CIDAN-XE: Computing in DRAM with Artificial Neurons
This paper presents a DRAM-based processing-in-memory (PIM) architecture, called CIDAN-XE. It contains a novel computing unit called the neuron processing element (NPE). Each NPE can perform a variety of operations that include logical, arithmetic, relational, and predicate operations on multi-bit o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-02-01
|
| Series: | Frontiers in Electronics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/felec.2022.834146/full |
| _version_ | 1819282992516825088 |
|---|---|
| author | Gian Singh Ankit Wagle Sunil Khatri Sarma Vrudhula |
| author_facet | Gian Singh Ankit Wagle Sunil Khatri Sarma Vrudhula |
| author_sort | Gian Singh |
| collection | DOAJ |
| description | This paper presents a DRAM-based processing-in-memory (PIM) architecture, called CIDAN-XE. It contains a novel computing unit called the neuron processing element (NPE). Each NPE can perform a variety of operations that include logical, arithmetic, relational, and predicate operations on multi-bit operands. Furthermore, they can be reconfigured to switch operations during run-time without increasing the overall latency or power of the operation. Since NPEs consume a small area and can operate at very high frequencies, they can be integrated inside the DRAM without disrupting its organization or timing constraints. Simulation results on a set of operations such as AND, OR, XOR, addition, multiplication, etc., show that CIDAN-XE achieves an average throughput improvement of 72X/5.4X and energy efficiency improvement of 244X/29X over CPU/GPU. To further demonstrate the benefits of using CIDAN-XE, we implement several convolutional neural networks and show that CIDAN-XE can improve upon the throughput and energy efficiency over the latest PIM architectures. |
| first_indexed | 2024-12-24T01:24:24Z |
| format | Article |
| id | doaj.art-14fc3552468049df9cb5c5c9519a24f1 |
| institution | Directory Open Access Journal |
| issn | 2673-5857 |
| language | English |
| last_indexed | 2024-12-24T01:24:24Z |
| publishDate | 2022-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Electronics |
| spelling | doaj.art-14fc3552468049df9cb5c5c9519a24f12022-12-21T17:22:34ZengFrontiers Media S.A.Frontiers in Electronics2673-58572022-02-01310.3389/felec.2022.834146834146CIDAN-XE: Computing in DRAM with Artificial NeuronsGian Singh0Ankit Wagle1Sunil Khatri2Sarma Vrudhula3School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, United StatesSchool of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, United StatesDepartment of Electrical and Computer Engineering, Texas A&M University, College Station, TX, United StatesSchool of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, United StatesThis paper presents a DRAM-based processing-in-memory (PIM) architecture, called CIDAN-XE. It contains a novel computing unit called the neuron processing element (NPE). Each NPE can perform a variety of operations that include logical, arithmetic, relational, and predicate operations on multi-bit operands. Furthermore, they can be reconfigured to switch operations during run-time without increasing the overall latency or power of the operation. Since NPEs consume a small area and can operate at very high frequencies, they can be integrated inside the DRAM without disrupting its organization or timing constraints. Simulation results on a set of operations such as AND, OR, XOR, addition, multiplication, etc., show that CIDAN-XE achieves an average throughput improvement of 72X/5.4X and energy efficiency improvement of 244X/29X over CPU/GPU. To further demonstrate the benefits of using CIDAN-XE, we implement several convolutional neural networks and show that CIDAN-XE can improve upon the throughput and energy efficiency over the latest PIM architectures.https://www.frontiersin.org/articles/10.3389/felec.2022.834146/fullartificial neuronprocessing in-memoryin-memory computingDRAMmemory wallenergy efficient architectures |
| spellingShingle | Gian Singh Ankit Wagle Sunil Khatri Sarma Vrudhula CIDAN-XE: Computing in DRAM with Artificial Neurons Frontiers in Electronics artificial neuron processing in-memory in-memory computing DRAM memory wall energy efficient architectures |
| title | CIDAN-XE: Computing in DRAM with Artificial Neurons |
| title_full | CIDAN-XE: Computing in DRAM with Artificial Neurons |
| title_fullStr | CIDAN-XE: Computing in DRAM with Artificial Neurons |
| title_full_unstemmed | CIDAN-XE: Computing in DRAM with Artificial Neurons |
| title_short | CIDAN-XE: Computing in DRAM with Artificial Neurons |
| title_sort | cidan xe computing in dram with artificial neurons |
| topic | artificial neuron processing in-memory in-memory computing DRAM memory wall energy efficient architectures |
| url | https://www.frontiersin.org/articles/10.3389/felec.2022.834146/full |
| work_keys_str_mv | AT giansingh cidanxecomputingindramwithartificialneurons AT ankitwagle cidanxecomputingindramwithartificialneurons AT sunilkhatri cidanxecomputingindramwithartificialneurons AT sarmavrudhula cidanxecomputingindramwithartificialneurons |