Embedded RISC Core Research Articles

Performance Improvement and Power Consumption Reduction of an Embedded RISC Core

This paper presents a branch prediction algorithm and a 4-way set-associative cache for performance improvement of an embedded RISC core and a clock-gating algorithm with observability don’t care (ODC) operation to reduce the power consumption of the core. The branch prediction algorithm has a structure using a branch target buffer (BTB) and 4-way set associative cache that has a lower miss rate than a direct-mapped cache. Pseudo-least recently used (LRU) policy is used for reducing the number of LRU bits. The clock-gating algorithm reduces dynamic power consumption. As a result of estimation of the performance and the dynamic power, the performance of the OpenRISC core applied to the proposed architecture is improved about 29% and the dynamic power of the core with the Chartered 0.18 μm technology library is reduced by 16%.

임베디드 RISC 코어의 성능 및 전력 개선

본 논문에서는 임베디드 RISC 코어의 성능 및 전력 소모 개선을 위해 동적 분기예측 구조, 4원 집합연관 캐쉬 구조, ODC 연산을 이용한 클록 게이팅 기법을 제시한다. 동적 분기 예측 구조는 분기 명령에 대해 다음에 실행될 명령에 대한 예측 주소를 저장하는 BTB (Branch Target Buffer)를 사용한다. 4원 집합연관 캐쉬는 네 개의 메모리 블록을 한 개의 캐쉬 블록에 사상되는 구조로서 직접사상 캐쉬에 비해 접근 실패율이 낮고 라인 교체 방식으로 Pseudo-LRU 방식을 채택하여 LRU 정보를 저장하는 비트 수를 감소시킨다. ODC를 이용한 클록게이팅 기법은 논리합성 개념인 무관조건의 입출력 ODC 조건을 찾아 클록 게이팅 로직을 삽입함으로써 동적 소비전력을 줄인다. 제시한 구조들을 임베디드 RISC 코어인 OpenRISC 코어에 적용하여 성능을 측정한 결과, 기존 OpenRISC 코어 대비 실행시간이 약 29% 향상 되었고, Chartered <TEX>$0.18{\mu}m$</TEX> 라이브러리를 이용하여 동적 전력을 측정한 결과, 기존 OpenRISC 코어 대비 소비전력이 16% 이상 감소하였다. This paper presents a branch prediction algorithm and a 4-way set-associative cache for performance improvement of embedded RISC core and a clock-gating algorithm using ODC (Observability Don't Care) operation to improve the power consumption of the core. The branch prediction algorithm has a structure using BTB(Branch Target Buffer) and 4-way set associative cache has lower miss rate than direct-mapped cache. Pseudo-LRU Policy, which is one of the Line Replacement Policies, is used for decreasing the number of bits that store LRU value. The clock gating algorithm reduces dynamic power consumption. As a result of estimation of performance and dynamic power, the performance of the OpenRISC core applied the proposed architecture is improved about 29% and dynamic power of the core using Chartered <TEX>$0.18{\mu}m$</TEX> technology library is reduced by 16%.

Platform-Based MPEG-4 SOC Design for Video Communications

An MPEG-4 video coding SOC design is presented in this paper. We adopt platform-based architecture with an embedded RISC core and efficient memory organization. A motion estimator supporting predictive diamond search and spiral full search is implemented for compromise between compression performance and design cost. The proposed data reuse scheme reduces required memory access bandwidth. For texture coding path, an interleaving DCT/IDCT scheduling with substructure sharing technique is proposed. Several key modules are integrated into an efficient platform in hardware/software co-design fashion. The cost-efficient video encoder SOC consumes 256.8 mW at 40 MHz and achieves real-time encoding of 30 CIF (352×288) frames per second.

A cost-effective design for MPEG2 audio decoder with embedded RISC core

MPEG2 audio decoding algorithms are involved of several complex-coding techniques and therefore difficult to do efficient dedicated architecture design. In this paper, we present an effective architecture for the MPEG2 audio decoder. The MPEG2 audio algorithms can be roughly divided into two types of operations. The first type is regular but computation-intensive such as filtering, matrixing, degrouping, and transformation operations. The second type is not regular but computation-intensive such as parsing bitstream, setting operation mode and controlling of all system operations. Based on standard cell design technique, the chip size is 6.4/spl times/6.4 mm/sup 2/, and the tested chip can run at maximum 43.5 MHz clock rate.