• Journal of Information Technology Applications and Management
• /
• 제11권1호
• /
• pp.189-200
• /
• 2004

Recently Flash Memory which is small and low-powered is widely used as a storage of embedded system, because an embedded system requests portability and a fast response. To resolve a difference of access time between a storage and RAM, Linux is using disk caching which copies a part of file on disk into RAM. It is not also an exception on embedded system. A READ access-time of flash memory is similar to RAMs. So, when a process on an embedded system reads data, it is similar to the time to access cached data in RAM and to access directly data on a flash memory. On the embedded system using limited memory, using a disk cache is that wastes much time and memory spaces to manage it and can not reflects the characteristic of a flash memory. This paper proposes the regular file access of limited using a page cache in the file system based on a flash memory and reflects the characteristic of a flash memory. The proposed algorithm minimizes power consumption because access numbers of the RAM are reduced and doesn't waste a memory space because it accesses directly to a flash memory Therefore, the performance improvement of the system applying the proposed algorithm is expected.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제14권4호
• /
• pp.391-406
• /
• 2014

The performance of General-Purpose computation on Graphics Processing Units (GPGPU) is heavily dependent on the memory access behavior. This sensitivity is due to a combination of the underlying Massively Parallel Processing (MPP) execution model present on GPUs and the lack of architectural support to handle irregular memory access patterns. Application performance can be significantly improved by applying memory-access-pattern-aware optimizations that can exploit knowledge of the characteristics of each access pattern. In this paper, we present an algorithmic methodology to semi-automatically find the best mapping of memory accesses present in serial loop nest to underlying data-parallel architectures based on a comprehensive static memory access pattern analysis. To that end we present a simple, yet powerful, mathematical model that captures all memory access pattern information present in serial data-parallel loop nests. We then show how this model is used in practice to select the most appropriate memory space for data and to search for an appropriate thread mapping and work group size from a large design space. To evaluate the effectiveness of our methodology, we report on execution speedup using selected benchmark kernels that cover a wide range of memory access patterns commonly found in GPGPU workloads. Our experimental results are reported using the industry standard heterogeneous programming language, OpenCL, targeting the NVIDIA GT200 architecture.

• ETRI Journal
• /
• 제44권6호
• /
• pp.1020-1033
• /
• 2022

In this paper, we propose novel disaggregated memory module (dMM) architecture and memory access control schemes to solve the collision and contention problems of memory disaggregation, reducing the average memory access time to less than 1 ㎲. In the schemes, the distributed scheduler in each dMM determines the order of memory read/write access based on delay-sensitive priority requests in the disaggregated memory access frame (dMAF). We used the memory-intensive first (MIF) algorithm and priority-based MIF (p-MIF) algorithm that prioritize delay-sensitive and/or memory-intensive (MI) traffic over CPU-intensive (CI) traffic. We evaluated the performance of the proposed schemes through simulation using OPNET and hardware implementation. Our results showed that when the offered load was below 0.7 and the payload of dMAF was 256 bytes, the average round trip time (RTT) was the lowest, ~0.676 ㎲. The dMM scheduling algorithms, MIF and p-MIF, achieved delay less than 1 ㎲ for all MI traffic with less than 10% of transmission overhead.

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.70-75
• /
• 2023

With the recent proliferation of memory-intensive workloads such as deep learning, analyzing memory access characteristics for efficient memory management is becoming increasingly important. Since read and write operations in memory access have different characteristics, an efficient memory management policy should take into accountthe characteristics of thesetwo operationsseparately. Although some previous studies have considered the different characteristics of reads and writes, they require a modified hardware architecture supporting read bits and write bits. Unlike previous approaches, we propose a software-based management policy under the existing memory architecture for considering read/write characteristics. The proposed policy logically partitions memory space into the read/write area and the write area by making use of reference bits and dirty bits provided in modern paging systems. Simulation experiments with memory access traces show that our approach performs better than the CLOCK algorithm by 23% on average, and the effect is similar to the previous policy with hardware support.

