Results 1  10
of
12
Memory Coherence in Shared Virtual Memory Systems
, 1989
"... This paper studies the memory coherence problem in designing said inaplementing a shared virtual memory on looselycoupled multiprocessors. Two classes of aIgoritb. ms for solving the problem are presented. A prototype shared virtual memory on an Apollo ring has been implemented based on these a ..."
Abstract

Cited by 885 (16 self)
 Add to MetaCart
This paper studies the memory coherence problem in designing said inaplementing a shared virtual memory on looselycoupled multiprocessors. Two classes of aIgoritb. ms for solving the problem are presented. A prototype shared virtual memory on an Apollo ring has been implemented based on these algorithms. Both theoretical and practical results show tkat the mentory coherence problem cast indeed be solved efficiently on a looselycoupled multiprocessor.
A Quantitative Comparison of Scheduling Algorithms for InputQueued Switches
 Computer Networks and ISDN Systems
, 1997
"... This paper quantitatively evaluates several alternative approaches to the scheduling of cells in a highbandwidth inputqueued ATM switch. In particular, we compare the performance of three algorithms described previously: FIFO queueing, parallel iterative matching (PIM), maximum matching and two new ..."
Abstract

Cited by 28 (4 self)
 Add to MetaCart
This paper quantitatively evaluates several alternative approaches to the scheduling of cells in a highbandwidth inputqueued ATM switch. In particular, we compare the performance of three algorithms described previously: FIFO queueing, parallel iterative matching (PIM), maximum matching and two new algorithms: iterative roundrobin matching with slip (SLIP) and leastrecently used (LRU). For the synthetic workloads we consider, including uniform and bursty traffic, SLIP performs almost identically to the other algorithms. Cases for which PIM and SLIP perform poorly are presented, indicating that care should be taken when using these algorithms. But, we show that the implementation complexity of SLIP is an order of magnitude less than for PIM, making it feasible to implement a 32x32 switch scheduler for SLIP on a single chip. 1 Introduction The past few years has seen increasing interest in arbitrary topology cellbased local area networks, such as ATM [5]. In these networks, hosts a...
A case for FAME: FPGA architecture model execution
 In Proc. of the 37th ACM/IEEE Int’l Symposium on Computer Architecture (ISCA 2010
, 2010
"... Given the multicore microprocessor revolution, we argue that the architecture research community needs a dramatic increase in simulation capacity. We believe FPGA Architecture Model Execution (FAME) simulators can increase the number of useful architecture research experiments per day by two orders ..."
Abstract

Cited by 18 (5 self)
 Add to MetaCart
Given the multicore microprocessor revolution, we argue that the architecture research community needs a dramatic increase in simulation capacity. We believe FPGA Architecture Model Execution (FAME) simulators can increase the number of useful architecture research experiments per day by two orders of magnitude over Software Architecture Model Execution (SAME) simulators. To clear up misconceptions about FPGAbased simulation methodologies, we propose a FAME taxonomy to distinguish the costperformance of variations on these ideas. We demonstrate our simulation speedup claim with a case study wherein we employ a prototype FAME simulator, RAMP Gold, to research the interaction between hardware partitioning mechanisms and operating system scheduling policy. The study demonstrates FAME’s capabilities: we run a modern parallel benchmark suite on a research operating system, simulate 64core target architectures with multilevel memory hierarchy timing models, and add experimental hardware mechanisms to the target machine. The simulation speedup achieved by our adoption of FAME—250×—enables experiments with more realistic time scales and data set sizes than are possible with SAME.
A Quantitative Comparison of Iterative Scheduling Algorithms for InputQueued Switches
 COMPUTER NETWORKS AND ISDN SYSTEMS
, 1998
"... In this paper we quantitatively evaluate three iterative algorithms for scheduling cells in a highbandwidth inputqueued ATM switch. In particular, we compare the performance of an algorithm described previously  parallel iterative matching (PIM)  with two new algorithms: iterative roundrob ..."
Abstract

