While (I) serverless computing is emerging as a popular form of cloud execution, datacenters are going through major changes: (II) storage dissaggregation in the system infrastructure level and (III) integration of domain-specific accelerators in the hardware level. Each of these three trends individually provide significant benefits; however, when combined the benefits diminish. On the convergence of these trends, the paper makes the observation that for serverless functions, the overhead of accessing dissaggregated storage overshadows the gains from accelerators. Therefore, to benefit from all these trends in conjunction, we propose In-Storage Domain-Specific Acceleration for Serverless Computing (dubbed DSCS-Serverless1). The idea contributes a server-less model that utilizes a programmable accelerator embedded within computational storage to unlock the potential of acceleration in disaggregated datacenters. Our results with eight applications show that integrating a comparatively small accelerator within the storage (DSCS-Serverless) that fits within the storage's power constraints (25 Watts), significantly outperforms a traditional disaggregated system that utilizes NVIDIA RTX 2080 Ti GPU (250 Watts). Further, the work highlights that disaggregation, serverless model, and the limited power budget for computation in storage device require a different design than the conventional practices of integrating microprocessors and FPGAs. This insight is in contrast with current practices of designing computational storage devices that are yet to address the challenges associated with the shifts in datacenters. In comparison with two such conventional designs that use ARM cores or a Xilinx FPGA, DSCS-Serverless provides 3.7× and 1.7× end-to-end application speedup, 4.3× and 1.9× energy reduction, and 3.2× and 2.3× better cost efficiency, respectively.

There has been an arms race for devising accelerators for deep learning in recent years. However, real-world applications are not only neural networks but often span across multiple domains, e.g., database queries, compression, encryption, video coding, signal processing, and traditional machine learning, which may or may not contain deep learning. The sole focus on this single domain is sub-optimal as it misses the potential to proliferate and promote cross-domain multi-acceleration as there is an opportunity to harness the power of chaining heterogeneous Domain-Specific Architectures (DSAs) in modern datacenter applications. However, there is a catch as the data motion overhead can outweigh the benefits from all these chained heterogeneous accelerators. We dub the data restructuring and communication overhead of executing a single application using a chain of accelerators [1] as the data motion overhead. In a stark contrast with most works on DSAs that deal with accelerating compute kernels, this work focuses on accelerating data motion within a chain of heterogeneous DSAs in a multi-accelerator datacenter. To that end, this paper introduces Data Motion Acceleration (DMX) for (1) reducing data movement, (2) accelerating data restructuring, and (3) enabling interoperability between heterogeneous accelerators from different domains through a cross-stack hardware-software solution. The results with five end-to-end applications show that utilizing DMX offers up to 8.2 ×, 13.6 ×, and 5.2 × improvement in latency, throughput, and energy efficiency in a multi-accelerator system, respectively.

As the huge growth of mobile traffic amount, conventional Radio Access Networks (RANs) suffer from high capital and operating expenditures, especially when new cellular standards are deployed. Software, and cloud RANs have been proposed, but the stringent latency requirements e.g., 1 ms transmission time interval, dictated by cellular networks is difficult to satisfy. We first present a real software RAN testbed based on an opensource LTE implementation. We also investigate the issue of quality assurance when deploying such software RANs in cloud. In particular, running software RANs in cloud leads to high latency, which may violate the latency requirements. We empirically study the problem of minimizing computational and networking latencies in lightweight container cloud. Our experiment results show the feasibility of running software RANs in real-time container cloud. More specifically, a feasible solution to host software RANs in cloud is to adopt lightweight containers with real-time kernels and fast packet processing networking.

We present a complete system, called Challenged Content Delivery Network (CCDN), to efficiently deliver multimedia content to mobile users who live in developing countries, rural areas, or over-populated cities with no or weak network infrastructure. These mobile users do not have always-on Internet access. We demo our CCDN, implemented on a Linux server, Raspberry Pi proxies, and Android phones from three aspects: multimedia, networking, and machine learning tools. We propose multiple optimization algorithm modules that compute personalized distribution plans, and maximize the overall user experience. CCDN allows people living in area with challenged networks access to multimedia content, like news reports, using mobile devices, such as smartphones. This in turn will help in eliminating the digital divide, which refers to information inequality to persons with different Internet accessing abilities.

We focus on the problem of efficient communications over access networks with asymmetric bandwidth and capability. We propose a resource-constrained asymmetric redundancy elimination algorithm (RCARE) to leverage downlink bandwidth and receiver capability to accelerate the uplink data transfer. RCARE can be deployed on a client or a proxy. Different from existing asymmetric algorithms, RCARE uses a flexible matching mechanism to identify redundant data and allocates a small sender cache to absorb the high downlink traffic overhead. Compared to existing redundancy elimination algorithms, RCARE provides a scalable sender cache that is adaptive based on resource and performance. We evaluate RCARE with real traffic traces collected from multiple servers and a campus gateway. The trace-driven simulation results indicate that RCARE achieves higher goodput gains and reduces downlink traffic compared to existing asymmetric communication algorithms. We design an adaptation algorithm for resource-constrained senders sending multiple data streams. Our algorithm takes samples from data streams and predicts how to invest cache size on individual data streams to achieve maximal uplink goodput gain. The adaptation algorithm improves the goodput gain by up to 87% compared to the baseline. In first 10% of data streams (sorted by the optimal goodput gains), RCARE achieves up to 42% goodput gain on average.

In this paper, we explore the problem of supporting efficient access to social media contents on social network sites for mobile devices without requiring mobile users to be online all the time. We propose and implement a broker/proxy based architecture that stages data at a broker/proxy, and selectively downloads to the mobile device only those contents that have a high likelihood of being viewed. The system determines the relevance of social media updates that continuously arrive (e.g., Facebook friend updates) for each user. Using knowledge of this relevance and current network/system conditions, we develop scheduling algorithms that determine which social contents are sent to the devices. We develop an Android app providing offline access to Facebook. Our experimental results indicate that our system is energy efficient, which saves energy by 6.9 times for WiFi and 9.1 times for cellular connections. We also use data traces gathered from our app to further drive extensive simulation based evaluations which show that our proposed algorithms provide efficient facilities for tuning the system's performance.

No abstract available.