Memory Chunks Research Articles

Shared heap management for memory-limited java virtual machines

One scarce resource in embedded systems is memory. Multitasking makes the lack of memory problem even worse. Most current embedded systems, which do not provide virtual memory, simply divide physical memory and evenly assign contiguous memory chunks to multiple applications. Such simple memory management can frequently cause the lack of available memory for some applications, while others are not using the full amount of assigned memory. To overcome inefficiency in current memory management, we present an efficient heap management scheme that allows multiple applications to share heap space. To reduce overall heap memory usage, applications adaptively acquire subheaps out of shared pool of memory and release surplus subheaps to shared pool. As a result, applications see noncontiguous multiple subheaps as a heap in their address space. We target Java applications to implement our heap-sharing scheme in the KVM from Sun Microsystems. To protect fragmented heap space with a limited number of regions in memory protection unit (MPU), we maintain only a limited number of subheaps. We experimentally evaluate our heap management scheme with J2ME MIDP applications. Our static and dynamic schemes reduce heap memory usage, on average, by 30 and 27%, respectively. For both schemes, overheads are kept low. The execution times in our schemes are increased only by 0.01% for static scheme and 0.35% for dynamic scheme, on average.

BRAIN LOCALIZATION OF MEMORY CHUNKS IN CHESSPLAYERS

Chess experts store domain-specific representations in their long-term memory; due to the activation of such representations, they perform with high accuracy in tasks that require the maintenance of previously seen information. Chunk-based theories of expertise (chunking theory: ; template theory: ) state that expertise is acquired mainly by the acquisition and storage in long-term memory of familiar chunks that allow quick recognition. This study tested some predictions of these theories by using fMRI while chessplayers performed a recognition memory task. These theories predict that chessplayers access long-term memory chunks of domain-specific information, which are presumably stored in the temporal lobes. It was also predicted that the recognition memory tasks would activate working memory areas in the frontal and parietal lobes. These predictions were supported by the data.

Chunks in expert memory: Evidence for the magical number four … or is it two?

This study aims to test the divergent predictions of the chunking theory (Chase & Simon, 1973) and template theory (Gobet & Simon, 1996a, 2000) with respect to the number of chunks held in visual short-term memory and the size of chunks used by experts. We presented game and random chessboards in both a copy and a recall task. In a within-subject design, the stimuli were displayed using two presentation media: (a) physical board and pieces, as in Chase and Simon's (1973) study; and (b) a computer display, as in Gobet and Simon's (1998) study. Results show that, in most cases, no more than three chunks were replaced in the recall task, as predicted by template theory. In addition, with game positions in the computer condition, chess Masters replaced very large chunks (up to 15 pieces), again in line with template theory. Overall, the results suggest that the original chunking theory overestimated short-term memory capacity and underestimated the size of chunks used, in particular with Masters. They also suggest that Cowan's (2001) proposal that STM holds four chunks may be an overestimate.

Adaptive application caching

This paper addresses the problem of optimum memory allocation for applications that cannot tolerate high access latency and cannot afford a huge chunk of process memory for a cache. It shows that by using estimation and filtering algorithms, memory usage can be controlled, while guaranteeing adequate performance. This adaptive management approach dynamically and constantly balances the memory and performance components of a cache in the face of evolving and changing access patterns. The policy is to monitor the hit ratio and memory in use and apply this knowledge to decide among (a) granting more memory, (b) replacing objects in cache, and (c) relinquishing memory. This approach has constant overhead independent of cache size and is less vulnerable to changing access patterns. This paper examines the efficacy of the traditional cache against the adaptive cache using pseudo-Monte Carlo simulation and concludes that the adaptive cache outperforms the other and eliminates the need for access pattern-based tuning.

Fresh Breeze

It is well-known that multiprocessor systems are vastly more difficult to program than systems that support sequential programming models. In a 1998 paper[11] this author argued that six important principles for supporting modular software construction are often violated by the architectures proposed for multiprocessor computer systems. The Fresh Breeze project concerns the architecture and design of a multiprocessor chip that can achieve superior performance while honoring these six principles.The envisioned multiprocessor chip will incorporate three ideas that are significant departures from mainstream thinking about multiprocessor architecture: (1) Simultaneous multithreading has been shown to have performance advantages relative to contemporary superscalar designs. This advantage can be exploited through use of a programming model that exposes parallelism in the form of multiple threads of computation. (2) The value of a shared address space is widely appreciated. Through the use of 64-bit pointers, the conventional distinction between "memory" and the file system can be abolished. This can provide a superior execution environment in support of program modularity and software reuse, as well as supporting multi-user data protection and security that is consistent with modular software structure. (3) No memory update; cycle-free heap. Data items are created, used, and released, but never modified once created. The allocation, release, and garbage collection of fixed-size chunks of memory will be implemented by efficient hardware mechanisms. A major benefit of this choice is that the multiprocessor cache coherence problem vanishes: any object retrieved from the memory system is immutable. In addition, it is easy to prevent the formation of pointer cycles, simplifying the design of memory management support.

The role of attack and defense semantics in skilled players' memory for chess positions.

There is much evidence that chess skill is based on chunks in memory that represent parts of positions from previously encountered games. However, the content of these chunks is a matter for debate. According to one view, (1) the closer two pieces are to each other on a board (proximity), the more likely they are to be in the same chunk, and (2) skilled players encode the precise locations of pieces. An alternative view is that what information is encoded in a chess chunk is determined more by processing of the attack/defense relations during evaluation. In three experiments, participants evaluated positions and completed recognition tests. Experiment 1 supported the view that expert players make more use of attack/defense relations than of locations of pieces in a recognition test. Experiments 2 and 3 demonstrated that, for both long and short presentation times, expert players' recognition for a piece within a position was primed more by a piece related by attack or defense than by a piece merely proximal. These findings challenge theories of expertise for chess that assume a primary role for proximity and location in determining which pieces are grouped together in memory.

Characterizing chunks in visual short-term memory: Not more than one feature per dimension?

Cowan defines a chunk as “a collection of concepts that have strong associations to one another and much weaker associations to other chunks currently in use.” This definition does not impose any constraints on the nature and number of elements that can be bound into a chunk. We present an experiment to demonstrate that such limitations exist for visual short-term memory, and that their analysis may lead to important insights into properties of visual memory.

The search for fixed generalizable limits of “pure STM” capacity: Problems with theoretical proposals based on independent chunks

Cowan's experimental techniques cannot constrain subject's recall of presented information to distinct independent chunks in short-term memory (STM). The encoding of associations in long-term memory contaminates recall of pure STM capacity. Even in task environments where the functional independence of chunks is convincingly demonstrated, individuals can increase the storage of independent chunks with deliberate practice – well above the magical number four.

The magical number 4 in short-term memory: a reconsideration of mental storage capacity.

Miller (1956) summarized evidence that people can remember about seven chunks in short-term memory (STM) tasks. However, that number was meant more as a rough estimate and a rhetorical device than as a real capacity limit. Others have since suggested that there is a more precise capacity limit, but that it is only three to five chunks. The present target article brings together a wide variety of data on capacity limits suggesting that the smaller capacity limit is real. Capacity limits will be useful in analyses of information processing only if the boundary conditions for observing them can be carefully described. Four basic conditions in which chunks can be identified and capacity limits can accordingly be observed are: (1) when information overload limits chunks to individual stimulus items, (2) when other steps are taken specifically to block the recording of stimulus items into larger chunks, (3) in performance discontinuities caused by the capacity limit, and (4) in various indirect effects of the capacity limit. Under these conditions, rehearsal and long-term memory cannot be used to combine stimulus items into chunks of an unknown size; nor can storage mechanisms that are not capacity-limited, such as sensory memory, allow the capacity-limited storage mechanism to be refilled during recall. A single, central capacity limit averaging about four chunks is implicated along with other, noncapacity-limited sources. The pure STM capacity limit expressed in chunks is distinguished from compound STM limits obtained when the number of separately held chunks is unclear. Reasons why pure capacity estimates fall within a narrow range are discussed and a capacity limit for the focus of attention is proposed.

日本語文と英語文における統語構造認識とマジカルナンバー7±2

George A. Millerは人間の短期記憶の容量は7±2程度のスロットしかないことを提唱している. 本研究では, 京大コーパスを用いて日本語文の各部分において係り先が未決定な文節の個数を数えあげ, その個数がおおよそ7±2の上限9程度でおさえられていたことを報告した. また, 英語文でも同様な調査を行ないNP程度のものをまとめて認識すると仮定した場合7±2の上限9程度でおさえられていたことを確認した. これらのことは, 文理解における情報の認知単位として日本語で文節, 英語ではNP程度のものを仮定すると, Millerの7±2の理論と, 言語解析・生成において短期記憶するものは7±2程度ですむというYngveの主張を整合性よく説明できることを意味する.

Expert Chess Memory: Revisiting the Chunking Hypothesis

After reviewing the relevant theory on chess expertise, this paper re-examines experimentally the finding of Chase and Simon (1973a) that the differences in ability of chess players at different skill levels to copy and to recall positions are attributable to the experts' storage of thousands of chunks (patterned clusters of pieces) in long-term memory. Despite important differences in the experimental apparatus, the data of the present experiments regarding latencies and chess relations between successively placed pieces are highly correlated with those of Chase and Simon. We conclude that the two-second inter-chunk interval used to define chunk boundaries is robust, and that chunks have psychological reality. We discuss the possible reasons why Masters in our new study used substantially larger chunks than the Master of the 1973 study, and extend the chunking theory to take account of the evidence for large retrieval structures (templates) in long-term memory.

