- Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are
- Low Power Microarchitecture with Instruction Reuse Frederico Pratas
- Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are
- Managing Leakage for Transient Data: Decay and Quasi-Static Memory Cells
- H : HitM : Miss Access Interval
- Abstract--Reducing the supply voltage to reduce dynamic power consumption in CMOS devices, inad-
- Improving Power Efficiency with an Asymmetric Set-Associative Cache
- We propose Instruction-based Prediction as a means to opti-mize directory-based cache coherent NUMA shared-memory.
- Abstract--The integration of memory on the same die as the processor (IRAM) has the potential to offer unprece-
- Copyright 1994-1996 IEEE. All rights reserved. This is an unapproved IEEE Standards Draft, subject to change. 1
- Widely shared data represent a serious threat to the scal-ability of shared-memory systems. The GLOW extensions
- IDENTIFICATION AND OPTIMIZATION OF SHARING PATTERNS FOR SCALABLE SHARED-MEMORY MULTIPROCESSORS
- Second Workshop on Programmability Issues for Multi-Core Computers
- Instruction-based Reuse-Distance Prediction for Effective Cache Management
- Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are
- High-speed routers often use commodity, fully-associative, TCAMs (Ternary Content Addressable
- TCP: Tag Correlating Prefetchers T.J. Watson Research Center
- Output dataSelect Comparators
- Dynamic Optimizations in Linda Systems Stefanos Kaxiras, Ioannis Schoinas
- Journal of Systems Architecture 46 (2000) 973-990, Elsevier Science B.V. Distributed Vector Architectures
- Journal of Systems Architecture 45 (1999) 1001-1022, Elsevier Science B.V. DataScalar: A Memory-Centric Approach to Computing
- DataScalar Architectures Doug Burger, Stefanos Kaxiras, and James R. Goodman
- Abstract--In this paper we argue that widely shared data are a more serious problem than previously recognized, and that furthermore, it is
- Kiloprocessor Extensions to SCI Stefanos Kaxiras
- IDENTIFICATION AND OPTIMIZATION OF SHARING PATTERNS FOR SCALABLE SHARED-MEMORY MULTIPROCESSORS
- Widely shared data represent a serious threat to the scal ability of sharedmemory systems. The GLOW extensions
- University of WisconsinMadison CS Technical Report 1368, April 1998 The Use of InstructionBased Prediction in Hardware Shared
- Abstract---In this paper we argue that widely shared data are a more serious problem than previously recognized, and that furthermore, it is
- Cache Decay: Exploiting Generational Behavior to Reduce Cache Leakage Power
- IPStash: A Set-Associative Memory Approach for Efficient IP-lookup
- DataScalar Architectures and the SPSD Execution Model Doug Burger, Stefanos Kaxiras, and James R. Goodman
- Abstract---The integration of memory on the same die as the processor (IRAM) has the potential to offer unprece
- We propose Instructionbased Prediction as a means to opti mize directorybased cache coherent NUMA sharedmemory.
- Abstract---Programs that make extensive use of widely shared var iables are expected to achieve modest speedups for nonbusbased
- DataScalar Architectures and the SPSD Execution Model Doug Burger, Stefanos Kaxiras, and James R. Goodman
- Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are
- Dynamic Dictionary-Based Data Compression for Level-1 Caches
- MLP-aware Instruction Queue Resizing: The Key to Power-Efficient Performance
- Modeling Cache Sharing on Chip Multiprocessor Architectures Pavlos Petoumenos,1
- Coherence Communication Prediction in Shared-Memory Multiprocessors Stefanos Kaxiras and Cliff Young
- DataScalar Architectures Doug Burger, Stefanos Kaxiras, and James R. Goodman
- UW CS TR-1339 Feb. 1997 Distributed Vector Architecture: Fine Grain Parallelism with
- Improving Cache Power Eciency with an Asymmetric Set-Associative Zhigang Hu and Margaret Martonosi
- DSPw orld, many mediaw orkloads have to perform a
- UW CS TR1339 Feb. 1997 Distributed Vector Architecture: Fine Grain Parallelism with
- Copyright 19941996 IEEE. All rights reserved. This is an unapproved IEEE Standards Draft, subject to change. 1
- Journal of Systems Architecture 46 (2000) 973990, Elsevier Science B.V. Distributed Vector Architectures
- In the DSP world, many media workloads have to perform a specific amount of work in a specific period of time. This
- Abstract---Reducing the supply voltage to reduce dynamic power consumption in CMOS devices, inad
- Simultaneous Multithreaded DSPs: Scaling from High Performance to Low Power
- Timekeeping in the Memory System: Predicting and Optimizing Memory Behavior
- Coherence Communication Prediction in SharedMemory Multiprocessors Stefanos Kaxiras and Cliff Young
- Kiloprocessor Extensions to SCI + Stefanos Kaxiras #
- Simultaneous Multithreaded DSPs: Scaling from High Performance to Low Power
- Journal of Systems Architecture 45 (1999) 10011022, Elsevier Science B.V. DataScalar: A MemoryCentric Approach to Computing
- Cache Decay: Exploiting Generational Behavior to Reduce Cache Leakage Power
- University of Wisconsin-Madison CS Technical Report 1368, April 1998 The Use of Instruction-Based Prediction in Hardware Shared-
- Abstract--Programs that make extensive use of widely shared var-iables are expected to achieve modest speedups for non-bus-based
