STeP-CiM: Strain-Enabled Ternary Precision Computation-In-Memory Based on Non-Volatile 2D Piezoelectric Transistors
We proposed 2D piezoelectric FET (PeFET)–based compute-enabled non-volatile memory for ternary deep neural networks (DNNs). PeFETs hinge on ferroelectricity for bit storage and piezoelectricity for bit sensing, exhibiting inherently amenable features for computation-in-memory of dot products of weig...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-07-01
|
| Series: | Frontiers in Nanotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnano.2022.905407/full |
| _version_ | 1818109471361073152 |
|---|---|
| author | Niharika Thakuria Reena Elangovan Sandeep K. Thirumala Anand Raghunathan Sumeet K. Gupta |
| author_facet | Niharika Thakuria Reena Elangovan Sandeep K. Thirumala Anand Raghunathan Sumeet K. Gupta |
| author_sort | Niharika Thakuria |
| collection | DOAJ |
| description | We proposed 2D piezoelectric FET (PeFET)–based compute-enabled non-volatile memory for ternary deep neural networks (DNNs). PeFETs hinge on ferroelectricity for bit storage and piezoelectricity for bit sensing, exhibiting inherently amenable features for computation-in-memory of dot products of weights and inputs in the signed ternary regime. PeFETs consist of a material with ferroelectric and piezoelectric properties coupled with a transition metal dichalcogenide channel. We utilized (a) ferroelectricity to store binary bits (0/1) in the form of polarization (−P/+P) and (b) polarization-dependent piezoelectricity to read the stored state by means of strain-induced bandgap change in the transition metal dichalcogenide channel. The unique read mechanism of PeFETs enables us to expand the traditional association of +P (−P) with low (high) resistance states to their dual high (low) resistance depending on read voltage. Specifically, we demonstrated that +P (−P) stored in PeFETs can be dynamically configured in (a) a low (high) resistance state for positive read voltages and (b) their dual high (low) resistance states for negative read voltages, without afflicting a read disturb. Such a feature, which we named as polarization-preserved piezoelectric effect reversal with dual voltage polarity (PiER), is unique to PeFETs and has not been shown in hitherto explored memories. We leveraged PiER to propose a Strain-enabled Ternary Precision Computation-in-Memory (STeP-CiM) cell with capabilities of computing the scalar product of the stored weight and input, both of which are represented with signed ternary precision. Furthermore, using multi-word line assertion of STeP-CiM cells, we achieved massively parallel computation of dot products of signed ternary inputs and weights. Our array-level analysis showed 91% lower delay and improvements of 15% and 91% in energy for in-memory multiply-and-accumulate operations compared to near-memory design approaches based on 2D FET–based SRAM and PeFET, respectively. We also analyzed the system-level implications of STeP-CiM by deploying it in a ternary DNN accelerator. STeP-CiM exhibits 6.11× to 8.91× average improvement in performance and 3.2× average improvement in energy over SRAM-based near-memory design. We also compared STeP-CiM to near-memory design based on PeFETs showing 5.67× to 6.13× average performance improvement and 6.07× average energy savings. |
| first_indexed | 2024-12-11T02:31:47Z |
| format | Article |
| id | doaj.art-2495a7c01ee4484db3656d39ee2c1c5e |
| institution | Directory Open Access Journal |
| issn | 2673-3013 |
| language | English |
| last_indexed | 2024-12-11T02:31:47Z |
| publishDate | 2022-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Nanotechnology |
