• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.2
• /
• pp.57-65
• /
• 2016

In this paper, we propose a system for efficient use of shared memory between CPU and GPU. The system, called Fusion Architecture, assures consistency of the shared memory and minimizes cache misses that frequently occurs on Heterogeneous System Architecture or Unified Virtual Memory based systems. It also maximizes the performance for memory intensive jobs by efficient allocation of GPU cores. To test between architectures on various scenarios, we introduce the Fusion Architecture Analyzer, which compares OpenMP, OpenCL, CUDA, and the proposed architecture in terms of memory overhead and process time. As a result, Proposed fusion architectures show that the Fusion Architecture runs benchmarks 55% faster and reduces memory overheads by 220% in average.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.104-108
• /
• 2021

In order to improve performance in IoT, edge computing system, a memory is usually configured in a hierarchical structure. Based on the distance from CPU, the access speed slows down in the order of registers, cache memory, main memory, and storage. Similar to the change in performance, energy consumption also increases as the distance from the CPU increases. Therefore, it is important to develop a technique that places frequently used data to the upper memory as much as possible to improve performance and energy consumption. However, the technique should solve the problem of cache performance degradation caused by lack of spatial locality that occurs when the data access stride is large. This study proposes a technique to selectively place data with large data access stride to a software-controlled cache. By using the proposed technique, data spatial locality can be improved by reducing the data access interval, and consequently, the cache performance can be improved.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.2
• /
• pp.151-158
• /
• 2016

The HSA resolves an old problem with existing CPU and GPU architectures by allowing both units to directly access each other's memory pools via unified virtual memory. In a physically realized system, however, frequent data exchanges between CPU and GPU for a virtual memory block result bottlenecks and coherence request overheads. In this paper, we propose Fusion Processor Architecture for efficient access of main memory from both CPU and GPU. It consists of Job Manager, Re-mapper, and Pre-fetcher to control, organize, and distribute work loads and working areas for GPU cores. These components help on reducing memory exchanges between the two processors and improving overall efficiency by eliminating faulty page table requests. To verify proposed algorithm architectures, we develop an emulator based on QEMU, and compare several architectures such as CUDA(Compute Unified Device Architecture), OpenMP, OpenCL. As a result, Proposed fusion processor architectures show 198% faster than others by removing unnecessary memory copies and cache-miss overheads.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.2
• /
• pp.178-184
• /
• 2004

In this paper, we designed an image processing system for the high speed line-scan camera which adopts the new memory model we proposed. As a resolution and a data rate of the line-scan camera are becoming higher, the faster image processing systems are needed. But many conventional systems are not sufficient to process the image data from the line-scan camera during a very short time. We designed the memory controller which eliminates the time for transferring image data from the line-scan camera to the main memory with high-speed SRAM and has a dual-port configuration therefore the DSP can access the main memory even though the memory controller are writing the image data. The memory controller is implemented by VHDL and Xilinx SPARTAN-IIE FPGA.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.9
• /
• pp.445-458
• /
• 2007

This article presents a novel infrastructure for large-memory database processing using commodity hardware with operating system support. We exploit inexpensive PCs and a high-speed network capable of Remote Direct Memory Access (RDMA) operations to build a new memory hierarchy between fast volatile memory and slow disk storage. The new memory hierarchy guarantees a reasonable response time, and its storage size enables us to run large-memory database systems with little performance degradation. The proposed architecture has two main components: (1) a remote memory system inside the Linux kernel to manage other computers' memory pages efficiently and (2) a remote memory pager responsible for manipulating remote read/write operations on remote memory pages. We insist that the proposed architecture is practical enough to support the rigorous demands of commercial in-memory database systems by demonstrating the performance of publicly available main-memory databases (e.g., MySQL) on our prototyped system. The experimental results show very interesting results from the TPC-C benchmark.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.2
• /
• pp.97-105
• /
• 2016

