Implementation of Autoencoders with Systolic Arrays through OpenCL

In the world of algorithm acceleration and the implementation of deep neural networks’ recall phase, OpenCL based solutions have a clear tendency to produce perfectly adapted kernels in graphic processor unit (GPU) architectures. However, they fail to obtain the same results when applied to field-programmable gate array (FPGA) based architectures. This situation, along with an enormous advance in new GPU architectures, makes it unfeasible to defend an acceleration solution based on FPGA, even in terms of energy efficiency. Our goal in this paper is to demonstrate that multikernel structures can be written based on classic systolic arrays in OpenCL, trying to extract the most advanced features of FPGAs without having to resort to traditional FPGA development using lower level hardware description languages (HDLs) such as Verilog or VHDL. This OpenCL methodology is based on the intensive use of channels (IntelFPGA extension of OpenCL) for the communication of both data and control and on the refinement of the OpenCL libraries using register transfer logic (RTL) code to improve the performance of the implementation of the base and activation functions of the neurons and, above all, to reflect the importance of adequate communication between the layers when implementing neuronal networks.

Simultaneous Smoothing and Untangling of 2D Meshes Based on Explicit Element Geometric Transformation and Element Stitching

Mesh quality can affect both the accuracy and efficiency of numerical solutions. This paper first proposes a geometry-based smoothing and untangling method for 2D meshes based on explicit element geometric transformation and element stitching. A new explicit element geometric transformation (EEGT) operation for polygonal elements is firstly presented. The transformation, if applied iteratively to an arbitrary polygon (even inverted), will improve its regularity and quality. Then a well-designed element stitching scheme is introduced, which is achieved by carefully choosing appropriate element weights to average the temporary nodes obtained by the above individual element transformation. Based on the explicit element geometric transformation and element stitching, a new mesh smoothing and untangling approach for 2D meshes is proposed. The proper choice of averaging weights for element stitching ensures that the elements can be transitioned smoothly and uniformly throughout the calculation domain. Numerical results show that the proposed method is able to produce high-quality meshes with no inverted elements for highly tangled meshes. Besides, the inherent regularity and fine-grained parallelism make it suitable for implementation on Graphic Processor Unit (GPU).

Metode Optimasi Memcached sebagai NoSQL Key-value Memory Cache

Memcached is an application that is used to store client query results on the web into the memory server as a temporary storage (cache). The goal is that the web remains responsive even though many access the web. Memcached uses key-value and the LRU (Least Recenly Used) algorithm to store data. In the default configuration Memcached can handle web-based applications properly, but if it is faced with an actual situation, where the process of transferring data and cache objects swells to thousands to millions of items, optimization steps are needed so that Memcached services can always be optimal, not experiencing Input / Output (I / O) overhead, and low latency. In a review of this paper, we will show some of the latest research in memcached optimization efforts. Some methods that can be used are clustering are; Memory partitioning, Graphic Processor Unit hash, User Datagram Protocol (UDP) transmission, Solid State Drive Hybird Memory and Memcached Hadoop distributed File System (HDFS)Keywords : memcached, optimization, web-app, overhead, latency

Waterblock Modelling for GPU Liquid Cooling

Nowadays, cooling of electronic chips is one of the most serious challenges due to the exponential growth in the demand of increasingly powerful computer systems; the overheating of these components has become a problem of high importance. For this reason, the new cooling technologies such as liquid cooling systems replace the conventional air-cooling systems to avoid the effect of hotspots generated on a chip. To make matters worse, the current use of video games is requiring a tremendous amount of energy dissipation, over passing the cooling requirements of CPUs. Therefore, in this paper a new geometry is proposed to keep cool the graphic processor unit (GPU) in a CPU, using water as the working fluid. The main aim of the design is to enhance the heat dissipation in the GPU, decrease the pressure drop during the cooling process and reduce the amount of material used to build the waterblock. A numerical simulation solves the energy and momentum equations. The thermal performance of the proposed geometry is compared with a commercial heat sink geometry previously characterized. The results for the new geometry show that greater heat dissipation is not reached (results are about the same as the results for the commercial geometry) but due to the modification made, there is less pressure drop, while reducing the size of the waterblock. These results make this new geometry quite a good candidate for the new state of the art of cooling waterblocks.