Hypergraph Partitioning for Automatic Memory Hierarchy Management

2006 ◽  
Author(s):  
Sriram Krishnamoorthy ◽  
Umit Catalyurek ◽  
Jarek Nieplocha ◽  
Atanas Rountev ◽  
P. Sadayappan
Keyword(s):  
Memory Hierarchy ◽  
Hypergraph Partitioning ◽  
Automatic Memory

Data management and query---Hypergraph partitioning for automatic memory hierarchy management

2006 ◽  
Author(s):  
Sriram Krishnamoorthy ◽  
Umit Catalyurek ◽  
Jarek Nieplocha ◽  
Atanas Rountev ◽  
P. Sadayappan
Keyword(s):  
Data Management ◽  
Memory Hierarchy ◽  
Hypergraph Partitioning ◽  
Automatic Memory

An ERP Investigation of Semantic Priming, Repetition Priming, and Negative Priming in Schizophrenic Patients

2006 ◽  
Vol 20 (3) ◽  
pp. 195-211 ◽  
Author(s):  
Michael Wagner ◽  
Lioba Baving ◽  
Patrick Berg ◽  
Rudolf Cohen ◽  
Brigitte Rockstroh
Keyword(s):  
Negative Priming ◽  
Repetition Priming ◽  
Event Related Potentials ◽  
Decision Task ◽  
Positive Priming ◽  
Retrieval Processes ◽  
Schizophrenic Patients ◽  
Related Potentials ◽  
Late Positive Complex ◽  
Automatic Memory

The processing of attended and nonattended stimuli in schizophrenic patients was examined with event-related potentials (ERPs) in a lexical decision task. In positive semantic and repetition priming the N400 amplitude did not differ between a group of 17 medicated schizophrenic patients and a group of 20 matched healthy controls. However, negative priming affected the N400 only in controls. Reaction time effects were dissociated from these ERP effects, with patients showing stronger positive priming than controls but identical negative priming. The semantic processes related to the N400 appear to be intact in schizophrenic patients, but patients seem to incorporate less context information (about the nonattended prime) in their episodic memory traces. A stronger increase of the posterior late positive complex in parallel to the stronger positive priming in schizophrenic patients may reflect relatively stronger automatic memory retrieval processes in patients.

scholarly journals MILC Code Performance on High End CPU and GPU Supercomputer Clusters

2018 ◽  
Vol 175 ◽  
pp. 02009
Author(s):  
Carleton DeTar ◽  
Steven Gottlieb ◽  
Ruizi Li ◽  
Doug Toussaint
Keyword(s):  
Conjugate Gradient ◽  
Memory Hierarchy ◽  
Xeon Phi ◽  
Intel Xeon Phi ◽  
Code Performance ◽  
Recent Developments ◽  
Knights Landing ◽  
Many Core ◽  
Intel Xeon

With recent developments in parallel supercomputing architecture, many core, multi-core, and GPU processors are now commonplace, resulting in more levels of parallelism, memory hierarchy, and programming complexity. It has been necessary to adapt the MILC code to these new processors starting with NVIDIA GPUs, and more recently, the Intel Xeon Phi processors. We report on our efforts to port and optimize our code for the Intel Knights Landing architecture. We consider performance of the MILC code with MPI and OpenMP, and optimizations with QOPQDP and QPhiX. For the latter approach, we concentrate on the staggered conjugate gradient and gauge force. We also consider performance on recent NVIDIA GPUs using the QUDA library.

Cache and Memory Hierarchy Design

1995 ◽  
Vol 23 (3) ◽  
pp. 28
Author(s):  
Daniel Tabak
Keyword(s):  
Memory Hierarchy

Novel memory hierarchy with e-STT-MRAM for near-future applications

2017 ◽  
Author(s):  
Shinobu Fujita ◽  
Hiroki Noguchi ◽  
Kazutaka Ikegami ◽  
Susumu Takeda ◽  
Kumiko Nomura ◽  
...  
Keyword(s):  
Memory Hierarchy ◽  
Near Future

EXPLOITING THE MEMORY HIERARCHY OF MULTICORE SYSTEMS FOR PARALLEL TRIANGULATION REFINEMENT

2012 ◽  
Vol 22 (03) ◽  
pp. 1250007 ◽  
Author(s):  
PEDRO RODRÍGUEZ ◽  
MARÍA CECILIA RIVARA ◽  
ISAAC D. SCHERSON
Keyword(s):  
Parallel Implementation ◽  
Memory Hierarchy ◽  
Random Selection ◽  
Multicore Systems ◽  
Algorithm Performance ◽  
Bisection Algorithm ◽  
Improve Algorithm ◽  
Triangulation Refinement ◽  
Selection Of

A novel parallelization of the Lepp-bisection algorithm for triangulation refinement on multicore systems is presented. Randomization and wise use of the memory hierarchy are shown to highly improve algorithm performance. Given a list of selected triangles to be refined, random selection of candidates together with pre-fetching of Lepp-submeshes lead to a scalable and efficient multi-core parallel implementation. The quality of the refinement is shown to be preserved.

Sign in / Sign up

Export Citation Format

Share Document