[FFmpeg-devel] lavc/hevcdsp_qpel_neon: using movi.16b instead of movi.2d

Message ID	tencent_6415A1936C8B9809466470816CA2BCCDE507@qq.com
State	Accepted
Commit	cc86343b960793a822d6c51b58a1a7e3319cb217
Headers	show Delivered-To: ffmpegpatchwork2@gmail.com 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; Message-ID: <tencent_6415A1936C8B9809466470816CA2BCCDE507@qq.com> To: ffmpeg-devel@ffmpeg.org Date: Wed, 15 Nov 2023 11:53:12 +0800 MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH] lavc/hevcdsp_qpel_neon: using movi.16b instead of movi.2d Precedence: list From: xufuji456 via ffmpeg-devel <ffmpeg-devel@ffmpeg.org> Reply-To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org> Cc: xufuji456 <839789740@qq.com> Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" <ffmpeg-devel-bounces@ffmpeg.org>
Series	[FFmpeg-devel] lavc/hevcdsp_qpel_neon: using movi.16b instead of movi.2d \| expand [FFmpeg-devel] lavc/hevcdsp_qpel_neon: using movi.16b instead of movi.2d

Context	Check	Description
yinshiyou/make_loongarch64	success	Make finished
yinshiyou/make_fate_loongarch64	success	Make fate finished
andriy/make_x86	success	Make finished
andriy/make_fate_x86	success	Make fate finished

diff --git a/libavcodec/aarch64/hevcdsp_epel_neon.S b/libavcodec/aarch64/hevcdsp_epel_neon.S index a2a051210f..c077c204cc 100644 --- a/libavcodec/aarch64/hevcdsp_epel_neon.S +++ b/libavcodec/aarch64/hevcdsp_epel_neon.S @@ -694,7 +694,7 @@ function ff_hevc_put_hevc_epel_h4_8_neon_i8mm, export=1 trn1 v4.2s, v4.2s, v5.2s trn1 v6.2s, v6.2s, v7.2s trn1 v4.2d, v4.2d, v6.2d - movi v16.2d, #0 + movi v16.16b, #0 usdot v16.4s, v4.16b, v30.16b xtn v16.4h, v16.4s st1 {v16.4h}, [x0], x10 @@ -714,8 +714,8 @@ function ff_hevc_put_hevc_epel_h6_8_neon_i8mm, export=1 trn2 v17.2s, v4.2s, v5.2s trn1 v6.2s, v6.2s, v7.2s trn1 v16.2d, v16.2d, v6.2d - movi v18.2d, #0 - movi v19.2d, #0 + movi v18.16b, #0 + movi v19.16b, #0 usdot v18.4s, v16.16b, v30.16b usdot v19.2s, v17.8b, v30.8b xtn v18.4h, v18.4s @@ -736,8 +736,8 @@ function ff_hevc_put_hevc_epel_h8_8_neon_i8mm, export=1 ext v7.16b, v4.16b, v4.16b, #3 zip1 v20.4s, v4.4s, v6.4s zip1 v21.4s, v5.4s, v7.4s - movi v16.2d, #0 - movi v17.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 usdot v16.4s, v20.16b, v30.16b usdot v17.4s, v21.16b, v30.16b xtn v16.4h, v16.4s @@ -761,9 +761,9 @@ function ff_hevc_put_hevc_epel_h12_8_neon_i8mm, export=1 trn1 v4.4s, v20.4s, v21.4s trn2 v5.4s, v20.4s, v21.4s trn1 v6.4s, v22.4s, v23.4s - movi v16.2d, #0 - movi v17.2d, #0 - movi v18.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 + movi v18.16b, #0 usdot v16.4s, v4.16b, v30.16b usdot v17.4s, v5.16b, v30.16b usdot v18.4s, v6.16b, v30.16b @@ -788,10 +788,10 @@ function ff_hevc_put_hevc_epel_h16_8_neon_i8mm, export=1 zip2 v22.4s, v0.4s, v6.4s zip1 v21.4s, v5.4s, v7.4s zip2 v23.4s, v5.4s, v7.4s - movi v16.2d, #0 - movi v17.2d, #0 - movi v18.2d, #0 - movi v19.