This commit implements a standard, compliant, version 3 and version 4 FFv1 encoder, entirely in Vulkan. The encoder is written in standard GLSL and requires a Vulkan 1.3 supporting GPU with the BDA extension. The encoder can use any amount of slices, but nominally, should use 32x32 slices (1024 in total) to maximize parallelism. All features are supported, as well as all pixel formats. This includes: - Rice - Range coding with a custom quantization table - PCM encoding CRC calculation is also massively parallelized on the GPU. Encoding of unaligned dimensions on subsampled data requires version 4, or requires oversizing the image to 64-pixel alignment and cropping out the padding via container flags. Performance-wise, this makes 1080p real-time screen capture possible at 60fps on even modest GPUs.
Showing the changes to libavcodec/allcodecs.c (1 of 17 files). Show all
Unified · Split
| @@ -116,6 +116,7 @@ extern const FFCodec ff_escape130_decoder; · 115 unmodified lines | |||
| 116 | extern const FFCodec ff_exr_encoder; | 116 | extern const FFCodec ff_exr_encoder; |
| 117 | extern const FFCodec ff_exr_decoder; | 117 | extern const FFCodec ff_exr_decoder; |
| 118 | extern const FFCodec ff_ffv1_encoder; | 118 | extern const FFCodec ff_ffv1_encoder; |
| 119 | extern const FFCodec ff_ffv1_vulkan_encoder; | ||
| 119 | extern const FFCodec ff_ffv1_decoder; | 120 | extern const FFCodec ff_ffv1_decoder; |
| 120 | extern const FFCodec ff_ffvhuff_encoder; | 121 | extern const FFCodec ff_ffvhuff_encoder; |
| 121 | extern const FFCodec ff_ffvhuff_decoder; | 122 | extern const FFCodec ff_ffvhuff_decoder; |