NVDEC/deko3d interop

nvdec_deko3d.c

// Sample code (untested) for interop between NVDEC and deko3d
//   * This only maps the luma plane, as an R8 texture (thus assuming 8-bit data),
//     for 10+ bit you would need R16
//   * For the chroma plane, the memblock can be shared with the luma plane, 
//     but you would need a new layout using R8G8 (R16G16 for 10+ bit),
//     to adjust the width and height for subsampling,
//     and to use (frame->data[1] - frame->data[0]) as offset into the memblock
//   * Note that hardware decoding backbuffers are issued (and reused) from a pool,
//     thus for efficient use you can cache images/buffer mappings. 
//     The map handle (ff_tx1_map_get_handle(map)) can be used a key for this.
//     Empirically around 5 maps are observed to be concurrently in use, with mpv as client.

// Create layout for the texture
// The important part is to use DkImageFlags_UsageVideo, 
// which ensures a consistent texture layout between NVDEC and the GPU
DkImageLayoutMaker layout_maker;
dkImageLayoutMakerDefaults(&layout_maker, dk_device);
layout_maker.type          = DkImageType_2D;
layout_maker.format        = DkImageFormat_R8_Unorm;
layout_maker.dimensions[0] = luma_width;
layout_maker.dimensions[1] = luma_height;
layout_maker.dimensions[2] = 1;
layout_maker.flags = DkImageFlags_UsageLoadStore | 
    DkImageFlags_Usage2DEngine | DkImageFlags_UsageVideo;

DkImageLayout layout;
dkImageLayoutInitialize(&layout, &layout_maker);

// Retrieve the CPU address of the decoded data,
// and create a GPU mapping (memblock) over it
AVFrame *frame; // The frame returned by the hardware decoder
AVTX1Map *map = ff_tx1_frame_get_fbuf_map(frame); 

DkMemBlockMaker memblock_maker;
dkMemBlockMakerDefaults(&memblock_maker, dk_device, ff_tx1_map_get_size(map));
memblock_maker.flags   = DkMemBlockFlags_CpuUncached |
    DkMemBlockFlags_GpuCached | DkMemBlockFlags_Image;
memblock_maker.storage = ff_tx1_map_get_addr(map);
DkMemBlock memblock = dkMemBlockCreate(&memblock_maker);

// Finally, create a texture over that memblock using the layout we calculated
DkImage image;
dkImageInitialize(&image, &layout, memblock, 0);


// Initialize image/sample descriptors as usual,
// and invalidate the texture cache before use


// Deinitialization
dkMemBlockDestroy(memblock)