Zobrazeno 1 - 10
of 71
pro vyhledávání: '"KANDEMIR, MAHMUT TAYLAN"'
Autor:
Huo, Pingyi, Devulapally, Anusha, Maruf, Hasan Al, Park, Minseo, Nair, Krishnakumar, Arunachalam, Meena, Akbulut, Gulsum Gudukbay, Kandemir, Mahmut Taylan, Narayanan, Vijaykrishnan
Deep Learning Recommendation Models (DLRMs) have become increasingly popular and prevalent in today's datacenters, consuming most of the AI inference cycles. The performance of DLRMs is heavily influenced by available bandwidth due to their large vec
Externí odkaz:
http://arxiv.org/abs/2409.16633
The growing prevalence of near-term intermediate-scale quantum (NISQ) systems has brought forth a heightened focus on the issue of circuit reliability. Several quantum computing activities, such as circuit design and multi-qubit mapping, are focused
Externí odkaz:
http://arxiv.org/abs/2305.11919
Existing quantum systems provide very limited physical qubit counts, trying to execute a quantum algorithm/circuit on them that have a higher number of logical qubits than physically available lead to a compile-time error. Given that it is unrealisti
Externí odkaz:
http://arxiv.org/abs/2301.00720
Autor:
Sharma, Aakash, Bhasi, Vivek M., Singh, Sonali, Jain, Rishabh, Gunasekaran, Jashwant Raj, Mitra, Subrata, Kandemir, Mahmut Taylan, Kesidis, George, Das, Chita R.
We aim to resolve this problem by introducing a comprehensive distributed deep learning (DDL) profiler, which can determine the various execution "stalls" that DDL suffers from while running on a public cloud. We have implemented the profiler by exte
Externí odkaz:
http://arxiv.org/abs/2208.14344
There is an increasing demand for intelligent processing on emerging ultra-low-power internet of things (IoT) devices, and recent works have shown substantial efficiency boosts by executing inference tasks directly on the IoT device (node) rather tha
Externí odkaz:
http://arxiv.org/abs/2204.13106
Autor:
Zhang, Jie, Kwon, Miryeong, Gouk, Donghyun, Koh, Sungjoon, Kim, Nam Sung, Kandemir, Mahmut Taylan, Jung, Myoungsoo
Large persistent memories such as NVDIMM have been perceived as a disruptive memory technology, because they can maintain the state of a system even after a power failure and allow the system to recover quickly. However, overheads incurred by a heavy
Externí odkaz:
http://arxiv.org/abs/2106.14241
Autor:
Gunasekaran, Jashwant Raj, Mishra, Cyan Subhra, Thinakaran, Prashanth, Kandemir, Mahmut Taylan, Das, Chita R.
With a growing demand for adopting ML models for a varietyof application services, it is vital that the frameworks servingthese models are capable of delivering highly accurate predic-tions with minimal latency along with reduced deploymentcosts in a
Externí odkaz:
http://arxiv.org/abs/2106.05345
Autor:
Gunasekaran, Jashwant Raj, Thinakaran, Prashanth, Mishra, Cyan Subhra, Kandemir, Mahmut Taylan, Das, Chita R.
We are witnessing an increasing trend towardsusing Machine Learning (ML) based prediction systems, span-ning across different application domains, including productrecommendation systems, personal assistant devices, facialrecognition, etc. These appl
Externí odkaz:
http://arxiv.org/abs/2008.09491
Autor:
Gunasekaran, Jashwant Raj, Cui, Michael, Thinakaran, Prashanth, Simons, Josh, Kandemir, Mahmut Taylan, Das, Chita R.
Traditionally, HPC workloads have been deployed in bare-metal clusters; but the advances in virtualization have led the pathway for these workloads to be deployed in virtualized clusters. However, HPC cluster administrators/providers still face chall
Externí odkaz:
http://arxiv.org/abs/2006.12560
Publikováno v:
HPCA 2019
In this work, we propose FUSE, a novel GPU cache system that integrates spin-transfer torque magnetic random-access memory (STT-MRAM) into the on-chip L1D cache. FUSE can minimize the number of outgoing memory accesses over the interconnection networ
Externí odkaz:
http://arxiv.org/abs/1903.01776