Exploiting Long-Term Temporal Cache Access Patterns for LRU Insertion Prioritization

2021 ◽  
pp. 2150010
Author(s):  
Shane Carroll ◽  
Wei-Ming Lin

In a CPU cache utilizing least recently used (LRU) replacement, cache sets manage a buffer which orders all cache lines in the set from LRU to most recently used (MRU). When a cache line is brought into cache, it is placed at the MRU and the LRU line is evicted. When re-accessed, a line is promoted to the MRU position. LRU replacement provides a simple heuristic to predict the optimal cache line to evict. However, LRU utilizes only simple, short-term access patterns. In this paper, we propose a method that uses a buffer called the history queue to record longer-term access-eviction patterns than the LRU buffer can capture. Using this information, we make a simple modification to LRU insertion policy such that recently-recalled blocks have priority over others. As lines are evicted, their addresses are recorded in a FIFO history queue. Incoming lines that have recently been evicted and now recalled (those in the history queue at recall time) remain in the MRU for an extended period of time as non-recalled lines entering the cache thereafter are placed below the MRU. We show that the proposed LRU insertion prioritization increases performance in single-threaded and multi-threaded workloads in simulations with simple adjustments to baseline LRU.

Author(s):  
Simone Amendola ◽  
Martin Plöderl ◽  
Michael P Hengartner

Abstract Background Ecological studies have explored associations between suicide rates and antidepressant prescriptions in the population, but most of them are limited as they analyzed short-term correlations that may be spurious. The aim of this long-term study was to examine whether trends in suicide rates changed in three European countries when the first antidepressants were introduced in 1960 and when prescription rates increased steeply after 1990 with the introduction of the serotonin reuptake inhibitors (SSRIs). Methods Data were extracted from the WHO Mortality Database. Suicide rates were calculated for people aged 10–89 years from 1951–2015 for Italy, 1955–2016 for Austria and 1951–2013 for Switzerland. Trends in suicide rates stratified by gender were analyzed using joinpoint regression models. Results There was a general pattern of long-term trends that was broadly consistent across all three countries. Suicide rates were stable or decreasing during the 1950s and 1960s, they rose during the 1970s, peaked in the early 1980s and thereafter they declined. There were a few notable exceptions to these general trends. In Italian men, suicide rates increased until 1997, then fell sharply until 2006 and increased again from 2006 to 2015. In women from all three countries, there was an extended period during the 2000s when suicide rates were stable. No trend changes occurred around 1960 or 1990. Conclusions The introduction of antidepressants around 1960 and the sharp increase in prescriptions after 1990 with the introduction of the SSRIs did not coincide with trend changes in suicide rates in Italy, Austria or Switzerland.


2012 ◽  
Vol 30 (15_suppl) ◽  
pp. e20511-e20511
Author(s):  
Anthony Paul Conley ◽  
Annie Guerin ◽  
Medha Sasane ◽  
Genevieve Gauthier ◽  
Frances Schwiep ◽  
...  

e20511 Background: The benefits of long-term (36 months) use of adjuvant imatinib (IM) in high risk GIST patients (pts) have been demonstrated in a recent multicenter, prospective clinical trial that compared efficacy and safety of 3 years vs 1 year IM treatment. However, in clinical practice, there is no consensus on the optimal IM treatment duration after surgery. The objective of this retrospective observational study was to compare the risk of recurrence and survival among primary resectable Kit positive GIST pts treated with adjuvant IM for a short vs an extended period of time in a real-world setting. Methods: Information on adult pts with primary resectable Kit positive GIST initiating imatinib ≤84 days after surgery was collected from 248 U.S. oncologists using an online data collection form. Detailed pt information following first GIST diagnosis, including demographic, GIST-related characteristics (e.g., risk profile), comorbidity profile, IM treatment characteristics, disease recurrence and mortality was collected for pts with short-term (6-12 months) and long-term IM use (≥24 months). Disease recurrence and mortality rates were estimated from the 1st surgery date to the 1st evidence of recurrence, mortality, or end of observation period. Multivariate Cox proportional hazard models were used to compare recurrence and mortality rates between short vs long term IM use pts. Results: Among the 246 short-term and 395 long-term IM pts, the median follow up was 884 and 963 days, respectively. The average age was similar [59.0 (10.4) vs 58.1 (9.5); p=.23] but short-term pts had less males [57.7% vs 69.6% (p<.01)] and a lower Miettinen risk score [0.3 vs 0.4, p< .01)] than long-term pts. Disease recurrence [7.3 vs 1.8%, (p< .01)] and mortality rates [6.9% vs 2.3%, (p < .01)] were also higher in short- vs long-term pts. The adjusted risk of recurrence was 4.77 times [95% CI: 1.98 – 11.48, (p<.01)] higher and mortality risk was 3.44 times [CI: 1.53 – 7.75, (p<.01)] higher in short- vs long-term pts. Conclusions: Use of IM over an extended period of time is associated with a reduction in long-term risk of disease recurrence and mortality.


Author(s):  
Deborah L. Nelson ◽  
Kim-Phuong L. Vu

Participants in this study were assigned to one of three different password generation groups: image-based mnemonic, text-based mnemonic, or proactive password checking restrictions alone; and asked to generate and later recall passwords for five separate fictitious online accounts. Password accuracy and recall time were measured following both a short-term (10-minute) and long-term (1-week) delay. Results indicated that passwords were more quickly generated and accurately recalled when they were generated using the image-based mnemonic technique or proactive password restrictions alone, as opposed to the text-based mnemonic technique. Furthermore, use of the image-based mnemonic technique resulted in the generation of passwords that were more resistant to forgetting. Implications and future research considerations are discussed.


2012 ◽  
Vol 30 (15_suppl) ◽  
pp. 10094-10094
Author(s):  
Annie Guerin ◽  
Anthony Paul Conley ◽  
Medha Sasane ◽  
Genevieve Gauthier ◽  
Frances Schwiep ◽  
...  

10094 Background: In clinical practice, significant variability is seen in duration of adjuvant IM use. The objective of this study is to compare characteristics of GIST pts receiving adjuvant IM for a short (6-12 months) vs extended period (≥24 months) to better understand factors that may influence treatment (trt) duration decisions. Methods: Physician prescribing patterns and clinical information on adult pts with primary resectable Kit positive GIST initiating IM ≤84 days post-surgery was collected from 248 U.S. oncologists using online data collection forms. In addition to physicians’ perception of short- vs long-term use, pts’ risk assessment, trt, demographics, and comorbidities were collected for 246 short-term and 395 long-term IM pts. Characteristics were compared using Wilcoxon and Chi-square tests. Results: While pts were similar in age [59.0 vs. 58.1, P =.23], ethnicity, and region of residence, the short-term group included fewer males (57.7% vs 69.6%, P <.01) and had a higher prevalence of cardiovascular (11.4% vs 5.8%, P = .01) and ischemic heart diseases (5.3% vs 1.5%, P<.01). Differences were also observed in indicators of pre-treatment risk profile (tumor size, location, and rupture during surgery, mitotic count, and Miettinen score) (Table). Findings were consistent with main reasons reported by physicians for prescribing adjuvant IM over longer duration; in addition to pt risk profile (76.6%), tolerability (70.6%), younger pts (59.7%), safety (39.1%), trt response (29.8%), and economic reasons (26.2%) were other reasons impacting trt decisions. Conclusions: Pt risk is an important factor in physicians’ decisions to prescribe adjuvant IM for extended duration. However, age, tolerability, and comorbidities, also play an important role. [Table: see text]


1996 ◽  
Vol 42 (8) ◽  
pp. 1342-1344 ◽  
Author(s):  
N S Weiss

Abstract Some women take an estrogen preparation for as long as several years to ease symptoms of the menopause. Such women appear to have little or no alteration in their risk of endometrial cancer, especially if they are also taking a progestogen, and no alteration in their risk of breast cancer. Similarly, the incidence of fractures is unaffected by relatively short-term hormone use. The risk of ischemic heart disease also is reduced among women who currently take estrogens (with or without a progestogen), but the influence of duration of use on this association is uncertain. Postmenopausal women who take estrogens for an extended period of time (e.g., a decade or more) incur a sharply increased risk of cancer of the endometrium. This is largely abated by use of a progestogen for at least 10 days per month. Such long-term estrogen use, whether accompanied by a progestogen or not, may increase the risk of breast cancer slightly, but this is an area of great controversy, at present unresolved. The incidence of both myocardial infarction and fracture is substantially reduced in long-term users of menopausal hormones.


