perf(exp/simd): optimize Sum funcs with horizontal reduction #17

	name: Tests (SIMD)

	on:
	push:
	branches:
	- master
	paths:
	- 'exp/simd/**'
	pull_request:
	paths:
	- 'exp/simd/**'

	env:
	GOEXPERIMENT: simd

	jobs:
	test-simd:
	# GitHub hosted runners run on several architectures.
	# Using Ubicloud ensures we run on AVX512.
	runs-on: ubicloud-standard-2
	strategy:
	fail-fast: false
	matrix:
	go:
	- "stable"

	steps:
	- uses: actions/checkout@v6

	- name: Set up Go
	uses: actions/setup-go@v6
	with:
	go-version: ${{ matrix.go }}

	- name: Test
	run: make test

	- name: Benchmark
	run: \|
	cd exp/simd/
	GOEXPERIMENT=simd go test -run=^Benchmark -benchmem -bench ./...

Provide feedback