Learn More
An efficient implementation of task parallelism is important for high productivity languages. Specifically, it requires a tasking layer that fulfills following requirements: (i) its performance scales to high core counts, and (ii) it is seamlessly integrated into a runtime system that performs inter-node communication and synchronization. More specifically,(More)
OBJECTIVE To assess and compare quality of life (QOL) of patients followed for a long time who underwent an ileal conduit (IC), continent reservoir (CR) or ileal neobladder (NB) using FACT-BL, a bladder-cancer-specific questionnaire. METHODS One hundred and forty-seven patients underwent radical cystectomy and urinary diversion for bladder cancer from(More)
BACKGROUND The aim was to determine the incidence of seed migration not only to the chest, but also to the abdomen and pelvis after transperineal interstitial prostate brachytherapy with loose (125)I seeds. METHODS We reviewed the records of 267 patients who underwent prostate brachytherapy with loose (125)I seeds. After seed implantation, orthogonal(More)
An efficient scheduler is important for task parallelism. It should provide scalable dynamic load-balancing mechanism among CPU cores. To meet this requirement, most runtime systems for task parallelism use work stealing as scheduling strategy. Work stealing schedulers typically steal work randomly. This strategy does not consider hardware specific(More)
This paper describes a task parallel implementation of ExaFMM, an open source implementation of fast multipole methods (FMM), using a lightweight task parallel library MassiveThreads. Although there have been many attempts on parallelizing FMM, experiences have almost exclusively been limited to formulation based on flat homogeneous parallel loops. FMM in(More)
The present study was undertaken to investigate the predictors in patients who received hormonal therapy (HT) for prostate-specific antigen recurrence (PSAR) after surgery. Predictors for the progression-free survival were assessed in 55 patients who received HT for PSAR after surgery. In multivariate analysis, primary Gleason grade > or =4 and PSA doubling(More)
Delinquent instructions are few static instructions that cause many branch prediction misses or cache misses. One of the most important characters of a delinquent instruction is that most part of delinquent instructions is executed in a small loop. Existing multithreading schemes cannot improve performance in such a small loop, because the existing schemes(More)
We investigated the usefulness of the fusion image created by transrectal ultrasonography (TRUS) and large-bore computed tomography (CT) for predicting pubic arch interference (PAI) during prostate seed brachytherapy. The TRUS volume study was performed in 21 patients, followed by large-bore computed tomography of patients in the lithotomy position. Then,(More)