Scratchpad memory: a design alternative for cache on-chip memory in embedded systems

By R. Banakar, S. Steinke, Bo-Sik Lee, M. Balakrishnan, Peter Marwedel. Proceedings of the Tenth International Symposium on Hardware/Software Codesign. CODES 2002 (IEEE Cat. No.02TH8627), 2002

795 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/5f839747993a7a412fcccd159bca9962c7cc72e4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

1. Luca Benini
2. Frank Kagan Gürkaynak
3. Michael Franz
4. Vasanth Venkatachalam
5. Davide Rossi
6. Eric Flamand
7. Giovanni De Micheli
8. Srinivasan Murali

In Hardware and Architecture

1. Luca Benini
2. Igor Loi
3. Frank Kagan Gürkaynak
4. Björn B. Brandenburg
5. Derek M. Jones
6. Giovanni De Micheli
7. Srinivasan Murali
8. Yonggang Wen

Citations in the corpus

• A near-threshold RISC-V core with DSP extensions for scalable IoT Endpoint Devices (2016, background): “…manages transfers between IO and L2 memory and the shared TCDM. Data access pattern predictability of key application kernels, the relatively low clock frequency target and the tightly constrained area and power budget make a shared TCDM preferable over a collection of coherent private caches[9].”
• Scheduling and locking in multiprocessor real-time operating systems (2011, background): “An alternative to caches are scratchpad memories (also called programmable caches), which function similarly to a cache in that they speed up memory references (Banakar et al., 2002).”
• Near-Threshold RISC-V Core With DSP Extensions for Scalable IoT Endpoint Devices (2017, positive): “Data access pattern predictability of key application kernels, the relatively low clock frequency target, and the tightly constrained area and power budget make a shared TCDM preferable over a collection of coherent private caches [9].”
• Power reduction techniques for microprocessor systems (2005, background): “In embedded systems, scratch pad memories [Panda et al. 2000; Banakar et al. 2002; Kandemir et al. 2002] have been the extension of choice.”
• An optimal memory allocation scheme for scratch-pad-based embedded systems (2002, methodology): “Even more surprising, the runtime measured in cycles was 18% better with a scratch pad when using a simple knapsack-based allo­cation algorithm [Banakar et al. 2002].”