vc1dsp.vc1_inv_trans_8x4_c: 626.2 vc1dsp.vc1_inv_trans_8x4_rvv_i32: 215.2 --- Changes since version 1: - Properly set VXRM (callee-clobbered). --- libavcodec/riscv/vc1dsp_init.c | 2 + libavcodec/riscv/vc1dsp_rvv.S | 73 ++++++++++++++++++++++++++++++++++ 2 files changed, 75 insertions(+) diff --git a/libavcodec/riscv/vc1dsp_init.c b/libavcodec/riscv/vc1dsp_init.c index b8a1015ce5..e63870ad44 100644 --- a/libavcodec/riscv/vc1dsp_init.c +++ b/libavcodec/riscv/vc1dsp_init.c @@ -29,6 +29,7 @@ void ff_vc1_inv_trans_8x8_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block void ff_vc1_inv_trans_8x8_rvv(int16_t block[64]); void ff_vc1_inv_trans_4x8_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_8x4_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); +void ff_vc1_inv_trans_8x4_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_4x4_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_put_pixels16x16_rvi(uint8_t *dst, const uint8_t *src, ptrdiff_t line_size, int rnd); void ff_put_pixels8x8_rvi(uint8_t *dst, const uint8_t *src, ptrdiff_t line_size, int rnd); @@ -55,6 +56,7 @@ av_cold void ff_vc1dsp_init_riscv(VC1DSPContext *dsp) if (flags & AV_CPU_FLAG_RVV_I32) { if (ff_rv_vlen_least(128)) { dsp->vc1_inv_trans_8x8 = ff_vc1_inv_trans_8x8_rvv; + dsp->vc1_inv_trans_8x4 = ff_vc1_inv_trans_8x4_rvv; dsp->vc1_inv_trans_4x8_dc = ff_vc1_inv_trans_4x8_dc_rvv; dsp->vc1_inv_trans_4x4_dc = ff_vc1_inv_trans_4x4_dc_rvv; dsp->avg_vc1_mspel_pixels_tab[0][0] = ff_avg_pixels16x16_rvv; diff --git a/libavcodec/riscv/vc1dsp_rvv.S b/libavcodec/riscv/vc1dsp_rvv.S index e15783d113..d003185ade 100644 --- a/libavcodec/riscv/vc1dsp_rvv.S +++ b/libavcodec/riscv/vc1dsp_rvv.S @@ -173,6 +173,31 @@ func ff_vc1_inv_trans_8_rvv, zve32x jr t0 endfunc + .variant_cc ff_vc1_inv_trans_4_rvv +func ff_vc1_inv_trans_4_rvv, zve32x + li t3, 17 + vmul.vx v8, v0, t3 + li t4, 22 + vmul.vx v10, v2, t3 + li t2, 10 + vmul.vx v14, v1, t4 + vadd.vv v24, v8, v10 # t1 + vsub.vv v25, v8, v10 # t2 + vmul.vx v16, v3, t2 + vmul.vx v18, v3, t4 + vmul.vx v20, v1, t2 + vadd.vv v26, v14, v16 # t3 + vsub.vv v27, v18, v20 # t4 + vadd.vv v0, v24, v26 + vsub.vv v1, v25, v27 + vadd.vv v2, v25, v27 + vsub.vv v3, v24, v26 + .irp n,0,1,2,3 + vssra.vx v\n, v\n, t1 # + 4 >> 3 or + 64 >> 7 + .endr + jr t0 +endfunc + func ff_vc1_inv_trans_8x8_rvv, zve32x csrwi vxrm, 0 vsetivli zero, 8, e16, m1, ta, ma @@ -223,6 +248,54 @@ func ff_vc1_inv_trans_8x8_rvv, zve32x ret endfunc +func ff_vc1_inv_trans_8x4_rvv, zve32x + csrwi vxrm, 0 + vsetivli zero, 4, e16, mf2, ta, ma + vlseg8e16.v v0, (a2) + jal t0, ff_vc1_inv_trans_8_rvv + vsseg8e16.v v0, (a2) + addi a3, a2, 1 * 8 * 2 + vsetivli zero, 8, e16, m1, ta, ma + vle16.v v0, (a2) + addi a4, a2, 2 * 8 * 2 + vle16.v v1, (a3) + addi a5, a2, 3 * 8 * 2 + vle16.v v2, (a4) + vle16.v v3, (a5) + .irp n,0,1,2,3 + # shift 4 vectors of 8 elems after transpose instead of 8 of 4 + vssra.vi v\n, v\n, 3 + .endr + li t1, 7 + jal t0, ff_vc1_inv_trans_4_rvv + add a3, a1, a0 + vle8.v v8, (a0) + add a4, a1, a3 + vle8.v v9, (a3) + add a5, a1, a4 + vle8.v v10, (a4) + vle8.v v11, (a5) + vsetvli zero, zero, e8, mf2, ta, ma + vwaddu.wv v0, v0, v8 + vwaddu.wv v1, v1, v9 + vwaddu.wv v2, v2, v10 + vwaddu.wv v3, v3, v11 + vsetvli zero, zero, e16, m1, ta, ma + .irp n,0,1,2,3 + vmax.vx v\n, v\n, zero + .endr + vsetvli zero, zero, e8, mf2, ta, ma + vnclipu.wi v8, v0, 0 + vnclipu.wi v9, v1, 0 + vse8.v v8, (a0) + vnclipu.wi v10, v2, 0 + vse8.v v9, (a3) + vnclipu.wi v11, v3, 0 + vse8.v v10, (a4) + vse8.v v11, (a5) + ret +endfunc + .macro mspel_op op pos n1 n2 add t1, \pos, a2 v\op\()e8.v v\n1, (\pos) From patchwork Tue Jun 4 18:59:07 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= X-Patchwork-Id: 49559 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a59:d153:0:b0:460:55fa:d5ed with SMTP id bt19csp96504vqb; Tue, 4 Jun 2024 11:59:37 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCVALd9JwwIMERfCVrL3csUUy/6eRawQGxZC4bqzdhV7TaZgkXBw0Gf83lWj6AcLZZUyP/A7fkmHMuI8y8RNZKg1afpXqNq0ggMgOA== X-Google-Smtp-Source: AGHT+IFlTeiNV0oClo0EY+WH5QOP1/P83NK3j+OxFXFkFWZL1cJJ8625CcQreqouxnsIZoOjLjW6 X-Received: by 2002:a17:906:3511:b0:a63:cb4e:9a10 with SMTP id a640c23a62f3a-a69a02688afmr21490666b.77.1717527577114; Tue, 04 Jun 2024 11:59:37 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1717527577; cv=none; d=google.com; s=arc-20160816; b=Gj1fgRLG4D+cdEclj6jIKUCoYGEV9pD0CJE1pB4KXfwihHddA+o/NHjH0SGTysQBzP 87NP5p+Q0+eVns61uk5uAOVqEo4yLz3XaBO8M1HJL7qoCmUwp/fkYatL9enHz67f+KmG 7yb9mspIKoFte+4bWzxNWBni43pI2ZSWmfyARcaZN3dyd7jPzBz8/X1QjmUnXEpwrcXn 3m+4vXIBoxkT0zlb+UeAaHxQ0KQRy3R8AXuKlUAGGffWNhAycXSZGSvfssIe7+VaZBrS kT4I/aBa65acBDrugqq1CkqQMxBvvylPFFxdIY3/PaQ6ChWduzFiwCU8fe+/fqIsGmFk 6EqA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:reply-to:list-subscribe :list-help:list-post:list-archive:list-unsubscribe:list-id :precedence:subject:mime-version:references:in-reply-to:message-id :date:to:from:delivered-to; bh=GX2XcwyIESKQfih463d5X8wgcPGQu1TzhknM1zTICZQ=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=TqrYXiSBBmBREyiNhvhs7ls5/ZxouIwAPaf6JTxY1M9Q3Uy4YMk5Nd4f6zSO2MEb5K 54oZhdrs+SDyUSflPJLfhndLyXx6l4IGSLIkysQtgC7P1AVZ2KUUYLBtA1l2kpdNPtmy