blake3
------

[![GoDoc](https://godoc.org/lukechampine.com/blake3?status.svg)](https://godoc.org/lukechampine.com/blake3)
[![Go Report Card](http://goreportcard.com/badge/lukechampine.com/blake3)](https://goreportcard.com/report/lukechampine.com/blake3)

```
go get lukechampine.com/blake3
```

`blake3` implements the [BLAKE3 cryptographic hash function](https://github.com/BLAKE3-team/BLAKE3).
This implementation aims to be performant without sacrificing (too much)
readability, in the hopes of eventually landing in `x/crypto`.

In addition to the pure-Go implementation, this package also contains AVX-512
and AVX2 routines (generated by [`avo`](https://github.com/mmcloughlin/avo))
that greatly increase performance for large inputs and outputs.

## Benchmarks

Tested on a 2020 MacBook Air (i5-7600K @ 3.80GHz). Benchmarks will improve as
soon as I get access to a beefier AVX-512 machine. :wink:

### AVX-512

```
BenchmarkSum256/64           120 ns/op       533.00 MB/s
BenchmarkSum256/1024        2229 ns/op       459.36 MB/s
BenchmarkSum256/65536      16245 ns/op      4034.11 MB/s
BenchmarkWrite               245 ns/op      4177.38 MB/s
BenchmarkXOF                 246 ns/op      4159.30 MB/s
```

### AVX2

```
BenchmarkSum256/64           120 ns/op       533.00 MB/s
BenchmarkSum256/1024        2229 ns/op       459.36 MB/s
BenchmarkSum256/65536      31137 ns/op      2104.76 MB/s
BenchmarkWrite               487 ns/op      2103.12 MB/s
BenchmarkXOF                 329 ns/op      3111.27 MB/s
```

### Pure Go

```
BenchmarkSum256/64           120 ns/op       533.00 MB/s
BenchmarkSum256/1024        2229 ns/op       459.36 MB/s
BenchmarkSum256/65536     133505 ns/op       490.89 MB/s
BenchmarkWrite              2022 ns/op       506.36 MB/s
BenchmarkXOF                1914 ns/op       534.98 MB/s
```

## Shortcomings

There is no assembly routine for single-block compressions. This is most
noticeable for ~1KB inputs.

Each assembly routine inlines all 7 rounds, causing thousands of lines of
duplicated code. Ideally the routines could be merged such that only a single
routine is generated for AVX-512 and AVX2, without sacrificing too much
performance.