From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org [79.124.17.100]) by master.gitmailbox.com (Postfix) with ESMTP id EBC3C4922A for ; Tue, 7 May 2024 07:37:54 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id CACDF68D751; Tue, 7 May 2024 10:36:51 +0300 (EEST) Received: from out162-62-57-49.mail.qq.com (out162-62-57-49.mail.qq.com [162.62.57.49]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 88DAF68D722 for ; Tue, 7 May 2024 10:36:41 +0300 (EEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=foxmail.com; s=s201512; t=1715067393; bh=p20tqNdhnlPdo1GAcR5Z0Kj2CW7SjAVvoqbF7rxR5h4=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=EB+pEX0SZGUtJnptslQvw8tUxA/nz2cvk9bl2DiiJ0Lxckbd0zfuigVgIo8UeMOkL 4t/o+7otLvTWMdMrXMjZyX12I5sXFce4XkoX6HH4D1cTrdWDlb6Hts4x7LHu8Gzkud WjW/R01Puz45OyjD2MVaOughCHmp6LtAaBvH9YYY= Received: from localhost.localdomain ([42.56.223.122]) by newxmesmtplogicsvrsza29-0.qq.com (NewEsmtp) with SMTP id 9188D283; Tue, 07 May 2024 15:36:24 +0800 X-QQ-mid: xmsmtpt1715067392tqjshk559 Message-ID: X-QQ-XMAILINFO: M0PjjqbLT90wL0yBJmkH6q4JmjXXYITvfwHrzdZ3qBKhNLdqCIdzZT9A0aJfYO V0NSHKlXOpt0PqGYKqOyvNN2jGzSPuhI3v7wvlqdNEYUeBFyibKM1cjmeAiRtMBcEwvQPa/qM1MD G2r0UiY4GWXEfe7oBLmBcgID5S6BjbOcXhEVLf07bxORyVxmGiQcOGGyNTx/OAKgX7pzz2FiEd+Q /Y+MkRQNBww+VVE5UBGFCjX0UFTAJtQlu7tWUPX3AWXf0FzlYlIeRMv921TENR7RkOPdS4/xztMh 99Xk+rG150uUPAn6IJ3LLkxKQqpAski0xEyj4ox+jGksxB30/oXJKX7vpIH7veRNjhvVYye3/UJs fU3uakfddsUHLjesIRshrNbWb0INdGe2G65a05FEy8vpIUYtFQy45US15BehaTLYVJX7ar0BE5qF DlukOYBsnvsht+MW49u3/0vESPSXLNJrOxl5E8h5mpZcfJRUTUkVzYxDh5ZPEJMH+WAvjVikx18H fklLYQ0CblQjQ+I78iZKj0ovM+EoBnQTS8cJvQNa6dnyjc0AsovcEoHhxY/L8874JdoY6lsa47pi FIa9mGY0H0R1Sx5MeiJMGqlqJ/t5KeJ/UDZqGDMHgJsNZh5zp2pGDFqQyB0RuThMEOoIrK7ksC1d WTtSE8353MKBaAZoKmAGa+k0JQYsGqH5n9vblwe6DpTdaMhoHriy6xpMs32V5h//GlUgfKyC2ACj LTcSvWWfwEFM6c7DnV4shAybOxE+8nXB+RqY2zLveQ5TZ2gnufQeh4bmsIQhAzt4C4KpTZN6RVAh 1CUewLKONZ0yEs5T/dd3w1LxeQfk+ZWtDqwIUgDjXJR58CX+Uk0jDNG3wKnRG+cFc1UbH4z1zZDW Ic3HKh2WBPpdqi3gA4+0QakjmSsQPCasah3uRAy+Wjq82+e5ICy7XLZSpcbOyEXkD8qEPDvQ9u X-QQ-XMRINFO: MSVp+SPm3vtS1Vd6Y4Mggwc= From: uk7b@foxmail.com To: ffmpeg-devel@ffmpeg.org Date: Tue, 7 May 2024 15:36:13 +0800 X-OQ-MSGID: <20240507073613.2871668-9-uk7b@foxmail.com> X-Mailer: git-send-email 2.45.0 In-Reply-To: <20240507073613.2871668-1-uk7b@foxmail.com> References: <20240507073613.2871668-1-uk7b@foxmail.com> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH v2 9/9] lavc/vp9dsp: R-V V mc tap hv 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 Cc: sunyuechi Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Archived-At: List-Archive: List-Post: From: sunyuechi C908: vp9_avg_8tap_smooth_4hv_8bpp_c: 32.0 vp9_avg_8tap_smooth_4hv_8bpp_rvv_i64: 15.0 vp9_avg_8tap_smooth_8hv_8bpp_c: 114.5 vp9_avg_8tap_smooth_8hv_8bpp_rvv_i64: 40.5 vp9_avg_8tap_smooth_16hv_8bpp_c: 338.7 vp9_avg_8tap_smooth_16hv_8bpp_rvv_i64: 46.5 vp9_avg_8tap_smooth_32hv_8bpp_c: 1270.7 vp9_avg_8tap_smooth_32hv_8bpp_rvv_i64: 134.0 vp9_avg_8tap_smooth_64hv_8bpp_c: 4923.5 vp9_avg_8tap_smooth_64hv_8bpp_rvv_i64: 523.5 vp9_put_8tap_smooth_4hv_8bpp_c: 30.5 vp9_put_8tap_smooth_4hv_8bpp_rvv_i64: 14.2 