From: James Almer <jamrial@gmail.com> To: ffmpeg-devel@ffmpeg.org Subject: [FFmpeg-devel] [PATCH 2/2] swscale/x86/input: add AVX2 optimized uyvytoyuv422 Date: Wed, 5 Jun 2024 17:28:53 -0300 Message-ID: <20240605202853.3135-2-jamrial@gmail.com> (raw) In-Reply-To: <20240605202853.3135-1-jamrial@gmail.com> uyvytoyuv422_c: 23991.8 uyvytoyuv422_sse2: 2817.8 uyvytoyuv422_avx: 2819.3 uyvytoyuv422_avx2: 1972.3 Signed-off-by: James Almer <jamrial@gmail.com> --- libswscale/x86/rgb2rgb.c | 6 ++++++ libswscale/x86/rgb_2_rgb.asm | 32 ++++++++++++++++++++++++-------- 2 files changed, 30 insertions(+), 8 deletions(-) diff --git a/libswscale/x86/rgb2rgb.c b/libswscale/x86/rgb2rgb.c index b325e5dbd5..21ccfafe51 100644 --- a/libswscale/x86/rgb2rgb.c +++ b/libswscale/x86/rgb2rgb.c @@ -136,6 +136,9 @@ void ff_uyvytoyuv422_sse2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, void ff_uyvytoyuv422_avx(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, const uint8_t *src, int width, int height, int lumStride, int chromStride, int srcStride); +void ff_uyvytoyuv422_avx2(uint8_t *ydst, uint8_t *udst, uint8_t *vdst, + const uint8_t *src, int width, int height, + int lumStride, int chromStride, int srcStride); #endif av_cold void rgb2rgb_init_x86(void) @@ -177,5 +180,8 @@ av_cold void rgb2rgb_init_x86(void) if (EXTERNAL_AVX(cpu_flags)) { uyvytoyuv422 = ff_uyvytoyuv422_avx; } + if (EXTERNAL_AVX2_FAST(cpu_flags)) { + uyvytoyuv422 = ff_uyvytoyuv422_avx2; + } #endif } diff --git a/libswscale/x86/rgb_2_rgb.asm b/libswscale/x86/rgb_2_rgb.asm index 76ca1eec03..0bf1278718 100644 --- a/libswscale/x86/rgb_2_rgb.asm +++ b/libswscale/x86/rgb_2_rgb.asm @@ -34,13 +34,16 @@ pb_shuffle3210: db 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 SECTION .text -%macro RSHIFT_COPY 3 +%macro RSHIFT_COPY 5 ; %1 dst ; %2 src ; %3 shift -%if cpuflag(avx) - psrldq %1, %2, %3 +%if mmsize == 32 + vperm2i128 %1, %2, %3, %5 + RSHIFT %1, %4 +%elif cpuflag(avx) + psrldq %1, %2, %4 %else mova %1, %2 - RSHIFT %1, %3 + RSHIFT %1, %4 %endif %endmacro @@ -233,26 +236,37 @@ cglobal uyvytoyuv422, 9, 14, 8, ydst, udst, vdst, src, w, h, lum_stride, chrom_s jge .end_line .loop_simd: +%if mmsize == 32 + movu xm2, [srcq + wtwoq ] + movu xm3, [srcq + wtwoq + 16 ] + movu xm4, [srcq + wtwoq + 16 * 2] + movu xm5, [srcq + wtwoq + 16 * 3] + vinserti128 m2, m2, [srcq + wtwoq + 16 * 4], 1 + vinserti128 m3, m3, [srcq + wtwoq + 16 * 5], 1 + vinserti128 m4, m4, [srcq + wtwoq + 16 * 6], 1 + vinserti128 m5, m5, [srcq + wtwoq + 16 * 7], 1 +%else movu m2, [srcq + wtwoq ] movu m3, [srcq + wtwoq + mmsize ] movu m4, [srcq + wtwoq + mmsize * 2] movu m5, [srcq + wtwoq + mmsize * 3] +%endif ; extract y part 1 - RSHIFT_COPY m6, m2, 1 ; UYVY UYVY -> YVYU YVY... + RSHIFT_COPY m6, m2, m4, 1, 0x20 ; UYVY UYVY -> YVYU YVY... pand m6, m1; YxYx YxYx... - RSHIFT_COPY m7, m3, 1 ; UYVY UYVY -> YVYU YVY... + RSHIFT_COPY m7, m3, m5, 1, 0x20 ; UYVY UYVY -> YVYU YVY... pand m7, m1 ; YxYx YxYx... packuswb m6, m7 ; YYYY YYYY... movu [ydstq + wq], m6 ; extract y part 2 - RSHIFT_COPY m6, m4, 1 ; UYVY UYVY -> YVYU YVY... + RSHIFT_COPY m6, m4, m2, 1, 0x13 ; UYVY UYVY -> YVYU YVY... pand m6, m1; YxYx YxYx... - RSHIFT_COPY m7, m5, 1 ; UYVY UYVY -> YVYU YVY... + RSHIFT_COPY m7, m5, m3, 1, 0x13 ; UYVY UYVY -> YVYU YVY... pand m7, m1 ; YxYx YxYx... packuswb m6, m7 ; YYYY YYYY... @@ -309,4 +323,6 @@ UYVY_TO_YUV422 INIT_XMM avx UYVY_TO_YUV422 +INIT_YMM avx2 +UYVY_TO_YUV422 %endif -- 2.45.1 _______________________________________________ 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".
next prev parent reply other threads:[~2024-06-05 20:29 UTC|newest] Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top 2024-06-05 20:28 [FFmpeg-devel] [PATCH 1/2] swscale/x86/input: add AVX2 optimized RGB32 to YUV functions James Almer 2024-06-05 20:28 ` James Almer [this message] 2024-06-05 21:00 ` [FFmpeg-devel] [PATCH 2/2] swscale/x86/input: add AVX2 optimized uyvytoyuv422 Andreas Rheinhardt 2024-06-06 6:03 ` Rémi Denis-Courmont 2024-06-06 7:01 ` Christophe Gisquet 2024-06-07 7:24 ` Rémi Denis-Courmont
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20240605202853.3135-2-jamrial@gmail.com \ --to=jamrial@gmail.com \ --cc=ffmpeg-devel@ffmpeg.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel This inbox may be cloned and mirrored by anyone: git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git # If you have public-inbox 1.1+ installed, you may # initialize and index your mirror using the following commands: public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \ ffmpegdev@gitmailbox.com public-inbox-index ffmpegdev Example config snippet for mirrors. AGPL code for this site: git clone https://public-inbox.org/public-inbox.git