David Alonso

MANGO: Exploring Manycore Architectures for Next-GeneratiOn HPC Systems

The Horizon 2020 MANGO project aims at exploring deeply heterogeneous accelerators for use in High-Performance Computing systems running multiple applications with different Quality of Service (QoS) levels. The main goal of the project is to exploit customization to adapt computing resources to reach the desired QoS. For this purpose, it explores different but interrelated mechanisms across the architecture and system software. In particular, in this paper we focus on the runtime resource management, the thermal management, and support provided for parallel programming, as well as introducing three applications on which the project foreground will be validated.

Enabling HPC for QoS-sensitive applications: The MANGO approach

In this paper, we provide an overview of the MANGO project and its goal. The MANGO project aims at addressing power, performance and predictability (the PPP space) in future High-Performance Computing systems. It starts from the fundamental intuition that effective techniques for all three goals ultimately rely on customization to adapt the computing resources to reach the desired Quality of Service (QoS). From this starting point, MANGO will explore different but interrelated mechanisms at various architectural levels, as well as at the level of the system software. In particular, to explore a new positioning across the PPP space, MANGO will investigate system-wide, holistic, proactive thermal and power management aimed at extreme-scale energy efficiency.

Insertion of an Edwards Sapien 3 prosthesis as a mitral valve in valve implantation via a transapical approach.

We report a case of transapical mitral valve‐in‐valve implantation for a deteriorated bioprosthesis using the Edwards Sapien 3 prosthesis via the transapical approach. This case demonstrates the safety and feasibility of using the Edwards Sapien 3 prosthesis in treating degenerated bioprosthetic mitral valves.

The MANGO FET-HPC Project: An Overview

In this paper, we provide an overview of the MANGO project and its goal. The MANGO project aims at addressing power, performance and predictability (the PPP space) in future High-Performance Computing systems. It starts from the fundamental intuition that effective techniques for all three goals ultimately rely on customization to adapt the computing resources to reach the desired Quality of Service (QoS). From this starting point, MANGO will explore different but interrelated mechanisms at various architectural levels, as well as at the level of the system software. In particular, to explore a new positioning across the PPP space, MANGO will investigate system-wide, holistic, proactive thermal and power management aimed at extreme-scale energy efficiency.

Placement of a Rigid Tricuspid Annuloplasty Ring Over a Flexible Ring for the Treatment of Recurrent Tricuspid Regurgitation

Abstract  We describe a technique that implants a rigid tricuspid annuloplasty ring over a previously inserted flexible ring for the treatment of recurrent tricuspid regurgitation. This technique avoids the trauma associated with the excision of a flexible ring in patients with friable annular tissue. (J Card Surg 2012;27:549‐550)

Early thrombosis of a tricuspid annuloplasty ring and mild hyperhomocysteinemia.

Tricuspid annuloplasty ring thrombosis is an extremely infrequent pathology, and no evidence-based antithrombotic management has been described. We present the case of a 40-year-old female with isolated mild hyperhomocysteinemia and early ring thrombus formation after surgical primary closure of an atrial septal defect and ring tricuspid annuloplasty. Clinical management, antithrombotic treatment, and hyperhomocysteinemia implications are discussed.

Exploring manycore architectures for next-generation HPC systems through the MANGO approach

Abstract The Horizon 2020 MANGO project aims at exploring deeply heterogeneous accelerators for use in High-Performance Computing systems running multiple applications with different Quality of Service (QoS) levels. The main goal of the project is to exploit customization to adapt computing resources to reach the desired QoS. For this purpose, it explores different but interrelated mechanisms across the architecture and system software. In particular, in this paper we focus on the runtime resource management, the thermal management, and support provided for parallel programming, as well as introducing three applications on which the project foreground will be validated.

A Machine Learning-Based Approach for Power and Thermal Management of Next-Generation Video Coding on MPSoCs

High Efficiency Video Coding (HEVC) provides high efficiency at the cost of increased computational complexity followed by increased power consumption and temperature of current Multi- Processor Systems-on-Chip (MPSoCs). In this paper, we propose a machine learning-based power and thermal management approach that dynamically learns the best encoder configuration and core frequency for each of the several video streams running in an MPSoC, using information from frame compression, quality, performance, total power and temperature. We implement our approach in an enterprise multicore server and compare it against state-of-the-art techniques. Our approach improves video quality and performance by 17% and 11%, respectively, while reducing average temperature by 12%, without degrading compression or increasing power.

TCT-643 Percutaneous Mitral Valve Repair for Acute Mitral Regurgitation Following an Acute Myocardial Infarction

MitraClip® (Abbott Vascular, Santa Clara, CA, USA) has become the most frequently used transcatheter mitral valve repair technology for correcting mitral regurgitation (MR). Data form real-world registries have shown that in a high-risk population with functional MR, left ventricular dysfunction (

Efficacy of Oral Anticoagulation in Stroke Prevention among Sinus-Rhythm Patients Who Lack Left Atrial Mechanical Contraction after Cryoablation.

The customary recommendation is that oral anticoagulation be withdrawn a few months after cryoablation for atrial fibrillation, independently of left atrial mechanical contraction in patients in sinus rhythm. Recently, a 5-fold increase in stroke has been described in sinus-rhythm patients who lack atrial mechanical contraction. One aim of this study was to evaluate the efficacy of oral anticoagulation in preventing postoperative stroke in such patients. This prospective study divided 154 sinus-rhythm patients into 2 groups, depending on the presence (108 patients) or absence (46 patients) of left atrial mechanical contraction at 6 months after surgery, and monitored them annually for 5 years. Those without left atrial contraction were maintained on acenocumarol. The primary endpoint was the occurrence of ischemic stroke. The median follow-up period was 29 ± 16 months; 4 patients (2.5%), all belonging to the group with preserved atrial contraction, had ischemic stroke; the group of patients without left atrial contraction had no episodes of stroke during follow-up. Logistic binary regression analyses showed no evidence of factors independently predictive of stroke. Among anticoagulated patients in sinus rhythm without left atrial contraction, we found the incidence of stroke to be zero. In a small, nonrandomized group such as this, we cannot discount the element of chance, yet we suggest that maintaining anticoagulation might lower the incidence of stroke in this population.