If this is your first visit, be sure to
check out the FAQ by clicking the
link above. You may have to register
before you can post: click the register link above to proceed. To start viewing messages,
select the forum that you want to visit from the selection below.
It appears that most of the time is spent inside the LLVM backend, but it's not trivial to speed that up so it doesn't sound like it will happen anytime soon.
Are changes needed on your side or mesa to make it worth it?
It appears that most of the time is spent inside the LLVM backend, but it's not trivial to speed that up so it doesn't sound like it will happen anytime soon.
Right now the effects on both pipeline compile times and runtime performance are negligible, and while i'm working on merging my code into the main branch, it'll be disabled by default. As of right now, it's just not worth using.
Are changes needed on your side or mesa to make it worth it?
How much does performance decrease when optimizations are off though?
Right now the effects on both pipeline compile times and runtime performance are negligible, and while i'm working on merging my code into the main branch, it'll be disabled by default. As of right now, it's just not worth using.
That said, Nvidia might eventually implement support for this flag as well.
The RADV Vulkan driver within Mesa has landed its VK_PIPELINE_CREATE_DISABLE_OPTIMIZATION_BIT support so applications/games can opt to disable optimizations when compiling a Vulkan pipeline. This is notably what was just covered the other day for helping to reduce stuttering with DXVK...
Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite
Leave a comment: