Abstract

General purpose programming on the graphics processing units (GPGPU) has received a lot of attention in the parallel computing community as it promises to offer the highest performance per dollar. The GPUs have been used extensively on regular problems that can be easily parallelized. In this paper, we describe two implementations of List Ranking, a traditional irregular algorithm that is difficult to parallelize on such massively multi-threaded hardware. We first present an implementation of Wyllie's algorithm based on pointer jumping. This technique does not scale well to large lists due to the suboptimal work done. We then present a GPU-optimized, Recursive Helman-JaJa (RHJ) algorithm. Our RHJ implementation can rank a random list of 32 million elements in about a second and achieves a speedup of about 8-9 over a CPU implementation as well as a speedup of 3-4 over the best reported implementation on the Cell Broadband engine. We also discuss the practical issues relating to the implementation of irregular algorithms on massively multi-threaded architectures like that of the GPU. Regular or coalesced memory accesses pattern and balanced load are critical to achieve good performance on the GPU.

Abstract

An acyclic vertex coloring of a graph is a proper vertex coloring such that there are no bichromatic cycles. The acyclic chromatic number of G, denoted a (G), is the minimum number of colors required for acyclic vertex coloring of graph G=(V, E). In this paper we show that for any graph G with maximum degree∆, a (G)≤ 3∆ 2+ 4∆+ 8

Abstract

The significant growth in computational power of modern Graphics Processing Units (GPUs) coupled with the advent of general purpose programming environments like NVIDIA's CUDA, has seen GPUs emerging as a very popular parallel computing platform. Till recently, there has not been a performance model for GPGPUs. The absence of such a model makes it difficult to definitively assess the suitability of the GPU for solving a particular problem and is a significant impediment to the mainstream adoption of GPUs as a massively parallel (super)computing platform. In this paper we present a performance prediction model for the CUDA GPGPU platform. This model encompasses the various facets of the GPU architecture like scheduling, memory hierarchy, and pipelining among others. We also perform experiments that demonstrate the effects of various memory access strategies. The proposed model can be used to analyze pseudo code for a CUDA kernel to obtain a performance estimate, in a way that is similar to performing asymptotic analysis. We illustrate the usage of our model and its accuracy with three case studies: matrix multiplication, list ranking, and histogram generation.

Abstract

In this paper, we discuss the numerical modeling of infinite media using transmitting boundary condition. This is done for simulating the propagation of elastic waves in soil media. Wave interaction with different kinds of boundaries is discussed explaining the numerical modeling procedure. Wave propagation in different directions is studied while calculating the velocities in different soil domain. For investigating the above-mentioned objectives, we used newly developed numerical model, viz., Applied Element Method and compared our results with Finite Element Method (FEM).

Abstract

Earthquake problems in India need no introduction. Some of the great earthquakes of the world occurred in India and neighborhood areas. During past two decades, India has witnessed 7 moderate earthquakes which caused large number of casualties and innumerable property loss. Most of these losses are due to poor quality of construction and generally low level of awareness of the earthquake hazard prevalent in the country. In this regard, there is a need for coordinated and sustained effort towards earthquake risk reduction in the country. This can be achieved through education and awareness building.

Abstract

Pipelines are common transportation means for oil and natural gas, which act as an important lifeline facility for any nation. Often the design of these pipelines is a difficult task because they commonly are installed underground passing through different types of soil media. Many of these existing pipelines run through the faulted area, which continuously exposed to considerable risk of failure due to movement along the fault. Installation and maintenance costs of these pipelines directly depend on the total length of the pipelines. Furthermore ideal alignment for any pipeline as a straight line between the source and destination point is not that easy in the area where fault are present. It becomes necessary to divert the alignment about fault line which increases the length and subsequently operational and installation costs of pipeline. Common problems seen in the pipeline crossing the fault are change of alignment due to movement along the fault.

