Araz Iusubov:
> From: ffmpeg-devel <ffmpeg-devel-boun...@ffmpeg.org> On Behalf Of Araz
> Iusubov
> Sent: Thursday, July 17, 2025 9:30 PM
> To: ffmpeg-devel@ffmpeg.org
> Cc: Araz Iusubov <primeadv...@gmail.com>
> Subject: [FFmpeg-devel] [PATCH, v6] avcodec/d3d12va_encode: texture array
> support for HEVC
>
> This patch adds support for the texture array feature used by AMD boards in
> the
> D3D12 HEVC encoder.
> In texture array mode, a single texture array is shared for all reference and
> reconstructed pictures using different subresources.
> The implementation ensures compatibility and has been successfully tested on
> AMD, Intel, and NVIDIA GPUs.
>
> v2 updates:
> 1. The reference to MaxL1ReferencesForB for the H.264 codec was updated to
> use the corresponding H.264 field instead of the HEVC one.
> 2. Max_subresource_array_size calculation was adjusted by removing the
> D3D12VA_VIDEO_ENC_ASYNC_DEPTH offset.
>
> v3 updates:
> 1. Fixed a type mismatch by explicitly casting AVD3D12VAFrame* to
> (uint8_t*) when assigning to data[0].
> 2. Adjusted logging format specifier for HRESULT to use `%lx`.
>
> v4 updates:
> 1. Moved texture array management to hwcontext_d3d12va for proper
> abstraction.
> 2. Added `texture_array` and `texture_array_size` fields to
> AVD3D12VAFramesContext.
> 3. Implemented shared texture array allocation during `av_hwframe_ctx_init`.
> 4. Frames now receive unique subresource indices via
> `d3d12va_pool_alloc_texture_array`.
> 5. Removed `d3d12va_create_texture_array`, allocation is now handled entirely
> within hwcontext.
> 6. Encoder now uses subresource indices provided by hwcontext instead of
> managing them manually.
>
> v5 updates:
> No changes, resubmitted as v4 was missed by patchwork.
>
> v6 updates:
> 1. Minor cosmetic fixes according to review of v5 2. Bumped lavu version to
> 60.5.100 and updated APIchanges
>
> ---
> doc/APIchanges | 4 +
> libavcodec/d3d12va_encode.c | 184 +++++++++++++++++++++++--------
> libavcodec/d3d12va_encode.h | 12 ++
> libavcodec/d3d12va_encode_hevc.c | 5 +-
> libavutil/hwcontext_d3d12va.c | 65 ++++++++++-
> libavutil/hwcontext_d3d12va.h | 18 +++
> libavutil/version.h | 4 +-
> 7 files changed, 240 insertions(+), 52 deletions(-)
>
> diff --git a/doc/APIchanges b/doc/APIchanges index d6e38245f8..eab06cd251
> 100644
> --- a/doc/APIchanges
> +++ b/doc/APIchanges
> @@ -2,6 +2,10 @@ The last version increases of all libraries were on
> 2025-03-28
>
> API changes, most recent first:
>
> +2025-07-xx - xxxxxxxxxx - lavu 60.5.100 - hwcontext_d3d12va.h
> + Add support for texture array mode AVD3D12VAFrame.subresource_index,
> + AVD3D12VAFramesContext.texture_array and texture_array_size
> +
> 2025-07-xx - xxxxxxxxxd - lavfi 11.2.100 - avfilter.h
> Add AVFilterGraph->max_buffered_frames.
>
> diff --git a/libavcodec/d3d12va_encode.c b/libavcodec/d3d12va_encode.c index
> e24a5b8d24..1f202f512c 100644
> --- a/libavcodec/d3d12va_encode.c
> +++ b/libavcodec/d3d12va_encode.c
> @@ -191,7 +191,8 @@ static int d3d12va_encode_issue(AVCodecContext
> *avctx,
> FFHWBaseEncodeContext *base_ctx = avctx->priv_data;
> D3D12VAEncodeContext *ctx = avctx->priv_data;
> D3D12VAEncodePicture *pic = base_pic->priv;
> - AVD3D12VAFramesContext *frames_hwctx = base_ctx->input_frames-
> >hwctx;
> + AVD3D12VAFramesContext *frames_hwctx_input = base_ctx-
> >input_frames->hwctx;
> + AVD3D12VAFramesContext *frames_hwctx_recon = base_ctx-
> >recon_frames->hwctx;
> int err, i, j;
> HRESULT hr;
> char data[MAX_PARAM_BUFFER_SIZE];
> @@ -221,7 +222,7 @@ static int d3d12va_encode_issue(AVCodecContext
> *avctx,
> D3D12_VIDEO_ENCODER_RESOLVE_METADATA_INPUT_ARGUMENTS
> input_metadata = {
> .EncoderCodec = ctx->codec->d3d12_codec,
> .EncoderProfile = ctx->profile->d3d12_profile,
> - .EncoderInputFormat = frames_hwctx->format,
> + .EncoderInputFormat = frames_hwctx_input->format,
> .EncodedPictureEffectiveResolution = ctx->resolution,
> };
>
> @@ -268,6 +269,8 @@ static int d3d12va_encode_issue(AVCodecContext
> *avctx,
> av_log(avctx, AV_LOG_DEBUG, "Recon surface is %p.\n",
> pic->recon_surface->texture);
>
> + pic->subresource_index = ctx->is_texture_array ?
> + pic->recon_surface->subresource_index : 0;
> +
> pic->output_buffer_ref = av_buffer_pool_get(ctx->output_buffer_pool);
> if (!pic->output_buffer_ref) {
> err = AVERROR(ENOMEM);
> @@ -325,11 +328,26 @@ static int d3d12va_encode_issue(AVCodecContext
> *avctx,
> goto fail;
> }
>
> + if (ctx->is_texture_array) {
> + d3d12_refs.pSubresources = av_calloc(d3d12_refs.NumTexture2Ds,
> +
> sizeof(*d3d12_refs.pSubresources));
> + if (!d3d12_refs.pSubresources) {
> + err = AVERROR(ENOMEM);
> + goto fail;
> + }
> + }
> +
> i = 0;
> - for (j = 0; j < base_pic->nb_refs[0]; j++)
> - d3d12_refs.ppTexture2Ds[i++] = ((D3D12VAEncodePicture *)base_pic-
> >refs[0][j]->priv)->recon_surface->texture;
> - for (j = 0; j < base_pic->nb_refs[1]; j++)
> - d3d12_refs.ppTexture2Ds[i++] = ((D3D12VAEncodePicture *)base_pic-
> >refs[1][j]->priv)->recon_surface->texture;
> + for (j = 0; j < base_pic->nb_refs[0]; j++) {
> + d3d12_refs.ppTexture2Ds[i] = ((D3D12VAEncodePicture *)base_pic-
> >refs[0][j]->priv)->recon_surface->texture;
> + d3d12_refs.pSubresources[i] = ctx->is_texture_array ?
> ((D3D12VAEncodePicture *)base_pic->refs[0][j]->priv)->subresource_index : 0;
> + i++;
> + }
> + for (j = 0; j < base_pic->nb_refs[1]; j++) {
> + d3d12_refs.ppTexture2Ds[i] = ((D3D12VAEncodePicture *)base_pic-
> >refs[1][j]->priv)->recon_surface->texture;
> + d3d12_refs.pSubresources[i] = ctx->is_texture_array ?