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 + movi v18.16b, #0 + movi v19.16b, #0 usdot v16.4s, v20.16b, v30.16b usdot v17.4s, v21.16b, v30.16b usdot v18.4s, v22.16b, v30.16b @@ -815,14 +815,14 @@ function ff_hevc_put_hevc_epel_h24_8_neon_i8mm, export=1 ext v26.16b, v1.16b, v1.16b, #1 ext v27.16b, v1.16b, v1.16b, #2 ext v28.16b, v1.16b, v1.16b, #3 - movi v16.2d, #0 - movi v17.2d, #0 - movi v18.2d, #0 - movi v19.2d, #0 - movi v20.2d, #0 - movi v21.2d, #0 - movi v22.2d, #0 - movi v23.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 + movi v18.16b, #0 + movi v19.16b, #0 + movi v20.16b, #0 + movi v21.16b, #0 + movi v22.16b, #0 + movi v23.16b, #0 usdot v16.4s, v0.16b, v30.16b usdot v17.4s, v5.16b, v30.16b usdot v18.4s, v6.16b, v30.16b @@ -861,14 +861,14 @@ function ff_hevc_put_hevc_epel_h32_8_neon_i8mm, export=1 ext v26.16b, v1.16b, v2.16b, #1 ext v27.16b, v1.16b, v2.16b, #2 ext v28.16b, v1.16b, v2.16b, #3 - movi v16.2d, #0 - movi v17.2d, #0 - movi v18.2d, #0 - movi v19.2d, #0 - movi v20.2d, #0 - movi v21.2d, #0 - movi v22.2d, #0 - movi v23.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 + movi v18.16b, #0 + movi v19.16b, #0 + movi v20.16b, #0 + movi v21.16b, #0 + movi v22.16b, #0 + movi v23.16b, #0 usdot v16.4s, v0.16b, v30.16b usdot v17.4s, v5.16b, v30.16b usdot v18.4s, v6.16b, v30.16b @@ -900,18 +900,18 @@ function ff_hevc_put_hevc_epel_h48_8_neon_i8mm, export=1 ext v16.16b, v1.16b, v2.16b, #1 ext v17.16b, v1.16b, v2.16b, #2 ext v18.16b, v1.16b, v2.16b, #3 - movi v20.2d, #0 - movi v21.2d, #0 - movi v22.2d, #0 - movi v23.2d, #0 + movi v20.16b, #0 + movi v21.16b, #0 + movi v22.16b, #0 + movi v23.16b, #0 usdot v20.4s, v0.16b, v30.16b usdot v21.4s, v4.16b, v30.16b usdot v22.4s, v5.16b, v30.16b usdot v23.4s, v6.16b, v30.16b - movi v24.2d, #0 - movi v25.2d, #0 - movi v26.2d, #0 - movi v27.2d, #0 + movi v24.16b, #0 + movi v25.16b, #0 + movi v26.16b, #0 + movi v27.16b, #0 usdot v24.4s, v1.16b, v30.16b usdot v25.4s, v16.16b, v30.16b usdot v26.4s, v17.16b, v30.16b @@ -928,10 +928,10 @@ function ff_hevc_put_hevc_epel_h48_8_neon_i8mm, export=1 ext v4.16b, v2.16b, v3.16b, #1 ext v5.16b, v2.16b, v3.16b, #2 ext v6.16b, v2.16b, v3.16b, #3 - movi v20.2d, #0 - movi v21.2d, #0 - movi v22.2d, #0 - movi v23.2d, #0 + movi v20.16b, #0 + movi v21.16b, #0 + movi v22.16b, #0 + movi v23.16b, #0 usdot v20.4s, v2.16b, v30.16b usdot v21.4s, v4.16b, v30.16b usdot v22.4s, v5.16b, v30.16b @@ -957,18 +957,18 @@ function ff_hevc_put_hevc_epel_h64_8_neon_i8mm, export=1 ext v16.16b, v1.16b, v2.16b, #1 ext v17.16b, v1.16b, v2.16b, #2 ext v18.16b, v1.16b, v2.16b, #3 - movi v20.2d, #0 - movi v21.2d, #0 - movi v22.2d, #0 - movi v23.2d, #0 + movi v20.16b, #0 + movi v21.16b, #0 + movi v22.16b, #0 + movi v23.16b, #0 usdot v20.4s, v0.16b, v30.16b usdot v21.4s, v4.16b, v30.16b usdot v22.4s, v5.16b, v30.16b usdot v23.4s, v6.16b, v30.16b - movi v24.2d, #0 - movi v25.2d, #0 - movi v26.2d, #0 - movi v27.2d, #0 + movi v24.16b, #0 + movi v25.16b, #0 + movi v26.16b, #0 + movi v27.16b, #0 usdot v24.4s, v1.16b, v30.16b usdot v25.4s, v16.16b, v30.16b usdot v26.4s, v17.16b, v30.16b @@ -989,18 +989,18 @@ function ff_hevc_put_hevc_epel_h64_8_neon_i8mm, export=1 ext v16.16b, v3.16b, v7.16b, #1 ext v17.16b, v3.16b, v7.16b, #2 ext v18.16b, v3.16b, v7.16b, #3 - movi v20.2d, #0 - movi v21.2d, #0 - movi v22.2d, #0 - movi v23.2d, #0 + movi v20.16b, #0 + movi v21.16b, #0 + movi v22.16b, #0 + movi v23.16b, #0 usdot v20.4s, v2.16b, v30.16b usdot v21.4s, v4.16b, v30.16b usdot v22.4s, v5.16b, v30.16b usdot v23.4s, v6.16b, v30.16b - movi v24.2d, #0 - movi v25.2d, #0 - movi v26.2d, #0 - movi v27.2d, #0 + movi v24.16b, #0 + movi v25.16b, #0 + movi v26.16b, #0 + movi v27.16b, #0 usdot v24.4s, v3.16b, v30.16b usdot v25.4s, v16.16b, v30.16b usdot v26.4s, v17.16b, v30.16b @@ -1593,7 +1593,7 @@ function ff_hevc_put_hevc_epel_uni_w_h4_8_neon_i8mm, export=1 trn1 v0.2s, v0.2s, v2.2s trn1 v1.2s, v1.2s, v3.2s zip1 v0.4s, v0.4s, v1.4s - movi v16.2d, #0 + movi v16.16b, #0 usdot v16.4s, v0.16b, v28.16b mul v16.4s, v16.4s, v30.4s sqrshl v16.4s, v16.4s, v31.4s @@ -1620,8 +1620,8 @@ function ff_hevc_put_hevc_epel_uni_w_h6_8_neon_i8mm, export=1 trn2 v6.2s, v0.2s, v1.2s trn1 v5.2s, v2.2s, v3.2s zip1 v4.2d, v4.2d, v5.2d - movi v16.2d, #0 - movi v17.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 usdot v16.4s, v4.16b, v28.16b usdot v17.2s, v6.8b, v28.8b mul v16.4s, v16.4s, v30.4s @@ -1640,8 +1640,8 @@ function ff_hevc_put_hevc_epel_uni_w_h6_8_neon_i8mm, export=1 endfunc .macro EPEL_UNI_W_H_CALC s0, s1, d0, d1 - movi \d0\().2d, #0 - movi \d1\().2d, #0 + movi \d0\().16b, #0 + movi \d1\().16b, #0 usdot \d0\().4s, \s0\().16b, v28.16b usdot \d1\().4s, \s1\().16b, v28.16b mul \d0\().4s, \d0\().4s, v30.4s @@ -1687,7 +1687,7 @@ function ff_hevc_put_hevc_epel_uni_w_h12_8_neon_i8mm, export=1 zip2 v7.4s, v1.4s, v3.4s zip1 v6.4s, v6.4s, v7.4s EPEL_UNI_W_H_CALC v4, v5, v16, v17 - movi v18.2d, #0 + movi v18.16b, #0 usdot v18.4s, v6.16b, v28.16b mul v18.4s, v18.4s, v30.4s sqrshl v18.4s, v18.4s, v31.4s @@ -2575,7 +2575,7 @@ DISABLE_I8MM .endm .macro EPEL_UNI_W_V4_CALC d0, s0, s1, s2, s3 - movi \d0\().2d, #0 + movi \d0\().16b, #0 umlsl \d0\().8h, \s0\().8b, v0.8b umlal \d0\().8h, \s1\().8b, v1.8b umlal \d0\().8h, \s2\().8b, v2.8b @@ -2626,7 +2626,7 @@ function ff_hevc_put_hevc_epel_uni_w_v4_8_neon, export=1 endfunc .macro EPEL_UNI_W_V8_CALC d0, s0, s1, s2, s3, t0, t1 - movi \d0\().2d, #0 + movi \d0\().16b, #0 umlsl \d0\().8h, \s0\().8b, v0.8b umlal \d0\().8h, \s1\().8b, v1.8b umlal \d0\().8h, \s2\().8b, v2.8b @@ -2720,8 +2720,8 @@ function ff_hevc_put_hevc_epel_uni_w_v8_8_neon, export=1 endfunc .macro EPEL_UNI_W_V12_CALC d0, d1, s0, s1, s2, s3, t0, t1, t2, t3 - movi \d0\().2d, #0 - movi \d1\().2d, #0 + movi \d0\().16b, #0 + movi \d1\().16b, #0 umlsl \d0\().8h, \s0\().8b, v0.8b umlsl2 \d1\().8h, \s0\().16b, v0.16b umlal \d0\().8h, \s1\().8b, v1.8b @@ -2793,8 +2793,8 @@ function ff_hevc_put_hevc_epel_uni_w_v12_8_neon, export=1 endfunc .macro EPEL_UNI_W_V16_CALC d0, d1, s0, s1, s2, s3, t0, t1, t2, t3 - movi \d0\().2d, #0 - movi \d1\().2d, #0 + movi \d0\().16b, #0 + movi \d1\().16b, #0 umlsl \d0\().8h, \s0\().8b, v0.8b umlsl2 \d1\().8h, \s0\().16b, v0.16b umlal \d0\().8h, \s1\().8b, v1.8b diff --git a/libavcodec/aarch64/hevcdsp_qpel_neon.S b/libavcodec/aarch64/hevcdsp_qpel_neon.S index 8adfa38ccf..bcee627cba 100644 --- a/libavcodec/aarch64/hevcdsp_qpel_neon.S +++ b/libavcodec/aarch64/hevcdsp_qpel_neon.S @@ -2180,8 +2180,8 @@ function ff_hevc_put_hevc_qpel_uni_w_h4_8_neon_i8mm, export=1 ext v3.16b, v0.16b, v0.16b, #3 zip1 v0.2d, v0.2d, v1.2d zip1 v2.2d, v2.2d, v3.2d - movi v16.2d, #0 - movi v17.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 usdot v16.4s, v0.16b, v28.16b usdot v17.4s, v2.16b, v28.16b addp v16.4s, v16.4s, v17.4s @@ -2210,9 +2210,9 @@ function ff_hevc_put_hevc_qpel_uni_w_h6_8_neon_i8mm, export=1 zip1 v0.2d, v0.2d, v1.2d zip1 v2.2d, v2.2d, v3.2d zip1 v4.2d, v4.2d, v5.2d - movi v16.2d, #0 - movi v17.2d, #0 - movi v18.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 + movi v18.16b, #0 usdot v16.4s, v0.16b, v28.16b usdot v17.4s, v2.16b, v28.16b usdot v18.4s, v4.16b, v28.16b @@ -2236,10 +2236,10 @@ endfunc .macro QPEL_UNI_W_H_CALC s0, s1, s2, s3, d0, d1, d2, d3 - movi \d0\().2d, #0 - movi \d1\().2d, #0 - movi \d2\().2d, #0 - movi \d3\().2d, #0 + movi \d0\().16b, #0 + movi \d1\().16b, #0 + movi \d2\().16b, #0 + movi \d3\().16b, #0 usdot \d0\().4s, \s0\().16b, v28.16b usdot \d1\().4s, \s1\().16b, v28.16b usdot \d2\().4s, \s2\().16b, v28.16b @@ -2255,8 +2255,8 @@ endfunc .endm .macro QPEL_UNI_W_H_CALC_HALF s0, s1, d0, d1 - movi \d0\().2d, #0 - movi \d1\().2d, #0 + movi \d0\().16b, #0 + movi \d1\().16b, #0 usdot \d0\().4s, \s0\().16b, v28.16b usdot \d1\().4s, \s1\().16b, v28.16b addp \d0\().4s, \d0\().4s, \d1\().4s @@ -2606,8 +2606,8 @@ function ff_hevc_put_hevc_qpel_h4_8_neon_i8mm, export=1 ext v3.16b, v0.16b, v0.16b, #3 zip1 v0.2d, v0.2d, v1.2d zip1 v2.2d, v2.2d, v3.2d - movi v16.2d, #0 - movi v17.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 usdot v16.4s, v0.16b, v31.16b usdot v17.4s, v2.16b, v31.16b addp v16.4s, v16.4s, v17.4s @@ -2633,9 +2633,9 @@ function ff_hevc_put_hevc_qpel_h6_8_neon_i8mm, export=1 zip1 v0.2d, v0.2d, v1.2d zip1 v2.2d, v2.2d, v3.2d zip1 v4.2d, v4.2d, v5.2d - movi v16.2d, #0 - movi v17.2d, #0 - movi v18.