search for: predecod

How would one implement the following scheme with minimal use of resources: Every Vorbis packet should be preprocessed to a certain extent, that is, the beginning of every audio packet should be parsed and some decoding steps executed. The result of this predecode as well as the rest of the packet should then be sent as output for final processing. I have skimmed through the standard, and as far as i can tell there is no field containing the packet length, however the 'end-of-packet'-condition is mentioned at severeal places, and it is also checked...

...s > is a difficult thing to get right in a general sort of way. Perhaps the > CostPerUse (or whatwever heuristics use it) can factor in the loop body > size so that tight loops are favored for smaller encodings. It is almost certainly that the inner loop doesn't fit in the processors predecode loop buffer. Modern intel X86 chips have a buffer that can hold a very small number of instructions and is bound by instruction count, code size, and sometimes # cache lines. If a loop fits in this it allows the processor to turn off the decoder completely for the loop, a significant power and p...

Jakob Stoklund Olesen <stoklund at 2pi.dk> writes: >> That was my initial reaction. Splitting should have at least >> rematerialized the value just before header2. That should significantly >> improve things. This is a classic motivational case for live range >> splitting. > > Well, not really. Note there there are plenty of registers available > and no

On May 3, 2011, at 3:23 PM, David A. Greene wrote: > Jakob Stoklund Olesen <stoklund at 2pi.dk> writes: > >>>> The greedy allocator is trying to pick registers so inner loops are as >>>> small as possible, but that is not always the right thing to do. >>> >>> How does it balance that against spill cost? >> >> I added the

...ult thing to get right in a general sort of way. Perhaps the >> CostPerUse (or whatwever heuristics use it) can factor in the loop body >> size so that tight loops are favored for smaller encodings. > > It is almost certainly that the inner loop doesn't fit in the processors predecode loop buffer. Modern intel X86 chips have a buffer that can hold a very small number of instructions and is bound by instruction count, code size, and sometimes # cache lines. If a loop fits in this it allows the processor to turn off the decoder completely for the loop, a significant power and p...