> ((D3D12VAEncodePicture *)base_pic->refs[1][j]->priv)->subresource_index : 0;
> + i++;
> + }
> }
>
> input_args.PictureControlDesc.IntraRefreshFrameIndex = 0; @@ -343,7
> +361,7 @@ static int d3d12va_encode_issue(AVCodecContext *avctx,
> output_args.Bitstream.pBuffer =
> pic->output_buffer;
> output_args.Bitstream.FrameStartOffset = pic-
> >aligned_header_size;
> output_args.ReconstructedPicture.pReconstructedPicture = pic-
> >recon_surface->texture;
> - output_args.ReconstructedPicture.ReconstructedPictureSubresource = 0;
> + output_args.ReconstructedPicture.ReconstructedPictureSubresource =
> + ctx->is_texture_array ? pic->subresource_index : 0;
> output_args.EncoderOutputMetadata.pBuffer = pic-
> >encoded_metadata;
> output_args.EncoderOutputMetadata.Offset = 0;
>
> @@ -369,52 +387,99 @@ static int d3d12va_encode_issue(AVCodecContext
> *avctx,
> goto fail;
> }
>
> -#define TRANSITION_BARRIER(res, before, after) \
> +#define TRANSITION_BARRIER(res, subres, before, after) \
> (D3D12_RESOURCE_BARRIER) { \
> .Type = D3D12_RESOURCE_BARRIER_TYPE_TRANSITION, \
> .Flags = D3D12_RESOURCE_BARRIER_FLAG_NONE, \
> .Transition = { \
> .pResource = res, \
> - .Subresource = D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES, \
> + .Subresource = subres, \
> .StateBefore = before, \
> .StateAfter = after, \
> }, \
> }
>
> barriers[0] = TRANSITION_BARRIER(pic->input_surface->texture,
> +
> + D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> D3D12_RESOURCE_STATE_COMMON,
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_READ);
> barriers[1] = TRANSITION_BARRIER(pic->output_buffer,
> +
> + D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> D3D12_RESOURCE_STATE_COMMON,
>
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE);
> - barriers[2] = TRANSITION_BARRIER(pic->recon_surface->texture,
> - D3D12_RESOURCE_STATE_COMMON,
> -
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE);
> - barriers[3] = TRANSITION_BARRIER(pic->encoded_metadata,
> + barriers[2] = TRANSITION_BARRIER(pic->encoded_metadata,
> +
> + D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> D3D12_RESOURCE_STATE_COMMON,
>
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE);
> - barriers[4] = TRANSITION_BARRIER(pic->resolved_metadata,
> + barriers[3] = TRANSITION_BARRIER(pic->resolved_metadata,
> +
> + D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> D3D12_RESOURCE_STATE_COMMON,
>
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE);
>
> - ID3D12VideoEncodeCommandList2_ResourceBarrier(cmd_list, 5, barriers);
> + ID3D12VideoEncodeCommandList2_ResourceBarrier(cmd_list, 4,
> + barriers);
>
> - if (d3d12_refs.NumTexture2Ds) {
> - D3D12_RESOURCE_BARRIER refs_barriers[3];
> -
> - for (i = 0; i < d3d12_refs.NumTexture2Ds; i++)
> - refs_barriers[i] = TRANSITION_BARRIER(d3d12_refs.ppTexture2Ds[i],
> -
> D3D12_RESOURCE_STATE_COMMON,
> -
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_READ);
> -
> - ID3D12VideoEncodeCommandList2_ResourceBarrier(cmd_list,
> d3d12_refs.NumTexture2Ds,
> - refs_barriers);
> + //set transit barriers for reference pic and recon pic
> + int barriers_ref_index = 0;
> + D3D12_RESOURCE_BARRIER *barriers_ref = NULL;
> + if (ctx->is_texture_array) {
> + barriers_ref = av_calloc(frames_hwctx_recon->texture_array_size *
> ctx-
> >plane_count,
> + sizeof(D3D12_RESOURCE_BARRIER));
> + } else {
> + barriers_ref =
> av_calloc(MAX_DPB_SIZE,sizeof(D3D12_RESOURCE_BARRIER));
> + }
> +
> + if (ctx->is_texture_array) {
> + // In Texture array mode, the D3D12 uses the same texture array
> (resource)for all
> + // the reference pics in ppTexture2Ds and also for the
> pReconstructedPicture,
> + // just different subresources.
