Lossy Checkpoint Compression in Full Waveform Inversion: a case study with ZFPv0.5.5 and the Overthrust Model

TL;DR

This paper introduces a method combining checkpointing with lossy compression to reduce data transfer and memory usage in large-scale Full-Waveform Inversion, demonstrating minimal impact on solution quality even at high compression rates.

Contribution

It presents a novel approach integrating error-controlled lossy compression with checkpointing in FWI, optimizing memory, time, and precision tradeoffs in high-performance computing.

Findings

High lossy compression rates up to 100x have minor impact on convergence.

Combining checkpointing with lossy compression reduces data movement and memory usage.

The method maintains solution quality despite significant data compression.

Abstract

This paper proposes a new method that combines check-pointing methods with error-controlled lossy compression for large-scale high-performance Full-Waveform Inversion (FWI), an inverse problem commonly used in geophysical exploration. This combination can significantly reduce data movement, allowing a reduction in run time as well as peak memory. In the Exascale computing era, frequent data transfer (e.g., memory bandwidth, PCIe bandwidth for GPUs, or network) is the performance bottleneck rather than the peak FLOPS of the processing unit. Like many other adjoint-based optimization problems, FWI is costly in terms of the number of floating-point operations, large memory footprint during backpropagation, and data transfer overheads. Past work for adjoint methods has developed checkpointing methods that reduce the peak memory requirements during backpropagation at the cost of additional floating-point computations. Combining this traditional checkpointing with error-controlled lossy compression, we explore the three-way tradeoff between memory, precision, and time to solution. We investigate how approximation errors introduced by lossy compression of the forward solution impact the objective function gradient and final inverted solution. Empirical results from these numerical experiments indicate that high lossy-compression rates (compression factors ranging up to 100) have a relatively minor impact on convergence rates and the quality of the final solution.