K0yZYj69yFFmNkgHuMasVOVkRtiKFpGVAKP2+yu5A6oMuSj6OTP4tQlKo2VZaxrbVE5D Tv7/BbeVeqHhHIGVvia1ddu7g0XfTLPpRKVjanxymb1J+fmITYbEjrHq2SoyqcmdRFYx y8t8TI8xsmxo40cg9Mi04hOFZeZcoLt4M9P27folLUhCiOFfS/PzvJtTiiKLu17PSVYm TtQA==; dara=google.com 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 a640c23a62f3a-a692e696334si151229366b.79.2024.06.04.11.59.36; Tue, 04 Jun 2024 11:59:37 -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 DA07768D6FF; Tue, 4 Jun 2024 21:59:18 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from ursule.remlab.net (vps-a2bccee9.vps.ovh.net [51.75.19.47]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 67AA468D4AF for ; Tue, 4 Jun 2024 21:59:09 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id F2A66C02E8 for ; Tue, 4 Jun 2024 21:59:08 +0300 (EEST) From: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Tue, 4 Jun 2024 21:59:07 +0300 Message-ID: <20240604185908.22309-3-remi@remlab.net> X-Mailer: git-send-email 2.45.1 In-Reply-To: <20240604185908.22309-1-remi@remlab.net> References: <20240604185908.22309-1-remi@remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCHv2 3/4] lavc/vc1dsp: R-V V vc1_inv_trans_4x8 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: FanE79RyYZig T-Head C908 (cycles): vc1dsp.vc1_inv_trans_4x8_c: 653.2 vc1dsp.vc1_inv_trans_4x8_rvv_i32: 234.0 --- libavcodec/riscv/vc1dsp_init.c | 2 + libavcodec/riscv/vc1dsp_rvv.S | 77 ++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+) diff --git a/libavcodec/riscv/vc1dsp_init.c b/libavcodec/riscv/vc1dsp_init.c index e63870ad44..cf9d42f377 100644 --- a/libavcodec/riscv/vc1dsp_init.c +++ b/libavcodec/riscv/vc1dsp_init.c @@ -28,6 +28,7 @@ void ff_vc1_inv_trans_8x8_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_8x8_rvv(int16_t block[64]); void ff_vc1_inv_trans_4x8_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); +void ff_vc1_inv_trans_4x8_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_8x4_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_8x4_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_4x4_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); @@ -57,6 +58,7 @@ av_cold void ff_vc1dsp_init_riscv(VC1DSPContext *dsp) if (ff_rv_vlen_least(128)) { dsp->vc1_inv_trans_8x8 = ff_vc1_inv_trans_8x8_rvv; dsp->vc1_inv_trans_8x4 = ff_vc1_inv_trans_8x4_rvv; + dsp->vc1_inv_trans_4x8 = ff_vc1_inv_trans_4x8_rvv; dsp->vc1_inv_trans_4x8_dc = ff_vc1_inv_trans_4x8_dc_rvv; dsp->vc1_inv_trans_4x4_dc = ff_vc1_inv_trans_4x4_dc_rvv; dsp->avg_vc1_mspel_pixels_tab[0][0] = ff_avg_pixels16x16_rvv; diff --git a/libavcodec/riscv/vc1dsp_rvv.S b/libavcodec/riscv/vc1dsp_rvv.S index