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 95167454DD for ; Sat, 30 Sep 2023 09:01:23 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 32B0E68CCC1; Sat, 30 Sep 2023 12:01:20 +0300 (EEST) Received: from ursule.remlab.net (vps-a2bccee9.vps.ovh.net [51.75.19.47]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 8B2FE68CB56 for ; Sat, 30 Sep 2023 12:01:13 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id B47EDC006B for ; Sat, 30 Sep 2023 12:01:12 +0300 (EEST) From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Sat, 30 Sep 2023 12:01:10 +0300 Message-ID: <20230930090112.376259-1-remi@remlab.net> X-Mailer: git-send-email 2.42.0 MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 1/3] swscale/rgb2rgb: rework RISC-V V uyvytoyuv422 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 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: This avoids using relatively slow register strides. --- libswscale/riscv/rgb2rgb_rvv.S | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/libswscale/riscv/rgb2rgb_rvv.S b/libswscale/riscv/rgb2rgb_rvv.S index 008f098bfe..3e7988ca01 100644 --- a/libswscale/riscv/rgb2rgb_rvv.S +++ b/libswscale/riscv/rgb2rgb_rvv.S @@ -101,34 +101,33 @@ func ff_interleave_bytes_rvv, zve32x endfunc #if (__riscv_xlen == 64) -.macro yuy2_to_i422p v_y0, v_y1, v_u, v_v +.macro yuy2_to_i422p y_shift addi sp, sp, -16 sd s0, (sp) - sd s1, 8(sp) addi a4, a4, 1 lw s0, 16(sp) srai a4, a4, 1 // pixel width -> chroma width - li s1, 2 1: mv t4, a4 mv t3, a3 mv t0, a0 - addi t6, a0, 1 mv t1, a1 mv t2, a2 addi a5, a5, -1 2: vsetvli t5, t4, e8, m1, ta, ma + vlseg2e16.v v16, (t3) sub t4, t4, t5 - vlseg4e8.v v8, (t3) + vnsrl.wi v24, v16, \y_shift // Y0 sh2add t3, t5, t3 - vsse8.v \v_y0, (t0), s1 + vnsrl.wi v25, v18, \y_shift // Y1 + vnsrl.wi v28, v16, 8 - \y_shift // U + vnsrl.wi v30, v18, 8 - \y_shift // V + vsseg2e8.v v24, (t0) sh1add t0, t5, t0 - vsse8.v \v_y1, (t6), s1 - sh1add t6, t5, t6 - vse8.v \v_u, (t1) + vse8.v v28, (t1) add t1, t5, t1 - vse8.v \v_v, (t2) + vse8.v v30, (t2) add t2, t5, t2 bnez t4, 2b @@ -138,17 +137,16 @@ endfunc add a2, a2, a7 bnez a5, 1b - ld s1, 8(sp) ld s0, (sp) addi sp, sp, 16 ret .endm func ff_uyvytoyuv422_rvv, zve32x - yuy2_to_i422p v9, v11, v8, v10 + yuy2_to_i422p 8 endfunc func ff_yuyvtoyuv422_rvv, zve32x - yuy2_to_i422p v8, v10, v9, v11 + yuy2_to_i422p 0 endfunc #endif -- 2.42.0 _______________________________________________ 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".