From patchwork Mon Sep 12 15:53:31 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= X-Patchwork-Id: 37873 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:3b1c:b0:96:9ee8:5cfd with SMTP id c28csp164262pzh; Mon, 12 Sep 2022 08:55:54 -0700 (PDT) X-Google-Smtp-Source: AA6agR7XkPdgyonXW5jaKAKH/SL1Ec4UHqgUkr/C9+eu+daBeVnAH5TRAIUGq/7Y8x56OH0IMnOD X-Received: by 2002:a05:6402:19:b0:447:901f:6b28 with SMTP id d25-20020a056402001900b00447901f6b28mr22198022edu.392.1662998153935; Mon, 12 Sep 2022 08:55:53 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1662998153; cv=none; d=google.com; s=arc-20160816; b=iODt4JyxG1yhYAJK2XJGNy8TVNHp4NhGMAlBO/xkab/P5wdwJ/Pasgj9BnSB48dtVL iekJNkoDA22KIMU4NoHJhmcxDdwVpEdCgaKNQWsM7jgIY/VNMx2YQ4xQhSOoT9p3vA48 20+K0hpCn2pgxJdIqtMvtLg9XO6KvSfNIm8FlcHeDOJEYw1VgTZ4Xlceqq83YaeeS7UJ 1iAkefsJc5YLSRohxbYOeqftBA93ha9iYr4z/MF4AMNPVKjwdCnPa7NOaWfFw0h1RCKk 82PXqIwcDuuCPtErtuxVro04iL9lDpJa6YHlp2A84WzMdlJr+2jbPcArfw/p63LR57qe 991w== 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=kj6oxgqlWiLEmjEUY0Vnp8DOSIeWq3DVbtQ50w+EnWA=; b=paxcUSd5d1XhLeVbF4924fktbPsjTESSj0CVzV4QmUYScJBxGgNymsCsa0gVgfswpS PXfSJwGAqyIL8uIvwdpBvEj7wSJLQV1zzw4ypjlpdMfTDSkOXHOyAVkMAslB10/fRNQp Ee+xnxPucMMWngNEC8RjkQ7IYS1wT9ndytrwaf8wdS+Nr57nfrrew3bDls8kTSKCTKh0 Qu8PHAIsQeI/7Ne42Sl1iVNSSfSB5mDAjPfGrdcimuJQ5wJhkhVr61w/9hPD2Zgi7bxF iodePW4momwd1JvmG+gZbQAPCexIGCHrp+U5t/+tNoKktZGnpRwucKoNFvMnKS62JpY+ KTCg== 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 v10-20020a056402348a00b0044de197f1ddsi5652628edc.550.2022.09.12.08.55.53; Mon, 12 Sep 2022 08:55:53 -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 88A5468BBA6; Mon, 12 Sep 2022 18:53:57 +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 3831468BB68 for ; Mon, 12 Sep 2022 18:53:45 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id BF060C00BC for ; Mon, 12 Sep 2022 18:53:36 +0300 (EEST) From: remi@remlab.net To: ffmpeg-devel@ffmpeg.org Date: Mon, 12 Sep 2022 18:53:31 +0300 Message-Id: <20220912155333.59843-16-remi@remlab.net> X-Mailer: git-send-email 2.37.2 In-Reply-To: <2652141.mvXUDI8C0e@basile.remlab.net> References: <2652141.mvXUDI8C0e@basile.remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 16/18] lavu/riscv: float vector windowed overlap/add with RVV 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: NzvVT4GlKHjO From: RĂ©mi Denis-Courmont --- libavutil/riscv/float_dsp_init.c | 3 +++ libavutil/riscv/float_dsp_rvv.S | 35 ++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/libavutil/riscv/float_dsp_init.c b/libavutil/riscv/float_dsp_init.c index ae089d2fdb..cf8c995d7c 100644 --- a/libavutil/riscv/float_dsp_init.c +++ b/libavutil/riscv/float_dsp_init.c @@ -29,6 +29,8 @@ void ff_vector_fmac_scalar_rvv(float *dst, const float *src, float mul, int len); void ff_vector_fmul_scalar_rvv(float *dst, const float *src, float mul, int len); +void ff_vector_fmul_window_rvv(float *dst, const float *src0, + const float *src1, const float *win, int len); void ff_vector_fmul_add_rvv(float *dst, const float *src0, const float *src1, const float *src2, int len); void ff_vector_fmul_reverse_rvv(float *dst, const float *src0, @@ -51,6 +53,7 @@ av_cold void ff_float_dsp_init_riscv(AVFloatDSPContext *fdsp) fdsp->vector_fmul = ff_vector_fmul_rvv; fdsp->vector_fmac_scalar = ff_vector_fmac_scalar_rvv; fdsp->vector_fmul_scalar = ff_vector_fmul_scalar_rvv; + fdsp->vector_fmul_window = ff_vector_fmul_window_rvv; fdsp->vector_fmul_add = ff_vector_fmul_add_rvv; fdsp->vector_fmul_reverse = ff_vector_fmul_reverse_rvv; fdsp->butterflies_float = ff_butterflies_float_rvv; diff --git a/libavutil/riscv/float_dsp_rvv.S b/libavutil/riscv/float_dsp_rvv.S index b376392294..65daaa2d27 100644 --- a/libavutil/riscv/float_dsp_rvv.S +++ b/libavutil/riscv/float_dsp_rvv.S @@ -73,6 +73,41 @@ NOHWF mv a2, a3 ret endfunc +func ff_vector_fmul_window_rvv, zve32f + // a0: dst, a1: src0, a2: src1, a3: window, a4: length + addi t0, a4, -1 + add t1, t0, a4 + slli t0, t0, 2 + slli t1, t1, 2 + add a2, a2, t0 + add t0, a0, t1 + add t3, a3, t1 + li t1, -4 // byte stride + +1: vsetvli t2, a4, e32, m4, ta, ma + slli t4, t2, 2 + vle32.v v16, (a1) + add a1, a1, t4 + vlse32.v v20, (a2), t1 + sub a2, a2, t4 + vle32.v v24, (a3) + add a3, a3, t4 + vlse32.v v28, (t3), t1 + sub t3, t3, t4 + vfmul.vv v0, v16, v28 + sub a4, a4, t2 + vfmul.vv v8, v16, v24 + vfnmsac.vv v0, v20, v24 + vfmacc.vv v8, v20, v28 + vse32.v v0, (a0) + add a0, a0, t4 + vsse32.v v8, (t0), t1 + sub t0, t0, t4 + bnez a4, 1b + + ret +endfunc + // (a0) = (a1) * (a2) + (a3) [0..a4-1] func ff_vector_fmul_add_rvv, zve32f 1: vsetvli t0, a4, e32, m8, ta, ma