Mehrzad Samadi

28 papers A* 7B 6Journal 12Unranked 2
YearRankTypeTitle / Venue / Authors
2025 — conf
Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models.
ACL (6)
Somshubra Majumdar, Vahid Noroozi, Mehrzad Samadi, Sean Narenthiran, Aleksander Ficek, Wasi Uddin Ahmad, Jocelyn Huang, Jagadeesh Balam, Boris Ginsburg
2025 J jnl
NVIDIA Nemotron Parse 1.1.
CoRR
Kateryna Chumachenko, Amala Sanjay Deshmukh, Jarno Seppänen, Ilia Karmanov, Chia-Chih Chen, Lukas Voegtle, Philipp Fischer, Marek Wawrzos, Saeid Motiian, Roman Ageev, Kedi Wu, Alexandre Milesi, Maryam Moosaei, Krzysztof Pawelec, Padmavathy Subramanian, Mehrzad Samadi, Xin-Yu Wang, Celina Dear, Sarah Stoddard, Jenna Diamond, Jesse Oliver, Leanna Chraghchian, Patrick Skelly, Tom Balough, Yao Xu, Jane Polak Scowcroft, Daniel Korzekwa, Darragh Hanley, Sandip Bhaskar, Timo Roman, Karan Sapra, Andrew Tao, Bryan Catanzaro
2025 J jnl
OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs.
CoRR
Wasi Uddin Ahmad, Aleksander Ficek, Mehrzad Samadi, Jocelyn Huang, Vahid Noroozi, Somshubra Majumdar, Boris Ginsburg
2025 J jnl
OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique.
CoRR
Wasi Uddin Ahmad, Somshubra Majumdar, Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi, Jocelyn Huang, Siddhartha Jain, Vahid Noroozi, Boris Ginsburg
2025 J jnl
Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models.
CoRR
Mehrzad Samadi, Aleksander Ficek, Sean Narenthiran, Siddhartha Jain, Wasi Uddin Ahmad, Somshubra Majumdar, Vahid Noroozi, Boris Ginsburg
2024 B conf
Leveraging Difference Recurrence Relations for High-Performance GPU Genome Alignment.
PACT
Alberto Zeni, Seth Onken, Marco Domenico Santambrogio, Mehrzad Samadi
2022 J jnl
A GPU-accelerated compute framework for pathogen genomic variant identification to aid genomic epidemiology of infectious disease: a malaria case study.
Briefings Bioinform.
Giovanna Carpi, Lev Gorenstein, Timothy T. Harkins, Mehrzad Samadi, Pankaj Vats
2018 J jnl
Rethinking Numerical Representations for Deep Neural Networks.
CoRR
Parker Hill, Babak Zamirai, Shengshuo Lu, Yu-Wei Chao, Michael Laurenzano, Mehrzad Samadi, Marios C. Papaefthymiou, Scott A. Mahlke, Thomas F. Wenisch, Jia Deng, Lingjia Tang, Jason Mars
2016 A* conf
Input responsiveness: using canary inputs to dynamically steer approximation.
PLDI
Michael A. Laurenzano, Parker Hill, Mehrzad Samadi, Scott A. Mahlke, Jason Mars, Lingjia Tang
2016 J jnl
Quality Control for Approximate Accelerators by Error Prediction.
IEEE Des. Test
Daya Shanker Khudia, Babak Zamirai, Mehrzad Samadi, Scott A. Mahlke
2015 B conf
Orchestrating Multiple Data-Parallel Kernels on Multiple Devices.
PACT
Janghaeng Lee, Mehrzad Samadi, Scott A. Mahlke
2015 A* conf
Rumba: an online quality management system for approximate computing.
ISCA
Daya Shanker Khudia, Babak Zamirai, Mehrzad Samadi, Scott A. Mahlke
2015 J jnl
SKMD: Single Kernel on Multiple Devices for Transparent CPU-GPU Collaboration.
ACM Trans. Comput. Syst.
Janghaeng Lee, Mehrzad Samadi, Yongjun Park, Scott A. Mahlke
2014 B conf
D
PACT
Davoud Anoushe Jamshidi, Mehrzad Samadi, Scott A. Mahlke
2014 — —
Dynamic Orchestration of Massively Data Parallel Execution.
Mehrzad Samadi
2014 J jnl
Leveraging GPUs using cooperative loop speculation.
ACM Trans. Archit. Code Optim.
Mehrzad Samadi, Amir Hormati, Janghaeng Lee, Scott A. Mahlke
2014 A* conf
Paraprox: pattern-based approximation for data parallel applications.
ASPLOS
Mehrzad Samadi, Davoud Anoushe Jamshidi, Janghaeng Lee, Scott A. Mahlke
2014 J jnl
Scaling Performance via Self-Tuning Approximation for Graphics Engines.
ACM Trans. Comput. Syst.
Mehrzad Samadi, Janghaeng Lee, Davoud Anoushe Jamshidi, Scott A. Mahlke, Amir Hormati
2014 B conf
VAST: the illusion of a large memory space for GPUs.
PACT
Janghaeng Lee, Mehrzad Samadi, Scott A. Mahlke
2013 B conf
APOGEE: Adaptive prefetching on GPUs for energy efficiency.
PACT
Ankit Sethia, Ganesh S. Dasika, Mehrzad Samadi, Scott A. Mahlke
2013 A* conf
SAGE: self-tuning approximation for graphics engines.
MICRO
Mehrzad Samadi, Janghaeng Lee, Davoud Anoushe Jamshidi, Amir Hormati, Scott A. Mahlke
2013 B conf
Transparent CPU-GPU collaboration for data-parallel kernels on heterogeneous systems.
PACT
Janghaeng Lee, Mehrzad Samadi, Yongjun Park, Scott A. Mahlke
2012 A* conf
Adaptive input-aware compilation for graphics engines.
PLDI
Mehrzad Samadi, Amir Hormati, Mojtaba Mehrara, Janghaeng Lee, Scott A. Mahlke
2012 — conf
Paragon: collaborative speculative loop execution on GPU and CPU.
GPGPU@ASPLOS
Mehrzad Samadi, Amir Hormati, Janghaeng Lee, Scott A. Mahlke
2011 J jnl
Dynamic Voltage and Frequency Scheduling for Embedded Processors Considering Power/Performance Tradeoffs.
IEEE Trans. Very Large Scale Integr. Syst.
Mostafa E. Salehi, Mehrzad Samadi, Mehrdad Najibi, Ali Afzali-Kusha, Massoud Pedram, Sied Mehdi Fakhraie
2011 A* conf
Dynamic parallelization of JavaScript applications using an ultra-lightweight speculation mechanism.
HPCA
Mojtaba Mehrara, Po-Chun Hsu, Mehrzad Samadi, Scott A. Mahlke
2011 A* conf
Sponge: portable stream programming on graphics engines.
ASPLOS
Amir Hormati, Mehrzad Samadi, Mark Woh, Trevor N. Mudge, Scott A. Mahlke
2008 J jnl
Dynamic power management with fuzzy decision support system.
IEICE Electron. Express
Mehrzad Samadi, Ali Afzali-Kusha