Hobbit: a high-performance, low-power microprocessor

Argade, Pramod V.; Aymeloglu, S.; Berenbaum, Alan D.; DePaolis, Michael V.; Franzo, R.T.; Freeman, R.D.; Inglis, D.; Komoriya, G.; Lee, H.; Little, T.R.; MacDonald, G.; McLellan, Hubert R.; Morgan, E.C.; Pham, H.; Ronkin, G.D.; Scavuzzo, R. J.; Woch, T.J.

doi:10.1109/cmpcon.1993.289642

Cited by 18 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The energy consumption in doze mode is about 1000 times less than that in active mode (Argade et al, 1993). The index on wireless broadcast data stream enables the mobile unit to remain in doze mode when it need not read the broadcast data.…”

Section: Introductionmentioning

confidence: 90%

An index replication scheme for wireless data broadcasting

Chung

Kim

2000

Journal of Systems and Software

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 90%

An index replication scheme for wireless data broadcasting

Chung

Kim

2000

Journal of Systems and Software

View full text Add to dashboard Cite

“…However, as circuit designers become more concerned about reducing energy consumption, switching energy will become less dominant and in our experiments we don't take it into account. The energy consumption in doze mode is about 1000 times less than that in active mode [3]. In order to evaluate energy consumption we set: E active = 1000 and E doze = 1 energy unit.…”

Section: B Energy Consumption Modelmentioning

confidence: 99%

Distributed Skip Air Index for smart broadcasting in intelligent transportation systems

Μαγλαράς

Katsaros

2012

2012 IEEE Intelligent Vehicles Symposium

View full text Add to dashboard Cite

Wireless data broadcast received a lot of attention from industries and academia in recent years. In any form of a push-based broadcast, access latency and tuning time are vital issues, and in order to address the tradeoff among these competing goals, the broadcasting of indices along with the data is the most viable solution. Currently, two broad indexing families exist: those that exploit some form of a tree structure, and those that are based on some 'distributed access on the air' mechanism. The latter family is the most popular and viable, because it allows for following 'air-pointers' without the need to first find a tree root. The champion method of the distributed air index is the Exponential index which however is not appropriate when the access pattern is skewed, i.e., some data items are more popular than the others. To address this shortcoming, we design a Distributed Skip Air Index (DiSAIn), which exploits access statistics in order to improve average tuning time, while it preserves the access latency equal to that of the original Exponential index. To attest the superiority of the proposed indexing method, we perform a detailed simulation evaluation of the two competing methods.

show abstract

“…Thus, unlike RISC processors, Hobbit has variable length instructions: 2-byte, 6-byte and 10-byte [2]. Table 5 summarizes dynamic usage of these instructions obtained from HINT.…”

Section: Instruction Set Analysismentioning

confidence: 99%

A technique for monitoring run-time dynamics of an operating system and a microprocessor executing user applications

Argade

Charles

Taylor³

1994

SIGPLAN Not.

View full text Add to dashboard Cite

In this paper, we present a non-invasive and efficient technique for simulating applications complete with their operating system interaction. The technique involves booting and initiating an application on a hardware development system, capturing the entire state of the application and the microprocessor at a well defined point in execution and then simulating the application on microprocessorsimulators. Extensive statistics generated from the simulators on run-time dynamics of the application, the operating system as well as the microprocessor enabled us to tune the operating system and the microprocessor architecture and implementation.The results also enabled us to optimize system level design choices by anticipating/ predicting the performance of the target system. Lastly, the results were used to adjust and refocus the evolution of the architecture of both the operating system and the microprocessor.

show abstract

Hobbit: a high-performance, low-power microprocessor

Cited by 18 publications

References 4 publications

An index replication scheme for wireless data broadcasting

An index replication scheme for wireless data broadcasting

Distributed Skip Air Index for smart broadcasting in intelligent transportation systems

A technique for monitoring run-time dynamics of an operating system and a microprocessor executing user applications

Contact Info

Product

Resources

About