d003185ade..e22950d25d 100644 --- a/libavcodec/riscv/vc1dsp_rvv.S +++ b/libavcodec/riscv/vc1dsp_rvv.S @@ -296,6 +296,83 @@ func ff_vc1_inv_trans_8x4_rvv, zve32x ret endfunc +func ff_vc1_inv_trans_4x8_rvv, zve32x + li a3, 8 * 2 + csrwi vxrm, 0 + vsetivli zero, 8, e16, m1, ta, ma + vlsseg4e16.v v0, (a2), a3 + li t1, 3 + jal t0, ff_vc1_inv_trans_4_rvv + addi t1, a2, 1 * 8 * 2 + vse16.v v0, (a2) + addi t2, a2, 2 * 8 * 2 + vse16.v v1, (t1) + addi t3, a2, 3 * 8 * 2 + vse16.v v2, (t2) + vse16.v v3, (t3) + vsetivli zero, 4, e16, mf2, ta, ma + vlseg8e16.v v0, (a2) + jal t0, ff_vc1_inv_trans_8_rvv + vadd.vi v4, v4, 1 + add t0, a1, a0 + vadd.vi v5, v5, 1 + vadd.vi v6, v6, 1 + add t1, a1, t0 + vadd.vi v7, v7, 1 + vssra.vi v0, v0, 7 + add t2, a1, t1 + vssra.vi v1, v1, 7 + vssra.vi v2, v2, 7 + add t3, a1, t2 + vssra.vi v3, v3, 7 + vssra.vi v4, v4, 7 + add t4, a1, t3 + vssra.vi v5, v5, 7 + vssra.vi v6, v6, 7 + add t5, a1, t4 + vssra.vi v7, v7, 7 + vle8.v v8, (a0) + add t6, a1, t5 + vle8.v v9, (t0) + vle8.v v10, (t1) + vle8.v v11, (t2) + vle8.v v12, (t3) + vle8.v v13, (t4) + vle8.v v14, (t5) + vle8.v v15, (t6) + vsetvli zero, zero, e8, mf4, ta, ma + vwaddu.wv v0, v0, v8 + vwaddu.wv v1, v1, v9 + vwaddu.wv v2, v2, v10 + vwaddu.wv v3, v3, v11 + vwaddu.wv v4, v4, v12 + vwaddu.wv v5, v5, v13 + vwaddu.wv v6, v6, v14 + vwaddu.wv v7, v7, v15 + vsetvli zero, zero, e16, mf2, ta, ma + .irp n,0,1,2,3,4,5,6,7 + vmax.vx v\n, v\n, zero + .endr + vsetvli zero, zero, e8, mf4, ta, ma + vnclipu.wi v8, v0, 0 + vnclipu.wi v9, v1, 0 + vse8.v v8, (a0) + vnclipu.wi v10, v2, 0 + vse8.v v9, (t0) + vnclipu.wi v11, v3, 0 + vse8.v v10, (t1) + vnclipu.wi v12, v4, 0 + vse8.v v11, (t2) + vnclipu.wi v13, v5, 0 + vse8.v v12, (t3) + vnclipu.wi v14, v6, 0 + vse8.v v13, (t4) + vnclipu.wi v15, v7, 0 + vse8.v v14, (t5) + vse8.v v15, (t6) + ret +endfunc + .macro mspel_op op pos n1 n2 add t1, \pos, a2 v\op\()e8.v v\n1, (\pos) From patchwork Tue Jun 4 18:59:08 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= X-Patchwork-Id: 49556 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a59:d153:0:b0:460:55fa:d5ed with SMTP id bt19csp96567vqb; Tue, 4 Jun 2024 11:59:47 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCX2ih+80ycGsDmC6U4PUypM53Q1Hm3MJdum4rKlef7eOpDwLEtMXHT8+Pp752RWi7uQAiIpdxGqi+im9ZP8ZHY5Tg8aybXpgEX52A== X-Google-Smtp-Source: AGHT+IHJ8VCmnUZUuPpsO9HRJc5sWhls4XVrIqOvwXTjMdwcEGkB4nQmcicvv67ZMetFwlrwCw4R X-Received: by 2002:a17:907:2717:b0:a63:41f7:d46 with SMTP id a640c23a62f3a-a699fa933a1mr19917866b.17.1717527586949; Tue, 04 Jun 2024 11:59:46 