Abstract

This paper presents the detailed seismic hazard assessment of the peninsular India (lat. 8-28N and long. 67.5-90E) which is considered to be seismically most stable landmasses of the Indian plate. Past seismic history in this region (Koyna, 10 December 1967; Bhadrachalam, 13 April 1969; Broach, 23 March 1970; Hyderabad, 30 June 1983; Latur, 30 September 1993; Jabalpur, 22 May 1997; Bhuj, 26 January 2001 etc) clearly shows that the seismicity of the area is varying. There were more than five damaging earthquakes with magnitudes greater than Mw 6.0 have occurred in this region, stressing the importance of detailed seismic hazard assessment for the region. For India, Bhatia et al. (1999) published a probabilistic seismic hazard map based on several well identified and prominent source zones in the country. An attempt has been made in this paper to study the present seismic status of this region incorporating the seismicity, tectonic and geological characteristics and using the collected earthquake data Peak Ground Acceleration was estimated using the attenuation relation developed by Iyengar and Raghukanth (2004). Estimated PGA values were used to compute the deviation with respect to assigned PGA values for various regions provided in Indian Standard code IS 1893:2002. The results show that, the estimated PGA in many areas of the Peninsular India is more than the specified value in the current seismic macrozonation map of the country. This provides an important basis for attempting the detailed microzonation of an area within the Penisular India. Key words: Seismic hazard, Peak ground acceleration (PGA), Peninsular India, Seismiczonation

Abstract

This paper present detailed seismic hazard assessment of the peninsular india which is considered to be seismically most stable landmasses of the indian plate. Past seismic history in this region clearly shows that the seismicity of the area is varying. There were more than five damaging earthquakes with magnitude greater than 6 have occurred in this region stressing the importance of detailed seismic hazard assessment for the region.

Abstract

This paper presents the detailed seismic hazard assessment of the peninsular India (lat. 8°-28°N and long. 67.5°-90°E) which is considered to be seismically most stable landmasses of the Indian plate. Past seismic history in this region (Koyna, 10 December 1967; Bhadrachalam, 13 April 1969; Broach, 23 March 1970; Hyderabad, 30 June 1983; Latur, 30 September 1993; Jabalpur, 22 May 1997; Bhuj, 26 January 2001 etc) clearly shows that the seismicity of the area is varying. There were more than five damaging earthquakes with magnitudes greater than Mw 6.0 have occurred in this region, stressing the importance of detailed seismic hazard assessment for the region. For India, Bhatia et al. (1999) published a probabilistic seismic hazard map based on several well identified and prominent source zones in the country. An attempt has been made in this paper to study the present seismic status of this region incorporating the seismicity, tectonic and geological characteristics and using the collected earthquake data Peak Ground Acceleration was estimated using the attenuation relation developed by Iyengar and Raghukanth (2004). Estimated PGA values were used to compute the deviation with respect to assigned PGA values for various regions provided in Indian Standard code IS 1893:2002. The results show that, the estimated PGA in many areas of the Peninsular India is more than the specified value in the current seismic macrozonation map of the country. This provides an important basis for attempting the detailed microzonation of an area within the Penisular India.

Abstract

Indian Subcontinent is one of the seismically active regions of the world. The seismicity of India can be divided into 4 groups: Himalayan Region, Indo-Gangetic Plain, Kutch-Kathiawar Region and the Peninsular India (Ref EU Report 2003). Himalayas are one of the rare sites of continent to continent collision and also tectonically very active belt. The high seismicity of the region can be observed from the past events occurred in the region as shown in Figure.1. Depending on the past earthquakes, Bureau of Indian Standards has prepared the Seismic Zonation map of India (IS-1893-2002), which divides the country into 4 different zones. As per the zonation map 57% land of the country falls under high seismic zone. These maps do not consider the frequency of occurrence of earthquakes; hence they do not divide the country into regions of equal hazard and risk. For cultural heritage and other important structures, these maps act only as a guideline for the expected intensities. For those structures, site specific seismic hazard maps have to be generated specially for use. Rigorous quantifications of seismic hazard in detail for the Delhi region have not been carried out so far. Chouhan (Proc.INSA) estimated the focal depth of earthquake around Delhi to be about 8 km. His frequency-magnitude analyses lead to the conclusion that the maximum size of an earthquake that may occur in this region would be 7.6. The work of Srivastav and Roy (1982) indicates that in a period of 50 years a magnitude 6 earthquakes are almost certain and that there is 80% probability of a 7 magnitude event visiting the region. Khattri (1992) has carried out an exercise estimating the seismic hazard for the northern region of the country. According to this study in a fifty year window of 1983 - 2033, the peak ground accelerations around Delhi would be 0.2 g with 10% probability of exceedence. Delhi and its environs have not yet experienced this level of ground vibration in the above time period. Even if these estimates need further refinement they indicate the nature of events expected for Delhi city (Iyengar, 2000). Keeping in view all these studies, the effect of any future earthquake in Delhi region is studied in this paper.