Rahmat Mulyawan

Rahmat Mulyawan

Auto-generated profile, based on publicly available information

Rahmat Mulyawan

The School of Electrical Engineering and Informatics Institut Teknologi Bandung (STEI-ITB) Jl. Ganesha No.10 Bandung Indonesia

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
15 October 2021 in IEEE Access
Verified
Journal Article
Open access
TATrio Adiono
Trio Adiono
APAdiwena Putra
Adiwena Putra
NSNana Sutisna
Nana Sutisna
ISInfall Syafalni
Infall Syafalni
RMRahmat Mulyawan
Rahmat Mulyawan
This paper presents a comprehensive hardware accelerator architecture of YOLOv3-Tiny targeted for low-cost FPGA with a high frame rate, high accuracy, and low latency. The proposed accelerator implements all YOLO layers in hardware including zero pad layer, convolution layer, leaky ReLU layer, batch normalization layer, max-pooling layer, and up-sampling layer. The architecture is built based on data flow and control flow hybrid architecture. The data preparation and computation process work asynchronously using the data flow paradigm, while the overall governing process is controlled by proposed custom instruction set which adopts the principle of control flow paradigm. The principle of General Matrix Multiplication (GEMM) is adopted to compute the convolution process. We designed a GEMM processor using an optimum size of systolic array architecture. The systolic core is small and the overall architecture supports the multicore system, making it scalable to be implemented on larger size FPGAs. We also proposed a hardware architecture for mapping feature maps into matrix form for GEMM convolution which can save on-chip memory space. Lastly, we modified the original YOLO algorithm to further optimize it in our hardware. The modification includes reducing the bit precision to reduce memory space and bandwidth requirement, merging the normalization layer with the convolution layer to reduce arithmetic complexity, and adding a new DLQ layer to keep the bit size small while maintaining the accuracy. Based on the experimental results, our proposed design manages to achieve a frame rate of 8.3 FPS with the throughput of 31.5 GOPS, outperforming the same convolution computation that is performed by Ryzen 5 3600 CPU up to $69.3\times $ in latency. Moreover, our proposed design also has the smallest clock cycle ratio up to $1.75\times $ than other commercial accelerators. The system is useful and suitable for edge computing applications.

14 January 2022 in IEEE Access
Verified
Journal Article
Open access
ISInfall Syafalni
Infall Syafalni
GJGilbert Jonatan
Gilbert Jonatan
NSNana Sutisna
Nana Sutisna
RMRahmat Mulyawan
Rahmat Mulyawan
TATrio Adiono
Trio Adiono
With recent development in internet speed and reliability, cloud computing has become a more reliable solution for the user. In many cases where data privacy is critical, fully homomorphic encryption (FHE) can be a security solution for securing cloud computing. FHE enables computation on encrypted data, hence it ensures data privacy in case of cloud computing. One popular scheme of FHE is the BFV homomorphic encryption scheme, which is based on ring learning with error (RLWE) computation. The BFV scheme uses ring polynomials as the main object, hence its encryption, decryption, and evaluation require high-degree polynomial multiplication. In this paper, we present comprehensive design and implementation of a hardware architecture to accelerate encryption and decryption in BFV scheme. Our accelerator uses convolution approach for calculating a polynomial multiplication. To implement the convolution, we use a systolic array to calculate polynomial convolution followed by a simple delayed subtraction to calculate polynomial modulo reduction inside our accelerator’s core. Moreover, we use a built-in Gaussian pseudo-random number generator (PRNG) to generate Gaussian noise in the encryption operations. Finally, we implement the 1024 degrees BFV accelerator on the Xilinx PYNQ Z1 board and compare the encryption and decryption performances to other methods as well as a software implementation on Intel Core i7 with 8GB memory. Experimental results show that our accelerator outperforms the clock cycles of other methods with the same polynomial degrees 1024 up to $22\times $ . Moreover, our proposed Gaussian PRNG has better $2\times $ correlation compared to the rotation-only-based PRNG. Finally, our accelerator accelerates up to $9\times $ for encryption and $3.5\times $ for decryption as well as $6.8\times $ for overall compared to Microsoft SEAL on Intel Core i7 processor with 8GB memory. The proposed design is scalable for higher degrees polynomial multiplication and useful for security technology such as high-speed secure cloud computing, blind computing, and secure communication.

9 January 2017 in IEEE Photonics Technology Letters
Verified
Journal Article
Closed access
RMRahmat Mulyawan
Rahmat Mulyawan
HCHyunchae Chun
Hyunchae Chun
AGAriel Gomez
Ariel Gomez
Sujan RajbhandariSujan Rajbhandari
Sujan Rajbhandari
GFGrahame Faulkner
Grahame Faulkner
DODominic O'BRien
Dominic O'BRien
This letter reports a demonstration of a $2\times 2$ multiple-input multiple-output (MIMO) indoor visible-light communication (VLC) system using a novel fluorescent optical concentrator-based receiver. This potentially allows a high degree of spatial multiplexing to be achieved using a simple receiver structure that can have a wide field-of-view. Details of a two-channel MIMO VLC system that operates at 32 Mb/s with a receiver acceptance angle of ±22.5° are given, and future directions are discussed.