> + D3D12_RESOURCE_DESC references_tex_array_desc = { 0 };
> +
> + pic->recon_surface->texture->lpVtbl->GetDesc(pic->recon_surface->textu
> + re, &references_tex_array_desc);
> +
> + for (uint32_t reference_subresource = 0; reference_subresource <
> references_tex_array_desc.DepthOrArraySize;
> + reference_subresource++) {
> +
> + //D3D12 DecomposeSubresource
> + uint32_t mip_slice, plane_slice, array_slice, array_size;
> + array_size = references_tex_array_desc.DepthOrArraySize;
> + mip_slice = reference_subresource %
> references_tex_array_desc.MipLevels;
> + array_slice = (reference_subresource /
> + references_tex_array_desc.MipLevels) % array_size;
> +
> + for (plane_slice = 0; plane_slice < ctx->plane_count;
> plane_slice++) {
> + //Calculate the subresource index
> + uint32_t planeOutputSubresource = mip_slice + array_slice *
> references_tex_array_desc.MipLevels +
> + plane_slice *
> references_tex_array_desc.MipLevels *
> array_size;
> + if (reference_subresource == pic->subresource_index) {
> + barriers_ref[barriers_ref_index++] =
> TRANSITION_BARRIER(pic-
> >recon_surface->texture, planeOutputSubresource,
> + D3D12_RESOURCE_STATE_COMMON,
> +
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE);
> + } else {
> + barriers_ref[barriers_ref_index++] =
> TRANSITION_BARRIER(pic-
> >recon_surface->texture, planeOutputSubresource,
> + D3D12_RESOURCE_STATE_COMMON,
> +
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_READ);
> + }
> + }
> + }
> + } else {
> + barriers_ref[barriers_ref_index++] = TRANSITION_BARRIER(pic-
> >recon_surface->texture,
> +
> D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> + D3D12_RESOURCE_STATE_COMMON,
> +
> + D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE);
> +
> + if (d3d12_refs.NumTexture2Ds) {
> + for (i = 0; i < d3d12_refs.NumTexture2Ds; i++)
> + barriers_ref[barriers_ref_index++] =
> TRANSITION_BARRIER(d3d12_refs.ppTexture2Ds[i],
> +
> D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> +
> D3D12_RESOURCE_STATE_COMMON,
> +
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_READ);
> + }
> }
> + ID3D12VideoEncodeCommandList2_ResourceBarrier(cmd_list,
> + barriers_ref_index, barriers_ref);
>
> ID3D12VideoEncodeCommandList2_EncodeFrame(cmd_list, ctx->encoder, ctx-
> >encoder_heap,
> &input_args, &output_args);
>
> barriers[3] = TRANSITION_BARRIER(pic->encoded_metadata,
> +
> + D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE,
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_READ);
>
> @@ -422,35 +487,35 @@ static int d3d12va_encode_issue(AVCodecContext
> *avctx,
>
>
> ID3D12VideoEncodeCommandList2_ResolveEncoderOutputMetadata(cmd_list,
> &input_metadata, &output_metadata);
>
> - if (d3d12_refs.NumTexture2Ds) {
> - D3D12_RESOURCE_BARRIER refs_barriers[3];
> -
