Weld: A Common Runtime for High Performance Data Analytics
Summary: Weld presents a common data-parallel IR and runtime to optimize across disjoint libraries (SQL, ML, graph, array), eliminating expensive cross-library data movement. By operator fusion and whole-workflow code generation, Weld plugs into Spark/TensorFlow/NumPy/Pandas and yields up to 30× end-to-end speedups. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Shoumik Palkar
- 2. James J. Thomas
- 3. Anil Shanbhag
- 4. Deepak Narayanan
- 5. Holger Pirk
- 6. Malte Schwarzkopf
- 7. Saman Amarasinghe
- 8. Matei Zaharia
Incoming Citations (Sorted by Pagerank)
Showing 35 of 35 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| Overall Rank | Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,972 | Palette: Enabling Scalable Analytics for Big-Memory, Multicore Machines | 2014 | SIGMOD | 4.1945683e-05 |
| 9,608 | Unified Data Analytics: State-of-the-art and Open Problems | 2022 | VLDB | 4.3177432e-05 |
| 2,170 | tf.data: A Machine Learning Data Processing Framework | 2021 | VLDB | 9.3821603e-05 |
| 2,818 | Implicit Parallelism through Deep Language Embedding | 2015 | SIGMOD | 8.0665558e-05 |
| 7,019 | Bridging the Gap Between HPC and Big Data Frameworks | 2017 | VLDB | 4.860057e-05 |
| 8,248 | Flare & Lantern: Efficiently Swapping Horses Midstream | 2019 | VLDB | 4.5509332e-05 |
| 2,172 | Spinning Fast Iterative Data Flows | 2012 | VLDB | 9.3706587e-05 |
| 10,897 | Welding Natural Language Queries to Analytics IRs with LLMs | 2024 | CIDR | 4.1945683e-05 |
| 1,873 | An Architecture for Compiling UDF-centric Workflows | 2015 | VLDB | 0.00010253002 |
| 2,896 | Evaluating End-to-End Optimization for Data Analytics Applications in Weld | 2018 | VLDB | 7.9452051e-05 |