System Design for Computation-in-Memory: From Primitive to Complex Functions

Zahedi, Mahdi; Shahroodi, Taha; Custers, Geert; Singh, Abhairaj; Wong, Stephan; Hamdioui, Said

doi:10.1109/vlsi-soc54400.2022.9939571

Cited by 8 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Binarization or, more generally, quantization of the forwarding signals has been extensively investigated to reduce the computational loads for inference in edge applications. [16] We compared the inference accuracy of our work with other resistive random access memory (RRAM)-based binary fully connected and convolutional neural networks in Table S3 and S4 (Supporting Information), [44][45][46] respectively. However, these works generally focus on the inference process without the online training and come at a cost of decreased inference accuracy.…”

Section: Discussionmentioning

confidence: 99%

Binary‐Stochasticity‐Enabled Highly Efficient Neuromorphic Deep Learning Achieves Better‐than‐Software Accuracy

Li,

Wang,

Wang

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

In this work, the requirement of using high‐precision (HP) signals is lifted and the circuits for implementing deep learning algorithms in memristor‐based hardware are simplified. The use of HP signals is required by the backpropagation learning algorithm since the gradient descent learning rule relies on the chain product of partial derivatives. However, it is both challenging and biologically implausible to implement such an HP algorithm in noisy and analog memristor‐based hardware systems. Herein, it is demonstrated that the requirement for HP signals handling is not necessary and more efficient deep learning can be achieved when using a binary stochastic learning algorithm. The new algorithm proposed in this work modifies elementary neural network operations, which improves energy efficiency by two orders of magnitude compared to traditional memristor‐based hardware and three orders of magnitude compared to complementary metal–oxide–semiconductor‐based hardware. It also provides better accuracy in pattern recognition tasks than the HP learning algorithm benchmarks.

show abstract

Section: Discussionmentioning

confidence: 99%

Binary‐Stochasticity‐Enabled Highly Efficient Neuromorphic Deep Learning Achieves Better‐than‐Software Accuracy

Li,

Wang,

Wang

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Resistive memories or memristive devices, such as ReRAM, PCM, and STT-MRAM [59,69,119,132], have recently been introduced as suitable candidates for both storage and computation units that can efficiently perform vector-matrix multiplication [138] and logical bulk bit-wise operations [26,73,113,114,139], as they can follow Kirchhoff's law inherently [121]. Therefore, many recent works [9,26,27,111,112,139,[143][144][145] exploit these devices in their CIM architectures. Memristor devices also enjoy non-volatility, highdensity, and near-zero standby power [73,119,139].…”

Section: Memristor-based Cim and Associated Non-idealitiesmentioning

confidence: 99%

“…2 [9,26,27,111,139] alongside its possible non-idealities. This memristor-based structure can suffer from at least four types of non-idealities or variations that can eventually affect the results of the enabled VMM operation, i.e., lead to errors in the VMM result: (1) The non-ideal digital to analog converter (DAC), due to the effective resistive load (known as 𝑅 𝐿𝑜𝑎𝑑 ) in its circuit [55], (2) Variation of synaptic conductance, which includes both imperfect programming operation (commonly known as write variations) and the process variation that exist in memristors [4,23,70,148], (3) The wire resistance and sneak paths, due to imperfect wires (i.e., wires with different resistances) and the changes in the voltages of the internal nodes while performing a VMM operation [56,148], and (4) non-ideal sensing circuit or analog to digital converters (ADCs), due to rigid or hard-to-accurately-change references used for distinguishing/sensing the end result [55,144]. Our work focuses on these specific non-idealities inherent to memristor technologies in a CIM architecture.…”

Section: Memristor-based Cim and Associated Non-idealitiesmentioning

confidence: 99%

“…Many previous works investigate how to provide new functionality using compute-capable memories based on conventional (e.g., [1,2,36,40,43,72,99,108,110]) and emerging memory technologies (e.g., [9,27,56,59,68,73,101,111,116,117,119,121,139,144]) to help solve the data movement overheads in today's systems. These works propose new functionality in at least three major categories: (1) support for logical operations (e.g., [26,73,86,110,119,121,139,144]), (2) support for complex operations, functions, and applications (e.g., [1,36,72,89,111,112,116,117,143]), and (3) programming and system support for the integration and adoption of such accelerators (e.g., [2,3,9,19,27,55,…”

Section: Computation-in-memory Acceleratorsmentioning

confidence: 99%

See 1 more Smart Citation

Demeter: A Fast and Energy-Efficient Food Profiler Using Hyperdimensional Computing in Memory

et al. 2022

View full text Add to dashboard Cite

Food profiling is an essential step in any food monitoring system needed to prevent health risks and potential frauds in the food industry. Significant improvements in sequencing technologies are pushing food profiling to become the main computational bottleneck. State-of-the-art profilers are unfortunately too costly for food profiling. Our goal is to design a food profiler that solves the main limitations of existing profilers, namely (1) working on massive data structures and (2) incurring considerable data movement, for a real-time monitoring system. To this end, we propose Demeter, the first platform-independent framework for food profiling. Demeter overcomes the first limitation through the use of hyperdimensional computing (HDC) and efficiently performs the accurate few-species classification required in food profiling. We overcome the second limitation by the use of an in-memory hardware accelerator for Demeter (named Acc-Demeter) based on memristor devices. Acc-Demeter actualizes several domain-specific optimizations and exploits the inherent characteristics of memristors to improve the overall performance and energy consumption of Acc-Demeter. We compare Demeter's accuracy with other industrial food profilers using detailed software modeling. We synthesize Acc-Demeter's required hardware using UMC's 65nm library by considering an accurate PCM model based on silicon-based prototypes. Our evaluations demonstrate that Acc-Demeter achieves a (1) throughput improvement of 192× and 724× and (2) memory reduction of 36× and 33× compared to Kraken2 and MetaCache (2 state-of-the-art profilers), respectively, on typical food-related databases. Demeter maintains an acceptable profiling accuracy (within 2% of existing tools) and incurs a very low area overhead.

show abstract

“…Figure 2 compares three leading memristor technologies (RRAM, MRAM, and PCM) with other conventional mem- List of some potential applications/algorithms/kernels that can be executed using memristor-based CIM [27].…”

Section: Introductionmentioning

confidence: 99%

Efficient Signed Arithmetic Multiplication on Memristor-Based Crossbar

et al. 2023

Self Cite

View full text Add to dashboard Cite

The vast potential of memristor-based computation-in-memory (CIM) engines has mainly triggered the mapping of best-suited applications. Nevertheless, with additional support, existing applications can also benefit from CIM. In particular, this paper proposes an energy and area-efficient CIM-based methodology to perform arithmetic signed matrix multiplications. Our approach combines a) the mapping of the signed operands on the 1T1R crossbar, and b) the augmentation of the periphery with customized circuits to support the execution of shift and accumulate needed for the arithmetic operations. The operand mapping is performed without the need for sign extension; hence, reducing the required memory size. To demonstrate the superiority of our scheme as compared with the state-of-the-art, simulations are performed for different case studies including a neural network and two kernels which are taken from the Polybench/C benchmark suite. The results show that our approach achieves up to 8× energy-saving and 3× area-saving compared with other CIM-based prior works. Memristor, computation-in-memory, signed computation. INDEX TERMS

show abstract

System Design for Computation-in-Memory: From Primitive to Complex Functions

Cited by 8 publications

References 43 publications

Binary‐Stochasticity‐Enabled Highly Efficient Neuromorphic Deep Learning Achieves Better‐than‐Software Accuracy

Binary‐Stochasticity‐Enabled Highly Efficient Neuromorphic Deep Learning Achieves Better‐than‐Software Accuracy

Demeter: A Fast and Energy-Efficient Food Profiler Using Hyperdimensional Computing in Memory

Efficient Signed Arithmetic Multiplication on Memristor-Based Crossbar

Contact Info

Product

Resources

About