Microcontrollers (MCUs) for endpoint smart sensor devices of internet-of-thing (IoT) are being implemented as system-on-chip (SoC) with on-chip instruction flash memory, in which user firmware is embedded. MCUs directly fetch binary code-based instructions through bit-line sense amplifier (S/A) integrated with on-chip flash memory. The S/A compares bit cell current with reference current to identify which data are programmed. The S/A in reading '0' (erased) cell data consumes a large sink current, which is greater than off-current for '1' (programmed) cell data. The main motivation of our approach is to reduce the number of accesses of erased cells by binary code level transformation. This paper proposes a built-in write/read path architecture using binary code inversion method based on hot-spot region detection of instruction code access to reduce sensing current in S/A. From the profiling result of instruction access patterns, hot-spot region of an original compiled binary code is conditionally inverted with the proposed bit-inversion techniques. The de-inversion hardware only consumes small logic current instead of analog sink current in S/A and it is integrated with the conventional S/A to restore original binary instructions. The proposed techniques are applied to the fully-custom designed MCU with ARM Cortex-M0$^{TM}$ using 0.18um Magnachip Flash-embedded CMOS process and the benefits in terms of power consumption reduction are evaluated for Dhrystone$^{TM}$ benchmark. The profiling environment of instruction code executions is implemented by extending commercial ARM KEIL$^{TM}$ MDK (MCU Development Kit) with our custom-designed access analyzer.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.114-124
• /
• 2014

HEVC is a state-of-the-art video coding standard developed by JCT-VC. HEVC provides about 2 times higher subjective coding efficiency than H.264/AVC. One of the main goal of HEVC development is to efficiently coding UHD resolution video so that HEVC is expected to be widely used for coding UHD resolution video. Decoding such high resolution video generates a large number of memory accesses, so a decoding system needs high-bandwidth for memory system and/or internal communication architecture. In order to determine such requirements, this paper presents an analysis of the memory access complexity for HEVC decoder. we first estimate the amount of memory access performed by software HEVC decoder on an embedded system and a desktop computer. Then, we present the memory bandwidth models for HEVC decoder by analyzing the data flow of HEVC decoding tools. Experimental results show the software decoder produce 6.9-40.5 GB/s of DRAM accesses. also, the analysis reveals the hardware decoder requires 2.4 GB/s of DRAM bandwidth.

• The KIPS Transactions:PartA
• /
• v.8A no.4
• /
• pp.419-428
• /
• 2001

Advances in circuit and integration technology are continuously boosting the speed of processors. One of the main challenges presented by such developments is the effective use of powerful processors in shared memory multiprocessor system. We believe that the interconnection problem is not solved even for small scale shared memory multiprocessor, since the speed of shared buses is unlikely to keep up with the bandwidth requirements of new powerful processors. In the past few years, point-to-point unidirectional connection have emerged as a very promising interconnection technology. The single slotted ring is the simplest form point-to-point interconnection. The main limitation of the single slotted ring architecture is that latency of access increase linearly with the number of the processors in the ring. Because of this, we proposed the dual slotted ring as an alternative to single slotted ring for cache-based multiprocessor system. In this paper, we analyze the proposed dual slotted ring architecture using new snooping protocol and enforce simulation to compare it with single slotted ring.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.1-11
• /
• 2012

As process technology scales down, the number of cores integrated into a processor increases dramatically, leading to significant performance improvement. Especially, the GPU(Graphics Processing Unit) containing many cores can provide high computational performance by maximizing the parallelism. In the GPU architecture, the access latency to the main memory becomes one of the major reasons restricting the performance improvement. In this work, we analyze the performance improvement of the 3D GPU architecture compared to the 2D GPU architecture quantitatively and investigate the potential problems of the 3D GPU architecture. In general, memory instructions account for 30% of total instructions, and global/local memory instructions constitutes 60% of total memory instructions. Therefore, the performance of the 3D GPU is expected to be improved significantly compared to the 2D GPU by reducing the delay of memory instructions. However, according to our experimental results, the 3D architecture improves the GPU performance only by 2% compared to the 2D architecture due to the memory bottleneck, since the performance reduction due to memory bottleneck in the 3D GPU architecture increases by 245% compared to the 2D architecture. This paper provides the guideline for suitable memory design by analyzing the efficiency of the memory architecture in 3D GPU architecture.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.9
• /
• pp.1867-1879
• /
• 1997

DREAM-S is a distributed main-memory database system for the real-time processing of shared operational datra in ATM switching systems. DREAM-S has a client-server architecture in which only the server has the diskstorage, and provides the T-Tree index structure for efficient accesses to the data. We propose a recovery technique for the T-Tree index structre in DREAM-S. Although main-memory database system offer efficient access performance, the database int he main-memory may be broken when system failure such as database transaction failure or power failure occurs. Therfore, a recovery technique that recovers the database (including index structures) is essential for fault tolerant ATM switching systems. Proposed recovery technique relieves the bottleneck of the server processors disk operations by maintaining the T-Tree index structure only in the main-memory. In addition, fast recovery is guaranteed even in large number of client systems since the T-Tree index structure(s) in each system can be recovered cncurrently.