| spelling | doaj.art-2495a7c01ee4484db3656d39ee2c1c5e2022-12-22T01:23:49ZengFrontiers Media S.A.Frontiers in Nanotechnology2673-30132022-07-01410.3389/fnano.2022.905407905407STeP-CiM: Strain-Enabled Ternary Precision Computation-In-Memory Based on Non-Volatile 2D Piezoelectric TransistorsNiharika ThakuriaReena ElangovanSandeep K. ThirumalaAnand RaghunathanSumeet K. GuptaWe proposed 2D piezoelectric FET (PeFET)–based compute-enabled non-volatile memory for ternary deep neural networks (DNNs). PeFETs hinge on ferroelectricity for bit storage and piezoelectricity for bit sensing, exhibiting inherently amenable features for computation-in-memory of dot products of weights and inputs in the signed ternary regime. PeFETs consist of a material with ferroelectric and piezoelectric properties coupled with a transition metal dichalcogenide channel. We utilized (a) ferroelectricity to store binary bits (0/1) in the form of polarization (−P/+P) and (b) polarization-dependent piezoelectricity to read the stored state by means of strain-induced bandgap change in the transition metal dichalcogenide channel. The unique read mechanism of PeFETs enables us to expand the traditional association of +P (−P) with low (high) resistance states to their dual high (low) resistance depending on read voltage. Specifically, we demonstrated that +P (−P) stored in PeFETs can be dynamically configured in (a) a low (high) resistance state for positive read voltages and (b) their dual high (low) resistance states for negative read voltages, without afflicting a read disturb. Such a feature, which we named as polarization-preserved piezoelectric effect reversal with dual voltage polarity (PiER), is unique to PeFETs and has not been shown in hitherto explored memories. We leveraged PiER to propose a Strain-enabled Ternary Precision Computation-in-Memory (STeP-CiM) cell with capabilities of computing the scalar product of the stored weight and input, both of which are represented with signed ternary precision. Furthermore, using multi-word line assertion of STeP-CiM cells, we achieved massively parallel computation of dot products of signed ternary inputs and weights. Our array-level analysis showed 91% lower delay and improvements of 15% and 91% in energy for in-memory multiply-and-accumulate operations compared to near-memory design approaches based on 2D FET–based SRAM and PeFET, respectively. We also analyzed the system-level implications of STeP-CiM by deploying it in a ternary DNN accelerator. STeP-CiM exhibits 6.11× to 8.91× average improvement in performance and 3.2× average improvement in energy over SRAM-based near-memory design. We also compared STeP-CiM to near-memory design based on PeFETs showing 5.67× to 6.13× average performance improvement and 6.07× average energy savings.https://www.frontiersin.org/articles/10.3389/fnano.2022.905407/fulldeep neural networkferroelectricin-memory-computingnon-volatile memorypiezoelectricultralow precision |
| spellingShingle | Niharika Thakuria Reena Elangovan Sandeep K. Thirumala Anand Raghunathan Sumeet K. Gupta STeP-CiM: Strain-Enabled Ternary Precision Computation-In-Memory Based on Non-Volatile 2D Piezoelectric Transistors Frontiers in Nanotechnology deep neural network ferroelectric in-memory-computing non-volatile memory piezoelectric ultralow precision |
| title | STeP-CiM: Strain-Enabled Ternary Precision Computation-In-Memory Based on Non-Volatile 2D Piezoelectric Transistors |
| title_full | STeP-CiM: Strain-Enabled Ternary Precision Computation-In-Memory Based on Non-Volatile 2D Piezoelectric Transistors |
| title_fullStr | STeP-CiM: Strain-Enabled Ternary Precision Computation-In-Memory Based on Non-Volatile 2D Piezoelectric Transistors |
| title_full_unstemmed | STeP-CiM: Strain-Enabled Ternary Precision Computation-In-Memory Based on Non-Volatile 2D Piezoelectric Transistors |
| title_short | STeP-CiM: Strain-Enabled Ternary Precision Computation-In-Memory Based on Non-Volatile 2D Piezoelectric Transistors |
| title_sort | step cim strain enabled ternary precision computation in memory based on non volatile 2d piezoelectric transistors |
| topic | deep neural network ferroelectric in-memory-computing non-volatile memory piezoelectric ultralow precision |
| url | https://www.frontiersin.org/articles/10.3389/fnano.2022.905407/full |
| work_keys_str_mv | AT niharikathakuria stepcimstrainenabledternaryprecisioncomputationinmemorybasedonnonvolatile2dpiezoelectrictransistors AT reenaelangovan stepcimstrainenabledternaryprecisioncomputationinmemorybasedonnonvolatile2dpiezoelectrictransistors AT sandeepkthirumala stepcimstrainenabledternaryprecisioncomputationinmemorybasedonnonvolatile2dpiezoelectrictransistors AT anandraghunathan stepcimstrainenabledternaryprecisioncomputationinmemorybasedonnonvolatile2dpiezoelectrictransistors AT sumeetkgupta stepcimstrainenabledternaryprecisioncomputationinmemorybasedonnonvolatile2dpiezoelectrictransistors |