> - for (i = 0; i < d3d12_refs.NumTexture2Ds; i++)
> - refs_barriers[i] = TRANSITION_BARRIER(d3d12_refs.ppTexture2Ds[i],
> -
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_READ,
> -
> D3D12_RESOURCE_STATE_COMMON);
> -
> - ID3D12VideoEncodeCommandList2_ResourceBarrier(cmd_list,
> d3d12_refs.NumTexture2Ds,
> - refs_barriers);
> + //swap the barriers_ref transition state
> + if (barriers_ref_index > 0) {
> + for (i = 0; i < barriers_ref_index; i++) {
> + D3D12_RESOURCE_STATES temp_statue =
> barriers_ref[i].Transition.StateBefore;
> + barriers_ref[i].Transition.StateBefore =
> barriers_ref[i].Transition.StateAfter;
> + barriers_ref[i].Transition.StateAfter = temp_statue;
> + }
> + ID3D12VideoEncodeCommandList2_ResourceBarrier(cmd_list,
> barriers_ref_index,
> + barriers_ref);
> }
>
> barriers[0] = TRANSITION_BARRIER(pic->input_surface->texture,
> +
> + D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_READ,
> D3D12_RESOURCE_STATE_COMMON);
> barriers[1] = TRANSITION_BARRIER(pic->output_buffer,
> +
> + D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE,
> D3D12_RESOURCE_STATE_COMMON);
> - barriers[2] = TRANSITION_BARRIER(pic->recon_surface->texture,
> - D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE,
> - D3D12_RESOURCE_STATE_COMMON);
> - barriers[3] = TRANSITION_BARRIER(pic->encoded_metadata,
> + barriers[2] = TRANSITION_BARRIER(pic->encoded_metadata,
> +
> + D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_READ,
> D3D12_RESOURCE_STATE_COMMON);
> - barriers[4] = TRANSITION_BARRIER(pic->resolved_metadata,
> + barriers[3] = TRANSITION_BARRIER(pic->resolved_metadata,
> +
> + D3D12_RESOURCE_BARRIER_ALL_SUBRESOURCES,
> D3D12_RESOURCE_STATE_VIDEO_ENCODE_WRITE,
> D3D12_RESOURCE_STATE_COMMON);
>
> - ID3D12VideoEncodeCommandList2_ResourceBarrier(cmd_list, 5, barriers);
> + ID3D12VideoEncodeCommandList2_ResourceBarrier(cmd_list, 4,
> + barriers);
>
> hr = ID3D12VideoEncodeCommandList2_Close(cmd_list);
> if (FAILED(hr)) {
> @@ -489,6 +554,14 @@ static int d3d12va_encode_issue(AVCodecContext
> *avctx,
> if (d3d12_refs.ppTexture2Ds)
> av_freep(&d3d12_refs.ppTexture2Ds);
>
> + if (ctx->is_texture_array) {
> + if (d3d12_refs.pSubresources)
> + av_freep(&d3d12_refs.pSubresources);
> + }
> +
> + if (barriers_ref)
> + av_freep(&barriers_ref);
> +
> return 0;
>
> fail:
> @@ -498,6 +571,14 @@ fail:
> if (d3d12_refs.ppTexture2Ds)
> av_freep(&d3d12_refs.ppTexture2Ds);
>
> + if (ctx->is_texture_array) {
> + if (d3d12_refs.pSubresources)
> + av_freep(&d3d12_refs.pSubresources);
> + }
> +
> + if (barriers_ref)
> + av_freep(&barriers_ref);
> +
> if (ctx->codec->free_picture_params)
> ctx->codec->free_picture_params(pic);
>
> @@ -1341,6 +1422,7 @@ fail:
> static int d3d12va_encode_create_recon_frames(AVCodecContext *avctx) {
> FFHWBaseEncodeContext *base_ctx = avctx->priv_data;
