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 D44A44BF82 for ; Thu, 18 Jul 2024 19:35:57 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 8320368DAF0; Thu, 18 Jul 2024 22:35:54 +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 23B9A68D85C for ; Thu, 18 Jul 2024 22:35:48 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id 81B35C01F0 for ; Thu, 18 Jul 2024 22:35:47 +0300 (EEST) From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Thu, 18 Jul 2024 22:35:44 +0300 Message-ID: <20240718193546.18939-3-remi@remlab.net> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20240718193546.18939-1-remi@remlab.net> References: <20240718193546.18939-1-remi@remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 3/5] lavc/h264dsp: correct VL and LMUL in idct_dc_add 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: T-Head C908 (cycles): h264_idct4_dc_add_8bpp_c: 94.7 h264_idct4_dc_add_8bpp_rvv_i32: 55.0 (before) h264_idct4_dc_add_8bpp_rvv_i32: 34.5 (after) h264_idct4_dc_add_9bpp_c: 94.7 h264_idct4_dc_add_9bpp_rvv_i32: 43.5 (before) h264_idct4_dc_add_9bpp_rvv_i32: 38.2 (after) h264_idct4_dc_add_10bpp_c: 94.7 h264_idct4_dc_add_10bpp_rvv_i32: 43.5 (before) h264_idct4_dc_add_10bpp_rvv_i32: 38.2 (after) h264_idct4_dc_add_12bpp_c: 94.7 h264_idct4_dc_add_12bpp_rvv_i32: 43.7 (before) h264_idct4_dc_add_12bpp_rvv_i32: 38.5 (after) h264_idct4_dc_add_14bpp_c: 94.7 h264_idct4_dc_add_14bpp_rvv_i32: 43.7 (before) h264_idct4_dc_add_14bpp_rvv_i32: 38.5 (after) --- libavcodec/riscv/h264idct_rvv.S | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/libavcodec/riscv/h264idct_rvv.S b/libavcodec/riscv/h264idct_rvv.S index 37b27fc92a..2648e06aeb 100644 --- a/libavcodec/riscv/h264idct_rvv.S +++ b/libavcodec/riscv/h264idct_rvv.S @@ -416,22 +416,23 @@ endfunc .endr .macro idct_dc_add8 width -func ff_h264_idct\width\()_dc_add_8_rvv, zve64x, zba +func ff_h264_idct\width\()_dc_add_8_rvv, zve64x .if \width == 8 - vsetivli zero, \width, e16, m1, ta, ma + vsetivli zero, \width, e8, mf2, ta, ma .else - vsetivli zero, \width, e16, mf2, ta, ma + vsetivli zero, \width, e8, mf4, ta, ma .endif lh a3, 0(a1) addi a3, a3, 32 srai a3, a3, 6 sh zero, 0(a1) .if \width == 8 + li a6, \width * \width vlse64.v v24, (a0), a2 - vsetvli t0, zero, e16, m8, ta, ma + vsetvli zero, a6, e16, m8, ta, ma .else vlse32.v v24, (a0), a2 - vsetvli t0, zero, e16, m4, ta, ma + vsetivli zero, \width * \width, e16, m2, ta, ma .endif vzext.vf2 v0, v24 vadd.vx v0, v0, a3 @@ -439,13 +440,14 @@ func ff_h264_idct\width\()_dc_add_8_rvv, zve64x, zba .if \width == 8 vsetvli zero, zero, e8, m4, ta, ma .else - vsetvli zero, zero, e8, m2, ta, ma + vsetvli zero, zero, e8, m1, ta, ma .endif vnclipu.wi v24, v0, 0 - vsetivli zero, \width, e8, m1, ta, ma .if \width == 8 + vsetivli zero, \width, e8, mf2, ta, ma vsse64.v v24, (a0), a2 .else + vsetivli zero, \width, e8, mf4, ta, ma vsse32.v v24, (a0), a2 .endif ret @@ -457,7 +459,11 @@ idct_dc_add8 8 .macro idct_dc_add width func ff_h264_idct\width\()_dc_add_16_rvv, zve64x, zba +.if \width == 8 vsetivli zero, \width, e16, m1, ta, ma +.else + vsetivli zero, \width, e16, mf2, ta, ma +.endif lw a3, 0(a1) addi a3, a3, 32 srai a3, a3, 6 @@ -487,7 +493,11 @@ func ff_h264_idct\width\()_dc_add_16_rvv, zve64x, zba vadd.vx v0, v0, a3 vmax.vx v0, v0, zero vmin.vx v0, v0, a5 +.if \width == 8 vsetivli zero, \width, e16, m1, ta, ma +.else + vsetivli zero, \width, e16, mf2, ta, ma +.endif vse16.v v0, (a0) vse16.v v1, (t4) vse16.v v2, (t5) -- 2.45.2 _______________________________________________ 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".