Terminating iterative solution of simultaneous equations in distributed message passing systems

Author(s):  
B. Szymanski ◽  
Y. Shi ◽  
N. Prywes
1999 ◽  
Vol 09 (01) ◽  
pp. 159-170 ◽  
Author(s):  
FREDERIC T. CHONG ◽  
ANANT AGARWAL

The benefits of hardware support for shared memory versus those for message passing are difficult to evaluate without an in-depth study of real applications on a common platform. We evaluate the communication mechanisms of the MIT Alewife machine, a multiprocessor which provides integrated cache-coherent shared memory, massage passing, and DMA. We perform this evaluation with "best-effort" implementations which solve several sparse, irregular benchmark problems with a preconditioned conjugate gradient sparse matrix solver (ICCG). We find that machines with fast global memory operations do not need message passing or bulk transfer to suport our irregular problems. This is primarily due to three reasons. First, a 5-to-1 ratio between global and local cache misses makes memory copies in bulk communication expensive relati to communication via shared memory. Second, although message passing has synchronization semantics superior to shared memory for data-driven computation, efficient shared memory can overcome this handicap by using global read-modify-writes to change from the traditional owner-computers model to a producer-computes model. Third, bulk transfers can result in high processor idle times in irregular applications.


SIMULATION ◽  
1969 ◽  
Vol 12 (2) ◽  
pp. 97-102 ◽  
Author(s):  
Richard Economy ◽  
George Burgin

The rotational acceleration for a rigid body has traditionally been represented by three simultaneous equations. Be cause of the computation time required for the iterative solution of simultaneous equations using a digital com puter, it is desirable to transform these equations to an explicit form for digital solution. The rotational equations are linear in the acceleration components. Thus, an explicit form can be obtained by either a determinate or a substi tution method. For problems where solution requires two or more of the cross-products-of-inertia terms, the determ inate method yields the most efficient equation form for digital solution. For the special case of body-plane sym metry (i.e., two cross-products-of-inertia terms are neg lected), the substitution method yields the most efficient form.


2017 ◽  
Vol 1 (1) ◽  
Author(s):  
La Ode Jabuddin ◽  
Ayub M Padangaran ◽  
Azhar Bafadal Bafadal

This study aims to: (1) Knowing the dynamics of fiscal policy and the performance of the agricultural sector, (2) Analyze the factors that influence fiscal policy and the performance                   of the agricultural sector, and (3) Analyzing the impact of fiscal policy on the performance of the agricultural sector. The data used in this study were pooled 2005-2013 data in the aggregate. Econometric model the impact of fiscal policy on the performance of the agricultural sector is built in the form of simultaneous equations, consisting of 7 equations with 25 total variables in the model, 7 endogenous variables, 12 exogenous variables, and 6 variables lag. The model is estimated by 2SLS method SYSLIN procedures and historical simulation with SIMNLIN procedure.The results showed that: (1) The development of fiscal policy in Southeast Sulawesi from year to year tends to increase, (2) The performance of the agricultural sector from the aspect of GDP has decreased, from the aspect of labor is still consistent, in terms of investment to grow positively, and assign roles which means to decrease the number of poor people, (3) factors affecting fiscal policy is local revenues, equalization funds, other revenues, as well as the lag fiscal policy, (4) the factors that affect the performance of the agricultural sector from the aspect GDP is labor, direct expenditure and GDP lag; from the aspect of labor is the total labor force, investment, land area, direct expenditure, as well as the lag of labor; from the aspect of investment is influenced by GDP per capita, land area, interest rates and investment lag; as well as from the aspect of poor people, are affected by population, investments, direct expenditure and poverty lag, (5). Fiscal policy impact on the agricultural sector GDP increase, a decrease in the number of poor, declining agricultural laborers, and a decrease in the amount of investment in the agricultural sector.Keywords: Fiscal policy, the performance of the agricultural sector, the simultaneous equations


Sign in / Sign up

Export Citation Format

Share Document