> + D3D12VAEncodeContext *ctx = avctx->priv_data;
> AVD3D12VAFramesContext *hwctx;
> enum AVPixelFormat recon_format;
> int err;
> @@ -1364,6 +1446,8 @@ static int
> d3d12va_encode_create_recon_frames(AVCodecContext *avctx)
> hwctx->flags = D3D12_RESOURCE_FLAG_VIDEO_ENCODE_REFERENCE_ONLY
> |
> D3D12_RESOURCE_FLAG_DENY_SHADER_RESOURCE;
>
> + hwctx->texture_array_size = ctx->is_texture_array ? MAX_DPB_SIZE +
> + 1 : 0;
> +
> err = av_hwframe_ctx_init(base_ctx->recon_frames_ref);
> if (err < 0) {
> av_log(avctx, AV_LOG_ERROR, "Failed to initialise reconstructed "
> @@ -1396,6 +1480,7 @@ int ff_d3d12va_encode_init(AVCodecContext *avctx)
> FFHWBaseEncodeContext *base_ctx = avctx->priv_data;
> D3D12VAEncodeContext *ctx = avctx->priv_data;
> D3D12_FEATURE_DATA_VIDEO_FEATURE_AREA_SUPPORT support = { 0 };
> + D3D12_FEATURE_DATA_FORMAT_INFO format_info = {0};
> int err;
> HRESULT hr;
>
> @@ -1431,6 +1516,15 @@ int ff_d3d12va_encode_init(AVCodecContext *avctx)
> goto fail;
> }
>
> + format_info.Format = ((AVD3D12VAFramesContext*)base_ctx->input_frames-
> >hwctx)->format;
> + if (FAILED(ID3D12VideoDevice_CheckFeatureSupport(ctx->hwctx->device,
> D3D12_FEATURE_FORMAT_INFO,
> + &format_info, sizeof(format_info)))) {
> + av_log(avctx, AV_LOG_ERROR, "Failed to query format plane count:
> 0x%x\n", hr);
> + err = AVERROR_EXTERNAL;
> + goto fail;
> + }
> + ctx->plane_count = format_info.PlaneCount;
> +
> err = d3d12va_encode_set_profile(avctx);
> if (err < 0)
> goto fail;
> @@ -1458,10 +1552,6 @@ int ff_d3d12va_encode_init(AVCodecContext *avctx)
> if (err < 0)
> goto fail;
>
> - err = d3d12va_encode_create_recon_frames(avctx);
> - if (err < 0)
> - goto fail;
> -
> err = d3d12va_encode_prepare_output_buffers(avctx);
> if (err < 0)
> goto fail;
> @@ -1487,6 +1577,10 @@ int ff_d3d12va_encode_init(AVCodecContext *avctx)
> goto fail;
> }
>
> + err = d3d12va_encode_create_recon_frames(avctx);
> + if (err < 0)
> + goto fail;
> +
> base_ctx->output_delay = base_ctx->b_per_p;
> base_ctx->decode_delay = base_ctx->max_b_depth;
>
> diff --git a/libavcodec/d3d12va_encode.h b/libavcodec/d3d12va_encode.h index
> 3b0b8153d5..c8e64ddffd 100644
> --- a/libavcodec/d3d12va_encode.h
> +++ b/libavcodec/d3d12va_encode.h
> @@ -52,6 +52,8 @@ typedef struct D3D12VAEncodePicture {
> ID3D12Resource *encoded_metadata;
> ID3D12Resource *resolved_metadata;
>
> + int subresource_index;
> +
> D3D12_VIDEO_ENCODER_PICTURE_CONTROL_CODEC_DATA pic_ctl;
>
> int fence_value;
> @@ -189,6 +191,16 @@ typedef struct D3D12VAEncodeContext {
> */
> AVBufferPool *output_buffer_pool;
>
> + /**
> + * Flag indicates if the HW is texture array mode.
> + */
> + int is_texture_array;
> +
> + /**
> + * The number of planes in the input DXGI FORMAT .
> + */
> + int plane_count;
> +
> /**
> * D3D12 video encoder.
