ReMAM: Low energy Resistive Multi-stage Associative Memory for energy efficient computing

Proceedings of the 24th Asia and South Pacific Design Automation Conference

2019

Self Cite

Associative memory in form of look-up table can decrease the energy consumption of GPGPU applications by exploiting data locality and reducing the number redundant computations. State of the art architectures utilize associative memory as static look-up tables. Static designs lack the ability to adapt to applications at runtime, limiting them to small segments of code with high redundancy. In this paper, we propose an adaptive look-up based approach, called ALOOK, which uses a dynamic update policy to maintain a set of recently used operations in associative memory. ALOOK updates with values computed by floating point units at runtime to adapt to the workload and matches the stored results to avoid recomputing similar operations. ALOOK utilizes a novel FPU architecture which accelerates GPU computation by parallelizing the operation lookup process. We test the efficiency of ALOOK on image processing, general purpose, and machine learning applications by integrating it beside FPUs in an AMD Southern Island GPU. Our evaluation shows that ALOOK provides 3.6× EDP (Energy Delay Product) and 32.8% performance speedup, compared to an unmodified GPU, for applications accepting less than 5% output error. The proposed ALOOK architecture improves the GPU performance by 2.0× as compared to state-of-the-art computational reuse methods for the same level of output error. CCS CONCEPTS • Computing methodologies → Machine learning approaches; Supervised learning;

Section: Related Workmentioning

confidence: 99%

“…Many of these applications involve a large number of redundant computations which can be exploited to save energy by using lookup tables composed of associative memory [18][19][20][21]. Commonly computed values are stored in memory rather than recomputing the same result repeatedly.…”

mentioning

confidence: 99%

ALook

Peroni

Proceedings of the 24th Asia and South Pacific Design Automation Conference

2019

Self Cite

“…Hanyu, et al in [21] introduced 5T-4MTJ TCAM cell which searches input data on cell complementary with very high sense margin. However, the energy consumption of NVM-based TCAMs is still high because of high number of charge and discharge cycles for each search operation [14], [6]. Work in [24] showed that using large temporal memory for computation reuse is not efficient in CMOS, hence they combined both temporal and spatial reuse to get a high hit rate.…”

Section: Related Workmentioning

confidence: 99%

“…This energy limits the application of TCAMs to classification [11] and IP look-up [12]. Voltage overscaling (VOS) has been used on CMOS-based TCAMs to reduce the energy consumption [13], [14]. However, this increases the system error-rate due to process variations and timing errors.…”

Section: Introductionmentioning

confidence: 99%

Approximate Computing Using Multiple-Access Single-Charge Associative Memory

Patil

IEEE Trans. Emerg. Topics Comput.

2018

Self Cite

Memory-based computing using associative memory is a promising way to reduce the energy consumption of important classes of streaming applications by avoiding redundant computations. A set of frequent patterns that represent basic functions are pre-stored in Ternary Content Addressable Memory (TCAM) and reused. The primary limitation to using associative memory in modern parallel processors is the large search energy required by TCAMs. In TCAMs, all rows that match, except hit rows, precharge and discharge for every search operation, resulting in high energy consumption. In this paper, we propose a new Multiple-Access Single-Charge (MASC) TCAM architecture which is capable of searching TCAM contents multiple times with only a single precharge cycle. In contrast to previous designs, the MASC TCAM keeps the match-line voltage of all miss-rows high and uses their charge for the next search operation, while only the hit rows discharge. We use periodic refresh to control the accuracy of the search. We also implement a new type of approximate associative memory by setting longer refresh times for MASC TCAMs, which yields search results within 1-2 bit Hamming distances of the exact value. To further decrease the energy consumption of MASC TCAM and reduce the area, we implement MASC with crossbar TCAMs. Our evaluation on AMD Southern Island GPU shows that using MASC (crossbar MASC) associative memory can improve the average floating point units energy efficiency by 33.4%, 38.1%, and 36.7% (37.7%, 42.6%, and 43.1%) for exact matching, selective 1-HD and 2-HD approximations respectively, providing an acceptable quality of service (PSNR>30dB and average relative error<10%). This shows that MASC (crossbar MASC) can achieve 1.77X (1.93X) higher energy savings as compared to the state of the art implementation of GPGPU that uses voltage overscaling on TCAM.

“…In computing, the goal of this approach is to store common inputs and their corresponding outputs. This style of associative memory can retrieve the closest output for given inputs in order to reduce power consumption [19,20]. This approach does not work well in applications without a large number of redundant calculations.…”

Section: Related Workmentioning

confidence: 99%

Cfpu

Peroni

Proceedings of the 54th Annual Design Automation Conference 2017

2017

Self Cite

Many applications, such as machine learning and data sensing are statistical in nature and can tolerate some level of inaccuracy in their computation. Approximate computation is a viable method to save energy and increase performance by trading energy for accuracy. There are a number of proposed approximate solutions, however, they are limited to a small range of applications because they cannot control the error rate of their output. In this paper, we propose a novel approximate floating point multiplier, called CFPU, which significantly reduces energy and improves performance of multiplication at the expense of accuracy. Our design approximately models multiplication by replacing the most costly step of the operation with a lower energy alternative. In order to tune the level of approximation, CFPU dynamically identifies the inputs which will produce the largest approximation error and processes them in precise CFPU mode. We showed that our CFPU can outperforms a standard FPU when at least 4% of multiplications are performed in approximate mode. In our tested applications this percentage of multiplications is substantially higher, leading to significant energy savings. Our experimental evaluation on AMD Southern Island GPU shows that replacing the proposed CFPU with traditional FPUs results in 77% energy savings and 3.5× energy-delay product improvement over eight general OpenCL applications while providing acceptable quality of service. In addition, for the same level of accuracy, the CFPU provides 2.4× energy-delay product improvement compared to stateof-the-art approximate multipliers.