From patchwork Tue Sep 20 14:40:10 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: 38092 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:3b1c:b0:96:9ee8:5cfd with SMTP id c28csp1989941pzh; Tue, 20 Sep 2022 07:42:51 -0700 (PDT) X-Google-Smtp-Source: AMsMyM67MsruxQIF/4b4u1NrfOfOEChOnMeHLszd0pPs2RgxGqE0oITkq14g3CqgKB0fxw62EcH9 X-Received: by 2002:a05:6402:1e92:b0:451:dcf:641d with SMTP id f18-20020a0564021e9200b004510dcf641dmr20728784edf.335.1663684971804; Tue, 20 Sep 2022 07:42:51 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1663684971; cv=none; d=google.com; s=arc-20160816; b=lrztVvQ3Q7r9aHUODxkSUN2faqjcjZ0yGeVWTy67/NqNb9AP3oFWF2fs7mS/7AAK98 u9pl1ImG0I4nl1cfgzLRhgmWZqltPKGvYuqGW2WtIc+I7uBDvq+0WDZ/kjWETsF9Qud8 QKCrBhc7SMEZhqTZsG1SPfg3n6mwIJSDI7dp6rQ/AOjDe+tkGV2YNDua1Sf5aV2IPMdJ Abgni/4vc9Z+ysyhjKujMyaIsszWlc0S1M6DPE/k4+cKGW11MKjB07lFsSON6EBClyee IY//jm2c7M/LcLxrvW2J+Nf+OJZ9ikOEbkDM2Gu1XwtfHie0JvYgGRF5EKH4r6zp3jb5 dcpg== 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=5AYvNhvxTd3NJr7LtOocIxpBTiHkHVXQTgTkhhm6x8s=; b=vUI4weokqJLsmkwzDgG4+AHy/t3xpJSXV1myN1UWgbrwzJDCfXC7nIVW8REhXGKijE j/RwHApkbXXOq+/NvfmiMWQ5AQgEO6Q5e5dEthK/zIRR20iapAA8Ch86jHV1/Ezyenjj NoZCsnW6S6oR67R3nu5+VNec80uUVv0lvAXRRfQqWxgUqocscrYIttiSvuttVyx6N0Lc wkkiK/qinfEuG0LbAmUS28YX3aOPYSTuAlqOhyvp+XhRo/brB/ppJl4xg0WHssj4KFig 6qAJIJTPgakeKxv7yocTVP5r8qCdBVZh08w7PtnO20LOA3G+DMUdS4SgNOtlbB40NQuP hXTQ== 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 s7-20020a056402520700b0044efcaeec2asi277991edd.167.2022.09.20.07.42.50; Tue, 20 Sep 2022 07:42:51 -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 CF29168B73A; Tue, 20 Sep 2022 17:40:38 +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 3E76F68BB01 for ; Tue, 20 Sep 2022 17:40:20 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id F2578C00C3 for ; Tue, 20 Sep 2022 17:40:17 +0300 (EEST) From: remi@remlab.net To: ffmpeg-devel@ffmpeg.org Date: Tue, 20 Sep 2022 17:40:10 +0300 Message-Id: <20220920144013.4959-23-remi@remlab.net> X-Mailer: git-send-email 2.37.2 In-Reply-To: <5602865.DvuYhMxLoT@basile.remlab.net> References: <5602865.DvuYhMxLoT@basile.remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 23/26] lavc/fmtconvert: RISC-V V int32_to_float_fmul_array8 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: /ka+0ivnda93 From: RĂ©mi Denis-Courmont --- libavcodec/riscv/fmtconvert_init.c | 7 ++++++- libavcodec/riscv/fmtconvert_rvv.S | 29 +++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 1 deletion(-) diff --git a/libavcodec/riscv/fmtconvert_init.c b/libavcodec/riscv/fmtconvert_init.c index aa7d44ff5a..1bc1dfda9a 100644 --- a/libavcodec/riscv/fmtconvert_init.c +++ b/libavcodec/riscv/fmtconvert_init.c @@ -28,6 +28,9 @@ void ff_int32_to_float_fmul_scalar_rvv(float *dst, const int32_t *src, float mul, int len); +void ff_int32_to_float_fmul_array8_rvv(FmtConvertContext *c, float *dst, + const int32_t *src, const float *mul, + int len); av_cold void ff_fmt_convert_init_riscv(FmtConvertContext *c, AVCodecContext *avctx) @@ -35,7 +38,9 @@ av_cold void ff_fmt_convert_init_riscv(FmtConvertContext *c, #ifdef HAVE_RVV int flags = av_get_cpu_flags(); - if (flags & AV_CPU_FLAG_RV_ZVE32F) + if (flags & AV_CPU_FLAG_RV_ZVE32F) { c->int32_to_float_fmul_scalar = ff_int32_to_float_fmul_scalar_rvv; + c->int32_to_float_fmul_array8 = ff_int32_to_float_fmul_array8_rvv; + } #endif } diff --git a/libavcodec/riscv/fmtconvert_rvv.S b/libavcodec/riscv/fmtconvert_rvv.S index c19b77e38a..b472be0505 100644 --- a/libavcodec/riscv/fmtconvert_rvv.S +++ b/libavcodec/riscv/fmtconvert_rvv.S @@ -38,3 +38,32 @@ NOHWF mv a2, a3 ret endfunc + +func ff_int32_to_float_fmul_array8_rvv, zve32f + srai a4, a4, 3 + +1: vsetvli t0, a4, e32, m1, ta, ma + vle32.v v24, (a3) + slli t1, t0, 2 + vlseg8e32.v v16, (a2) + slli t2, t0, 2 + 3 + vsetvli t3, zero, e32, m8, ta, ma + vfcvt.f.x.v v16, v16 + add a3, a3, t1 + vsetvli t0, a4, e32, m1, ta, ma + vfmul.vv v16, v16, v24 + add a2, a2, t2 + vfmul.vv v17, v17, v24 + sub a4, a4, t0 + vfmul.vv v18, v18, v24 + vfmul.vv v19, v19, v24 + vfmul.vv v20, v20, v24 + vfmul.vv v21, v21, v24 + vfmul.vv v22, v22, v24 + vfmul.vv v23, v23, v24 + vsseg8e32.v v16, (a1) + add a1, a1, t2 + bnez a4, 1b + + ret +endfunc