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 + movi v18.16b, #0 usdot v16.4s, v0.16b, v31.16b usdot v17.4s, v2.16b, v31.16b usdot v18.4s, v4.16b, v31.16b @@ -2668,10 +2668,10 @@ function ff_hevc_put_hevc_qpel_h8_8_neon_i8mm, export=1 zip1 v2.2d, v2.2d, v3.2d zip1 v4.2d, v4.2d, v5.2d zip1 v6.2d, v6.2d, v7.2d - movi v16.2d, #0 - movi v17.2d, #0 - movi v18.2d, #0 - movi v19.2d, #0 + movi v16.16b, #0 + movi v17.16b, #0 + movi v18.16b, #0 + movi v19.16b, #0 usdot v16.4s, v0.16b, v31.16b usdot v17.4s, v2.16b, v31.16b usdot v18.4s, v4.16b, v31.16b @@ -2688,10 +2688,10 @@ function ff_hevc_put_hevc_qpel_h8_8_neon_i8mm, export=1 endfunc .macro QPEL_H_CALC s0, s1, s2, s3, d0, d1, d2, d3 - movi \d0\().2d, #0 - movi \d1\().2d, #0 - movi \d2\().2d, #0 - movi \d3\().2d, #0 + movi \d0\().16b, #0 + movi \d1\().16b, #0 + movi \d2\().16b, #0 + movi \d3\().16b, #0 usdot \d0\().4s, \s0\().16b, v31.16b usdot \d1\().4s, \s1\().16b, v31.16b usdot \d2\().4s, \s2\().16b, v31.16b @@ -2716,8 +2716,8 @@ function ff_hevc_put_hevc_qpel_h12_8_neon_i8mm, export=1 QPEL_H_CALC v16, v1, v2, v3, v20, v21, v22, v23 addp v20.4s, v20.4s, v22.4s addp v21.4s, v21.4s, v23.4s - movi v24.2d, #0 - movi v25.2d, #0 + movi v24.16b, #0 + movi v25.16b, #0 usdot v24.4s, v18.16b, v31.16b usdot v25.4s, v19.16b, v31.16b addp v24.4s, v24.4s, v25.4s diff --git a/libavcodec/aarch64/mpegaudiodsp_neon.S b/libavcodec/aarch64/mpegaudiodsp_neon.S index b6ef131228..9799c271d0 100644 --- a/libavcodec/aarch64/mpegaudiodsp_neon.S +++ b/libavcodec/aarch64/mpegaudiodsp_neon.S @@ -56,7 +56,7 @@ function ff_mpadsp_apply_window_\type\()_neon, export=1 .ifc \type, fixed ld1r {v16.2s}, [x2] // dither_state sxtl v16.2d, v16.2s - movi v29.2d, #0 + movi v29.16b, #0 movi v30.2d, #(1<<OUT_SHIFT)-1 trn1 v31.2d, v29.2d, v30.2d trn2 v30.2d, v30.2d, v29.2d @@ -74,9 +74,9 @@ function ff_mpadsp_apply_window_\type\()_neon, export=1 add x11, x6, #(32)<<2 // w + 32 add x12, x7, #(32)<<2 // w2 + 32 mov x15, #8 - movi v17.2d, #0 - movi v18.2d, #0 - movi v19.2d, #0 + movi v17.16b, #0 + movi v18.16b, #0 + movi v19.16b, #0 2: subs x15, x15, #1 ld1 {v0.4s}, [x8], x9 diff --git a/libswscale/aarch64/hscale.S b/libswscale/aarch64/hscale.S index b49443c964..b3873fc4b7 100644 --- a/libswscale/aarch64/hscale.S +++ b/libswscale/aarch64/hscale.S @@ -50,10 +50,10 @@ function ff_hscale8to15_X8_neon, export=1 add x12, x16, x7 // filter1 = filter0 + filterSize*2 add x13, x12, x7 // filter2 = filter1 + filterSize*2 add x4, x13, x7 // filter3 = filter2 + filterSize*2 - movi v0.2d, #0 // val sum part 1 (for dst[0]) - movi v1.2d, #0 // val sum part 2 (for dst[1]) - movi v2.2d, #0 // val sum part 3 (for dst[2]) - movi v3.2d, #0 // val sum part 4 (for dst[3]) + movi v0.16b, #0 // val sum part 1 (for dst[0]) + movi v1.16b, #0 // val sum part 2 (for dst[1]) + movi v2.16b, #0 // val sum part 3 (for dst[2]) + movi v3.16b, #0 // val sum part 4 (for dst[3]) add x17, x3, w8, uxtw // srcp + filterPos[0] add x8, x3, w0, uxtw // srcp + filterPos[1] add x0, x3, w11, uxtw // srcp + filterPos[2] @@ -108,10 +108,10 @@ function ff_hscale8to15_X4_neon, export=1 ldp w8, w9, [x5] // filterPos[idx + 0], [idx + 1] ldp w10, w11, [x5, #8] // filterPos[idx + 