h3r2tic

// Copyright (c) 2023 Tomasz Stachowiak
//
// This contribution is dual licensed under EITHER OF
// 
//     Apache License, Version 2.0, (http://www.apache.org/licenses/LICENSE-2.0)
//     MIT license (http://opensource.org/licenses/MIT)
// 
// at your option.

#include "/inc/frame_constants.hlsl"

vurtun

// ref: http://www.codercorner.com/RadixSortRevisited.htm
// http://stereopsis.com/radix.html
// int/float: https://github.com/lshamis/FloatRadixSort
// string: https://github.com/rantala/string-sorting/blob/master/src/msd_ce.cpp

struct str {
  const char *str;
  const char *end;
  int len;
};

JarkkoPFC

struct vec3f {float x, y, z;};
struct vec4f {float x, y, z, w;};
struct mat44f {vec4f x, y, z, w;};

//============================================================================
// sphere_screen_extents
//============================================================================
// Calculates the exact screen extents xyzw=[left, bottom, right, top] in
// normalized screen coordinates [-1, 1] for a sphere in view space. For
// performance, the projection matrix (v2p) is assumed to be setup so that

dwilliamson

#include "FunctionalPropertyModifiers.h"


void fpmCallStore::CallAll(double time)
{
    for (auto i : m_FunctionCallMap)
    {
        const fpmFunctionCalls& calls = i->value;
        calls.call_all_fn(i->key, calls, time);

vurtun

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <assert.h>
#include <string.h>
#include <stdarg.h>
#include <limits.h>

#define cast(t,p) ((t)(p))
#define szof(a) ((int)sizeof(a))

douglashill

// A minimal iOS app set up entirely in code using Objective-C rather than using a storyboard and UIApplicationSceneManifest in the Info.plist.
// Last updated for iOS 18.
// Swift version: https://gist.github.com/douglashill/b8125f7e2336b6a47461df0d4898f64d

@import UIKit;

@interface SceneDelegate : UIResponder <UIWindowSceneDelegate>
@end

@implementation SceneDelegate

pervognsen

Multi-dimensional array views for systems programmers

As C programmers, most of us think of pointer arithmetic for multi-dimensional arrays in a nested way:

The address for a 1-dimensional array is base + x. The address for a 2-dimensional array is base + x + y*x_size for row-major layout and base + y + x*y_size for column-major layout. The address for a 3-dimensional array is base + x + (y + z*y_size)*x_size for row-column-major layout. And so on.

paniq

from math import *

# a performant solution would store a prefix sum of line lengths to
# a sidechannel and then use that to do a bsearch; on the GPU,
# you'd do a sum tree / histopyramid as a preprocessing step
def find_point(points, d):
    d = d
    for i in range(1, len(points)):
        x0,y0 = points[i-1]
        x1,y1 = points[i]

keebus

// library.h -------------------------------------------------------------------
#define opaque(Type) Type; int $sizeof_##Type(void);

#define opaque_impl(Type) int $sizeof_##Type(void) { return sizeof(Type); }

#define local(Type) ((Type *)alloca($sizeof_##Type()))

// foo.h -----------------------------------------------------------------------

nadavrot

High-Performance Matrix Multiplication

This is a short post that explains how to write a high-performance matrix multiplication program on modern processors. In this tutorial I will use a single core of the Skylake-client CPU with AVX2, but the principles in this post also apply to other processors with different instruction sets (such as AVX512).

Intro

Matrix multiplication is a mathematical operation that defines the product of