Browsing LCS Technical Memos (1974 - 2003) by Author "Lee, Walter"
Now showing items 1-7 of 7
-
How to Build Scalable On-Chip ILP Networks for a Decentralized Architecture
(2000-04)The era of billion transistors-on-a-chip is creating a completely different set of design constraints, forcing radically new microprocessor archiecture designs. This paper examines a few of the possible microarchitectures ... -
Maps: a Compiler-Managed Memory System for RAW Machines
(1998-07)Microprocessors of the next decade and beyond will be built using VLSI chips employing billions of transistors. In this generation of microprocessors, achieving a high level of parallelism at a reasonable clock speed will ... -
A Software Framework for Supporting General Purpose Applications on RAW Computation Fabrics
(2001-07)This paper presents SUDS (Software Un-Do Systems), a data speculation system for Raw processors. SUDS manages specultation in software. Thekey to managing speculation in software is to use the compiler to minimize the ... -
Space - Time Scheduling of Instruction-Level Parallelism on a Raw Machine
(1997-12)Advances in VLSI technology will enable chips with over a billion transistors within the next decade. Unfortunately, the centralized-resource architectures of modern microprocessors are ill-suited to exploit such advances. ... -
Strength Reduction of Integer Division and Modulo Operations
(1999-11)Integer division, modulo, and remainder operations are expressive and useful operations. They are logical candidates to express complex data accesses such as the wrap-around behavior in queues using ring buffers, array ... -
A Theoretical and Practical Approach to Instruction Scheduling on Spatial Architectures
(2002-12)This paper studies the problem of instruction assignment and scheduling on spatial architectures. Spatial architectures are architectures whose resources are organized in clusters, with non-zero communication delays between ... -
UDM: User Direct Messaging for General-Purpose Multiprocessing
(1996-03)User Direct Messaging (UDM) allows user-level, processor-to- processor messaging to coexist with general multiprogramming and virtual memory. Direct messaging, where processors launch and receive messages in tens of cycles ...
