Timezone: »

DietCode: Automatic Optimization for Dynamic Tensor Programs
Bojian Zheng · Ziheng Jiang · Cody Hao Yu · Haichen Shen · Joshua Fromm · Yizhi Liu · Yida Wang · Luis Ceze · Tianqi Chen · Gennady Pekhimenko


Achieving high performance for compute-intensive operators in machine learning (ML) workloads is a crucial but challenging task. Many ML and system practitioners rely on vendor libraries or auto-schedulers to do the job. While the former requires large engineering efforts, the latter only supports static-shape workloads in existing works. It is difficult, if not impractical, to apply existing auto-schedulers directly to dynamic-shape workloads, as this leads to extremely long auto-scheduling time.We observe that the key challenge faced by existing auto-schedulers when handling a dynamic-shape workload is that they cannot construct a unified search space for all the possible shapes of the workload, because their search space is shape-dependent. To address this, we propose DietCode, a new auto-scheduler framework that efficiently supports dynamic-shape workloads by constructing a shape-generic search space and cost model. Under this construction, all shapes jointly search within the same space and update the same cost model when auto-scheduling, which is therefore more efficient compared with existing auto-schedulers.We evaluate DietCode using state-of-the-art machine learning workloads on a modern GPU. Our evaluation shows that DietCode has the following key strengths when auto-scheduling an entire model end-to-end: (1) reduces the auto-scheduling time by up to 5.88x less than the state-of-the-art auto-scheduler on the uniformly sampled dynamic shapes (94.1x estimated if all possible shapes are included), (2) improves performance by up to 69.5% better than the auto-scheduler and 18.6% better than the vendor library. All these advantages make DietCode an efficient and practical solution for dynamic-shape workloads.

Author Information

Bojian Zheng (University of Toronto)
Ziheng Jiang (University of Washington and OctoML)
Cody Hao Yu (Amazon Web Services)
Haichen Shen (Amazon)
Joshua Fromm (OctoML, University of Washington)
Yizhi Liu (Amazon)
Yida Wang (Amazon)
Luis Ceze (University of Washington and OctoML)
Tianqi Chen (CMU)
Gennady Pekhimenko (University of Toronto)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors