[QST] Which algorithms have CPU compression?
iomartin opened this issue · 5 comments
I want to provide a SW fallback option to my nvcomp-based application and I was wondering which algorithms have a CPU implementation.
The examples show Gdeflate and LZ4 only and I couldn't find code for the others, but I wanted to check first.
And if I compress something with the high level interface, will I be able to decompress with the CPU implementations and vice-versa?
nvCOMP doesn't offer, or officially support, any CPU implementation. You will need to use some other form, whether OSS or commercial for a solution.
GDeflate does have a CPU implementation via libnvcomp_gdeflate_cpu.so, but I suppose it's the only one then.
This issue has been labeled inactive-30d due to no recent activity in the past 30 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed. This issue will be labeled inactive-90d if there is no activity in the next 60 days.
This issue has been labeled inactive-90d due to no recent activity in the past 90 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed.
Deflate, Gdeflate, and LZ4 have CPU compression provided in the binaries on Linux, and can be used as shown in the examples, as you mentioned. You can check the examples/CMakeLists.txt to work out the dependencies. They aren't provided in the Windows binaries at the moment.