snowclipsed

const std = @import("std");
const mem = std.mem;
const json = std.json;
const Allocator = mem.Allocator;
const Thread = std.Thread;

// Constants
pub const MIN_PARALLEL_TEXT_SIZE = 10_000;
pub const DEFAULT_CHUNK_SIZE = 1024 * 64;
pub const MAX_THREADS = 8;

snowclipsed

const std = @import("std");
const builtin = @import("builtin");
const time = std.time;
const atomic = std.atomic;

const CACHE_LINE_SIZE: usize = atomic.cache_line;
const CHUNK_SIZE: usize = 1;
const NEON_ALIGNMENT = 16;
// For ARM NEON, we use 4-wide vectors as that's the native SIMD width
const Vec4f = @Vector(4, f32);

snowclipsed

// To run tests, do :
// zig test -OReleaseSafe -Dcpu=native -Dtarget=native matmul.zig
// To run main, do :
// zig build-exe -OReleaseFast -Dcpu=native -Dtarget=native matmul.zig
// ./matmul


//
// ███╗   ███╗ █████╗ ████████╗███╗   ███╗██╗   ██╗██╗     ░░░░░░███████╗██╗ ██████╗ 
// ████╗ ████║██╔══██╗╚══██╔══╝████╗ ████║██║   ██║██║     ░░░░░░╚══███╔╝██║██╔════╝ 

snowclipsed

import React, { useState, useEffect, useCallback, useRef } from 'react';

/**
 * Represents a point in 3D space within the Lorenz system.
 */
interface Point {
  x: number;
  y: number;
  z: number;
}

snowclipsed

import React, { useState, useEffect, useCallback, useRef } from 'react';

type ColoredChar = {
  char: string;
  color: string;
};

const defaultConfig = {
  scale: 0.05,

snowclipsed

const std = @import("std");
const c = @cImport({
    @cInclude("stb_image.h");
});

fn cubic(x: f32) f32 {
    const a = -0.5;
    const abs_x = @abs(x);
    if (abs_x <= 1.0) {
        return (a + 2.0) * abs_x * abs_x * abs_x - (a + 3.0) * abs_x * abs_x + 1.0;

snowclipsed

const std = @import("std");

// Can also try:
// 8 x 64
// 16 x 64
// Top GFLOPs/s on an Intel® Core™ i7-13620H Processor = 300.9 GFLOPs/s
// Comments were added using Claude.
// To run simply run zig build-exe -O ReleaseFast matmul_FP32.zig, then run the binary ./matmul_FP32
// To test simply run zig test -O ReleaseFast matmul_FP32.zig
// To test performance on a generated binary, run : sudo perf stat -e cache-misses,cache-references,instructions,cycles ./matmul_FP32