2], [idx + 3] - movi v16.2d, #0 // initialize accumulator for idx + 0 - movi v17.2d, #0 // initialize accumulator for idx + 1 - movi v18.2d, #0 // initialize accumulator for idx + 2 - movi v19.2d, #0 // initialize accumulator for idx + 3 + movi v16.16b, #0 // initialize accumulator for idx + 0 + movi v17.16b, #0 // initialize accumulator for idx + 1 + movi v18.16b, #0 // initialize accumulator for idx + 2 + movi v19.16b, #0 // initialize accumulator for idx + 3 mov x12, x4 // filter pointer for idx + 0 add x13, x4, x7 // filter pointer for idx + 1 @@ -253,8 +253,8 @@ function ff_hscale8to15_4_neon, export=1 ldp w12, w13, [x5, #16] // filterPos[idx + 4][0..3], [idx + 5][0..3], next iteration ldp w14, w15, [x5, #24] // filterPos[idx + 6][0..3], [idx + 7][0..3], next iteration - movi v0.2d, #0 // Clear madd accumulator for idx 0..3 - movi v5.2d, #0 // Clear madd accumulator for idx 4..7 + movi v0.16b, #0 // Clear madd accumulator for idx 0..3 + movi v5.16b, #0 // Clear madd accumulator for idx 4..7 ld4 {v1.8h, v2.8h, v3.8h, v4.8h}, [x4], #64 // load filter idx + 0..7 @@ -299,8 +299,8 @@ function ff_hscale8to15_4_neon, export=1 ld4 {v16.8b, v17.8b, v18.8b, v19.8b}, [sp] ld4 {v1.8h, v2.8h, v3.8h, v4.8h}, [x4], #64 // load filter idx + 0..7 - movi v0.2d, #0 // Clear madd accumulator for idx 0..3 - movi v5.2d, #0 // Clear madd accumulator for idx 4..7 + movi v0.16b, #0 // Clear madd accumulator for idx 0..3 + movi v5.16b, #0 // Clear madd accumulator for idx 4..7 uxtl v16.8h, v16.8b // unsigned extend long, covert src data to 16-bit uxtl v17.8h, v17.8b // unsigned extend long, covert src data to 16-bit @@ -499,10 +499,10 @@ function ff_hscale8to19_X8_neon, export=1 ldr w11, [x5], #4 // filterPos[idx + 2] add x4, x13, x7 // filter3 = filter2 + filterSize*2 ldr w9, [x5], #4 // filterPos[idx + 3] - movi v0.2d, #0 // val sum part 1 (for dst[0]) - movi v1.2d, #0 // val sum part 2 (for dst[1]) - movi v2.2d, #0 // val sum part 3 (for dst[2]) - movi v3.2d, #0 // val sum part 4 (for dst[3]) + movi v0.16b, #0 // val sum part 1 (for dst[0]) + movi v1.16b, #0 // val sum part 2 (for dst[1]) + movi v2.16b, #0 // val sum part 3 (for dst[2]) + movi v3.16b, #0 // val sum part 4 (for dst[3]) add x17, x3, w8, uxtw // srcp + filterPos[0] add x8, x3, w0, uxtw // srcp + filterPos[1] add x0, x3, w11, uxtw // srcp + filterPos[2] @@ -560,10 +560,10 @@ function ff_hscale8to19_X4_neon, export=1 ldp w8, w9, [x5] ldp w10, w11, [x5, #8] - movi v16.2d, #0 // initialize accumulator for idx + 0 - movi v17.2d, #0 // initialize accumulator for idx + 1 - movi v18.2d, #0 // initialize accumulator for idx + 2 - movi v19.2d, #0 // initialize accumulator for idx + 3 + movi v16.16b, #0 // initialize accumulator for idx + 0 + movi v17.16b, #0 // initialize accumulator for idx + 1 + movi v18.16b, #0 // initialize accumulator for idx + 2 + movi v19.16b, #0 // initialize accumulator