• 한국정보과학회논문지:시스템및이론
• /
• 제32권9호
• /
• pp.457-464
• /
• 2005

본 논문에서는 임의의 좌표를 기준으로 17가지 접근방식을 지원하는 3차원 메모리 시스템을 제안한다. 제안하는 메모리 시스템은 메모리 모듈 할당 함수와 주소 할당 함수를 토대로 선 접근방식 13가지, 사각형 접근방식 3가지, 육면체 접근방식 1가지 등 모두 17가지 접근방식을 제공한다. 즉, 임의의 좌표에서 임의의 간격을 갖고 17가지 접근방식 중 어떠한 접근방식 내에서도 다수개의 데이타에 동시접근하는 기능을 제공한다. 이를 위해 제안하는 메모리 시스템은 메모리 모듈 선택 회로, 읽기/쓰기를 위한 데이타 라우팅 회로, 주소 계산 및 라우팅 회로들로 구성된다. 본 논문에서 제안하는 메모리 시스템은 응용 프로그램에 따라 쉽게 확장될 수 있으며, 메모리 시스템에 저장된 데이타를 개발자와 프로그래머가 논리적인 3차원 배열로 간주하여 처리할 수 있도록 데이타의 하드웨어 독립성을 지원한다 또한 제안한 메모리 시스템은 다양한 접근방식 내의 다수개의 데이타에 동시접근 할 수 있기 때문에 볼륨 렌더링이나 볼륨 클리핑 등과 같은 다양한 3차원 응용 분야 및 다중해상도를 지원하는 프레임 버퍼를 위한 시스템 구조의 메모리 시스템으로써 적합하다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권3호
• /
• 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.

• 전기전자학회논문지
• /
• 제10권1호
• /
• pp.22-29
• /
• 2006

본 논문에서는 마이크로프로세서와 주변블록 사이에서 SDRAM을 사용함에 있어서 DMA(Direct Memory Access)에 의한 효율적인 SDRAM 접근방식을 제시하고 있다. 여기에서 마이크로프로세서는 AMBA 버스를 통해서 SDRAM에 접근을 하고 DMA는 DMA 전용 버스를 통해서 SDRAM에 접근한다. 마이크로프로세서가 SDRAM에 접근하지 않고 다른 레지스터에 접근하거나, 아니면 마이크로프로세서 캐쉬에서 히트(hit)신호가 발생하여 SDRAM에 접근할 필요가 없을 때에 주변 블록에서는 DMA를 통해서 SDRAM에 접근하여 데이타를 읽거나 쓰기 동작을 통해서 SDRAM을 효율적으로 사용할 수 있다. 이 방법은 DMA가 마이크로프로세서의 SDRAM 억세스를 최소한의 방해로 SDRAM을 사용할 수 있다. 이와 같은 방법을 이용함으로써 전체적인 시스템 효율을 높여 약 16.8% 정도의 성능 향상 효과를 가져옴을 확인 할 수 있었다.

• 전자공학회논문지
• /
• 제51권4호
• /
• pp.33-41
• /
• 2014

본 논문에서는 모바일 시스템 환경에서 멀티포트 메모리 컨트롤러의 특성을 고려한 직접 메모리 접근 컨트롤러를 사용하여 고속 데이터 전송을 효과적으로 수행하는 메모리 액세스 방법을 보인다. 제안된 직접 메모리 접근 컨트롤러는 여러 개의 직접 메모리 접근 채널을 제어 할 수 있는 통합 채널 관리 기능을 제공하며, 그 채널들은 물리적으로 분리되어 서로 독립적으로 동작한다. 제안된 직접 메모리 접근 방법을 통한 데이터 전송을 이용함으로써 읽기 동작에 대하여 72%, 쓰기 동작에 대하여 69%의 데이터 전송 성능 향상을 얻었다. 특히, 4 채널 접근 모드에 대해서 제안된 방법이 기존 직접 메모리 접근 방법에 비하여 63% 적은 전체 전송 사이클을 가짐으로써 전송 성능 향상에 기여할 수 있음을 보인다.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제2권3호
• /
• pp.197-204
• /
• 2002

DRAM, SRAM, and FLASH memory are three major memory devices currently used in most electronic applications. But, they have very distinct attributes, therefore, each memory could be used only for limited applications. MRAM (Magneto-resistive Random Access Memory) is a promising candidate for a universal memory that meets all application needs with non-volatile, fast operational speed, and low power consumption. The simplest architecture of MRAM cell is a series of MTJ (Magnetic Tunnel Junction) as a data storage part and MOS transistor as a data selection part. To be a commercially competitive memory device, scalability is an important factor as well. This paper is testing the actual electrical parameters and the scaling factors to limit MRAM technology in the semiconductor based memory device by an actual integration of MRAM core cell. Electrical tuning of MOS/MTJ, and control of resistance are important factors for data sensing, and control of magnetic switching for data writing.

• 대한임베디드공학회논문지
• /
• 제11권2호
• /
• 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.