Package: didgpu
Title: GPU-Accelerated, Checkpointed Difference-in-Differences
        Estimator
Version: 0.1.2
Authors@R: 
    person(given = "Joshua",
           family = "Ammons",
           role = c("aut", "cre", "cph"),
           email = "jdammons89@gmail.com")
Description: A clean-room reimplementation of the heterogeneity-robust
        dynamic difference-in-differences estimator of de Chaisemartin
        and D'Haultfoeuille (2024) <doi:10.1162/rest_a_01414>, designed
        for long-running econometric work: per-cell checkpointing to
        disk, resumable runs after crash or out-of-memory, parallel
        cluster bootstrap, configurable backends (pure R, optional
        'Rcpp' and 'CUDA'), and bit-for-bit numerical equivalence with
        the reference 'DIDmultiplegtDYN' package across binary,
        multivalued, and continuous treatments.
License: MIT + file LICENSE
URL: https://github.com/JoshuaAmmons/didgpu
BugReports: https://github.com/JoshuaAmmons/didgpu/issues
Encoding: UTF-8
Roxygen: list(markdown = TRUE)
RoxygenNote: 7.3.2
Depends: R (>= 4.1)
Imports: data.table, jsonlite, MASS, Rcpp, sandwich, stats, utils,
        tools
Suggests: broom, contdid, cowplot, did, DIDmultiplegt,
        DIDmultiplegtDYN, DRDID, eventstudyr, fect, fixest, ggplot2,
        HonestDiD, openxlsx, polars, quadprog, splines2, testthat (>=
        3.0.0)
LinkingTo: Rcpp, RcppEigen
SystemRequirements: GNU make; optional NVIDIA CUDA Toolkit (>= 12.0)
        with cuBLAS and cuSOLVER for the GPU backend
Config/testthat/edition: 3
Config/pak/sysreqs: nvidia-cuda-dev make
Repository: https://joshuaammons.r-universe.dev
Date/Publication: 2026-10-30 22:06:23 UTC
RemoteUrl: https://github.com/JoshuaAmmons/didgpu
RemoteRef: HEAD
RemoteSha: adf4955f4510a9b420d854c7a0cdc452b0978543
NeedsCompilation: yes
Packaged: 2026-10-31 01:28:31 UTC; root
Author: Joshua Ammons [aut, cre, cph]
Maintainer: Joshua Ammons <jdammons89@gmail.com>