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1717527586; cv=none; d=google.com; s=arc-20160816; b=ncJUklCEpBDYgpjwRsiinU7kWmX5kuyCGI8SSrqOxeGYbs5czkoWVUQxbeENP2vjx5 z5LPwh26/f9/6yX+UpAyDCMY59fwCgJL0g8adnp8iVy/9m4Wls1MjAOfCNzrVNpIe9qd wSTNAedkiBjGhSY2LkwOzXlYoLODUIAxAHMwvQ1RrHl8KHTV0N99wRAWYvCtfkbpcRMi UsegrRJLbgWM1LcnTPeuheNHfg8eGF7Hy4DR7QLjtTrU+1DY8j/aq6ommSHjq5HqiR5w 3x7SH8awLWzCDEQ9pdEOjYruJYoOXshphhXSte29t0IFh/voz4VkorvhfPpgGAPyq5G2 aaRQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:reply-to:list-subscribe :list-help:list-post:list-archive:list-unsubscribe:list-id :precedence:subject:mime-version:references:in-reply-to:message-id :date:to:from:delivered-to; bh=v2YUgWgOQkALVUex6byVyqhWrtaDEnzPddMh69BB07k=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=uQUxQ5U6FFhIrtE/YpmdmMcFi2CRASANugxmPNhLARK7ejCMrUhBDQ6bVa2ukA3Jb0 Gf7v6SZstHa+0T+A3FgdxWUH3mCzTduw6G12y+UD8zrFAjYurD5V8XQLhjuNeTwKzkmZ KbgusQ8Q083OxKRusZoRviXIWPuZ1dqNMPclLUBkPMKqwqre6Pq4hNIMVU8YJ+WO6fq8 q6oEBvalO5tiL0f7u0W9HOK+UzA1YgUPGCM3lWnpv2JgEtNo7yVBO8PvIrzf7NnuZbwA 5wNuNypTjfF3ES61aOsUrEOy7G2fHZ2SsXo9eG1K1Bu9mCburvfzqxEF74D8SfVjen9x UmDA==; dara=google.com 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 a640c23a62f3a-a67e6f0264dsi537092866b.155.2024.06.04.11.59.46; Tue, 04 Jun 2024 11:59:46 -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 41DDD68D707; Tue, 4 Jun 2024 21:59:20 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from ursule.remlab.net (vps-a2bccee9.vps.ovh.net [51.75.19.47]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 847A068D4EE for ; Tue, 4 Jun 2024 21:59:09 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id 34125C02E9 for ; Tue, 4 Jun 2024 21:59:09 +0300 (EEST) From: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Tue, 4 Jun 2024 21:59:08 +0300 Message-ID: <20240604185908.22309-4-remi@remlab.net> X-Mailer: git-send-email 2.45.1 In-Reply-To: <20240604185908.22309-1-remi@remlab.net> References: <20240604185908.22309-1-remi@remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCHv2 4/4] lavc/vc1dsp: R-V V vc1_inv_trans_4x4 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: X4p8Jn4uc2Pv T-Head C908 (cycles): vc1dsp.vc1_inv_trans_4x4_c: 310.7 vc1dsp.vc1_inv_trans_4x4_rvv_i32: 120.0 We could use 1 `vlseg4e64.v` instead of 4 `vle16.v`, but that seems to be about 7% slower. --- libavcodec/riscv/vc1dsp_init.c | 2 ++ libavcodec/riscv/vc1dsp_rvv.S | 47 ++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) diff --git a/libavcodec/riscv/vc1dsp_init.c b/libavcodec/riscv/vc1dsp_init.c index cf9d42f377..de9002f395 100644 --- a/libavcodec/riscv/vc1dsp_init.c +++ b/libavcodec/riscv/vc1dsp_init.c @@ -32,6 +32,7 @@ void ff_vc1_inv_trans_4x8_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_8x4_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_8x4_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_vc1_inv_trans_4x4_dc_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); +void ff_vc1_inv_trans_4x4_rvv(uint8_t *dest, ptrdiff_t stride, int16_t *block); void ff_put_pixels16x16_rvi(uint8_t *dst, const uint8_t *src, ptrdiff_t line_size, int rnd); void ff_put_pixels8x8_rvi(uint8_t *dst, const uint8_t *src, ptrdiff_t line_size, int rnd); void ff_avg_pixels16x16_rvv(uint8_t *dst, const uint8_t *src, ptrdiff_t line_size, int rnd); @@ -59,6 +60,7 @@ av_cold void ff_vc1dsp_init_riscv(VC1DSPContext *dsp) dsp->vc1_inv_trans_8x8 = ff_vc1_inv_trans_8x8_rvv; dsp->vc1_inv_trans_8x4 = ff_vc1_inv_trans_8x4_rvv; dsp->vc1_inv_trans_4x8 = ff_vc1_inv_trans_4x8_rvv; + dsp->vc1_inv_trans_4x4 = ff_vc1_inv_trans_4x4_rvv; dsp->vc1_inv_trans_4x8_dc = ff_vc1_inv_trans_4x8_dc_rvv; dsp->vc1_inv_trans_4x4_dc = ff_vc1_inv_trans_4x4_dc_rvv; dsp->avg_vc1_mspel_pixels_tab[0][0] = ff_avg_pixels16x16_rvv; diff --git a/libavcodec/riscv/vc1dsp_rvv.S b/libavcodec/riscv/vc1dsp_rvv.S index e22950d25d..03c942cba2 100644 --- a/libavcodec/riscv/vc1dsp_rvv.S +++ b/libavcodec/riscv/vc1dsp_rvv.S @@ -113,6 +113,8 @@ func ff_vc1_inv_trans_4x4_dc_rvv, zve32x ret endfunc +#include "../../riscv-tests/debug.S" + .variant_cc ff_vc1_inv_trans_8_rvv func ff_vc1_inv_trans_8_rvv, zve32x li t4, 12 @@ -373,6 +375,51 @@ func ff_vc1_inv_trans_4x8_rvv, zve32x ret endfunc +func ff_vc1_inv_trans_4x4_rvv, zve32x + li a3, 8 * 2 + csrwi vxrm, 0 + vsetivli zero, 4, e16, mf2, ta, ma + vlsseg4e16.v v0, (a2), a3 + li t1, 3 + jal t0, ff_vc1_inv_trans_4_rvv + vsseg4e16.v v0, (a2) + addi t1, a2, 1 * 4 * 2 + vle16.v v0, (a2) + addi t2, a2, 2 * 4 * 2 + vle16.v v1, (t1) + addi t3, a2, 3 * 4 * 2 + vle16.v v2, (t2) + vle16.v v3, (t3) + li t1, 7 + jal t0, ff_vc1_inv_trans_4_rvv + add t1, a1, a0 + vle8.v v8, (a0) + add t2, a1, t1 + vle8.v v9, (t1) + add t3, a1, t2 + vle8.v v10, (t2) + vle8.v v11, (t3) + vsetvli zero, zero, e8, mf4, ta, ma + vwaddu.wv v0, v0, v8 + vwaddu.wv v1, v1, v9 + vwaddu.wv v2, v2, v10 + vwaddu.wv v3, v3, v11 + vsetvli zero, zero, e16, mf2, ta, ma + .irp n,0,1,2,3 + vmax.vx v\n, v\n, zero + .endr + vsetvli zero, zero, e8, mf4, ta, ma + vnclipu.wi v8, v0, 0 + vnclipu.wi v9, v1, 0 + vse8.v v8, (a0) + vnclipu.wi v10, v2, 0 + vse8.v v9, (t1) + vnclipu.wi v11, v3, 0 + vse8.v v10, (t2) + vse8.v v11, (t3) + ret +endfunc + .macro mspel_op op pos n1 n2 add t1, \pos, a2 v\op\()e8.v v\n1, (\pos)