@article{li_li_lin_li_2017, title={Significant and sustaining elevation of blood oxygen induced by Chinese cupping therapy as assessed by near-infrared spectroscopy}, volume={8}, ISSN={["2156-7085"]}, DOI={10.1364/boe.8.000223}, abstractNote={Cupping therapy has been used in traditional Chinese medicine for thousands of years to relieve muscle pain/tendency/fatigue and to cure or reduce symbols of other diseases. However, its therapeutic effect is sparsely interpreted in the language of modern physiology. To objectively evaluate its therapeutic effect, we focused on dry cupping treatment and utilized near-infrared spectroscopy (NIRS) to assess the concentration change in oxy-hemoglobin ([HbO2]), deoxy-hemoglobin ([Hb]), and blood volume in the course of cupping therapy over 13 volunteers on the infraspinatus muscle, where is usually applied for shoulder pains. Both a prominent drop in [Hb] and a significant elevation in [HbO2] in the tissue surrounding the cupping site were observed during both cupping and post-treatment, manifesting the enhancement of oxygen uptake. This resulting promotion indicates potential positive therapeutic effect of cupping therapy in hemodynamics for facilitating muscular functions.}, number={1}, journal={BIOMEDICAL OPTICS EXPRESS}, author={Li, Ting and Li, Yaoxian and Lin, Yu and Li, Kai}, year={2017}, month={Jan}, pages={223–229} } @inproceedings{wang_solihin_2015, title={Emulating cache organizations on real hardware using performance cloning}, DOI={10.1109/ispass.2015.7095815}, abstractNote={Computer system designers need a deep understanding of end users' workload in order to arrive at an optimum design. Unfortunately, many end users will not share their software to designers due to the proprietary or confidential nature of their software. Researchers have proposed workload cloning, which is a process of extracting statistics that summarize the behavior of users' workloads through profiling, followed by using them to drive the generation of a representative synthetic workload (clone). Clones can be used in place of the original workloads to evaluate computer system performance, helping designers to understand the behavior of users workload on the simulated machine models without the users having to disclose proprietary or sensitive information about the original workload. In this paper, we propose infusing environment-specific information into the clone. This Environment-Specific Clone (ESC) enables the simulation of hypothetical cache configurations directly on a machine with a different cache configuration. We validate ESC on both real systems as well as cache simulations. Furthermore, we present a case study of how page mapping affects cache performance. ESC enables such a study at native machine speed by infusing the page mapping information into clones, without needing to modify the OS or hardware. We then analyze the factors that determine how page mapping impact cache performance, and how various applications are affected differently.}, booktitle={Ieee international symposium on performance analysis of systems and}, author={Wang, Y. P. and Solihin, Y.}, year={2015}, pages={298–307} } @article{wang_solihin_balakrishnan_2015, title={MeToo: Stochastic Modeling of Memory Traffic Timing Behavior}, ISSN={["1089-795X"]}, DOI={10.1109/pact.2015.36}, abstractNote={The memory subsystem (memory controller, bus, andDRAM) is becoming a bottleneck in computer system performance. Optimizing the design of the multicore memory subsystem requires good understanding of the representative workload. A common practice in designing the memory subsystem is to rely on trace simulation. However, the conventional method of relying on traditional traces faces two major challenges. First, many software users are apprehensive about sharing their code (source or binaries) due to the proprietary nature of the code or secrecy of data, so representative traces are sometimes not available. Second, there is a feedback loop where memory performance affects processor performance, which in turnalters the timing of memory requests that reach the bus. Such feedback loop is difficult to capture with traces. In this paper, we present MeToo, a framework for generating synthetic memory traffic for memory subsystem design exploration. MeToo uses a small set of statistics that summarizes the performance behavior of the original applications, and generates synthetic traces or executables stochastically, allowing applications to remain proprietary. MeToo uses novel methods for mimicking the memory feedback loop. We validate MeToo clones, and show very good fit with the original applications' behavior, with an average error of only 4.2%, which is a small fraction of the errors obtained using geometric inter-arrival(commonly used in queueing models) and uniform inter-arrival.}, journal={2015 INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURE AND COMPILATION (PACT)}, author={Wang, Yipeng and Solihin, Yan and Balakrishnan, Ganesh}, year={2015}, pages={457–467} }