D esigners of microarchitectures for generalpurpose microprocessors once based their design decisions on experts’ intuition and rules of thumb. Since the mid-1980s, however, microarchitecture research has become a systematic process that uses simulation tools extensively. Although architectural simulators model microarchitectures at a high abstraction level, the increasing complexity of both th...

The paper describes a novel hashing method suitable for lookup functions. Traditional methods are either of lower hash quality or inferior performance. In this paper, we show how to compute a high-quality hash digest at extremely high performance on Intel ® processors using the crc32 instruction. Our method also generates multiple 32-bit hashes of an input data buffer, which have low correlatio...

Instruction Memoization is a technique that enables performing multiple-cycle computations in a single cycle by exploiting redundant instructions. The technique is based on the notion of memoing: saving the input and output of previous calculations and using the output if the input is encountered again. Several recent papers have proven that non-trivial speedup (over 10%) can be obtained by usi...

Instruction selection implements a program under compilation by selecting processor instructions and has tremendous impact on the performance of the code generated by a compiler. This paper introduces a graph-based universal representation that unifies data and control flow for both programs and processor instructions. The representation is the essential prerequisite for a constraint model for ...

A power consumption measurement framework for embedded processing systems is presented in this work. Given an assembly or machine level program as input to this setup, the energy consumption of the specific program in the specific processing systems may be estimated. The instruction level power models are derived based on the power supply current measurement technique. The instantaneous variati...

In hardware software codesign paradigm often a performance estimation of the system is needed for hardware software partitioning. The tremendous growth of application specific embedded systems necessitate high level system design tools for rapid prototyping. This work involves design of a language Sim-nML which will be the base for a high level system design environment. The language is simple,...

To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called taskoriented language grounding. We propose an end-to-end trainable neural architecture for task-oriented language grounding in 3D environments which assumes no prio...