• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.5
• /
• pp.292-303
• /
• 2010

On-chip cache memories play an important role in both performance and energy consumption points of view in resource-constrained embedded systems by filtering many off-chip memory accesses. We propose a 2-level data cache architecture with a low energy-delay product tailored for the embedded systems. The L1 data cache is small and direct-mapped, and employs a write-through policy. In contrast, the L2 data cache is set-associative and adopts a write-back policy. Consequently, the L1 data cache is accessed in one cycle and is able to provide high cache bandwidth while the L2 data cache is effective in reducing global miss rate. To reduce the penalty of high miss rate caused by the small L1 cache and power consumption of address generation, we propose an ECP(Early Cache hit Predictor) scheme. The ECP predicts if the L1 cache has the requested data using both fast address generation and L1 cache hit prediction. To reduce high energy cost of accessing the L2 data cache due to heavy write-through traffic from the write buffer laid between the two cache levels, we propose a one-way write scheme. From our simulation-based experiments using a cycle-accurate simulator and embedded benchmarks, the proposed 2-level data cache architecture shows average 3.6% and 50% improvements in overall system performance and the data cache energy consumption.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.16 no.1
• /
• pp.80-90
• /
• 2016

Thanks to superior leakage energy efficiency compared to SRAM cells, STTRAM cells are considered as a promising alternative for a memory element in on-chip caches. However, the main disadvantage of STTRAM cells is high write energy and latency. In this paper, we propose a low-cost write filter (WF) cache which resides between the load/store queue and STTRAM-based L1 data cache. To maximize efficiency of the WF cache, the line allocation and access policies are optimized for reducing energy consumption of STTRAM-based L1 data cache. By efficiently filtering the write operations in the STTRAM-based L1 data cache, our proposed WF cache reduces energy consumption of the STTRAM-based L1 data cache by up to 43.0% compared to the case without the WF cache. In addition, thanks to the fast hit latency of the WF cache, it slightly improves performance by 0.2%.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.9-16
• /
• 2022

Today, with the advent of the 4th industrial revolution, IoT (Internet of Things) systems are advancing rapidly. For this reason, a various application with high-performance and large-capacity are emerging. Therefore, there is a need for low-power and high-performance memory for computing systems with these applications. In this paper, we propose an effective structure for the L1 cache memory, which consumes the most energy in the computing system. The proposed cache system is largely composed of two parts, the L1 main cache and the buffer cache. The main cache is 2 banks, and each bank consists of a 2-way set association. When the L1 cache hits, the data is copied into buffer cache according to the proposed algorithm. According to simulation, the proposed L1 cache system improved the performance of energy delay products by about 65% compared to the existing 4-way set associative cache memory.

• Journal of Computing Science and Engineering
• /
• v.11 no.2
• /
• pp.69-77
• /
• 2017

Recent GPUs have adopted cache memory to benefit general-purpose GPU (GPGPU) programs. However, unlike CPU programs, GPGPU programs typically have considerably less temporal/spatial locality. Moreover, the L1 data cache is used by many threads that access a data size typically considerably larger than the L1 cache, making it critical to bypass L1 data cache intelligently to enhance GPU cache performance. In this paper, we examine GPU cache access behavior and propose a simple hardware-based GPU cache bypassing method that can be applied to GPU applications without recompiling programs. Moreover, we introduce a hybrid method that integrates static profiling information and hardware-based bypassing to further enhance performance. Our experimental results reveal that hardware-based cache bypassing can boost performance for most benchmarks, and the hybrid method can achieve performance comparable to state-of-the-art compiler-based bypassing with considerably less profiling cost.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.13 no.3
• /
• pp.125-131
• /
• 2018

STT-RAM is attracting as a next generation Non-volatile memory for replacing cache memory with low leakage energy, high integration and memory access performance similar to SRAM. However, there is problem of write operations as the other Non_volatile memory. Hybrid cache memory using SRAM and STT-RAM is attracting attention as a cache memory structure with lowe power consumption. Despite this, reducing the leakage energy consumption by the STT-RAM is still lacking access to the Dynamic energy. In this paper, we proposed as energy management method such as a way-selection approach for hybrid L2 cache fo SRAM and STT-RAM and memory selection method of write/read operation. According to the simulation results, the proposed hybrid cache memory reduced the average energy consumption by 40% on SPEC CPU 2006, compared with SRAM cache memory.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.1
• /
• pp.43-54
• /
• 2010

