PR #20973 opened by Steven Xiao (younengxiao) URL: https://code.ffmpeg.org/FFmpeg/FFmpeg/pulls/20973 Patch URL: https://code.ffmpeg.org/FFmpeg/FFmpeg/pulls/20973.patch
This code submission is purposed to support the **motion estimation precision mode** for the D3D12 video encoder. By default, the D3D12 video encoder uses **MAXIMUM**, which means no restriction—it uses the highest precision supported by the driver. Maximum precision increases computational load and latency. In certain scenarios (such as real-time encoding or low-power devices), applications may want to reduce precision to improve speed or reduce power consumption. This requires the encoder to support user-defined motion estimation precision modes. *** **`D3D12_VIDEO_ENCODER_MOTION_ESTIMATION_PRECISION_MODE`** defines several precision modes: * **MAXIMUM**: No restriction, uses the maximum precision supported by the driver. * **FULL\_PIXEL**: Allows only full-pixel precision. * **HALF\_PIXEL**: Allows half-pixel precision. * **QUARTER\_PIXEL**: Allows quarter-pixel precision. * **EIGHTH\_PIXEL**: Allows eighth-pixel precision (introduced in Windows 11). The flag **`D3D12_VIDEO_ENCODER_SUPPORT_FLAG_MOTION_ESTIMATION_PRECISION_MODE_LIMIT_AVAILABLE`** in **`D3D12_VIDEO_ENCODER_SUPPORT_FLAGS`** indicates whether the video encoder supports limiting the motion estimation precision mode under the current configuration. From 7589b78b1e08f03bf9746fb6482f54345f274b6e Mon Sep 17 00:00:00 2001 From: stevxiao <[email protected]> Date: Wed, 19 Nov 2025 13:14:17 -0500 Subject: [PATCH] support motion estimation precision mode source version 1 --- libavcodec/d3d12va_encode.c | 2 +- libavcodec/d3d12va_encode.h | 21 ++++++++++++++++++++- libavcodec/d3d12va_encode_h264.c | 11 +++++++++++ libavcodec/d3d12va_encode_hevc.c | 11 +++++++++++ 4 files changed, 43 insertions(+), 2 deletions(-) diff --git a/libavcodec/d3d12va_encode.c b/libavcodec/d3d12va_encode.c index aa8a5982be..0e1e2de2f0 100644 --- a/libavcodec/d3d12va_encode.c +++ b/libavcodec/d3d12va_encode.c @@ -1205,7 +1205,7 @@ static int d3d12va_create_encoder(AVCodecContext *avctx) .EncodeProfile = ctx->profile->d3d12_profile, .InputFormat = frames_hwctx->format, .CodecConfiguration = ctx->codec_conf, - .MaxMotionEstimationPrecision = D3D12_VIDEO_ENCODER_MOTION_ESTIMATION_PRECISION_MODE_MAXIMUM, + .MaxMotionEstimationPrecision = (D3D12_VIDEO_ENCODER_MOTION_ESTIMATION_PRECISION_MODE)ctx->me_precision, }; hr = ID3D12VideoDevice3_CreateVideoEncoder(ctx->video_device3, &desc, &IID_ID3D12VideoEncoder, diff --git a/libavcodec/d3d12va_encode.h b/libavcodec/d3d12va_encode.h index 5bd1eedb7f..24fc3f9435 100644 --- a/libavcodec/d3d12va_encode.h +++ b/libavcodec/d3d12va_encode.h @@ -156,6 +156,11 @@ typedef struct D3D12VAEncodeContext { */ int max_frame_size; + /** + * Motion estimation precision mode + */ + int me_precision; + /** * Explicitly set RC mode (otherwise attempt to pick from * available modes). @@ -338,7 +343,21 @@ int ff_d3d12va_encode_close(AVCodecContext *avctx); { "max_frame_size", \ "Maximum