for idx + 3 mov x12, x4 // filter + 0 add x13, x4, x7 // filter + 1 @@ -865,10 +865,10 @@ function ff_hscale16to15_X8_neon_asm, export=1 add x12, x16, x7 // filter1 = filter0 + filterSize*2 add x13, x12, x7 // filter2 = filter1 + filterSize*2 add x4, x13, x7 // filter3 = filter2 + filterSize*2 - movi v0.2d, #0 // val sum part 1 (for dst[0]) - movi v1.2d, #0 // val sum part 2 (for dst[1]) - movi v2.2d, #0 // val sum part 3 (for dst[2]) - movi v3.2d, #0 // val sum part 4 (for dst[3]) + movi v0.16b, #0 // val sum part 1 (for dst[0]) + movi v1.16b, #0 // val sum part 2 (for dst[1]) + movi v2.16b, #0 // val sum part 3 (for dst[2]) + movi v3.16b, #0 // val sum part 4 (for dst[3]) add x17, x3, w8, uxtw // srcp + filterPos[0] add x8, x3, w10, uxtw // srcp + filterPos[1] add x10, x3, w11, uxtw // srcp + filterPos[2] @@ -945,10 +945,10 @@ function ff_hscale16to15_X4_neon_asm, export=1 ldp w8, w9, [x5] ldp w10, w11, [x5, #8] - movi v16.2d, #0 // initialize accumulator for idx + 0 - movi v17.2d, #0 // initialize accumulator for idx + 1 - movi v18.2d, #0 // initialize accumulator for idx + 2 - movi v19.2d, #0 // initialize accumulator for idx + 3 + movi v16.16b, #0 // initialize accumulator for idx + 0 + movi v17.16b, #0 // initialize accumulator for idx + 1 + movi v18.16b, #0 // initialize accumulator for idx + 2 + movi v19.16b, #0 // initialize accumulator for idx + 3 mov x12, x4 // filter + 0 add x13, x4, x7 // filter + 1 @@ -1270,10 +1270,10 @@ function ff_hscale16to19_X8_neon_asm, export=1 add x13, x12, x7 // filter2 = filter1 + filterSize*2 lsl w10, w10, #1 add x4, x13, x7 // filter3 = filter2 + filterSize*2 - movi v0.2d, #0 // val sum part 1 (for dst[0]) - movi v1.2d, #0 // val sum part 2 (for dst[1]) - movi v2.2d, #0 // val sum part 3 (for dst[2]) - movi v3.2d, #0 // val sum part 4 (for dst[3]) + movi v0.16b, #0 // val sum part 1 (for dst[0]) + movi v1.16b, #0 // val sum part 2 (for dst[1]) + movi v2.16b, #0 // val sum part 3 (for dst[2]) + movi v3.16b, #0 // val sum part 4 (for dst[3]) add x17, x3, w8, uxtw // srcp + filterPos[0] add x8, x3, w10, uxtw // srcp + filterPos[1] add x10, x3, w11, uxtw // srcp + filterPos[2] @@ -1348,10 +1348,10 @@ function ff_hscale16to19_X4_neon_asm, export=1 ldp w8, w9, [x5] ldp w10, w11, [x5, #8] - movi v16.2d, #0 // initialize accumulator for idx + 0 - movi v17.2d, #0 // initialize accumulator for idx + 1 - movi v18.2d, #0 // initialize accumulator for idx + 2 - movi v19.2d, #0 // initialize accumulator for idx + 3 + movi v16.16b, #0 // initialize accumulator for idx + 0 + movi v17.16b, #0 // initialize accumulator for idx + 1 + movi v18.16b, #0 // initialize accumulator for idx + 2 + movi v19.16b, #0 // initialize accumulator for idx + 3 mov x12, x4 // filter + 0 add x13, x4, x7 // filter + 1

[FFmpeg-devel] lavc/hevcdsp_qpel_neon: using movi.16b instead of movi.2d

Checks

Commit Message

Comments

Patch