Templates in Chess Memory: A Mechanism for Recalling Several Boards

This paper addresses empirically and theoretically a question derived from the chunking theory of memory (Chase & Simon, 1973a, 1973b): To what extent is skilled chess memory limited by the size of short-term memory (about seven chunks)? This question is addressed first with an experiment where subjects, ranking from class A players to grandmasters, are asked to recall up to five positions presented during 5 s each. Results show a decline of percentage of recall with additional boards, but also show that expert players recall more pieces than is predicted by the chunking theory in its original form. A second experiment shows that longer latencies between the presentation of boards facilitate recall. In a third experiment, a Chessmaster gradually increases the number of boards he can reproduce with higher than 70% average accuracy to nine, replacing as many as 160 pieces correctly. To account for the results of these experiments, a revision of the Chase–Simon theory is proposed. It is suggested that chess players, like experts in other recall tasks, use long-term memory retrieval structures (Chase & Ericsson, 1982) or templates in addition to chunks in short-term memory to store information rapidly.

Recall of random and distorted chess positions: implications for the theory of expertise.

This paper explores the question, important to the theory of expert performance, of the nature and number of chunks that chess experts hold in memory. It examines how memory contents determine players' abilities to reconstruct (1) positions from games, (2) positions distorted in various ways, and (3) random positions. Comparison of a computer simulation with a human experiment supports the usual estimate that chess Masters store some 50,000 chunks in memory. The observed impairment of recall when positions are modified by mirror image reflection implies that each chunk represents a specific pattern of pieces in specific location. A good account of the results of the experiments is given by the template theory proposed by Gobet and Simon (in press) as an extension of Chase and Simon's (1973b) initial chunking proposal, and in agreement with other recent proposals for modification of the chunking theory (Richman, Staszewski, & Simon, 1995) as applied to various recall tasks.

Where buses cannot go

No aspect of computer design is sacred, not even the system bus, which is giving way to switches in multiprocessing systems, where performance is key. System buses, which string computers together out of circuit boards, have come to strangle system performance in many cases. Another interconnection architecture, though, can free a system from the bus's clutch. Variously known as a switch, crossbar, or crosspoint, it has long been used in speciality computers and is now making its way into lower-cost machines. Meanwhile, silicon and packaging technology have been refined to the point that the crossbar architecture can vie with the system bus for a place in low-cost multiprocessors. More specifically, the crossbar is well suited to use in distributed memory systems, where there is a need for broad path ways for communications between the chunks of memory themselves. The roots of such an approach go deep. In fact, it may be said to have started with an idea for keeping as much data traffic as possible out of general circulation: cache memory.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Further evidence for hierarchical chunking in rat spatial memory.

In Experiment 1, rats were given a test to determine the order of preference among 3 types of food. Two groups of rats then were trained on a 12-arm radial maze in Experiment 2, with the 3 foods placed in fixed-arm locations for 1 group and in locations that varied randomly across sessions for the other group. The results replicated those of Dallal and Meck (1990) by showing faster learning and more clustering of arm choices by food type in the fixed-locations group than in the random-locations group. Two further experiments were performed to test the chunking hypothesis. Observations of working memory in Experiment 3 and the reorganization of reference memory in Experiment 4 both supported the chunking hypothesis by showing superior spatial memory and arm chunking by food type when chunk integrity was maintained than when it was compromised.

Episodes as chunks in narrative memory

Story statements cluster into episodes, so we expected the memory representations of statements to cluster into separate episode chunks in memory. Experiment 1 confirmed this chunking idea by showing that the recall of episode actions depends on the length of that episode, but not on the lengths of other episodes. Specifically, adding more actions to an episode increased recall of the original actions but didn't affect recall of other episodes. Further, subjects rated the original actions as more important than the added actions, thus suggesting that unimportant actions increased the recall of important actions in that episode. Another experiment showed that the more subordinate actions an episode contains, the more likely a statement summarizing that episode is to be recalled.

Encoding Variability: A Role in Immediate and Long-Term Memory?

Two experiments tested the effect of variable encoding on recall. In the first, critical items occupied the same or different contexts, and presumably memory chunks, across successive study trials. There was no advantage either early or later in learning for items occurring in two contexts. In the second experiment, a list of homographs was learned and retention was tested one week later. During acquisition, independent groups of subjects were provided with none, one, or two meanings for each homograph. There was no advantage, either during acquisition or at retention, for lists having two versus one encoding per word.

Rhythmic groups and subjective chunks in memory for melodies

Memory for brief melodic phrases was tested using a short-term recognition-memory paradigm. The five-note phrases were rhythmically separated from each other and presented in lists four phrases in length. A single five-note test item followed each list and either corresponded rhythmically to one of the phrases as presented in the list (within items) or to the last three notes of one phrase and the first two notes of the next (across items). Within items were easier than across items. Slow presentation (3 notes/sec) was slightly easier than fast (6 notes/see). The J-shaped serial position curve typical of short-term memory for verbal material was obtained. The results support the position that rhythmic grouping of input determines subjective chunking and memory storage, facilitating the recognition of test items chunked in the same way as list items.