BE/BTech & ME/MTech Final Year Projects for Computer Science | Information Technology | ECE Engineer | IEEE Projects Topics, PHD Projects Reports, Ideas and Download | Sai Info Solution | Nashik |Pune |Mumbai
director@saiinfo settings_phone02536644344 settings_phone+919270574718 +919096813348 settings_phone+917447889268
logo


SAI INFO SOLUTION


Diploma | BE |B.Tech |ME | M.Tech |PHD

Project Development and Training

Search Project by Domainwise


TiM-DNN: Ternary In-Memory Accelerator for Deep Neural Networks


3D Reconstruction in Canonical
Abstract


The use of lower precision has emerged as a popular technique to optimize the compute and storage requirements of complex deep neural networks (DNNs). In the quest for lower precision, recent studies have shown that ternary DNNs (which represent weights and activations by signed ternary values) represent a promising sweet spot, achieving accuracy close to full-precision networks on complex tasks. We propose TiM-DNN, a programmable in-memory accelerator that is specifically designed to execute ternary DNNs. TiM-DNN supports various ternary representations including unweighted {‚??1, 0, 1}, symmetric weighted {‚??a, 0, a}, and asymmetric weighted {‚??a, 0, b} ternary systems. The building blocks of TiM-DNN are TiM tiles‚?? specialized memory arrays that perform massively parallel signed ternary vector‚??matrix multiplications with a single access. TiM tiles are in turn composed of ternary processing cells (TPCs), bit-cells that function as both ternary storage units and signed ternary multiplication units. We evaluate an implementation of TiM-DNN in 32-nm technology using an architectural simulator calibrated with SPICE simulations and RTL synthesis. We evaluate TiM-DNN across a suite of state-of-the-art DNN benchmarks including both deep convolutional and recurrent neural networks. A 32-tile instance of TiM-DNN achieves a peak performance of 114 TOPs/s, consumes 0.9-W power, and occupies 1.96 mm2 chip area, representing a 300√? and 388√? improvement in TOPS/W and TOPS/mm2, respectively, compared to an NVIDIA Tesla V100 GPU. In comparison to specialized DNN accelerators, TiM-DNN achieves 55√?-240√? and 160√?-291√? improvement in TOPS/W and TOPS/mm2, respectively. Finally, when compared to a well-optimized near-memory accelerator for ternary DNNs, TiM-DNN demonstrates 3.9√?-4.7√? improvement in system-level energy and 3.2√?-4.2√? speedup, underscoring the potential of in-memory computing for ternary DNNs.

KeyWords
AI hardware, in-memory computing, lowprecision deep neural networks (DNNs), ternary dot-products, ternary neural networks



Share
Share via WhatsApp
BE/BTech & ME/MTech Final Year Projects for Computer Science | Information Technology | ECE Engineer | IEEE Projects Topics, PHD Projects Reports, Ideas and Download | Sai Info Solution | Nashik |Pune |Mumbai
Call us : 09096813348 / 02536644344
Mail ID : developer.saiinfo@gmail.com
Skype ID : saiinfosolutionnashik