Amar Phanishayee

Amar Phanishayee

Auto-generated profile, based on publicly available information

Amar Phanishayee

Meta Platforms, Inc., Bellevue, USA

Research Focus & Metrics

Representative Publications

View All Publications
11 October 2009
Verified
Conference Paper
Open access
PDF file
DADavid G. Andersen
David G. Andersen
JFJason Franklin
Jason Franklin
MKMichael Kaminsky
Michael Kaminsky
APAmar Phanishayee
Amar Phanishayee
LTLawrence Tan
Lawrence Tan
VVVijay Vasudevan
Vijay Vasudevan

30 March 2025
Verified
Conference Paper
Open access
SLSeonho Lee
Seonho Lee
APAmar Phanishayee
Amar Phanishayee
DMDivya Mahajan
Divya Mahajan
Deep learning kernels exhibit a high level of predictable memory accesses and compute patterns, making GPU's architecture well-suited for their execution. Moreover, software and runtime system for GPUs further enable optimizations that aim to better utilize the stream multiprocessors, on-chip bandwidth, multiple levels of cache hierarchy, and off-chip high-bandwidth memory. In the context of deep learning, the entire space of models and GPUs is constantly evolving, as newer models emerge with simultaneous upgrades to the device. However, access to newer GPUs is often limited, raising important questions about the performance of new model architectures on existing GPUs, existing models on new GPUs, and new model architectures on new GPUs. To address these questions, we introduce NeuSight, a forecasting framework to predict the performance of a diverse range of deep learning models, for both training and inference, on unseen GPUs, without requiring actual execution of the target model on the target GPU. The framework leverages both GPU hardware behavior and software library optimizations to estimate the end-to-end performance of these models. We observe that prior work in this area suffers from high absolute error percentages when forecasting performance on unseen models and new GPUs, as they attempt to model the complex task of predicting the latency of a deep learning kernel on a GPU directly using a machine learning approach. Instead, with NeuSight, we decompose the prediction into smaller problems, while bounding the prediction through fundamental performance laws. NeuSight decomposes a single deep learning kernel prediction into smaller working sets called tiles, which are executed independently on the GPU. Tile-granularity predictions are determined using a machine learning approach and aggregated to estimate the end-to-end latency. As such, NeuSight outperforms prior work across a variety of deep learning workloads and the most up-to-date GPUs. It reduces the percentage error from 121.4% and 30.8% to 2.3% in predicting the latency of GPT3 model for training and inference on H100, in comparison to state-of-the-art prior work, respectively, where GPT3 and H100 were not used to train any framework.

22 April 2024
Verified
Conference Paper
Open access
SASaurabh Agarwal
Saurabh Agarwal
APAmar Phanishayee
Amar Phanishayee
SVShivaram Venkataraman
Shivaram Venkataraman

20 June 2025
Verified
Conference Paper
Open access
WCWeiwei Chu
Weiwei Chu
XXXinfeng Xie
Xinfeng Xie
JYJiecao Yu
Jiecao Yu
JWJie Wang
Jie Wang
APAmar Phanishayee
Amar Phanishayee
JPJong-Soo Park
Jong-Soo Park

1 September 2026 in IEEE Micro
Verified
Journal Article
Closed access
DMDivya Mahajan
Divya Mahajan
SLSeonho Lee
Seonho Lee
JKJunkyum Kim
Junkyum Kim
SGSeokjin Go
Seokjin Go
APAmar Phanishayee
Amar Phanishayee