From patchwork Wed Oct 5 16:12:53 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: 38565 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:4d9:b0:9c:f4b:4e41 with SMTP id 25csp700802pzd; Wed, 5 Oct 2022 09:13:13 -0700 (PDT) X-Google-Smtp-Source: AMsMyM4GKVXdLN7QfMdiyO2yTPnVPUbRDjCtuh8A+UGYJc06KIxt/LNRROkWgFmW4KG/M3JRtlej X-Received: by 2002:a17:907:a48:b0:77c:51b0:5aeb with SMTP id be8-20020a1709070a4800b0077c51b05aebmr280971ejc.61.1664986393388; Wed, 05 Oct 2022 09:13:13 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1664986393; cv=none; d=google.com; s=arc-20160816; b=BTK4l18IJkMPOQG9r8dyueJZpZkrv8Cvg7zwNwe/+jaulMt0ThojRGWjDOuSlcHDax 15hZf3kKJC4jbADG3/YNDY9D/x+HTscQ6RSY+ok0ujZXx/XrV7thlgByPzZyuQMPbqaR 54ObxDHK4yveGpD1OYKMDJ5hKoUyJHXnOTWZHagO7SZ0ycJ1E9UbcAzLHxCDCmHpi59z 8uoRgss8vES8zgT8Q/jOpzRw7rJyKijrC2l/DS+wYnwMiiiIxuyUwHkdgDG8IS9KCDhJ TTRSPuOJn9w0KMRBapfaGtm/xaZbA9co97sbOTcLQugP9TUQ1m1RP0ZH9uWD8uvThCfe J6iw== 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=VkDnBKdOgPAoKxZAQF9kBoC8ZfmCz7PhGx6izdKb5aQ=; b=DM8cgeI8gxxpFsGme7OHDp2OAjTBmZ9rMbtZM+iPbWBmiyKlOsUcMpFytg96+/3hh2 saXOoFGEEem/gXX+hDeMd/BqbSehenACK+8r/T/h5rpGKHxiTlQ5M7yDXJtjQlwK/68r GwfHwQdnDZ3NJLfLot7VVEMW1cUWwqbDKfZWyb6r09maZn3+MWgcdhXR8gY912E0Bxtr r8tYsTNC7T13pVfQCUpKJ8UJhffJbs1wrYFPKPUOxXbdFGnQkkHnislKdVIhrcB+V21A lM9wdReZB78+yX5CbQXt+30OoKMrPaPWAtw6Hnspe+N65zZgx6kQ0BuiwHvoL8mthA+t XH7Q== 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 cw3-20020a170906478300b0076f077cec04si12361808ejc.365.2022.10.05.09.13.12; Wed, 05 Oct 2022 09:13:13 -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 176D268BD20; Wed, 5 Oct 2022 19:13:01 +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 D201D68BD12 for ; Wed, 5 Oct 2022 19:12:57 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id 2B37DC000A for ; Wed, 5 Oct 2022 19:12:57 +0300 (EEST) From: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Wed, 5 Oct 2022 19:12:53 +0300 Message-Id: <20221005161256.27612-1-remi@remlab.net> X-Mailer: git-send-email 2.37.2 In-Reply-To: <12083658.O9o76ZdvQC@basile.remlab.net> References: <12083658.O9o76ZdvQC@basile.remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 1/4] lavc/opusdsp: RISC-V V (128-bit) postfilter 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: KtPHUnfm53Hz This is implemented for a vector size of 128-bit. Since the scalar product in the inner loop covers 5 samples or 160 bits, we need a group multipler of 2. To avoid reconfiguring the vector type, the outer loop, which loads multiple input samples sticks to the same multipler. Consequently, the outer loop loads 8 samples per iteration. This is safe since the minimum period of the CELT codec is 15 samples. The same code would also work, albeit needlessly inefficiently with a vector length of 256 bits. A proper implementation will follow instead. --- libavcodec/opusdsp.c | 2 ++ libavcodec/opusdsp.h | 1 + libavcodec/riscv/Makefile | 2 ++ libavcodec/riscv/opusdsp_init.c | 42 ++++++++++++++++++++++++ libavcodec/riscv/opusdsp_rvv.S | 57 +++++++++++++++++++++++++++++++++ 5 files changed, 104 insertions(+) create mode 100644 libavcodec/riscv/opusdsp_init.c create mode 100644 libavcodec/riscv/opusdsp_rvv.S diff --git a/libavcodec/opusdsp.c b/libavcodec/opusdsp.c index badcfcc884..0764d712e4 100644 --- a/libavcodec/opusdsp.c +++ b/libavcodec/opusdsp.c @@ -58,6 +58,8 @@ av_cold void ff_opus_dsp_init(OpusDSP *ctx) #if ARCH_AARCH64 ff_opus_dsp_init_aarch64(ctx); +#elif ARCH_RISCV + ff_opus_dsp_init_riscv(ctx); #elif ARCH_X86 ff_opus_dsp_init_x86(ctx); #endif diff --git a/libavcodec/opusdsp.h b/libavcodec/opusdsp.h index 3ea3d14bf0..c2a301e832 100644 --- a/libavcodec/opusdsp.h +++ b/libavcodec/opusdsp.h @@ -30,5 +30,6 @@ void ff_opus_dsp_init(OpusDSP *ctx); void ff_opus_dsp_init_x86(OpusDSP *ctx); void ff_opus_dsp_init_aarch64(OpusDSP *ctx); +void ff_opus_dsp_init_riscv(OpusDSP *ctx); #endif /* AVCODEC_OPUSDSP_H */ diff --git a/libavcodec/riscv/Makefile b/libavcodec/riscv/Makefile index eae87ea231..965942f4df 100644 --- a/libavcodec/riscv/Makefile +++ b/libavcodec/riscv/Makefile @@ -12,6 +12,8 @@ OBJS-$(CONFIG_FMTCONVERT) += riscv/fmtconvert_init.o RVV-OBJS-$(CONFIG_FMTCONVERT) += riscv/fmtconvert_rvv.o OBJS-$(CONFIG_IDCTDSP) += riscv/idctdsp_init.o RVV-OBJS-$(CONFIG_IDCTDSP) += riscv/idctdsp_rvv.o +OBJS-$(CONFIG_OPUS_DECODER) += riscv/opusdsp_init.o +RVV-OBJS-$(CONFIG_OPUS_DECODER) += riscv/opusdsp_rvv.o OBJS-$(CONFIG_PIXBLOCKDSP) += riscv/pixblockdsp_init.o \ riscv/pixblockdsp_rvi.o RVV-OBJS-$(CONFIG_PIXBLOCKDSP) += riscv/pixblockdsp_rvv.o diff --git a/libavcodec/riscv/opusdsp_init.c b/libavcodec/riscv/opusdsp_init.c new file mode 100644 index 0000000000..f1d2c871e3 --- /dev/null +++ b/libavcodec/riscv/opusdsp_init.c @@ -0,0 +1,42 @@ +/* + * Copyright © 2022 Rémi Denis-Courmont. + * + * This file is part of FFmpeg. + * + * FFmpeg is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * FFmpeg is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with FFmpeg; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include "config.h" + +#include "libavutil/attributes.h" +#include "libavutil/cpu.h" +#include "libavutil/riscv/cpu.h" +#include "libavcodec/opusdsp.h" + +void ff_opus_postfilter_rvv_128(float *data, int period, float *g, int len); + +av_cold void ff_opus_dsp_init_riscv(OpusDSP *d) +{ +#if HAVE_RVV + int flags = av_get_cpu_flags(); + + if (flags & AV_CPU_FLAG_RVV_F32) + switch (ff_get_rv_vlenb()) { + case 16: + d->postfilter = ff_opus_postfilter_rvv_128; + break; + } +#endif +} diff --git a/libavcodec/riscv/opusdsp_rvv.S b/libavcodec/riscv/opusdsp_rvv.S new file mode 100644 index 0000000000..79b46696cd --- /dev/null +++ b/libavcodec/riscv/opusdsp_rvv.S @@ -0,0 +1,57 @@ +/* + * Copyright © 2022 Rémi Denis-Courmont. + * + * This file is part of FFmpeg. + * + * FFmpeg is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * FFmpeg is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with FFmpeg; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include "libavutil/riscv/asm.S" + +func ff_opus_postfilter_rvv_128, zve32f + addi a1, a1, 2 + slli a1, a1, 2 + lw t1, 4(a2) + vsetivli zero, 3, e32, m1, ta, ma + vle32.v v24, (a2) + sub a1, a0, a1 // a1 = &x4 = &data[-(period + 2)] + vsetivli zero, 5, e32, m2, ta, ma + vslide1up.vx v8, v24, t1 + lw t2, 8(a2) + vle32.v v16, (a1) + vslide1up.vx v24, v8, t2 // v24 = { g[2], g[1], g[0], g[1], g[2] } +2: + vsetvli t0, a3, e32, m2, ta, ma + vle32.v v0, (a0) + sub a3, a3, t0 +3: + vsetivli zero, 5, e32, m2, ta, ma + lw t2, 20(a1) + vfmul.vv v8, v24, v16 + addi a0, a0, 4 + vslide1down.vx v16, v16, t2 + addi a1, a1, 4 + vfredusum.vs v0, v8, v0 + vsetvli zero, t0, e32, m2, ta, ma + vmv.x.s t1, v0 + addi t0, t0, -1 + vslide1down.vx v0, v0, zero + sw t1, -4(a0) + bnez t0, 3b + + bnez a3, 2b + + ret +endfunc