2016 ◽  
Vol 39 ◽  
Author(s):  
Mary C. Potter

AbstractRapid serial visual presentation (RSVP) of words or pictured scenes provides evidence for a large-capacity conceptual short-term memory (CSTM) that momentarily provides rich associated material from long-term memory, permitting rapid chunking (Potter 1993; 2009; 2012). In perception of scenes as well as language comprehension, we make use of knowledge that briefly exceeds the supposed limits of working memory.


Author(s):  
D.E. Loudy ◽  
J. Sprinkle-Cavallo ◽  
J.T. Yarrington ◽  
F.Y. Thompson ◽  
J.P. Gibson

Previous short term toxicological studies of one to two weeks duration have demonstrated that MDL 19,660 (5-(4-chlorophenyl)-2,4-dihydro-2,4-dimethyl-3Hl, 2,4-triazole-3-thione), an antidepressant drug, causes a dose-related thrombocytopenia in dogs. Platelet counts started to decline after two days of dosing with 30 mg/kg/day and continued to decrease to their lowest levels by 5-7 days. The loss in platelets was primarily of the small discoid subpopulation. In vitro studies have also indicated that MDL 19,660: does not spontaneously aggregate canine platelets and has moderate antiaggregating properties by inhibiting ADP-induced aggregation. The objectives of the present investigation of MDL 19,660 were to evaluate ultrastructurally long term effects on platelet internal architecture and changes in subpopulations of platelets and megakaryocytes.Nine male and nine female beagle dogs were divided equally into three groups and were administered orally 0, 15, or 30 mg/kg/day of MDL 19,660 for three months. Compared to a control platelet range of 353,000- 452,000/μl, a doserelated thrombocytopenia reached a maximum severity of an average of 135,000/μl for the 15 mg/kg/day dogs after two weeks and 81,000/μl for the 30 mg/kg/day dogs after one week.


2020 ◽  
Vol 29 (4) ◽  
pp. 710-727
Author(s):  
Beula M. Magimairaj ◽  
Naveen K. Nagaraj ◽  
Alexander V. Sergeev ◽  
Natalie J. Benafield

Objectives School-age children with and without parent-reported listening difficulties (LiD) were compared on auditory processing, language, memory, and attention abilities. The objective was to extend what is known so far in the literature about children with LiD by using multiple measures and selective novel measures across the above areas. Design Twenty-six children who were reported by their parents as having LiD and 26 age-matched typically developing children completed clinical tests of auditory processing and multiple measures of language, attention, and memory. All children had normal-range pure-tone hearing thresholds bilaterally. Group differences were examined. Results In addition to significantly poorer speech-perception-in-noise scores, children with LiD had reduced speed and accuracy of word retrieval from long-term memory, poorer short-term memory, sentence recall, and inferencing ability. Statistically significant group differences were of moderate effect size; however, standard test scores of children with LiD were not clinically poor. No statistically significant group differences were observed in attention, working memory capacity, vocabulary, and nonverbal IQ. Conclusions Mild signal-to-noise ratio loss, as reflected by the group mean of children with LiD, supported the children's functional listening problems. In addition, children's relative weakness in select areas of language performance, short-term memory, and long-term memory lexical retrieval speed and accuracy added to previous research on evidence-based areas that need to be evaluated in children with LiD who almost always have heterogenous profiles. Importantly, the functional difficulties faced by children with LiD in relation to their test results indicated, to some extent, that commonly used assessments may not be adequately capturing the children's listening challenges. Supplemental Material https://doi.org/10.23641/asha.12808607


2019 ◽  
Vol 25 ◽  
pp. 114
Author(s):  
Alyssa Dufour ◽  
Setareh Williams ◽  
Richard Weiss ◽  
Elizabeth Samelson

Sign in / Sign up

Export Citation Format

Share Document