Enabling resource-efficient aiot system with cross-level optimization: A survey
The emerging field of artificial intelligence of things (AIoT, AI+ IoT) is driven by the
widespread use of intelligent infrastructures and the impressive success of deep learning …
widespread use of intelligent infrastructures and the impressive success of deep learning …
A modern primer on processing in memory
Modern computing systems are overwhelmingly designed to move data to computation. This
design choice goes directly against at least three key trends in computing that cause …
design choice goes directly against at least three key trends in computing that cause …
Ambit: In-memory accelerator for bulk bitwise operations using commodity DRAM technology
Many important applications trigger bulk bitwise operations, ie, bitwise operations on large
bit vectors. In fact, recent works design techniques that exploit fast bulk bitwise operations to …
bit vectors. In fact, recent works design techniques that exploit fast bulk bitwise operations to …
Benchmarking a new paradigm: Experimental analysis and characterization of a real processing-in-memory system
Many modern workloads, such as neural networks, databases, and graph processing, are
fundamentally memory-bound. For such workloads, the data movement between main …
fundamentally memory-bound. For such workloads, the data movement between main …
Tetris: Scalable and efficient neural network acceleration with 3d memory
The high accuracy of deep neural networks (NNs) has led to the development of NN
accelerators that improve performance by two orders of magnitude. However, scaling these …
accelerators that improve performance by two orders of magnitude. However, scaling these …
Drisa: A dram-based reconfigurable in-situ accelerator
Data movement between the processing units and the memory in traditional von Neumann
architecture is creating the" memory wall" problem. To bridge the gap, two approaches, the …
architecture is creating the" memory wall" problem. To bridge the gap, two approaches, the …
Google workloads for consumer devices: Mitigating data movement bottlenecks
We are experiencing an explosive growth in the number of consumer devices, including
smartphones, tablets, web-based computers such as Chromebooks, and wearable devices …
smartphones, tablets, web-based computers such as Chromebooks, and wearable devices …
SIMDRAM: A framework for bit-serial SIMD processing using DRAM
N Hajinazar, GF Oliveira, S Gregorio… - Proceedings of the 26th …, 2021 - dl.acm.org
Processing-using-DRAM has been proposed for a limited set of basic operations (ie, logic
operations, addition). However, in order to enable full adoption of processing-using-DRAM …
operations, addition). However, in order to enable full adoption of processing-using-DRAM …
Processing data where it makes sense: Enabling in-memory computation
Today's systems are overwhelmingly designed to move data to computation. This design
choice goes directly against at least three key trends in systems that cause performance …
choice goes directly against at least three key trends in systems that cause performance …
Rowhammer: A retrospective
This retrospective paper describes the RowHammer problem in dynamic random access
memory (DRAM), which was initially introduced by Kim et al. at the ISCA 2014 Conference …
memory (DRAM), which was initially introduced by Kim et al. at the ISCA 2014 Conference …