심재웅 교수

Current-generation Deep Neural Networks (DNNs), such as AlexNet and VGG, rely heavily on dense floating-point matrix multiplication (GEMM), which maps well to GPUs (regular parallelism, high TFLOP/s). Because of this, GPUs are widely used for accelerating DNNs. Current FPGAs offer superior energy efficiency (Ops/Watt), but they do not offer the performance of today's GPUs on DNNs. In this paper, we look at upcoming FPGA technology advances, the rapid pace of innovation in DNN algorithms, and con

Deep neural networks (DNNs) are widely used in data analytics, since they deliver state-of-the-art accuracies. Binarized neural networks (BNNs) are recently proposed optimized variant of DNNs. BNNs constraint network weight and/or neuron value to either +1 or −1, which is representable in 1 bit. This leads to dramatic algorithm efficiency improvement, due to reduction in the memory and computational demands. This paper evaluates the opportunity to further improve the execution efficiency of BNNs

With the emergence of data science, graph computing has become increasingly important these days. Unfortunately, graph computing typically suffers from poor performance when mapped to modern computing systems because of the overhead of executing atomic operations and inefficient utilization of the memory subsystem. Meanwhile, emerging technologies, such as Hybrid Memory Cube (HMC), enable the processing-in-memory (PIM) functionality with offloading operations at an instruction level. Instruction

Tuning code for GPGPU and other emerging many-core platforms is a challenge because few models or tools can precisely pinpoint the root cause of performance bottlenecks. In this paper, we present a performance analysis framework that can help shed light on such bottlenecks for GPGPU applications. Although a handful of GPGPU profiling tools exist, most of the traditional tools, unfortunately, simply provide programmers with a variety of measurements and metrics obtained by running applications, a

Recurrent neural networks (RNNs) provide state-of-the-art accuracy for performing analytics on datasets with sequence (e.g., language model). This paper studied a state-of-the-art RNN variant, Gated Recurrent Unit (GRU). We first proposed memoization optimization to avoid 3 out of the 6 dense matrix vector multiplications (SGEMVs) that are the majority of the computation in GRU. Then, we study the opportunities to accelerate the remaining SGEMVs using FPGAs, in comparison to 14-nm ASIC, GPU, and

Recent technology advancements allow for the integration of large memory structures on-die or as a die-stacked DRAM. Such structures provide higher bandwidth and faster access time than off-chip memory. Prior work has investigated using the large integrated memory as a cache, or using it as part of a heterogeneous memory system under management of the OS. Using this memory as a cache would waste a large fraction of total memory space, especially for the systems where stacked memory could be as l

Die-stacking technology allows conventional DRAM to be integrated with processors. While numerous opportunities to make use of such stacked DRAM exist, one promising way is to use it as a large cache. Although previous studies show that DRAM caches can deliver performance benefits, there remain inefficiencies as well as significant hardware costs for auxiliary structures. This paper presents two innovations that exploit the bursty nature of memory requests to streamline the DRAM cache. The first

General Matrix to Matrix multiplication (GEMM) is the cornerstone for a wide gamut of applications in high performance computing (HPC), scientific computing (SC) and more recently, deep learning. In this work, we present a customizable matrix multiplication framework for the Intel HARPv2 CPU+FPGA platform that includes support for both traditional single precision floating point and reduced precision workloads. Our framework supports arbitrary size GEMMs and consists of two parts: (1) a simple a

While unified virtual memory and demand paging in modern GPUs provide convenient abstractions to programmers for working with large-scale applications, they come at a significant performance cost. We provide the first comprehensive analysis of major inefficiencies that arise in page fault handling mechanisms employed in modern GPUs. To amortize the high costs in fault handling, the GPU runtime processes a large number of GPU page faults together. We observe that this batched processing of page f

Wafer maps provide important information for engineers for detecting root causes of failure in a semiconductor manufacturing process. Thus, there has been active research into the automation of wafer map pattern classification. With recent advances in deep learning, a convolutional neural network (CNN) has yielded state-of-the-art performance in wafer map pattern classification. Because a large amount of labeled training data is required, experienced engineers need to annotate large quantities o

Die-stacked DRAM can provide large amounts of in-package, high-bandwidth cache storage. For server and high-performance computing markets, however, such DRAM caches must also provide sufficient support for reliability and fault tolerance. While conventional off-chip memory provides ECC support by adding one or more extra chips, this may not be practical in a 3D stack. In this paper, we present a DRAM cache organization that uses error-correcting codes (ECCs), strong checksums (CRCs), and dirty d

Exclusive last-level caches (LLCs) reduce memory accesses by effectively utilizing cache capacity. However, they require excessive on-chip bandwidth to support frequent insertions of cache lines on eviction from upper-level caches. Non-inclusive caches, on the other hand, have the advantage of using the on-chip bandwidth more effectively but suffer from a higher miss rate. Traditionally, the decision to use the cache as exclusive or non-inclusive is made at design time. However, the best option