Source: gemmlowp Section: science Priority: optional Maintainer: Debian Science Maintainers Uploaders: Mo Zhou Build-Depends: debhelper (>= 12~), cmake, Standards-Version: 4.3.0 Homepage: https://github.com/google/gemmlowp Vcs-Browser: https://salsa.debian.org/science-team/gemmlowp Vcs-Git: https://salsa.debian.org/science-team/gemmlowp.git Package: libgemmlowp-dev Section: libdevel Architecture: any Multi-Arch: foreign Depends: ${misc:Depends}, # ${shlibs:Depends}, # there is no binary file in this package. Description: small self-contained low-precision GEMM library This is not a full linear algebra library, only a GEMM library: it only does general matrix multiplication ("GEMM"). . Its performance goals differ from typical GEMM performance goals in the following ways: 1. It cares not only about speed, but also about minimizing power usage. It specifically cares about charge usage in mobile/embedded devices. 2. Most GEMMs are optimized primarily for large dense matrix sizes (>= 1000). It does care about large sizes, but it also cares specifically about the typically smaller matrix sizes encountered in various mobile applications. . Keep in mind (previous section) that gemmlowp itself is a pure-headers-only library.