Cited by 12 (0 self)
 Add to MetaCart
In this paper we quantitatively evaluate three iterative algorithms for scheduling cells in a highbandwidth inputqueued ATM switch. In particular, we compare the performance of an algorithm described previously  parallel iterative matching (PIM)  with two new algorithms: iterative roundrobin matching with slip (iSLIP) and iterative leastrecently used (iLRU). We also compare each algorithm against FIFO inputqueueing and perfect outputqueueing. For the synthetic workloads we consider, including uniform and bursty traffic, iSLIP performs almost identically to the other algorithms. Cases for which PIM and iSLIP perform poorly are presented, indicating that care should be taken when using these algorithms. But, we show that the implementation complexity of iSLIP is an order of magnitude less than for PIM, making it feasible to implement a 32 x 32 switch scheduler for iSLIP on a single chip.
Characterization of Organic Illumination Systems
, 1989
"... Recent anecdotal reports of novel principles of illumination have stressed qualitative aspects. This note presents a quantitative study of an organic illumintation system, characterizing the temperature and currentflow properties of the system as functions of time and device parameters. Theoretical ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
Recent anecdotal reports of novel principles of illumination have stressed qualitative aspects. This note presents a quantitative study of an organic illumintation system, characterizing the temperature and currentflow properties of the system as functions of time and device parameters. Theoretical and practical implications of these measurements are discussed. Copyright 1989 Digital Equipment Corporation d i g i t a l Western Research Laboratory 100 Hamilton Avenue Palo Alto, California 94301 USA 1. Introduction There has been a great deal of interest of late in triboluminescence and electroluminescence in organic materials. Triboluminescence in wintergreen Life Savers has been investigated by many over the years [8], while electroluminescence in organic thin films is an active area of current research both here and abroad [10]. In early December 1988, our attention was called to work by Bill Bidermann on electroluminescence in pickles [23]. It was reported that inserting iro...
A one parameter representation for the IsgurWise function
, 1995
"... We use a 1S lattice QCD heavylight wavefunction to generate a single parameter, model independent description of the IsgurWise function. Using recent data we find the zerorecoil slope to be ¸ 0 (1) = \Gamma1:16 \Sigma 0:17, while the second derivative turns out to be ¸ 00 (1) = 2:64 \Sigma 0: ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
We use a 1S lattice QCD heavylight wavefunction to generate a single parameter, model independent description of the IsgurWise function. Using recent data we find the zerorecoil slope to be ¸ 0 (1) = \Gamma1:16 \Sigma 0:17, while the second derivative turns out to be ¸ 00 (1) = 2:64 \Sigma 0:74. 1 Introduction The recent development of the Heavy Quark Effective Theory [1] yields an expression for the ¯ B ! D () l¯ l decay rate in terms of a single unknown form factor, the IsgurWise function (IW). This function is absolutely normalized at zero recoil point up to corrections of order 1 m 2 Q [2]. It is currently believed that these corrections can be calculated with less than 5% uncertainty [3], which would allow a precise determination of the CKM matrix element jV cb j from the study of ¯ B ! D () l¯ l decay as a function of the D () meson recoil. In this note we take a somewhat different approach. We use an established LQCD result [4, 5] for the heavylight wave...
A one parameter representation for the IsgurWise function
, 1995
"... We use a 1S lattice QCD heavylight wavefunction to generate a single parameter, model independent description of the IsgurWise function. Using recent data we find the zerorecoil slope to be 0 (1) = \Gamma1:16 \Sigma 0:17, while the second derivative turns out to be 00 (1) = 2:64 \Sigma 0 ..."
Abstract
 Add to MetaCart
We use a 1S lattice QCD heavylight wavefunction to generate a single parameter, model independent description of the IsgurWise function. Using recent data we find the zerorecoil slope to be 0 (1) = \Gamma1:16 \Sigma 0:17, while the second derivative turns out to be 00 (1) = 2:64 \Sigma 0:74. 1 Introduction The recent development of the Heavy Quark Effective Theory [1] yields an expression for the B ! D () l l decay rate in terms of a single unknown form factor, the IsgurWise function (IW). This function is absolutely normalized at zero recoil point up to corrections of order 1 m 2 Q [2]. It is currently believed that these corrections can be calculated with less than 5% uncertainty [3], which would allow a precise determination of the CKM matrix element jV cb j from the study of B ! D () l l decay as a function of the D () meson recoil. In this note we take a somewhat different approach. We use an established LQCD result [4, 5] for the heavylight wavefuncti...
1 N * Mass Spectrum from an Anisotropic Action
, 2000
"... Results are reported for N * masses in the 1/2+ and 1/2 − sectors on an anisotropic lattice. The gauge action is the usual plaquette plus rectangle type, the quark action is of the D234 type, both having tadpoleimproved treelevel coefficients. Clear splittings from the nucleon ground state are obs ..."
Abstract
 Add to MetaCart
Results are reported for N * masses in the 1/2+ and 1/2 − sectors on an anisotropic lattice. The gauge action is the usual plaquette plus rectangle type, the quark action is of the D234 type, both having tadpoleimproved treelevel coefficients. Clear splittings from the nucleon ground state are observed with smeared operators and 500 configurations. The first excited states in each channel are further isolated, using a correlation matrix and the variational method. The basic pattern of these splittings is consistent with experimental observations. 1.
Using FPGAs to Simulate Novel Datacenter Network Architectures At Scale by
"... All rights reserved. ..."
Pentaquark Update After Ten Years
, 1998
"... Studying scattering of heavy flavor hadrons and looking for bound states is shown to give experimental information otherwise unobtainable about effective twobody interactions between constituent (qq)6 and (¯qq)8 pairs respectively in color sextet and color octet states. All the successes of the con ..."
Abstract
 Add to MetaCart
Studying scattering of heavy flavor hadrons and looking for bound states is shown to give experimental information otherwise unobtainable about effective twobody interactions between constituent (qq)6 and (¯qq)8 pairs respectively in color sextet and color octet states. All the successes of the constituent quark model in (uds) hadron spectroscopy are shown to depend only on effective twobody interactions in color 3 ∗ and singlet states. New directions for bound pentaquark searches are discussed following the availability of vertex detectors which can pinpoint events where a proton is emitted from a secondary vertex. Any such event indicates a particle decaying weakly by proton emission and the discovery of a new particle if its mass is higher than that of known charmed baryons. There is no combinatorial background and striking decay signatures like pφπ − are no longer needed. The beauty pentaquark ( ¯ bsuud) and the doublystrange pentaquark (¯cssud) may be relevant to future searches. A simple calculation shows that the effects of flavorSU(3) breaking on their binding relative to the relevant thresholds are similar to that for the singlystrange pentaquark (¯csuud) relative to the Dsp threshold. I.