Nirmal Saxena
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Nirmal Saxena has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
E.J. McCluskey
Center for Reliable Computing, Stanford, CA, USA
2 shared publicationsGuangshan Duan
GPU Architecture NVIDIA Shanghai, China
1 shared publication- Nikhil Jain
Nvidia Corporation, Santa Clara, CA, USA
1 shared publication P. Franco
Stanford University, CA, USA
1 shared publicationPaul Racunas
GPU Architecture NVIDIA, Westford, MA, USA
1 shared publicationRichard Bramley
GPU Architecture NVIDIA, Santa Clara, CA, USA
1 shared publication
Latest Publications
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 46 (1) , 10-18
Silent Data Corruption: Optimal Mitigation Strategies for Data Center Computing
Given current datacenter compute scales, extended job durations, and existing detection mechanisms, the risk of silent data corruption (SDC) exposure is substantial. Leveraging existing detection coverage and SDC characteristics, we propose optimized SDC mitigation strategies that balance availability and reliability. These optimization strategies strive to achieve Shannon’s like bounds on the overhead required for reliable (meaning SDC mitigation) compute channels. While error-correcting codes effectively address transient faults in memory, storage, and high-speed links, residual SDC risks persist. We advocate for algorithm-based error detection (ABED) to bridge this gap and stress the need for ongoing ABED research to adapt to evolving compute patterns. Low-level fault simulation for SDC assessment in long-running jobs is impractical; instead, near-real-time evaluation is essential. Although our approach partially addresses systematic faults, robust design verification and manufacturing tests remain critical for comprehensive fault management. This work highlights the urgency of scalable, efficient SDC detection in large-scale systems.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 46 (1) , 10-18
Silent Data Corruption: Optimal Mitigation Strategies for Data Center Computing
Given current datacenter compute scales, extended job durations, and existing detection mechanisms, the risk of silent data corruption (SDC) exposure is substantial. Leveraging existing detection coverage and SDC characteristics, we propose optimized SDC mitigation strategies that balance availability and reliability. These optimization strategies strive to achieve Shannon’s like bounds on the overhead required for reliable (meaning SDC mitigation) compute channels. While error-correcting codes effectively address transient faults in memory, storage, and high-speed links, residual SDC risks persist. We advocate for algorithm-based error detection (ABED) to bridge this gap and stress the need for ongoing ABED research to adapt to evolving compute patterns. Low-level fault simulation for SDC assessment in long-running jobs is impractical; instead, near-real-time evaluation is essential. Although our approach partially addresses systematic faults, robust design verification and manufacturing tests remain critical for comprehensive fault management. This work highlights the urgency of scalable, efficient SDC detection in large-scale systems.
- Open Access
- 15 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 43-53
DrGPU: A Top-Down Profiler for GPU Applications
GPUs have become common in HPC systems to accelerate scientific computing and machine learning applications. Efficiently mapping these applications to rapid evolutions of GPU architectures for high performance is a well-known challenge. Various performance inefficiencies exist in GPU kernels that impede applications from obtaining bare-metal performance. While existing tools are able to measure these inefficiencies, they mostly focus on data collection and presentation, requiring significant manual efforts to understand the root causes for actionable optimization. Thus, we develop DrGPU, a novel profiler that performs top-down analysis to guide GPU code optimization. As its salient feature, DrGPU leverages hardware performance counters available in commodity GPUs to quantify stall cycles, decompose them into various stall reasons, pinpoint root causes, and provide intuitive optimization guidance. With the help of DrGPU, we are able to analyze important GPU benchmarks and applications and obtain nontrivial speedups --- up to 1.77X on V100 and 2.03X on GTX 1650.
- 15 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 43-53
Open AccessDrGPU: A Top-Down Profiler for GPU Applications
GPUs have become common in HPC systems to accelerate scientific computing and machine learning applications. Efficiently mapping these applications to rapid evolutions of GPU architectures for high performance is a well-known challenge. Various performance inefficiencies exist in GPU kernels that impede applications from obtaining bare-metal performance. While existing tools are able to measure these inefficiencies, they mostly focus on data collection and presentation, requiring significant manual efforts to understand the root causes for actionable optimization. Thus, we develop DrGPU, a novel profiler that performs top-down analysis to guide GPU code optimization. As its salient feature, DrGPU leverages hardware performance counters available in commodity GPUs to quantify stall cycles, decompose them into various stall reasons, pinpoint root causes, and provide intuitive optimization guidance. With the help of DrGPU, we are able to analyze important GPU benchmarks and applications and obtain nontrivial speedups --- up to 1.77X on V100 and 2.03X on GTX 1650.
- 1 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
On the Measurement of Safe Fault Failure Rates in High-Performance Compute Processors
Accurate determination of the safe-fault failure rate of complex digital designs is an exascale problem. We present a novel measurement methodology and results which could have a profound impact on the performance and availability for GPUs in safety critical systems. We extend our analysis with a methodology for in-the-field verification.
- 1 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
On the Measurement of Safe Fault Failure Rates in High-Performance Compute Processors
Accurate determination of the safe-fault failure rate of complex digital designs is an exascale problem. We present a novel measurement methodology and results which could have a profound impact on the performance and availability for GPUs in safety critical systems. We extend our analysis with a methodology for in-the-field verification.
- 27 September 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 53 (11) , 1483-1492
Efficient design diversity estimation for combinational circuits
Redundant systems are designed using multiple copies of the same resource (e.g., a logic network or a software module) in order to increase system dependability: Design diversity has long been used to protect redundant systems against common-mode failures. The conventional notion of diversity relies on "independent" generation of "different" implementations of the same logic function. In a recent paper, we presented a metric to quantify diversity among several designs. The problem of calculating the diversity metric is NP-complete (i.e., can be of exponential complexity). In this paper, we present efficient techniques to estimate the value of the design diversity metric. For datapath designs, we have formulated very fast techniques to calculate the value of the metric by taking advantage of the regularity in the datapath structures. For general combinational logic circuits, we present an adaptive Monte-Carlo simulation technique for estimating accurate bounds on the value of the metric.
- 27 September 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 53 (11) , 1483-1492
Efficient design diversity estimation for combinational circuits
Redundant systems are designed using multiple copies of the same resource (e.g., a logic network or a software module) in order to increase system dependability: Design diversity has long been used to protect redundant systems against common-mode failures. The conventional notion of diversity relies on "independent" generation of "different" implementations of the same logic function. In a recent paper, we presented a metric to quantify diversity among several designs. The problem of calculating the diversity metric is NP-complete (i.e., can be of exponential complexity). In this paper, we present efficient techniques to estimate the value of the design diversity metric. For datapath designs, we have formulated very fast techniques to calculate the value of the metric by taking advantage of the regularity in the datapath structures. For general combinational logic circuits, we present an adaptive Monte-Carlo simulation technique for estimating accurate bounds on the value of the metric.
- 1 May 1992
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 41 (5) , 638-645
Simple bounds on serial signature analysis aliasing for random testing
- 1 May 1992
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 41 (5) , 638-645
Simple bounds on serial signature analysis aliasing for random testing