The existing timeout based cache leakage management techniques reduce the leakage energy consumption of the cache significantly by switching off the power supply to the inactive cache line. Since these techniques were mainly proposed for single-processor systems, their efficiency is reduced significantly in multiprocessor systems with a shared L2 cache because of the cache interferences among simultaneously executing tasks. In this paper, we propose a novel cache partition strategy which partitions the shared L2 cache considering the inactive cycles of the cache line. Furthermore, we propose the adaptive task-aware timeout management technique which considers the characteristics of each task and adapts the timeout dynamically. Experimental results from the simulation show that the proposed technique reduces the leakage energy consumption of the shared L2 cache by 73% for the 2-way CMP and 56% for the 4-way CMP on average compared to the existing representative leakage management technique, respectively.

• KIPS Transactions on Computer and Communication Systems
• /
• v.1 no.1
• /
• pp.1-10
• /
• 2012

The way-lookup cache and the way-tracking cache are considered to be the most energy-efficient when used for level 1 and level 2 caches, respectively. This paper proposes an energy-efficient set-associative cache using the bi-mode way-selector that combines the way selecting techniques of the way-tracking cache and the way-lookup cache. The simulation results using an Alpha 21264-based system show that the bi-mode way-selecting L1 instruction cache consumes 27.57% of the energy consumed by the conventional set-associative cache and that it is as energy-efficient as the way-lookup cache when used for L1 instruction cache. The bi-mode way-selecting L1 data cache consumes 28.42% of the energy consumed by the conventional set-associative cache, which means that it is more energy-efficient than the way-lookup cache by 15.54% when used for L1 data cache. The bi-mode way-selecting L2 cache consumes 15.41% of the energy consumed by the conventional set-associative cache, which means that it is more energy-efficient than the way-tracking cache by 16.16% when used for unified L2 cache. These results show that the proposed cache can provide the best level of energy-efficiency regardless of the cache level.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.51-62
• /
• 2021

On-chip caches of graphics processing units (GPUs) have contributed to improved GPU performance by reducing long memory access latency. However, cache efficiency remains low despite the facts that recent GPUs have considerably mitigated the bottleneck problem of L1 data cache. Although the cache miss rate is a reasonable metric for cache efficiency, it is not necessarily proportional to GPU performance. In this study, we introduce a second key determinant to overcome the problem of predicting the performance gains from L1 data cache based on the assumption that miss rate only is not accurate. The proposed technique estimates the benefits of the cache by measuring the balance between cache efficiency and throughput. The throughput of the cache is predicted based on the warp occupancy information in the warp pool. Then, the warp occupancy is used for a second bypass phase when workloads show an ambiguous miss rate. In our proposed architecture, the L1 data cache is turned off for a long period when the warp occupancy is not high. Our two-level bypassing technique can be applied to recent GPU models and improves the performance by 6% on average compared to the architecture without bypassing. Moreover, it outperforms the conventional bottleneck-based bypassing techniques.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.5
• /
• pp.306-315
• /
• 2006

In general, the hit ratio of the first level cache is one of the most important factors in determining the performance of computer systems. Prefetching from lower level memory structure is one of the most useful techniques for improving the hit ratio of the first level cache. In this paper, we propose a prefetch on continuous same page access (CSPA) scheme which improves the prefetch efficiency of the instruction cache and reduces prefetch cost at the same time. The proposed CSPA scheme traces the page addresses of executed instructions to count how many times the same memory page is accessed continuously. To increase the prefetch efficiency, the CSPA scheme initiates prefetch only if the number of accesses to the same page exceeds the threshold value. Generally, the size of a L1 cache block is smaller than that of a L2 cache block. Therefore, one L2 cache block contains a number of L1 cache blocks. To reduce the number of unnecessary accesses to the L2 cache due to prefetch, the CSPA scheme enables prefetch only when the missed L1 block and the prefetch L1 block are in the same L2 cache block, leading to reduced prefetch cost. According to our simulations, the proposed prefetching scheme improves the performance by up to 6.7%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4B
• /
• pp.783-787
• /
• 2000

A microprocessor, which is used as a CPU for state-of-the-art personal computers, adopts 256KB or 512KB L2(Level 2) cache memory. This cache hires Direct Mapping Procedure, 32B Line Size, and no Write Allocation. In this cache architecture, we can expert about 2.5% hit ratio improvement by using 8-way Set Associative Mapping instead of Direct Mapping, 128B Line Size instead of 32B, and Write Allocation.