> */
> diff --git a/libavcodec/d3d12va_encode_hevc.c
> b/libavcodec/d3d12va_encode_hevc.c
> index 938ba01f54..7e1d973f7e 100644
> --- a/libavcodec/d3d12va_encode_hevc.c
> +++ b/libavcodec/d3d12va_encode_hevc.c
> @@ -280,9 +280,8 @@ static int
> d3d12va_encode_hevc_init_sequence_params(AVCodecContext *avctx)
> }
>
> if (support.SupportFlags &
> D3D12_VIDEO_ENCODER_SUPPORT_FLAG_RECONSTRUCTED_FRAMES_REQUIR
> E_TEXTURE_ARRAYS) {
> - av_log(avctx, AV_LOG_ERROR, "D3D12 video encode on this device
> requires
> texture array support, "
> - "but it's not implemented.\n");
> - return AVERROR_PATCHWELCOME;
> + ctx->is_texture_array = 1;
> + av_log(avctx, AV_LOG_DEBUG, "D3D12 video encode on this device
> + uses texture array mode.\n");
> }
>
> desc = av_pix_fmt_desc_get(base_ctx->input_frames->sw_format);
> diff --git a/libavutil/hwcontext_d3d12va.c b/libavutil/hwcontext_d3d12va.c
> index
> 6507cf69c1..05418c9d94 100644
> --- a/libavutil/hwcontext_d3d12va.c
> +++ b/libavutil/hwcontext_d3d12va.c
> @@ -49,6 +49,7 @@ typedef struct D3D12VAFramesContext {
> ID3D12GraphicsCommandList *command_list;
> AVD3D12VASyncContext sync_ctx;
> UINT luma_component_size;
> + int nb_surfaces_used;
> } D3D12VAFramesContext;
>
> typedef struct D3D12VADevicePriv {
> @@ -174,7 +175,8 @@ fail:
>
> static void d3d12va_frames_uninit(AVHWFramesContext *ctx) {
> - D3D12VAFramesContext *s = ctx->hwctx;
> + D3D12VAFramesContext *s = ctx->hwctx;
> + AVD3D12VAFramesContext *hwctx = ctx->hwctx;
>
> D3D12_OBJECT_RELEASE(s->sync_ctx.fence);
> if (s->sync_ctx.event)
> @@ -185,6 +187,11 @@ static void
> d3d12va_frames_uninit(AVHWFramesContext *ctx)
> D3D12_OBJECT_RELEASE(s->command_allocator);
> D3D12_OBJECT_RELEASE(s->command_list);
> D3D12_OBJECT_RELEASE(s->command_queue);
> +
> + if (hwctx->texture_array) {
> + D3D12_OBJECT_RELEASE(hwctx->texture_array);
> + hwctx->texture_array = NULL;
> + }
> }
>
> static int d3d12va_frames_get_constraints(AVHWDeviceContext *ctx, const void
> *hwconfig, AVHWFramesConstraints *constraints) @@ -228,6 +235,28 @@
> static void free_texture(void *opaque, uint8_t *data)
> av_freep(&data);
> }
>
> +static AVBufferRef *d3d12va_pool_alloc_texture_array(AVHWFramesContext
> +*ctx) {
> + AVD3D12VAFrame *desc = av_mallocz(sizeof(*desc));
> + D3D12VAFramesContext *s = ctx->hwctx;
> + AVD3D12VAFramesContext *hwctx = ctx->hwctx;
> + AVBufferRef *buf;
> +
> + // In Texture array mode, the D3D12 uses the same texture address for
> all the
> pictures,
> + //just different subresources.
> + desc->subresource_index = s->nb_surfaces_used;
> + desc->texture = hwctx->texture_array;
> +
> + buf = av_buffer_create((uint8_t *)desc, sizeof(*desc), NULL, NULL,
> + 0);
> +
> + if (!buf) {
> + av_free(desc);
> + return NULL;
> + }
> + s->nb_surfaces_used++;
> + return buf;
> +}
> +
> static AVBufferRef *d3d12va_pool_alloc(void *opaque, size_t size) {
> AVHWFramesContext *ctx = (AVHWFramesContext *)opaque;
> @@ -236,6 +265,11 @@ static AVBufferRef *d3d12va_pool_alloc(void *opaque,
> size_t size)
>
> AVBufferRef *buf;
> AVD3D12VAFrame *frame;
> +
> + //For texture array mode, no need to create texture.
> + if (hwctx->texture_array_size > 0)
> + return d3d12va_pool_alloc_texture_array(ctx);
> +
> D3D12_HEAP_PROPERTIES props = { .Type = D3D12_HEAP_TYPE_DEFAULT };
> D3D12_RESOURCE_DESC desc = {
> .Dimension = D3D12_RESOURCE_DIMENSION_TEXTURE2D,
> @@ -280,7 +314,9 @@ fail:
>
> static int d3d12va_frames_init(AVHWFramesContext *ctx) {
> - AVD3D12VAFramesContext *hwctx = ctx->hwctx;
> + AVD3D12VAFramesContext *hwctx = ctx->hwctx;
> + AVD3D12VADeviceContext *device_hwctx = ctx->device_ctx->hwctx;
> +
> int i;
>
> for (i = 0; i < FF_ARRAY_ELEMS(supported_formats); i++) { @@ -298,6
> +334,31
> @@ static int d3d12va_frames_init(AVHWFramesContext *ctx)
> return AVERROR(EINVAL);
> }
>
> + //For texture array mode, create texture array resource in the init
> stage.
