Lines Matching full:we

5 Panda Runtime should be scalable onto different devices/OSes. So we need some abstraction level for…
6 For now, all targets suppose interaction with the user, so we have some limitations for the STW pau…
7 We have very limited memory resources for IoT target, so we should maximize efforts on reducing mem…
33 Mode are chosen at the startup time (we'll use profile info from cloud for that).
107 However, we can also support such version of the object header(Hash is stored just after the object…
123 This scenario decreases the size of a Monitor instance, and we don't need to save Hash somewhere du…
125 But, this scenario will be useful if we have allocator and GC which decreases such a situation to a…
152 Heavyweight Lock - we have competition for this object(few threads try to lock this object).
172 If we don't use strings compressing, each string has this structure:
184 If we use strings compressing, each string has this structure:
202 …ash state inside Mark Word as a container for string hash value (of course we should save object h…
228 - support for pool extension and reduction(i.e., we can add another memory chunk to the allocator, …
249 So, if we can hold JIT memory usage at some reasonable level - Arena Allocator ideally fits JIT req…
257 For example, if we have some callgraph info, we can use it and allocate code for connected methods …
301 We can use profile information about allocation size for improving main allocator metrics.
302 If we see a very popular allocation size in profile, we can add it as an explicit segregated size a…
309 There is no universal approach in this paper, but we can try to mix approach from this paper 
316 For the cases when we can get memory shortage we should have some preallocated buffer which allow R…
362 So we should have possibility to use optimal GC for each application.
368 …e used only for debug and profiling purposes. I.e., we can disable GC and measure in mode "What if…
389 We need to conduct more performance analysis experiments for choosing optimal scheme, but for now l…
403 If we prioritize energy-efficiency metric and the heap sizes at average not gigantic, it seems that…
404 So we can support it optionally for experiments. As alternative we can introduce some average age m…
411 Note: we'll use adaptive thresholds for triggering Minor GC for minimizing STW pause
412 Note #2: we can tune minor GC by trying make concurrent marking and re-mark, but it will require co…
424 Note: If we don't have Survivor spaces we can implement non-moving generational GC. 
462 Concurrent marking(triggered when we reach some threshold for tenured generation size):
466 1. Cleanup - reclaims empty regions and determines if we need mixed collections to reclaim tenured …
488 Note: compaction is target and mode dependent, so for low-memory devices we can consider [semi-spac…
489 For straight-forward approach we can consider some support from OS to minimize overlapping of semi-…
497 * ExecState structure has field with address of some page used for safepoints and we knew offset of…
516 For each safepoint, we should have a method that can provide GC with information about objects on t…
518 But for JIT/compiler, it looks like we need some generated(by JIT/compiler) method that can get all…
520 We'll jump to its beginning from signal handler, and in the end, we should jump back to the safepoi…
536 * should we generate method for each safepoint, or all safepoints at once?
546 1. We store reference to a white object into a black object
551 …we can solve these issues with GC WRB(write barrier). GC WRB can be _pre_(inserted before the stor…
564 …neration to the young generation(or inter-region references). In this case we always know external…
572 Note: Sometimes we don't check if object and stored reference in different generations. Because we …
577 For example we concurrently moving object from one place(`from-space`) to the another(`to-space`).
578 At some moment we can have two instance of the one object.
579 So we need one of these conditions should stand if we want to keep heap consistent:
591 Note: for performance, we can put into ExecState address of conditional flag for conditional barrie…