DooKey
[H]F Junkie
- Joined
- Apr 25, 2001
- Messages
- 13,560
The latest version of TrueAudio has been posted on Github by the team. This version offers a new speedup option called the "head-tail" partitioned method. Additionally, there are other enhancements that cutdown on memory use, buffer transfer and synchronization overhead. So head over to Github and get this if it's something you are using. Thanks cagey.
The majority of the computation overhead (the “tail”) occurs in the background, in between buffer submissions to TAN, and thus this method is very friendly to parallel processing. At the same time, it provides a significant latency overhead reduction and performance speedup, since the calling audio thread is not blocked waiting for the entire convolution to be calculated–only for a very short “head” portion.
The majority of the computation overhead (the “tail”) occurs in the background, in between buffer submissions to TAN, and thus this method is very friendly to parallel processing. At the same time, it provides a significant latency overhead reduction and performance speedup, since the calling audio thread is not blocked waiting for the entire convolution to be calculated–only for a very short “head” portion.