From: Lynne <dev@lynne.ee> To: ffmpeg-devel@ffmpeg.org Cc: Lynne <dev@lynne.ee> Subject: [FFmpeg-devel] [PATCH 14/18] vulkan_ffv1: externalize extended lookup check Date: Sat, 12 Apr 2025 09:22:45 +0200 Message-ID: <20250412072256.77815-14-dev@lynne.ee> (raw) In-Reply-To: <20250412072256.77815-1-dev@lynne.ee> 8% speedup on nvidia on 4k. --- libavcodec/vulkan/ffv1_dec.comp | 3 +-- libavcodec/vulkan_ffv1.c | 6 ++++++ 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/libavcodec/vulkan/ffv1_dec.comp b/libavcodec/vulkan/ffv1_dec.comp index a6272d4832..4cc3b9987f 100644 --- a/libavcodec/vulkan/ffv1_dec.comp +++ b/libavcodec/vulkan/ffv1_dec.comp @@ -47,8 +47,7 @@ ivec2 get_pred(ivec2 sp, ivec2 off, int p, int sw, uint8_t quant_table_idx) quant_table[quant_table_idx][1][(top[0] - top[1]) & MAX_QUANT_TABLE_MASK] + quant_table[quant_table_idx][2][(top[1] - top[2]) & MAX_QUANT_TABLE_MASK]; - if ((quant_table[quant_table_idx][3][127] != 0) || - (quant_table[quant_table_idx][4][127] != 0)) { + if (extend_lookup[quant_table_idx] > 0) { TYPE cur2 = TYPE(0); if (off.x > 0) { const ivec2 yoff_border2 = off.x == 1 ? ivec2(-1, -1) : ivec2(-2, 0); diff --git a/libavcodec/vulkan_ffv1.c b/libavcodec/vulkan_ffv1.c index aaebcd53b5..72cacb1678 100644 --- a/libavcodec/vulkan_ffv1.c +++ b/libavcodec/vulkan_ffv1.c @@ -88,6 +88,7 @@ typedef struct FFv1VkParameters { uint32_t crcref; int rct_offset; + uint8_t extend_lookup[8]; uint8_t bits_per_raw_sample; uint8_t quant_table_count; uint8_t version; @@ -120,6 +121,7 @@ static void add_push_data(FFVulkanShader *shd) GLSLC(1, uint32_t crcref; ); GLSLC(1, int rct_offset; ); GLSLC(0, ); + GLSLC(1, uint8_t extend_lookup[8]; ); GLSLC(1, uint8_t bits_per_raw_sample; ); GLSLC(1, uint8_t quant_table_count; ); GLSLC(1, uint8_t version; ); @@ -456,6 +458,10 @@ static int vk_ffv1_end_frame(AVCodecContext *avctx) .golomb = f->ac == AC_GOLOMB_RICE, .check_crc = !!(avctx->err_recognition & AV_EF_CRCCHECK), }; + for (int i = 0; i < f->quant_table_count; i++) + pd.extend_lookup[i] = (f->quant_tables[i][3][127] != 0) || + (f->quant_tables[i][4][127] != 0); + /* For some reason the C FFv1 encoder/decoder treats these differently */ if (sw_format == AV_PIX_FMT_GBRP10 || sw_format == AV_PIX_FMT_GBRP12 || -- 2.47.2 _______________________________________________ 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".
next prev parent reply other threads:[~2025-04-12 7:25 UTC|newest] Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top 2025-04-12 7:22 [FFmpeg-devel] [PATCH 01/18] hwcontext_vulkan: disable descriptor buffer extension on Intel Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 02/18] vulkan_ffv1: enable acceleration " Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 03/18] vulkan_ffv1: remove unused define Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 04/18] vulkan_ffv1: slightly optimize the range decoder Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 05/18] vulkan_ffv1: optimize symbol reader Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 06/18] vulkan_ffv1: allocate just as much memory for slice state as needed Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 07/18] vulkan_ffv1: init overread/corrupt fields Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 08/18] vulkan_ffv1: fallback to upload if mapping packet fails, fix fallback Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 09/18] vulkan_ffv1: fix reset shader dependencies Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 10/18] vulkan_ffv1: improve buffer barrier correctness for slice state Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 11/18] vulkan_ffv1: fix left-2 sample addressing Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 12/18] vulkan_ffv1: cache only 2 lines when decoding RGB Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 13/18] ffv1/vulkan: redo context count tracking and quant_table_idx management Lynne 2025-04-13 20:39 ` Jerome Martinez 2025-04-12 7:22 ` Lynne [this message] 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 15/18] vulkan_ffv1: remove need for scratch data during setup Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 16/18] vulkan_ffv1: shortcut +-1 coeffs in symbol reading Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 17/18] vulkan: add support for expect/assume Lynne 2025-04-12 7:22 ` [FFmpeg-devel] [PATCH 18/18] vulkan_ffv1: add cached symbol reader for AMD Lynne 2025-04-13 13:38 ` [FFmpeg-devel] [PATCH 01/18] hwcontext_vulkan: disable descriptor buffer extension on Intel Jerome Martinez
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=20250412072256.77815-14-dev@lynne.ee \ --to=dev@lynne.ee \ --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