In AEOS (Automated Empirical Optimization of Software), an automated suite of searches are combined with context-sensitive timers and various methods of performing code transformations to auto-adapt high performance kernels to hardware evolving at the frantic pace dictated by Moore's Law. The author's widely used ATLAS (Automatically Tuned Linear Algebra Software) was one of the pioneering packages that made AEOS the state-of-the-art way to produce and maintain HPC kernels. This talk outlines our approach to this critical area of investigation, the types of research that are required to advance the field, and future plans.

R. Clint Whaley is an associate professor in the Computer Science Department of the University of Texas at San Antonio. He received his PhD in Computer Science in December 2004 from Florida State University in the area of optimizing compilers, his MS in Computer Science in May 1994, from the University of Tennessee at Knoxville in the area parallel programming, and his BS in Mathematics in May of 1991. He was a full-time researcher at the University of Tennessee at Knoxville as a Research Associate from May 1994 to June 1999, and as a Senior Research Associate from June 1999 to December 2001. He was a Post-doctoral researcher and adjunct at Florida State University from January 2005 through June 2005, and then held the title of assistant professor at the University of Texas at San Antonio from 2005 to 2012 before promotion with tenure. His research interests include empirical optimization, optimizing compilers, high performance computing, computer architecture and parallel computing.

Power consumption has imposed a first-order design constraint to the entire spectrum of computer systems, from the smallest hand-held devices to the largest data centers. Limitations on the power consumption due to the small battery capacity in mobile devices, or the limited cooling capacity in desktops, or the tight electricity expense budget in data centers, require innovations that allow computer systems with larger numbers of cores to dynamically adapt to time-varying needs of modern workloads within a limited power budget. In the first part of my talk, I will provide the background of power management for computer systems. In the second part of my talk, I will introduce FreqPar, a power management solution that controls the power consumption of a many-core processor under a fixed power budget, as well as to optimize the performance of the processor by dynamically adjusting the frequency of each core on a multi-core processor. In the third part of my talk, I will summarize my previous projects on power management for multi-core processor, GPU/CPU heterogeneous systems, cooling power and computational power co-optimization, and data center power optimization.

Kai Ma is currently a PhD candidate in the Department of Computer and Electrical Engineering, at The Ohio State University. He is passionate about building practical power/energy-efficiency systems, with a particular interest in multi-core system and GPU/CPU heterogeneous systems. He also enjoys working on Linux kernel hacking and large-scale computer system performance tuning.

Thought-controlled prosthetic limbs have been tested on human subjects. However, the invasive nature of the brain-machine interface is an impediment, even though it has allowed quadriplegic people to move wheelchairs and prosthetic arms. DARPA’s prosthetics program has made enormous progress in upper-limb prosthetics. However, the neural interface was rerouted through limited number of chest muscles to transform the electroneurographic (ENG) peripheral neural signals into detectable electromyographic (EMG) muscle signals losing many degrees of freedom (DoF) and requiring training of uncomfortable chest muscle movement to control prostheses. The obstacles of both non-invasive approach and direct communication with nerves have inspired me to bring a noble neural interface using regenerated peripheral nerve systems (PNS). The peripheral nerve system has a natural regenerative capability. When it gets damaged or even cut, the natural healing system and regenerative function is initiated. Although the damaged nerves on the distal side degenerate and lose the function of delivering neural signals, if the nerves on the proximal side are supported properly and reconnected to the distal side nerve stump, the proximal nerves can grow back and even reinnervate muscles. I have developed bio-compatible microconduits and individually accessible microelectrodes. The microconduits serve as a nerve regeneration scaffold and microelectrodes build an electrical communication pathway between regenerated peripheral nerves inside scaffolds and data acquisition systems outside the amputated bodies. The electrical interface of sensory and motor axons separated by microconduits will make it possible to implement bidirectional communication between prosthetic limbs and amputated bodies. Individually addressable motor axons will be able to control the natural 22 DoF prosthetic arms through over 100 microelectrodes. The regenerated sensory axons in the microconduits will be stimulated by microsensors in the prostheses and the patient will be able to feel sensations.

Nanotechnology is set to have a major impact on our society and the way we live. It has already brought advances such as self-cleaning windows, high efficiency solar cells, ice accumulation resistant aircraft exteriors, and nanoparticle reinforced nanocomposites that are lighter and tougher than steel. Medical nanotechnological breakthroughs in areas such as drug delivery and cancer detection are also on the horizon, and have the potential to revolutionize our health care system. This talk focuses on a particular type of nanotechnological breakthrough: nano-particle doped micropatternable multi-functional polymers. Polymers are inherently electrically insulating and non-magnetic but these properties can be modified by the introduction of conducting and/or magnetic nanoparticles in the polymer matrix. This enables the polymers to retain their inherent benefits (ease of fabrication, cost, mechanical and surface properties) while being rendered functional in some way, e.g., being conductive, magnetic, or mechanically active. This talk will cover the fabrication and process technology of micropatternable multifunctional nanocomposite polymers/resists for M- (micro-) and N- (nano) EMS (electromechanical systems), and discuss their employment in a number of applications, such as: shape-conformable micro-electrodes for applications in tissue tomography, wearable sensors, conductive threads, flexible 3-D printed electronics, solar cells, and sensors will also be discussed.

MEMS (micro electromechanical system) is a highly miniaturized electromechanical device with a typical dimension varying from a few to a few hundred µm. Due to its high level of precision and parallelism, MEMS has been actively studied as a breakthrough solution in life science and medicine. In the field of mechanobiology, MEMS technologies have been widely used to characterize fundamental mechanical properties of cells to elucidate dynamic and complex interactions between the cell mechanics and the cellular processes. This talk will focus on MEMS-based approaches for the mechanical characterization of adherent cells. A unique MEMS mass sensor with a spatially uniform mass sensitivity was developed and used to measure the mass, the growth rate, and the stiffness of the target cells on a single cell level.