Pith. sign in

REVIEW 4 cited by

Learning to Optimize Tensor Programs

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1805.08166 v4 pith:5JSSVHRL submitted 2018-05-21 cs.LG stat.ML

Tianqi Chen , Lianmin Zheng , Eddie Yan , Ziheng Jiang , Thierry Moreau , Luis Ceze , Carlos Guestrin , Arvind Krishnamurthy This is my paper · ORCID
classification cs.LGstat.ML
keywords learningtensorlibrariesdeepeffectiveengineeringframeworkimplementations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce a learning-based framework to optimize tensor programs for deep learning workloads. Efficient implementations of tensor operators, such as matrix multiplication and high dimensional convolution, are key enablers of effective deep learning systems. However, existing systems rely on manually optimized libraries such as cuDNN where only a narrow range of server class GPUs are well-supported. The reliance on hardware-specific operator libraries limits the applicability of high-level graph optimizations and incurs significant engineering costs when deploying to new hardware targets. We use learning to remove this engineering burden. We learn domain-specific statistical cost models to guide the search of tensor operator implementations over billions of possible program variants. We further accelerate the search by effective model transfer across workloads. Experimental results show that our framework delivers performance competitive with state-of-the-art hand-tuned libraries for low-power CPU, mobile GPU, and server-class GPU.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Transition-Aware Backend Dispatch for Edge LLM Inference

    cs.AR 2026-07 conditional novelty 6.0 of 10

    Transition-aware backend dispatch—conditioning each operator's backend choice on the previous backend—reduces replayed latency, energy, and EDP by up to 17.4%, 14.4%, and 28.5% versus static assignment in seven edge-L...

  2. Tensor Program Optimization for the RISC-V Vector Extension Using Probabilistic Programs

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Integrating RVV tensor intrinsics into TVM's MetaSchedule autotuner yields AI kernels that are 29-50% faster than hand-written muRISCV-NN and 35-46% faster than compiler autovectorization on tested RVV 1.0 hardware.

  3. Pearl: Automatic Code Optimization Using Deep Reinforcement Learning

    cs.PL 2025-06 conditional novelty 6.0 of 10

    An RL agent with a graph neural network learns loop nest optimizations for the Tiramisu compiler and generalizes to unseen benchmarks, reporting 2.02x and 3.36x geometric mean speedups over Tiramisu and Pluto.

  4. A Multi-level Compiler Backend for Accelerated Micro-kernels Targeting RISC-V ISA Extensions

    cs.PL 2025-02 conditional novelty 6.0 of 10

    A multi-level MLIR/xDSL backend for the Snitch RISC-V accelerator reaches up to 95% FPU utilization on micro-kernels and 90% when lowered from linalg, without register spilling.

Pith tools