From patchwork Tue May 14 20:58:44 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: 48889 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a21:3a48:b0:1af:fc2d:ff5a with SMTP id zu8csp1208148pzb; Tue, 14 May 2024 13:59:02 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCXR0j3+XdWJNLjv9x2IAatuFJo11NL7vJkdllKECu7C1vs5tDHwXHO9cwRq6dXe0GQlrS9P+cNqjBM3Kr/07BAJ3bdHkQ/Lh4laug== X-Google-Smtp-Source: AGHT+IHu/HjheuHAg/HY6poEioiQFTy/D0MCTE//Aqz94BXganSAm5f4gpGbr9mLMoUAL+go4b2g X-Received: by 2002:a50:baeb:0:b0:56e:2ebc:5c4 with SMTP id 4fb4d7f45d1cf-5734d5ceae0mr9722818a12.20.1715720342589; Tue, 14 May 2024 13:59:02 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1715720342; cv=none; d=google.com; s=arc-20160816; b=HPjktNUAR4FCGtedDfmGnTwunygEroBMHMG+JTh/F0rbCeQBSHFo+kaHX2r1Y666OY Lkh/c8xdKuzJ4Eb2bkiZ2zatIIQr40rK9Jq1Bc4hmO6Psk+PrShyye0GnbPgBCfG8zz1 yKMQAckggwDp/P9n5AYr/VRyClwjpWRNopDH2JIdGeQahvOiTfheCTMQkMuhABqsZqMZ lvBvMf2tGqkt2tAnuFYzvA1+VD0YLarnyH4vYydmQ1KlpCOjRYTEP/kXYaGHUea8YfJ8 S+p1OgWsgMjYIK3CIt7htWt3FFfean1TRL8e9PjV/oDmMQS00XRjN+OX4soSEl+g4Ck3 vEtA== 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=p2v0bo/Rl9+DC1jJbbhewFFkZj7/xSiSGw8m6yVUw6A=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=AImvGY2k35KKVUfMSvPwBoROGm/nGShzWO7BIu52xvVGElFwlTggU+RWO+il1r4IC9 DsPsxVSstmbVFB7rEIYoS07PchaKA0VR21AqO0Dgh0B+GZcZCzdNPX5OG4ozZ5HU2h+L Tsi3DwmkNp5bRhke3E7zMWc7q0r1zo8c/geJN24bnzQVFlCfG7HJ3psLZAvP23xmssY7 eC9Feliz5It3Jn4bnz5V1KoBz6pVNBxaulVsneIYDm3G65kVi6nhPgysiJdBKnfJCtpK HAenrR3lqZeCaavnLik/gPwmrPcDOyHFuN2WRI0gz2OfX8VIQtLn+fd82IBhl+pYo7R9 QJfg==; 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-5733c2d4662si6437758a12.339.2024.05.14.13.59.02; Tue, 14 May 2024 13:59:02 -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 C1B0568D75B; Tue, 14 May 2024 23:58:53 +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 9B05268D4C3 for ; Tue, 14 May 2024 23:58:45 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id 3D004C01A3 for ; Tue, 14 May 2024 23:58:45 +0300 (EEST) From: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Tue, 14 May 2024 23:58:44 +0300 Message-ID: <20240514205844.43728-2-remi@remlab.net> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20240514205844.43728-1-remi@remlab.net> References: <20240514205844.43728-1-remi@remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCHv3 2/2] lavc/flacdsp: R-V V flac_wasted33 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: rVMiowXT9Chf T-Head C908: flac_wasted_33_c: 786.2 flac_wasted_33_rvv_i64: 486.5 --- libavcodec/riscv/flacdsp_init.c | 4 ++++ libavcodec/riscv/flacdsp_rvv.S | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) diff --git a/libavcodec/riscv/flacdsp_init.c b/libavcodec/riscv/flacdsp_init.c index 454787470b..4f1652dbe7 100644 --- a/libavcodec/riscv/flacdsp_init.c +++ b/libavcodec/riscv/flacdsp_init.c @@ -32,6 +32,7 @@ void ff_flac_lpc32_rvv(int32_t *decoded, const int coeffs[32], void ff_flac_lpc32_rvv_simple(int32_t *decoded, const int coeffs[32], int pred_order, int qlevel, int len); void ff_flac_wasted32_rvv(int32_t *, int shift, int len); +void ff_flac_wasted33_rvv(int64_t *, const int32_t *, int shift, int len); void ff_flac_decorrelate_indep2_16_rvv(uint8_t **out, int32_t **in, int channels, int len, int shift); void ff_flac_decorrelate_indep4_16_rvv(uint8_t **out, int32_t **in, @@ -84,6 +85,9 @@ av_cold void ff_flacdsp_init_riscv(FLACDSPContext *c, enum AVSampleFormat fmt, c->wasted32 = ff_flac_wasted32_rvv; + if (flags & AV_CPU_FLAG_RVV_I64) + c->wasted33 = ff_flac_wasted33_rvv; + # if (__riscv_xlen >= 64) switch (fmt) { case AV_SAMPLE_FMT_S16: diff --git a/libavcodec/riscv/flacdsp_rvv.S b/libavcodec/riscv/flacdsp_rvv.S index d7009cdec2..6287faa260 100644 --- a/libavcodec/riscv/flacdsp_rvv.S +++ b/libavcodec/riscv/flacdsp_rvv.S @@ -115,6 +115,38 @@ func ff_flac_wasted32_rvv, zve32x ret endfunc +func ff_flac_wasted33_rvv, zve64x + srli t0, a2, 5 + li t1, 1 + bnez t0, 2f + sll a2, t1, a2 +1: + vsetvli t0, a3, e32, m4, ta, ma + vle32.v v8, (a1) + sub a3, a3, t0 + vwmulsu.vx v16, v8, a2 + sh2add a1, t0, a1 + vse64.v v16, (a0) + sh3add a0, t0, a0 + bnez a3, 1b + + ret + +2: // Pessimistic case: wasted >= 32 + vsetvli t0, a3, e32, m4, ta, ma + vle32.v v8, (a1) + sub a3, a3, t0 + vwcvtu.x.x.v v16, v8 + sh2add a1, t0, a1 + vsetvli zero, zero, e64, m8, ta, ma + vsll.vx v16, v16, a2 + vse64.v v16, (a0) + sh3add a0, t0, a0 + bnez a3, 2b + + ret +endfunc + #if (__riscv_xlen == 64) func ff_flac_decorrelate_indep2_16_rvv, zve32x ld a0, (a0)