> + //This texture array will be used for all the pictures,but with different
> subresources.
> + if (hwctx->texture_array_size > 0) {
> + D3D12_HEAP_PROPERTIES props = { .Type = D3D12_HEAP_TYPE_DEFAULT
> + };
> +
> + D3D12_RESOURCE_DESC desc = {
> + .Dimension = D3D12_RESOURCE_DIMENSION_TEXTURE2D,
> + .Alignment = 0,
> + .Width = ctx->width,
> + .Height = ctx->height,
> + .DepthOrArraySize = hwctx->texture_array_size,
> + .MipLevels = 1,
> + .Format = hwctx->format,
> + .SampleDesc = {.Count = 1, .Quality = 0 },
> + .Layout = D3D12_TEXTURE_LAYOUT_UNKNOWN,
> + .Flags = hwctx->flags,
> + };
> +
> + if (FAILED(ID3D12Device_CreateCommittedResource(device_hwctx-
> >device, &props, D3D12_HEAP_FLAG_NONE, &desc,
> + D3D12_RESOURCE_STATE_COMMON, NULL, &IID_ID3D12Resource,
> (void **)&hwctx->texture_array))) {
> + av_log(ctx, AV_LOG_ERROR, "Could not create the texture\n");
> + return AVERROR(EINVAL);
> + }
> + }
> +
> ffhwframesctx(ctx)->pool_internal =
> av_buffer_pool_init2(sizeof(AVD3D12VAFrame),
> ctx, d3d12va_pool_alloc, NULL);
>
> diff --git a/libavutil/hwcontext_d3d12va.h b/libavutil/hwcontext_d3d12va.h
> index 212a6a6146..d48d847d11 100644
> --- a/libavutil/hwcontext_d3d12va.h
> +++ b/libavutil/hwcontext_d3d12va.h
> @@ -111,6 +111,11 @@ typedef struct AVD3D12VAFrame {
> */
> ID3D12Resource *texture;
>
> + /**
> + * In texture array mode, the index of subresource
> + */
> + int subresource_index;
> +
> /**
> * The sync context for the texture
> *
> @@ -137,6 +142,19 @@ typedef struct AVD3D12VAFramesContext {
> * @see https://learn.microsoft.com/en-us/windows/win32/api/d3d12/ne-
> d3d12-d3d12_resource_flags
> */
> D3D12_RESOURCE_FLAGS flags;
> +
> + /**
> + * In texture array mode, the D3D12 uses the same the same texture array
> (resource)for all
> + * pictures.
> + */
> + ID3D12Resource *texture_array;
> +
> + /**
> + * In texture array mode, the D3D12 uses the same texture array
> (resource)for
> all
> + * pictures, but different subresources to represent each picture.
> + * This is the size of the texture array (in number of subresources).
> + */
> + int texture_array_size;
> } AVD3D12VAFramesContext;
>
> #endif /* AVUTIL_HWCONTEXT_D3D12VA_H */ diff --git a/libavutil/version.h
> b/libavutil/version.h index 2c0aa3e35e..29cd31e229 100644
> --- a/libavutil/version.h
> +++ b/libavutil/version.h
> @@ -79,8 +79,8 @@
> */
>
> #define LIBAVUTIL_VERSION_MAJOR 60
> -#define LIBAVUTIL_VERSION_MINOR 4
> -#define LIBAVUTIL_VERSION_MICRO 101
> +#define LIBAVUTIL_VERSION_MINOR 5
> +#define LIBAVUTIL_VERSION_MICRO 100
>
> #define LIBAVUTIL_VERSION_INT
> AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \
> LIBAVUTIL_VERSION_MINOR, \
> --
> 2.45.2.windows.1
>
LGTM, will apply
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