vp9_put_8tap_smooth_8hv_8bpp_c: 91.7 vp9_put_8tap_smooth_8hv_8bpp_rvv_i64: 22.7 vp9_put_8tap_smooth_16hv_8bpp_c: 328.7 vp9_put_8tap_smooth_16hv_8bpp_rvv_i64: 45.0 vp9_put_8tap_smooth_32hv_8bpp_c: 1166.7 vp9_put_8tap_smooth_32hv_8bpp_rvv_i64: 131.0 vp9_put_8tap_smooth_64hv_8bpp_c: 4532.5 vp9_put_8tap_smooth_64hv_8bpp_rvv_i64: 512.5 --- libavcodec/riscv/vp9_mc_rvv.S | 94 ++++++++++++++++++++++++++++++++++ libavcodec/riscv/vp9dsp_init.c | 3 +- 2 files changed, 96 insertions(+), 1 deletion(-) diff --git a/libavcodec/riscv/vp9_mc_rvv.S b/libavcodec/riscv/vp9_mc_rvv.S index 01404bbde5..0dcec94bbf 100644 --- a/libavcodec/riscv/vp9_mc_rvv.S +++ b/libavcodec/riscv/vp9_mc_rvv.S @@ -358,6 +358,99 @@ func ff_\op\()_8tap_\name\()_\len\()\type\()_rvv, zve32x endfunc .endm +.macro epel_hv_once len name op + sub a2, a2, a3 + sub a2, a2, a3 + sub a2, a2, a3 + .irp n 0 2 4 6 8 10 12 14 + epel_load_inc v\n \len put \name h 1 t + .endr + addi a4, a4, -1 +1: + addi a4, a4, -1 + epel_load v30 \len \op \name v 0 s + vse8.v v30, (a0) + vmv.v.v v0, v2 + vmv.v.v v2, v4 + vmv.v.v v4, v6 + vmv.v.v v6, v8 + vmv.v.v v8, v10 + vmv.v.v v10, v12 + vmv.v.v v12, v14 + epel_load v14 \len put \name h 1 t + add a2, a2, a3 + add a0, a0, a1 + bnez a4, 1b + epel_load v30 \len \op \name v 0 s + vse8.v v30, (a0) +.endm + +.macro epel_hv op name len +func ff_\op\()_8tap_\name\()_\len\()hv_rvv, zve32x +#if __riscv_xlen == 64 + addi sp, sp, -64 + .irp n 0,1,2,3,4,5,6,7 + sd s\n, \n\()<<3(sp) + .endr +#else + addi sp, sp, -32 + .irp n 0,1,2,3,4,5,6,7 + sw s\n, \n\()<<2(sp) + .endr +#endif +.ifc \len,64 +#if __riscv_xlen == 64 + addi sp, sp, -48 + .irp n 0,1,2,3,4,5 + sd a\n, \n\()<<3(sp) + .endr +#else + addi sp, sp, -24 + .irp n 0,1,2,3,4,5 + sw a\n, \n\()<<2(sp) + .endr +#endif +.endif +.ifc \op,avg + csrwi vxrm, 0 +.endif + epel_filter \name h t + epel_filter \name v s + vsetvlstatic8 \len a6 m2 + epel_hv_once \len \name \op +.ifc \len,64 +#if __riscv_xlen == 64 + .irp n 0,1,2,3,4,5 + ld a\n, \n\()<<3(sp) + .endr + addi sp, sp, 48 +#else + .irp n 0,1,2,3,4,5 + lw a\n, \n\()<<2(sp) + .endr + addi sp, sp, 24 +#endif + addi a0, a0, 32 + addi a2, a2, 32 + epel_filter \name h t + epel_hv_once \len \name \op +.endif +#if __riscv_xlen == 64 + .irp n 0,1,2,3,4,5,6,7 + ld s\n, \n\()<<3(sp) + .endr + addi sp, sp, 64 +#else + .irp n 0,1,2,3,4,5,6,7 + lw s\n, \n\()<<2(sp) + .endr + addi sp, sp, 32 +#endif + + ret +endfunc +.endm + .irp len 64, 32, 16, 8, 4 copy_avg \len .irp op put avg @@ -368,6 +461,7 @@ endfunc .irp type h v epel \len \op \name \type .endr + epel_hv \op \name \len .endr .endr .endr diff --git a/libavcodec/riscv/vp9dsp_init.c b/libavcodec/riscv/vp9dsp_init.c index a45aea530d..554fcefa6e 100644 --- a/libavcodec/riscv/vp9dsp_init.c +++ b/libavcodec/riscv/vp9dsp_init.c @@ -131,7 +131,8 @@ static av_cold void vp9dsp_mc_init_riscv(VP9DSPContext *dsp, int bpp) init_subpel2(idx, 1, 0, h, type); \ if (flags & AV_CPU_FLAG_RVB_ADDR) { \ init_subpel2(idx, 0, 1, v, type); \ - } + } \ + init_subpel2(idx, 1, 1, hv, type) init_subpel3(0, put); init_subpel3(1, avg); -- 2.45.0 _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".