28 December 2022 in IEEE Access
Verified
Journal Article
Open access
NSNana Sutisna
Nana Sutisna
AIAndi M. Riyadhus Ilmy
Andi M. Riyadhus Ilmy
ISInfall Syafalni
Infall Syafalni
RMRahmat Mulyawan
Rahmat Mulyawan
TATrio Adiono
Trio Adiono
This paper proposes a FAst paRAllel and pipeliNE Q-learning accelerator (FARANE-Q) for a configurable Reinforcement Learning (RL) algorithm that is implemented in a System on Chip (SoC). The proposed work offers flexibility, configurability, and scalability while maintaining computation speed and accuracy to overcome the challenges of a dynamic environment and increasing complexity. The proposed method includes a HW/SW design methodology for the SoC architecture to achieve flexibility. Moreover, we also propose joint optimizations on the algorithm, architecture, and implementation to obtain optimum (high efficiency) performance, specifically in energy and area efficiency. Furthermore, we implemented the proposed design in a real-time Zynq Ultra96-V2 FPGA platform to evaluate the functionality with an actual use case of smart navigation. Experimental results confirm that the proposed accelerator FARANE-Q outperforms state-of-the-art works by achieving a throughput of up to 148.55 MSps. It corresponds to the energy efficiency of 1747.64 MSps/W per agent for 32-bit and 2424.33 MSps/W per agent for 16-bit FARANE-Q. Moreover, the proposed 16-bit FARANE-Q outperforms other related works by offering an improvement of at least 1.23× in energy efficiency. The designed system also maintains an error accuracy of less than 0.4% with optimized bit precision for more than eight fraction bits. The proposed FARANE-Q also offers a speed up of processing time up to 1795× compared to embedded SW computation executed on ARM Zynq processor and 280× of computation of full software executed on i7 processor. Hence, the proposed work has the potential to be used for smart navigation, robotic control, and predictive maintenance.

30 August 2023 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
TATrio Adiono
Trio Adiono
RRRhesa Muhammad Ramadhan
Rhesa Muhammad Ramadhan
NSNana Sutisna
Nana Sutisna
ISInfall Syafalni
Infall Syafalni
RMRahmat Mulyawan
Rahmat Mulyawan
CLChang Hong Lin
Chang Hong Lin
This article proposes a scalable accelerator for deep learning (DL) implementation on edge computing, which is often limited by power, storage, and computation speed. The accelerator is based on systolic array cores with 126 processing elements (PEs) and optimized for YOLOv3-Tiny with $448\times448$ input images. Two multicast (MC) network architectures, feature map multicasting and weight multicasting, are introduced to control data stream distribution within the multicores. Results show that the proposed weight multicast (W-MC) systems outperformed the feature map multicast (FMAP-MC) systems in multicore scenarios, with up to $2.23\times $ frame rates per second (FPS). The 4-core W-MC system achieved the best efficiency with an overall frame rate of 13.73 FPS/W and an overall throughput of 35.83 GOPS/W. The 8-core W-MC system delivered the best performance, with a frame rate of 38.50 FPS after normalization to the standard YOLOv3-Tiny network. The proposed accelerator offers better computational efficiency and greater accelerator utilization in real-world inference scenarios, compared to previous state-of-the-art works.

9 July 2024 in IEEE Access
Verified
Journal Article
Open access
TATrio Adiono
Trio Adiono
ESErwin Setiawan
Erwin Setiawan
MJMichael Jonathan
Michael Jonathan
RMRahmat Mulyawan
Rahmat Mulyawan
NSNana Sutisna
Nana Sutisna
Wasiu PopoolaWasiu Popoola
Wasiu Popoola
Visible Light Communication (VLC) system, a wireless system that utilizing the visible light spectrum to transmit data has been considered to become a complementary technology to radio frequency (RF) wireless technology in overcoming spectrum limitations. Recent research in Visible Light Communication (VLC) has been extensive. However, most experiments were conducted under ideal conditions, with only a few demonstrating real-time results with networking capabilities. To address this limitation, this paper proposes and details the design of a real-time VLC prototype that supports TCP/IP networking. First, we propose a system-on-chip (SoC) architecture for a VLC system. We design Register-Transfer-Level (RTL) modules using orthogonal frequency-division multiplexing (OFDM) for time synchronization, channel estimation, and equalization. Additionally, we optimize the Sampling Frequency Offset (SFO) estimation and compensation in the receiver to address the mismatch between TX and RX clock oscillators. The optimization of the SFO module is done by eliminating division operations. To realize full-stack design we integrate our design, consisting baseband processor in an FPGA as physical layer device, Linux’s kernel TCP/IP stack and the analog output to the VLC analog front-end. This full system design are evaluated over real channel at 1 m distance of transmitter and receiver. Experimental evaluations show that our VLC system can do network tests in an end-to-end system with commercial-off-the-shelf (COTS) networking devices and real applications such as internet browsers. Our VLC system offers a maximum real-time net TCP data rate of 6.65 Mb/s as measured using the iperf tool. Theses experimental results show that our VLC system achieves a 6× data rate improvement as compared to the state-of-the-art work. Specifically, our SFO compensator results demonstrate an improvement in TCP data rate of 8.25× and a reduction in frame loss of 22.42%. Moreover, our system also provides design features in terms of flexibility and scalability for future development.