Inventor · disambiguated record
Rangharajan Venkatesan
Also filed as: VENKATESAN RANGHARAJAN
13 granted patents·6 pending applications·13 citations·filing 2013–2024
85Inventor score
Top patents by PatentIndex Score
19 records- 0185US12412082B2Fine-grained per-vector scaling for neural network quantizationNVIDIA CORP·Filed 2020·Granted Sep 9, 2025·2 cites·21 claims
- 0285US12045307B2Fine-grained per-vector scaling for neural network quantizationNVIDIA CORP·Filed 2020·Granted Jul 23, 2024·2 cites·22 claims
- 0383US11886980B2Neural network accelerator using logarithmic-based arithmeticNVIDIA CORP·Filed 2019·Granted Jan 30, 2024·4 cites·20 claims
- 0482US12406169B2Optimally clipped tensors and vectorsNVIDIA CORP·Filed 2022·Granted Sep 2, 2025·1 cites·26 claims
- 0576US12118454B2Neural network accelerator using logarithmic-based arithmeticNVIDIA CORP·Filed 2023·Granted Oct 15, 2024·0 cites·20 claims
- 0676US2024311626A1Asynchronous accumulator using logarithmic-based arithmeticNVIDIA CORP·Filed 2024·Application pending·0 cites
- 0774US11270197B2Efficient neural network accelerator dataflowsNVIDIA CORP·Filed 2019·Granted Mar 8, 2022·2 cites·7 claims
- 0869US12387089B2Efficient neural network accelerator dataflowsNVIDIA CORP·Filed 2021·Granted Aug 12, 2025·0 cites·15 claims
- 0969US10255186B2Approximate cache memoryPURDUE RESEARCH FOUNDATION·Filed 2017·Granted Apr 9, 2019·1 cites·20 claims
- 1064US12033060B2Asynchronous accumulator using logarithmic-based arithmeticNVIDIA CORP·Filed 2020·Granted Jul 9, 2024·0 cites·19 claims
- 1158US11151040B2Approximate cache memoryPURDUE RESEARCH FOUNDATION·Filed 2019·Granted Oct 19, 2021·0 cites·17 claims
- 1254US12141225B2Inference accelerator using logarithmic-based arithmeticNVIDIA CORP·Filed 2020·Granted Nov 12, 2024·0 cites·18 claims
- 1354US9805790B2Memory cell with retention using resistive memoryINTEL CORP·Filed 2013·Granted Oct 31, 2017·1 cites·20 claims
- 1453US2024160406A1Low-precision floating-point datapath in a computer processorNVIDIA CORP·Filed 2023·Application pending·0 cites
- 1552US2025125819A1Energy-efficient datapath for vector-scaled hierarchical codebook quantizationNVIDIA CORP·Filed 2024·Application pending·0 cites
- 1651US11769040B2Scalable multi-die deep learning systemNVIDIA CORP·Filed 2019·Granted Sep 26, 2023·0 cites·19 claims
- 1751US2022261650A1Machine learning training in logarithmic number systemNVIDIA CORP·Filed 2021·Application pending·0 cites
- 1848US2022067513A1Efficient softmax computationNVIDIA CORP·Filed 2020·Application pending·0 cites
- 1946US2023068941A1Quantized neural network training and inferenceNVIDIA CORP·Filed 2022·Application pending·0 cites
Join the waitlist — get patent alerts
Get an alert when Rangharajan Venkatesan files or is granted a new patent.
We store only your email — no account needed. See our privacy policy.
Identity basis: PatentsView inventor disambiguation (2025Q4-odp release). How scoring works →