In: Other Topics

Submitted By raft62
Words 1250
Pages 5
Geology – Earthquakes I chose to do my assignment on earthquakes, because I have been through many growing up in California, and I have always wondered about them. There are many types of earthquakes. The most common are tectonic, which my paper will be about. There are also volcanic, collapse and explosion earthquakes. All earthquakes create waves that travel through the Earth's interior. An earthquake is the sudden shifting of the earth's natural means of releasing stress. When the shifting occurs, it creates vibrations, called seismic waves. The speed of seismic waves depends on the elasticity of the materials through which they are traveling. Rocks have elastic properties. When forces are applied to rocks, such as pulling, pushing, twisting, or compression, they change their shape. Rocks like other materials with elastic properties have an elastic limit,any additional force will deform the object's shape. The elasticity of a material is controlled by its density and stiffness. There are three types of waves that are created when stress is released as energy in earthquakes. Primary waves or P-waves, is the fastest, and the first detected by seismographs. They are able to move through both liquid and solid rock. P-waves are like sound waves; they are compressed and expand matter as they move through it. Secondary waves or S-waves, are the waves directly following the P-waves, they are transverse waves. As they move, S-waves cut the rock they travel through sideways at right angles to the direction of motion. S-waves can't travel through liquid, and they are the most dangerous type of waves, because they are larger than P-waves, and produce vertical and horizontal motion in the ground surface. Another name for P and S waves is body waves. There are also two types of surface waves, rayleighwaves and love waves. Rayleigh waves move both horizontally and…...

Similar Documents

Adv Comparch

...16K 32K 32K 64K associativity (dc/ic) 2 4 4 8 4 64K 8 Με τις προσομοιώσης και με τους τύπους που προαναφέρθηκαν υπολογίσαμε τα ipc για κάθε ζητούμενη ιεραρχία μνήμης και κάναμε τη γραφική(οι μετρήσεις μετά από κάθε ζητούμενο): IPC # art 1 0.045074 2 0.044773 3 0.044509 4 0.044460 gzip 0.135081 0.135202 0.135994 0.136015 mcf 0.074851 0.075072 0.075395 0.075420 equake 0.121923 0.122304 0.122627 0.122643 5 0.044464 0.137202 0.076103 0.122800 6 0.044464 0.137208 0.076056 0.122820 Για να γίνει όμως πιο κατανοητό το τι σημαίνουν αυτές οι μεταβολές παραθέτουμε τη βελτιωση % σε σχέση με την πρώτη ιεραρχία μνήμης: IPC improvement% Ακολουθεί η γραφικη για το dc_miss_rate Και οι αντίστοιχες μετρήσεις: # 1 2 3 4 5 6 art 0.250169 0.251383 0.213636 0.213695 0.212731 0.212659 gzip mcf equake 0.066665 0.186052 0.035207 0.066547 0.183907 0.032961 0.057635 0.174644 0.031160 0.057119 0.173539 0.031146 0.047042 0.158395 0.029751 0.046935 0.159030 0.029571 Στη συνέχεια η γραφική για τo ic_miss_rate Kαι οι αντίστοιχες μετρήσεις: # 1 2 3 4 5 6 art gzip mcf equake 0.000074 0.000105 0.000215 0.000161 0.000011 0.000038 0.000016 0.000100 0.000003 0.000006 0.000004 0.000006 0.000002 0.000005 0.000003 0.000005 0.000000 0.000001 0.000001 0.000002 0.000000 0.000001 0.000001 0.000002 Συμπεράσματα:Παρατηρούμε ότι το IPC όσο αυξάνεται το μέγεθος της μνήμης αυξάνεται αισθητά.Επιπλέον παρατηρούμε μια μικρότερη αύξηση στο ipc όσον αφορά την......

Words: 3991 - Pages: 16

Pentium 4

...is shown in Figure 1. The benchmarks we use for our experiments are from the SPEC 2000 benchmark suite. The integer benchmarks are crafty, bzip2, gcc, mcf, and parser. The floating point benchmarks are ammp, art, and equake. Power measurements are taken from the beginning of the benchmark run to completion. Each result shown represents an average of 3 consecutive runs of the benchmark. For a given benchmark, the variation of total energy during the 3 runs ranged from .5% (best case) to 1.0% (worst case). We use one compiler in this study. The compiler is the Intel C++ compiler v.6.0.1 for Linux. This is an advanced compiler featuring many levels of optimization. Each of the flags used in the study are documented in [4]. The compiler provides support for the additional x86 instructions available on the Pentium 4 and contains optimizations targeting the Pentium 4 pipeline. 4. Results We categorize the flags controlling the compiler optimizations as either general or specific. The general opti- Proceedings of the Seventh Workshop on Interaction between Compilers and Computer Architectures (INTERACT’03) 0-7695-1889-03/03 $17.00 © 2003 IEEE 2.5 O0 2 normalized energy O1 O3 xW 1.5 ip/ipo prof_gen/use 1 0.5 0 crafty parser mcf vortex gcc bzip2 art ammp equake average Figure 2. Normalized total energy usage mization flags are those flags which enable a set of compiler optimizations. These flags are used to simplify compilation by enabling a group of optimizations......

Words: 4099 - Pages: 17

A Survey of Checkpointing Strategies for Shared-Memory Hpc Applications

...OMP Benchmarks The SPEC OMP benchmark suite was developed by the SPEC High Performance Group for performance testing of shared memory systems. It used the OpenMP versions of SPEC CPU2000 benchmarks and candidates. The benchmark suite has OMPM2001 for medium and OMPL2001 for large compute intensive applications. OMPM2001 has 9 applications which are written in Fortran and 2 that are written in C. The applications are listed below: • 310.wupwise m - this application is used for Quantum Chromodynamics • 312.swim m - Shallow water modelling • 314.mgrid m - Multi-grid solver in 3D potential field • 316.applu m - Parabolic/elliptic partial differential equations • 318.galgel m - Analysis of oscillatory instability(Fluid Dynamics) 19 • 320.equake m - Finite element simulation for earthquake modelling • 324.apsi m - Distribution of various pollutants • 326.gafort m - Genetic Algorithm • 328.fma3d m - Finite element crash simulation • 330.art m - Neural network simulation • 332.ammp m - Computational chemistry 8 Pattern analysis By investigating the code manually, we extracted possible memory access patterns from all 8 applications and kernels. We measured the number of synchronisation and worksharing constructs in the applications. 1. Loop parallelization The normal loop parallelizations, for and do, where each thread operated on a sub-set of entries from an array. Here the program is non-deterministic within the loop since the threads may execute in any order. However,......

Words: 7288 - Pages: 30