A consistency-free memory architecture for sort-last parallel rendering processors

Woo Chan Park, Cheong Ghil Kim, Duk Ki Yoon, Kil Whan Lee, Il San Kim, Tack Don Han

Research output: Contribution to journalArticle

Abstract

Current rendering processors are aiming to process triangles as fast as possible and they have the tendency of equipping with multiple rasterizers to be capable of handling a number of triangles in parallel for increasing polygon rendering performance. However, those parallel architectures may have the consistency problem when more than one rasterizer try to access the data at the same address. This paper proposes a consistency-free memory architecture for sort-last parallel rendering processors, in which a consistency-free pixel cache architecture is devised and effectively associated with three different memory systems consisting of a single frame buffer, a memory interface unit, and consistency-test units. Furthermore, the proposed architecture can reduce the latency caused by pixel cache misses because the rasterizer does not wait until cache miss handling is completed when the pixel cache miss occurs. The experimental results show that the proposed architecture can achieve almost linear speedup upto four rasterizers with a single frame buffer.

Original languageEnglish
Pages (from-to)272-284
Number of pages13
JournalJournal of Systems Architecture
Volume53
Issue number5-6
DOIs
Publication statusPublished - 2007 May 1

Fingerprint

Memory architecture
Pixels
Data storage equipment
Parallel architectures
Interfaces (computer)
Computer systems

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture

Cite this

Park, Woo Chan ; Kim, Cheong Ghil ; Yoon, Duk Ki ; Lee, Kil Whan ; Kim, Il San ; Han, Tack Don. / A consistency-free memory architecture for sort-last parallel rendering processors. In: Journal of Systems Architecture. 2007 ; Vol. 53, No. 5-6. pp. 272-284.
@article{98a11160c4b944d4b67fc47662fde429,
title = "A consistency-free memory architecture for sort-last parallel rendering processors",
abstract = "Current rendering processors are aiming to process triangles as fast as possible and they have the tendency of equipping with multiple rasterizers to be capable of handling a number of triangles in parallel for increasing polygon rendering performance. However, those parallel architectures may have the consistency problem when more than one rasterizer try to access the data at the same address. This paper proposes a consistency-free memory architecture for sort-last parallel rendering processors, in which a consistency-free pixel cache architecture is devised and effectively associated with three different memory systems consisting of a single frame buffer, a memory interface unit, and consistency-test units. Furthermore, the proposed architecture can reduce the latency caused by pixel cache misses because the rasterizer does not wait until cache miss handling is completed when the pixel cache miss occurs. The experimental results show that the proposed architecture can achieve almost linear speedup upto four rasterizers with a single frame buffer.",
author = "Park, {Woo Chan} and Kim, {Cheong Ghil} and Yoon, {Duk Ki} and Lee, {Kil Whan} and Kim, {Il San} and Han, {Tack Don}",
year = "2007",
month = "5",
day = "1",
doi = "10.1016/j.sysarc.2006.10.010",
language = "English",
volume = "53",
pages = "272--284",
journal = "Journal of Systems Architecture",
issn = "1383-7621",
publisher = "Elsevier",
number = "5-6",

}

A consistency-free memory architecture for sort-last parallel rendering processors. / Park, Woo Chan; Kim, Cheong Ghil; Yoon, Duk Ki; Lee, Kil Whan; Kim, Il San; Han, Tack Don.

In: Journal of Systems Architecture, Vol. 53, No. 5-6, 01.05.2007, p. 272-284.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A consistency-free memory architecture for sort-last parallel rendering processors

AU - Park, Woo Chan

AU - Kim, Cheong Ghil

AU - Yoon, Duk Ki

AU - Lee, Kil Whan

AU - Kim, Il San

AU - Han, Tack Don

PY - 2007/5/1

Y1 - 2007/5/1

N2 - Current rendering processors are aiming to process triangles as fast as possible and they have the tendency of equipping with multiple rasterizers to be capable of handling a number of triangles in parallel for increasing polygon rendering performance. However, those parallel architectures may have the consistency problem when more than one rasterizer try to access the data at the same address. This paper proposes a consistency-free memory architecture for sort-last parallel rendering processors, in which a consistency-free pixel cache architecture is devised and effectively associated with three different memory systems consisting of a single frame buffer, a memory interface unit, and consistency-test units. Furthermore, the proposed architecture can reduce the latency caused by pixel cache misses because the rasterizer does not wait until cache miss handling is completed when the pixel cache miss occurs. The experimental results show that the proposed architecture can achieve almost linear speedup upto four rasterizers with a single frame buffer.

AB - Current rendering processors are aiming to process triangles as fast as possible and they have the tendency of equipping with multiple rasterizers to be capable of handling a number of triangles in parallel for increasing polygon rendering performance. However, those parallel architectures may have the consistency problem when more than one rasterizer try to access the data at the same address. This paper proposes a consistency-free memory architecture for sort-last parallel rendering processors, in which a consistency-free pixel cache architecture is devised and effectively associated with three different memory systems consisting of a single frame buffer, a memory interface unit, and consistency-test units. Furthermore, the proposed architecture can reduce the latency caused by pixel cache misses because the rasterizer does not wait until cache miss handling is completed when the pixel cache miss occurs. The experimental results show that the proposed architecture can achieve almost linear speedup upto four rasterizers with a single frame buffer.

UR - http://www.scopus.com/inward/record.url?scp=33947316920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947316920&partnerID=8YFLogxK

U2 - 10.1016/j.sysarc.2006.10.010

DO - 10.1016/j.sysarc.2006.10.010

M3 - Article

AN - SCOPUS:33947316920

VL - 53

SP - 272

EP - 284

JO - Journal of Systems Architecture

JF - Journal of Systems Architecture

SN - 1383-7621

IS - 5-6

ER -