Kashif Inayat

Mr. Kashif Inayat

Incheon National University
+1
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 May 2022 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
Kashif InayatKashif Inayat
Kashif Inayat
JCJaeyong Chung
Jaeyong Chung
Deep learning applications have become ubiquitous in today’s era and it has led to vast development in machine learning (ML) accelerators. Systolic arrays have been a primary part of ML accelerator architecture. To fully leverage the systolic arrays, it is required to explore the computer arithmetic data-path components and their tradeoffs in accelerators. We present a novel factored systolic array (FSA) architecture, in which the carry propagation adder (CPA) and carry-save adder (CSA) perform hybrid accumulation on least significant bit (LSB) bits and most significant bits (MSB) bits, respectively, inside each processing element. In addition, a small CPA to complete accumulation for MSB bits along with rounding logic for each column of the array is placed, which not only reduces the area, delay, and power but also balances the combinational and sequential area tradeoffs. We demonstrate the hybrid accumulator with partial CPA factoring in “Gemmini,” an open-source practical systolic array accelerator and factoring technique does not change the functionality of the base design. We implemented three baselines, original Gemmini and two variants of it, and show that the proposed approach leads to overall significant reduction in area within the range 12.8% – 50.2% and in power within the range 18.6% – 41% with improved or similar delay in comparison to the baselines.

29 August 2024 in International Journal of Information Security
Verified
Journal Article
Open access
PDF file
SKSafiullah Khan
Safiullah Khan
Kashif InayatKashif Inayat
Kashif Inayat
FMFahad Muslim
Fahad Muslim
YSYasir Ali Shah
Yasir Ali Shah
Muhammad Atif Ur RehmanMuhammad Atif Ur Rehman
Muhammad Atif Ur Rehman
AAAkmalbek Abdusalomov
Akmalbek Abdusalomov
The Internet of Things (IoT) nodes consist of sensors that collect environmental data and then perform data exchange with surrounding nodes and gateways. Cybersecurity attacks pose a threat to the data security that is being transmitted in any IoT network. Cryptographic primitives are widely adopted to address these threats; however, the substantial computation demands limit their applicability in the IoT ecosystem. In addition, each IoT node varies with respect to the area and throughput (TP) requirements, thus demanding flexible implementation for encryption/decryption processes. To solve these issues, this work implements the NIST lightweight cryptography standard, Ascon, on a SAED 32 nm process design kit (PDK) library by employing loop folded, loop unrolled and fully unrolled architectures. The fully unrolled architecture can achieve the highest TP but at the cost of higher area utilisation. Unrolling by a lower factor results in lower area implementations, enabling the exploration of design space to tackle the trade-off between area and TP performance of the design. The implementation results show that, for loop folded architecture, Ascon-128 and Ascon-128a require 36.7k $$\upmu \textrm{m}^{2}$$ μ m 2 and 38.5k $$\upmu \textrm{m}^{2}$$ μ m 2 chip area, respectively compared to 277.1k $$\upmu \textrm{m}^{2}$$ μ m 2 and 306.6k $$\upmu \textrm{m}^{2}$$ μ m 2 required by their fully unrolled implementations. The proposed implementation strategies can adjust the number of rounds to accommodate the varied requirements of IoT ecosystems. An implementation with an open-source 45 nm PDK library is also undertaken for enhanced generalization and reproducibility of the results.

