Accelerated Ray Tracing on the KSR 1 Virtual Shared - Memory Parallel Computer

نویسنده

  • R. J. Hubbold
چکیده

This report describes the results of experiments with accelerated ray tracing on a virtual shared-memory parallel computer. The machine used, the Kendall Square Research KSR1, is described in sufficient detail for its novel features to be appreciated. The report describes a new ray tracer written specifically to capitalise on the KSR1’s features. Models used in the experiments include well-known test cases from the Haines database, permitting comparison with previously reported results. The results show a speed-up which is 76.9% of linear scaling on 256 processors. The report analyses the performance of the software and draws conclusions about the suitability of this type of machine for image synthesis.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Interactive Ray Tracing on a Virtual Shared-Memory Parallel Computer

This paper describes the results of experiments with accelerated ray tracing on a virtual shared-memory parallel computer and attempts to determine whether this kind of architecture would be suitable for an interactive ray tracing system. The machine used, the Kendall Square Research KSR1, is described in sufficient detail for its novel features to be appreciated. The paper describes a new ray ...

متن کامل

1 An Efficient Parallel Ray Tracing Scheme for Highly Parallel Architectures

The production of realistic image generated by computer requires a huge amount of computation and a large memory capacity. The use of highly parallel com­ puters allows this process to be performed faster. Distributed memory parallel computers (DMPCs), such as hypercubes or transputer-based machines, offer an attractive perfor­ mance/cost ratio when the load balancing has been balance and the p...

متن کامل

An Efficient Parallel Ray Tracing Scheme for Highly Parallel Architectures

The production of realistic image generated by computer requires a huge amount of computation and a large memory capacity. The use of highly parallel computers allows this process to be performed faster. Distributed memory parallel computers (DMPCs), such as hypercubes or transputer-based machines, ooer an attractive performance/cost ratio when the load balancing has been balance and the partit...

متن کامل

Virtual Shared Memory and Distributed Memory Implementations of Parallel Algorithms for Numerical Integration

Parallel globally adaptive algorithms for numerical integration provide a simple example of algorithms that exploit control parallelism. In this paper we consider the implementation of such algorithms on both virtual shared memory (KSR-1) and distributed memory (iPSC/860) machines and investigate how the characteristics of the diierent architectures aaect the choice of implementation and thereb...

متن کامل

Fast Implicit Kd-trees: Accelerated Isosurface Ray Tracing and Maximum Intensity Projection for Large Scalar Fields

Many scientific data sets are 3D or 4D scalar fields, for which typically isosurfaceand volume visualization methods are used to extract information. These data sets are either massively complex (e.g., seismic data sets), or steadily increasing in size due to the permanently improving resolutions of different 3D scanners (e.g., CTand MRTscanners) or calculation results (e.g., CFD-simulations). ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1994