Source: golang-github-minio-blake2b-simd
Section: devel
Priority: optional
Maintainer: Debian Go Packaging Team <team+pkg-go@tracker.debian.org>
Uploaders: Andrius Merkys <merkys@debian.org>
Build-Depends: debhelper (>= 12),
               dh-golang,
               golang-any
Standards-Version: 4.3.0
Homepage: https://github.com/minio/blake2b-simd
Vcs-Browser: https://salsa.debian.org/go-team/packages/golang-github-minio-blake2b-simd
Vcs-Git: https://salsa.debian.org/go-team/packages/golang-github-minio-blake2b-simd.git
XS-Go-Import-Path: github.com/minio/blake2b-simd
Testsuite: autopkgtest-pkg-go

Package: golang-github-minio-blake2b-simd-dev
Architecture: all
Depends: ${misc:Depends}
Description: Fast hashing using pure Go implementation of BLAKE2b with SIMD instructions
 BLAKE2b-SIMD Pure Go implementation of BLAKE2b using SIMD
 optimizations.  Introduction This package was initially based
 on the pure go BLAKE2b (https://github.com/dchest/blake2b)
 implementation of Dmitry Chestnykh and merged with the (cgo
 dependent) AVX optimized BLAKE2 (https://github.com/codahale/blake2)
 implementation (which in turn is based on the official implementation
 (https://github.com/BLAKE2/BLAKE2). It does so by using Go's Assembler
 (https://golang.org/doc/asm) for amd64 architectures with a golang only
 fallback for other architectures.
 .
 In addition to AVX there is also support for AVX2 as well as SSE. Best
 performance is obtained with AVX2 which gives roughly a 4X performance
 increase approaching hashing speeds of 1GB/sec on a single core.
 .
 BLAKE2b is a hashing algorithm that operates on 64-bit integer values. The
 AVX2 version uses the 256-bit wide YMM registers in order to essentially
 process four operations in parallel. AVX and SSE operate on 128-bit
 values simultaneously (two operations in parallel). Below are excerpts
 from compressAvx2_amd64.s, compressAvx_amd64.s, and compress_generic.go
 respectively.
 .
     VPADDQ  YMM0,YMM0,YMM1   /* v0 += v4, v1 += v5, v2 += v6, v3 += v7 */
 .
     VPADDQ  XMM0,XMM0,XMM2   /* v0 += v4, v1 += v5 */ VPADDQ
     XMM1,XMM1,XMM3   /* v2 += v6, v3 += v7 */
 .
     v0 += v4 v1 += v5 v2 += v6 v3 += v7