• Corpus ID: 14506526

A Study of Out-of-Order Completion for the MIPS R10K Superscalar Processor

@inproceedings{Mishra2001ASO,
  title={A Study of Out-of-Order Completion for the MIPS R10K Superscalar Processor},
  author={Prabhat Mishra and Nikil D. Dutt and Alex Nicolau pmishra},
  year={2001}
}
Instruction level parallelism (ILP) improves performance for VLIW, EPIC, and Superscalar processors. Out-of-order execution improves performance further. The advantage of out-of-order execution is not fully utilized due to in-order completion. In this report we study the performance loss due to in-order completion for MIPS R10000 processor. 

Figures and Tables from this paper

SEESAW: Using Superpages to Improve VIPT Caches
TLDR
SEESAW dynamically reduces the number of ways that are looked up based on the page size, improving performance and energy.
Baseline VIPT Cache Parameters ( d ) VESPA ( VIPT enhancements for superpage accesses ) Cache Parameters
TLDR
SEESAW dynamically reduces the number of ways that are looked up based on the page size, improving performance and energy.
Specification-driven validation of programmable embedded systems
TLDR
This thesis presents a top-down validation methodology that complements the existing bottom-up approaches and leverages the system architect's knowledge about the behavior of the design through architecture specification and developed validation techniques to ensure that the static and dynamic behaviors of the specified architecture is well formed.
Side channel attack resistant elliptic curves cryptosystem on multi-cores for power efficiency
TLDR
A multiplier adjuster technique is presented to improve the execution time and the power consumption for the last unbalanced iteration of Elliptic Curves Cryptography (ECC) by appropriately applying dummy instructions between point-addition and point-doubling operations.
Functional abstraction driven design space exploration of heterogeneous programmable architectures
TLDR
The DSE results demonstrate the power of reuse in composing heterogeneous architectures using functional abstraction primitives allowing for a reduction in the time for specification and exploration by at least an order of magnitude.

References

SHOWING 1-9 OF 9 REFERENCES
Available instruction-level parallelism for superscalar and superpipelined machines
TLDR
A parameterizable code reorganization and simulation system was developed and used to measure instruction-level parallelism and the average degree of superpipelining metric is introduced, suggesting that this metric is already high for many machines.
200-MHz superscalar RISC microprocessor
TLDR
Clock and power distribution as well as circuit design techniques of several blocks are addressed and the MIPS R10000, 200-MHz, 64-b superscalar dynamic issue RISC microprocessor is presented.
Branch Prediction, Instruction-Window Size, and Cache Size: Performance Trade-Offs and Simulation Techniques
TLDR
This paper provides a comprehensive set of SimpleScalar simulation results from SPECint95 programs, showing the interactions among instruction-window size, branch-prediction accuracy, and instruction- and data-cache size and major mechanisms driving the observed trade-offs are described.
V-SAT: a visual specification and analysis tool for system-on-chip exploration
TLDR
It is believed that V-SAT provides a powerful environment, both for early design space exploration, as well as for the detailed design of SOC architectures.
EXPRESSION: a language for architecture exploration through compiler/simulator retargetability
TLDR
EXPRESSION is described, a language supporting architectural design space exploration for embedded systems-on-chip (SOC) and automatic generation of a retargetable compiler/simulator toolkit and its efficacy in supporting exploration and automatic software toolkit generation for an embedded SOC codesign flow is demonstrated.
Trailblazing: A Hierarchical Approach to Percolation Scheduling
  • A. Nicolau, S. Novack
  • Business
    1993 International Conference on Parallel Processing - ICPP'93
  • 1993
Percolation Scheduling (PS) is a system for performing parallelizing transformations for the VLIW and super-scalar cumputation models.
Seddighnezhad. 200-mhz superscalar risc microprocessor.IEEE Journal of Solid-State Circuits
  • 1996
The Mips R10000 superscalar microprocessor
The Mips R10000 is a dynamic, superscalar microprocessor that implements the 64-bit Mips 4 instruction set architecture. It fetches and decodes four instructions per cycle and dynamically issues them
Processor-memory co-exploration driven by an architectural description language
  • In Intl. Conf. on VLSI Design
  • 2001