summaryrefslogtreecommitdiff
path: root/lib/gras_impl
AgeCommit message (Collapse)Author
2012-12-15misc fixes to buffer reworkJosh Blum
2012-12-15created input and output update per indexJosh Blum
2012-12-15work on the buffer queue apiJosh Blum
2012-12-13endless buffer acking implementationJosh Blum
2012-12-13some work on the circular buffer allocJosh Blum
2012-12-06guess at heuristic improvement - somewhat profilesJosh Blum
2012-12-05tag is just an offset and object, created stream tag and pkt messageJosh Blum
2012-12-01changed lookahead to preload, thats all it isJosh Blum
2012-12-01mark fail: not ready until a new buffer appearsJosh Blum
2012-11-29added some more misc debug macrosJosh Blum
2012-11-28should we accumulate? a guess at heuristic improvementJosh Blum
2012-11-26reset queue ref before popJosh Blum
2012-11-25front buffer accumulate on reserve failJosh Blum
2012-11-24created common function is_work_allowed and input checkJosh Blum
at least one port needs a tag or an item, this helps the reserve items == 0 case
2012-11-23async atomic notification of stop conditionJosh Blum
2012-11-22extra asserts for sign on consume/produceJosh Blum
2012-11-22buffer_queue use custom method, since inherited push is not consistentJosh Blum
2012-11-21addressed some bugs from the stitching commitJosh Blum
2012-11-21implement buffer stitching on input, output always flushesJosh Blum
2012-11-21guard against empty consumesJosh Blum
2012-11-19const correctness for sbuffer get()Josh Blum
2012-11-18improvements to done logic (helps reserve 0 case)Josh Blum
2012-11-18support for null buffers when reserve == 0Josh Blum
2012-11-17added common flush code, flush before produce_bufferJosh Blum
2012-11-13created API for passive work-flowJosh Blum
2012-11-11fixed input fail logic w/ input_queues.is_front_maximalJosh Blum
2012-11-09input buffers deal with empty buffersJosh Blum
2012-11-09switch to boost software licenseJosh Blum
2012-11-09common typedef for item countJosh Blum
2012-11-07some fixes from the last commitJosh Blum
2012-11-07io fails and io config workJosh Blum
2012-11-06consume and produce calls do it in-placeJosh Blum
2012-11-06work on python blocks and unit testJosh Blum
2012-11-05polish up work and notify apiJosh Blum
There is a formal api to mark done, and IO failures. Notify topology was created for consistency. So far, there output fail is unimplemented, and input fail requires an additional check.
2012-11-01moved out a bunch of work, rate, fcast logicJosh Blum
2012-10-28work on stand-alone library buildJosh Blum
2012-10-28Merge branch 'rc0_work'Josh Blum
Conflicts: Apology
2012-10-14added input fail logic to conditionally accumulateJosh Blum
2012-10-14input_buffer_queues logic cleanup for accumulate implementationJosh Blum
2012-10-13simplfied input queues, WIP, but workingJosh Blum
2012-10-13lots of mini tweaks for QA passing, WIP...Josh Blum
2012-10-12working on qa passing, temp input accumulation logicJosh Blum
2012-10-11make use of new message registration macrosJosh Blum
2012-10-06reimplement the output multiple items/work output items calculationsJosh Blum
2012-10-05cleanup task conclusion logicJosh Blum
2012-10-05created configurable thread poolJosh Blum
2012-10-04for loop for any_inputs_done is actually lighter-weightJosh Blum
2012-10-04implementation for the top block global configJosh Blum
2012-10-04swig issues worked out, Work can be work againJosh Blum
2012-10-04Merge branch 'master' into port_configJosh Blum
generated by cgit (git 2.34.1) at 2025-03-13 15:53:31 +0000