frame size (in bytes)",\ OFFSET(common.max_frame_size), AV_OPT_TYPE_INT, \ - { .i64 = 0 }, 0, INT_MAX / 8, FLAGS } + { .i64 = 0 }, 0, INT_MAX / 8, FLAGS }, \ + { "me_precision", \ + "Motion estimation precision mode",\ + OFFSET(common.me_precision), AV_OPT_TYPE_INT, \ + { .i64 = 0 }, 0, 4, FLAGS, .unit = "me_precision" }, \ + { "maximum", "Maximum (best quality, slowest)", 0, AV_OPT_TYPE_CONST, \ + { .i64 = 0 }, 0, 0, FLAGS, .unit = "me_precision" }, \ + { "full_pixel", "Full pixel precision", 0, AV_OPT_TYPE_CONST, \ + { .i64 = 1 }, 0, 0, FLAGS, .unit = "me_precision" }, \ + { "half_pixel", "Half pixel precision", 0, AV_OPT_TYPE_CONST, \ + { .i64 = 2 }, 0, 0, FLAGS, .unit = "me_precision" }, \ + { "quarter_pixel", "Quarter pixel precision", 0, AV_OPT_TYPE_CONST, \ + { .i64 = 3 }, 0, 0, FLAGS, .unit = "me_precision" }, \ + { "eighth_pixel", "Eighth pixel precision", 0, AV_OPT_TYPE_CONST, \ + { .i64 = 4 }, 0, 0, FLAGS, .unit = "me_precision" } #define D3D12VA_ENCODE_RC_MODE(name, desc) \ { #name, desc, 0, AV_OPT_TYPE_CONST, { .i64 = RC_MODE_ ## name }, \ diff --git a/libavcodec/d3d12va_encode_h264.c b/libavcodec/d3d12va_encode_h264.c index 967544ea24..7c815b4fe1 100644 --- a/libavcodec/d3d12va_encode_h264.c +++ b/libavcodec/d3d12va_encode_h264.c @@ -211,6 +211,17 @@ static int d3d12va_encode_h264_init_sequence_params(AVCodecContext *avctx) av_log(avctx, AV_LOG_DEBUG, "D3D12 video encode on this device uses texture array mode.\n"); } + if (ctx->me_precision != 0) { + if (support.SupportFlags & D3D12_VIDEO_ENCODER_SUPPORT_FLAG_MOTION_ESTIMATION_PRECISION_MODE_LIMIT_AVAILABLE) { + av_log(avctx, AV_LOG_VERBOSE, "Hardware supports motion estimation " + "precision mode limits.\n"); + } else { + ctx->me_precision = 0; + av_log(avctx, AV_LOG_WARNING, "Hardware does not support motion estimation " + "precision mode limits. The me_precision parameter may be ignored.\n"); + } + } + desc = av_pix_fmt_desc_get(base_ctx->input_frames->sw_format); av_assert0(desc); diff --git a/libavcodec/d3d12va_encode_hevc.c b/libavcodec/d3d12va_encode_hevc.c index 01e5b4cb4c..9ca733fbd5 100644 --- a/libavcodec/d3d12va_encode_hevc.c +++ b/libavcodec/d3d12va_encode_hevc.c @@ -283,6 +283,17 @@ static int d3d12va_encode_hevc_init_sequence_params(AVCodecContext *avctx) av_log(avctx, AV_LOG_DEBUG, "D3D12 video encode on this device uses texture array mode.\n"); } + if (ctx->me_precision != 0) { + if (support.SupportFlags & D3D12_VIDEO_ENCODER_SUPPORT_FLAG_MOTION_ESTIMATION_PRECISION_MODE_LIMIT_AVAILABLE) { + av_log(avctx, AV_LOG_VERBOSE, "Hardware supports motion estimation " + "precision mode limits.\n"); + } else { + ctx->me_precision = 0; + av_log(avctx, AV_LOG_WARNING, "Hardware does not support motion estimation " + "precision mode limits. The me_precision parameter may be ignored.\n"); + } + } + desc = av_pix_fmt_desc_get(base_ctx->input_frames->sw_format); av_assert0(desc); -- 2.49.1 _______________________________________________ ffmpeg-devel mailing list -- [email protected] To unsubscribe send an email to [email protected]
