Vikram K. Narayana

Vikram K. Narayana

Auto-generated profile, based on publicly available information

Vikram K. Narayana

The George Washington University

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
30 October 2015 in IEEE Photonics Journal
Verified
Journal Article
Open access
SSShuai Sun
Shuai Sun
ABAbdel-Hameed A. Badawy
Abdel-Hameed A. Badawy
VNV. Narayana
V. Narayana
TETarek El-Ghazawi
Tarek El-Ghazawi
VSVolker J. Sorger
Volker J. Sorger
Moore's law for traditional electric integrated circuits is facing increasingly more challenges in both physics and economics. Among those challenges is the fact that the bandwidth per compute on the chip is dropping, whereas the energy needed for data movement keeps rising. We benchmark various interconnect technologies, including electrical, photonic, and plasmonic options. We contrast them with hybrid photonic-plasmonic interconnect(s) [HyPPI(s)], where we consider plasmonics for active manipulation devices and photonics for passive propagation integrated circuit elements and further propose another novel hybrid link that utilizes an on-chip laser for intrinsic modulation, thus bypassing electrooptic modulation. Our analysis shows that such hybridization will overcome the shortcomings of both pure photonic and plasmonic links. Furthermore, it shows superiority in a variety of performance parameters such as point-to-point latency, energy efficiency, throughput, energy delay product, crosstalk coupling length, and bit flow density, which is a new metric that we defined to reveal the tradeoff between the footprint and performance. Our proposed HyPPIs show significantly superior performance compared with other links.

1 September 2011
Verified
Conference Paper
Closed access
TLTeng Li
Teng Li
VNVikram K. Narayana
Vikram K. Narayana
Esam El-ArabyEsam El-Araby
Esam El-Araby
TETarek El-Ghazawi
Tarek El-Ghazawi
Modern Graphic Processing Units (GPUs) are widely used as application accelerators in the High Performance Computing (HPC) field due to their massive floating-point computational capabilities and highly data-parallel computing architecture. Contemporary high performance computers equipped with co-processors such as GPUs primarily execute parallel applications using the Single Program Multiple Data (SPMD) model, which requires balanced computing resources of both microprocessor and co-processors to ensure full system utilization. While the inclusion of GPUs in HPC systems provides more computing resources and significant performance improvements, the asymmetrical distribution of the number of GPUs relative to the microprocessors can result in an underutilization of overall system computing resources. In this paper, we propose a GPU resource virtualization approach to allow underutilized microprocessors to share the GPUs. We analyze factors affecting the parallel execution performance on GPUs and conduct a theoretical performance estimation based on the most recent GPU architectures as well as the SPMD model. Then we present the implementation details of the virtualization infrastructure, followed by an experimental verification of the proposed concepts using an NVIDIA Fermi GPU computing node. The results demonstrate a considerable performance gain over the traditional SPMD execution without virtualization. Furthermore, the proposed solution enables full utilization of the asymmetrical system resources, through the sharing of the GPUs among microprocessors, while incurring low overheads due to the virtualization layer.

1 November 2010 in ACM Transactions on Reconfigurable Technology and Systems
Verified
Journal Article
Open access
MHMiaoqing Huang
Miaoqing Huang
VNVikram K. Narayana
Vikram K. Narayana
HSHarald Simmler
Harald Simmler
OSOlivier Serres
Olivier Serres
TETarek El-Ghazawi
Tarek El-Ghazawi
High-performance reconfigurable computing involves acceleration of significant portions of an application using reconfigurable hardware. When the hardware tasks of an application cannot simultaneously fit in an FPGA, the task graph needs to be partitioned and scheduled into multiple FPGA configurations, in a way that minimizes the total execution time. This article proposes the Reduced Data Movement Scheduling (RDMS) algorithm that aims to improve the overall performance of hardware tasks by taking into account the reconfiguration time, data dependency between tasks, intertask communication as well as task resource utilization. The proposed algorithm uses the dynamic programming method. A mathematical analysis of the algorithm shows that the execution time would at most exceed the optimal solution by a factor of around 1.6, in the worst-case. Simulations on randomly generated task graphs indicate that RDMS algorithm can reduce interconfiguration communication time by 11% and 44% respectively, compared with two other approaches that consider data dependency and hardware resource utilization only. The practicality, as well as efficiency of the proposed algorithm over other approaches, is demonstrated by simulating a task graph from a real-life application - N-body simulation - along with constraints for bandwidth and FPGA parameters from existing high-performance reconfigurable computers. Experiments on SRC-6 are carried out to validate the approach.