26 April 2023 in Sensors
Verified
Journal Article
Open access
PDF file
Kashif InayatKashif Inayat
Kashif Inayat
FMFahad Muslim
Fahad Muslim
JIJaved Iqbal
Javed Iqbal
Syed Agha Hassnain MohsanSyed Agha Hassnain Mohsan
Syed Agha Hassnain Mohsan
HAHend Khalid Alkahtani
Hend Khalid Alkahtani
SMSamih M. Mostafa
Samih M. Mostafa
Systolic arrays are an integral part of many modern machine learning (ML) accelerators due to their efficiency in performing matrix multiplication that is a key primitive in modern ML models. Current state-of-the-art in systolic array-based accelerators mainly target area and delay optimizations with power optimization being considered as a secondary target. Very few accelerator designs directly target power optimizations and that too using very complex algorithmic modifications that in turn result in a compromise in the area or delay performance. We present a novel Power-Intent Systolic Array (PI-SA) that is based on the fine-grained power gating of the multiplication and accumulation (MAC) block multiplier inside the processing element of the systolic array, which reduces the design power consumption quite significantly, but with an additional delay cost. To offset the delay cost, we introduce a modified decomposition multiplier to obtain smaller reduction tree and to further improve area and delay, we also replace the carry propagation adder with a carry save adder inside each sub-multiplier. Comparison of the proposed design with the baseline Gemmini naive systolic array design and its variant, i.e., a conventional systolic array design, exhibits a delay reduction of up to 6%, an area improvement of up to 32% and a power reduction of up to 57% for varying accumulator bit-widths.

1 July 2020
Verified
Conference Paper
Closed access
IUInayat Ullah
Inayat Ullah
Kashif InayatKashif Inayat
Kashif Inayat
JYJoon-Sung Yang
Joon-Sung Yang
JCJaeyong Chung
Jaeyong Chung
Systolic arrays are re-gaining the attention as the heart to accelerate machine learning workloads. This paper shows that a large design space exists at the logic level despite the simple structure of systolic arrays and proposes a novel systolic array based on factoring and radix-8 multipliers. The factored systolic array (FSA) extracts out the booth encoding and the hard-multiple generation which is common across all processing elements, reducing the delay and the area of the whole systolic array. This factoring is done at the cost of an increased number of registers, however, the reduced pipeline register requirement in radix-8 offsets this effect. The proposed factored 16-bit multiplier achieves up to 15%, 13%, and 23% better delay, area, and power, respectively, compared with the radix-4 multipliers even if the register overhead is included. The proposed FSA architecture improves delay, area, and power up to 11%, 20% and 31%, respectively, for different bitwidths when compared with the conventional radix-4 systolic array.

23 July 2018 in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
Verified
Journal Article
Closed access
PDF file
Kashif InayatKashif Inayat
Kashif Inayat
Seong Oun HwangSeong Oun Hwang
Seong Oun Hwang
This paper presents a distributed Load Balancing Trade Framework (LBTF) with focus on demand response and Advanced Metering Infrastructure (AMI) security in smart grid. This comprehensive energy market model LBTF framework can achieve good balance in demand response in two ways. First way is utility-grid contract, which introduced a simple reward policy using distributed proof-of-work (PoW) consensus algorithm in Blockchain to motivate consumer to use less energy in peak hours. Through this policy consensus algorithm reward electric units to the consumers in peak hours. And in second way scheme introduce Micro-grid contract, which is a peer to peer (P2P) trade in global market. Those consumer (prosumer) who can generate energy using renewable resources can sell their surplus energy to other consumer through this contract. Furthermore, hash functions, public key encryption and digital signatures have been used to provide privacy preserving to the consumers and integrity to the stored data.

11 March 2021 in Electronics
Verified
Journal Article
Open access
PDF file
Kashif InayatKashif Inayat
Kashif Inayat
JCJaeyong Chung
Jaeyong Chung
Systolic arrays are the primary part of modern deep learning accelerators and are being used widely in real-life applications such as self-driving cars. This paper presents a novel factored systolic array, where the carry propagation adder for accumulation and the rounding logic are extracted out from each processing element, which reduces the area, power and delay of the processing elements substantially. The factoring is performed in the column-wise manner and the cost of the factored logic, placed at each column output, is amortized by the processing elements in a column. We demonstrate the proposed factoring in an open source systolic array, Gemmini. The factoring technique does not change the functionality of the base design and is transparent to applications. We show that the proposed technique leads to substantial reduction in area and delay up to 45.3% and 23.7%, respectively, compared to the Gemmini baseline.