Engineering Papers⌕ Search

Engineering topics

Bethel, Edward W

Publications and source records attributed to Bethel, Edward W.

Using wesBench to Study the Rendering Performance of Graphics Processing Units

Graphics operations consist of two broad operations. The first, which we refer to here as vertex operations, consists of transformation, lighting, primitive assembly, and so forth. The second, which we refer to as pixel or fragment operations, consist of rasterization, texturing, scissoring, blending, and fill. Overall GPU rendering performance is a function of throughput of both these interdependent stages: if one stage is slower than the other, the faster stage will be forced to run more slowly and overall rendering performance will be adversely affected. This relationship is commutative: if the later stage has a greater workload than the earlier stage, the earlier stage will be forced to 'slow down.' For example, a large triangle that covers many screen pixels will incur a very small amount of work in the vertex stage while at the same time incurring a relatively large amount of work in the fragment stage. Rendering performance of a scene consisting of many large-area triangles will be limited by throughput of the fragment stage, which will have relatively more work than the vertex stage. There are two main objectives for this document. First, we introduce a new graphics benchmark, wesBench, which is useful for measuring performance of both stages of the rendering pipeline under varying conditions. Second, we present its methodology for measuring performance and show results of several performance measurement studies aimed at producing better understanding of GPU rendering performance characteristics and limits under varying configurations. First, in Section 2, we explore the 'crossover' point between geometry and rasterization. Second, in Section 3, we explore additional performance characteristics, some of which are ill- or un-documented. Lastly, several appendices provide additional material concerning problems with the gfxbench benchmark, and details about the new wesBench graphics benchmark.

97 MATHEMATICS AND COMPUTING↗

Occam's Razor and Petascale Visual Data Analysis

One of the central challenges facing visualization research is how to effectively enable knowledge discovery. An effective approach will likely combine application architectures that are capable of running on today?s largest platforms to address the challenges posed by large data with visual data analysis techniques that help find, represent, and effectively convey scientifically interesting features and phenomena.

97 MATHEMATICS AND COMPUTING↗

Bin-Hash Indexing: A Parallel Method for Fast Query Processing

This paper presents a new parallel indexing data structure for answering queries. The index, called Bin-Hash, offers extremely high levels of concurrency, and is therefore well-suited for the emerging commodity of parallel processors, such as multi-cores, cell processors, and general purpose graphics processing units (GPU). The Bin-Hash approach first bins the base data, and then partitions and separately stores the values in each bin as a perfect spatial hash table. To answer a query, we first determine whether or not a record satisfies the query conditions based on the bin boundaries. For the bins with records that can not be resolved, we examine the spatial hash tables. The procedures for examining the bin numbers and the spatial hash tables offer the maximum possible level of concurrency; all records are able to be evaluated by our procedure independently in parallel. Additionally, our Bin-Hash procedures access much smaller amounts of data than similar parallel methods, such as the projection index. This smaller data footprint is critical for certain parallel processors, like GPUs, where memory resources are limited. To demonstrate the effectiveness of Bin-Hash, we implement it on a GPU using the data-parallel programming language CUDA. The concurrency offered by the Bin-Hash index allows us to fully utilize the GPU's massive parallelism in our work; over 12,000 records can be simultaneously evaluated at any one time. We show that our new query processing method is an order of magnitude faster than current state-of-the-art CPU-based indexing technologies. Additionally, we compare our performance to existing GPU-based projection index strategies.

97 MATHEMATICS AND COMPUTING↗

Seeing the Unseeable

The SciDAC Visualization and Analytics Center for Enabling Technologies (VACET) isa highly productive effort combining the forces of leading visualization researchersfrom five different institutions to solve some of the most challenging dataunderstanding problems in modern science. The VACET technology portfolio isdiverse, spanning all typical visual data analysis use models and effectivelybalancing forward-looking research with focused software architecture andengineering resulting in a production-quality software infrastructure. One of the keyelements in VACET's success is a rich set of projects that are collaborations withscience stakeholders: these efforts focus on identifying and overcoming obstacles toscientific knowledge discovery in modern, large, and complex scientific datasets.

97 MATHEMATICS AND COMPUTING↗