Memory cell (computing) | EPFL Graph Search

The memory cell is the fundamental building block of computer memory. The memory cell is an electronic circuit that stores one bit of binary information and it must be set to store a logic 1 (high voltage level) and reset to store a logic 0 (low voltage level). Its value is maintained/stored until it is changed by the set/reset process. The value in the memory cell can be accessed by reading it. Over the history of computing, different memory cell architectures have been used, including core memory and bubble memory. Today, the most common memory cell architecture is MOS memory, which consists of metal–oxide–semiconductor (MOS) memory cells. Modern random-access memory (RAM) uses MOS field-effect transistors (MOSFETs) as flip-flops, along with MOS capacitors for certain types of RAM. The SRAM (static RAM) memory cell is a type of flip-flop circuit, typically implemented using MOSFETs. These require very low power to keep the stored value when not being accessed. A second type, DRAM

Reference current generator, and method of programming, adjusting and/or operating same

Marija Blagojevic, Michel Declercq, Maher Kayal, Marc Pastre, Lionel Portmann

There are many inventions described and illustrated herein. In a first aspect, the present invention is a technique and circuitry for reading data that is stored in memory cells. In one embodiment of this aspect, the present invention is a technique and circuitry for generating a reference current that is used, in conjunction with a sense amplifier, to read data that is stored in memory cells of a DRAM device. The technique and circuitry for generating a reference current may be implemented using an analog configuration, a digital configuration, and/or combinations of analog and digital configurations.

2005

Semiconductor memory cell, array, architecture and device, and method of operating same

Serguei Okhonin

There are many inventions described and illustrated herein. In a first aspect, the present invention is directed to a memory cell and technique of reading data from and writing data into that memory cell. In this regard, in one embodiment of this aspect of the invention, the memory cell includes two transistors which store complementary data states. That is, the two-transistor memory cell includes a first transistor that maintains a complementary state relative to the second transistor. As such, when programmed, one of the transistors of the memory cell stores a logic low (a binary "0") and the other transistor of the memory cell stores a logic high (a binary "1"). The data state of the two-transistor complementary memory cell may be read and/or determined by sampling, sensing measuring and/or detecting the polarity of the logic states stored in each transistor of complementary memory cell. That is, the two-transistor complementary memory cell is read by sampling, sensing measuring and/or detecting the difference in signals (current or voltage) stored in the two transistors.

2007

In-Memory Hardware and Architectural Extensions for Workloads Acceleration

William Andrew Simon

Utilization of edge devices has exploded in the last decade, with such use cases as wearable devices, autonomous driving, and smart homes. As their ubiquity grows, so do expectations of their capabilities. Simultaneously, their formfactor and use cases limit power availability. Thus, improving performance while limiting area and power consumption is paramount. In this vein, in-SRAM Computing (iSC) moves computation from the CPU into the SRAM memory hierarchy. This has multiple benefits. First, reduced data movement mitigates power consumption and latency. Second, the entire memory array can be utilized to perform hundreds of concurrent operations. This thesis exploits iSC while addressing the aforementioned challenges via a BitLine Accelerator for Devices on the Edge (BLADE). BLADE can be implemented in any SRAM system and utilizes local wordline groups to perform computations at a frequency 2.8x higher than state-of-the-art iSC architectures. BLADE is thoroughly simulated, fabricated, and benchmarked at the transistor, architecture, and software abstraction levels. Experimental results demonstrate performance/energy gains over an equivalent NEON accelerated processor for a variety of edge device workloads, namely, cryptography (4x performance gain/6x energy reduction), video encoding (6x/2x), and convolutional neural networks (3x/1.5x), while maintaining the highest frequency/energy ratio (up to 2.2Ghz@1V) of any conventional iSC computing architecture, and a low area overhead of less than 8%. With BLADE implemented, the possibilities for enhancement are manifold, with one such example being approximate computing. To this end, a CArryless Partial Product InExact Multiplier (CAPPIEM) halves multiplication latency while incurring negligible area overhead. As a standalone multiplier, CAPPIEM reduces the area/power-delay-product by 73/43%, respectively. Further, CAPPIEM has the unique property of computing exact results when one input is a Fibonacci encoded value. This property is exploited via a retraining strategy which quantizes neural network weights to Fibonacci values, ensuring exact computation during inference. Benchmarking on Squeezenet 1.0, DenseNet-121, and ResNet-18 demonstrate accuracy degradations of only 0.4/1.1/1.7%, while improving training time by up to 300x. A second BLADE enhancement is the use of Hybrid Caches (HCs) consisting of both SRAM and eNVRAM bitcells. HCs increase capacity and power savings via eNVRAM's small area footprint and low leakage energy. However, eNVRAMs also incur long write latency and limited endurance. To mitigate these drawbacks, this thesis presents SHyCache, an HC architecture and supporting programming model. By explicitly allocating variables with high read/write access ratios to the eNVRAM array, SHyCache reduces access time, power consumption, and area overhead, while maintaining maximal utilization efficiency and ease of programming. Benchmarks on a range of cache hierarchy variations using three deep neural networks demonstrate a design space that can be exploited to optimize performance, power consumption, or endurance, while demonstrating maximum performance gains of 1.7/1.4/1.3x and power consumption reductions of 5.1/5.2/5.4x.

EPFL2022

In-Memory Hardware and Architectural Extensions for Workloads Acceleration

William Andrew Simon

EPFL2022