22 March 2018 in Optics Express
Verified
Journal Article
Closed access
PDF file
SSShuai Sun
Shuai Sun
RZRuoyu Zhang
Ruoyu Zhang
JPJiaxin Peng
Jiaxin Peng
VNVikram K. Narayana
Vikram K. Narayana
HDHamed Dalir
Hamed Dalir
VSVolker Sorger
Volker Sorger
While augmenting network on chips (NoC) with photonic links enables high-bandwidth communication, the overhead for photonics is rather large, mainly driven by bulky footprints and the multi-functionality of transceivers. The latter requires, in addition to a photon source, signal modulation and detection. If the NoC were photonically augmented at every network point to enable all-to-all connectivity, the resulting photonic overhead would be excessive. Besides, the high bandwidth of a single optical bus may be sufficient to supply the data-sharing demand of a network. Spatial signal routing is a necessary function of data communication in NoCs. However, if photonic links are used to augment electronics, an energy-costly optical-electrical-optical (OEO) conversion is required since routing is currently executed in the electronic domain. Here we show a novel integrated broadband hybrid photonic-plasmonic device termed an MO detector featuring dual light modulation and detection. With 10 dB extinction ratio and 0.8 dB insertion loss at the modulation state and 0.7 A/W responsivity at the detection state based on the finite-different time-domain simulation, this transceiver-like device (i) eliminates the OEO conversion, (ii) reduces optical losses from photodetectors via bypassing the photodetector when not needed, and (iii) enables cognitive routing strategies for network-on-chips. As such, the MO detector acts as a micrometer-compact transceiver for next-generation NoCs.

20 May 2014
Verified
Conference Paper
Open access
TLTeng Li
Teng Li
VNVikram K. Narayana
Vikram K. Narayana
TETarek El-Ghazawi
Tarek El-Ghazawi
The incorporation of GPUs as co-processors has brought forth significant performance improvements for High-Performance Computing (HPC). Efficient utilization of the GPU resources is thus an important consideration for computer scientists. In order to obtain the required performance while limiting the energy consumption, researchers and vendors alike are seeking to apply traditional CPU approaches into the GPU computing domain. For instance, newer NVIDIA GPUs now support concurrent execution of independent kernels as well as Dynamic Voltage and Frequency Scaling (DVFS). Amidst these new developments, we are faced with new opportunities for efficiently scheduling GPU computational kernels under performance and energy constraints. In this paper, we carry out performance and energy optimizations geared towards the execution phases of concurrent kernels in GPU-based computing. When multiple GPU kernels are enqueued for concurrent execution, the sequence in which they are initiated can significantly affect the total execution time and the energy consumption. We attribute this behavior to the relative synergy among kernels that are launched within close proximity of each other. Accordingly, we define metrics for computing the extent to which kernels are symbiotic, by modeling their complementary resource requirements and execution characteristics. We then propose a symbiotic scheduling algorithm to obtain the best possible kernel launch sequence for concurrent execution. Experimental results on the latest NVIDIA K20 GPU demonstrate the efficacy of our proposed algorithm-based approach, by showing near-optimal results within the solution space of both performance and energy consumption. As our further experimental study on DVFS finds that increasing the GPU frequency in general leads to improved performance and energy saving, the proposed approach reduces the necessity for over-clocking and can be readily adopted by programmers with minimal programming effort and risk.

3 May 2011
Verified
Conference Paper
Open access
PDF file
LWLingyuan Wang
Lingyuan Wang
MHMiaoqing Huang
Miaoqing Huang
VNVikram K. Narayana
Vikram K. Narayana
TETarek El-Ghazawi
Tarek El-Ghazawi