mmozeiko

#pragma once

// uncompressed png writer & reader
// supports only 8-bit and 16-bit formats

// Performance comparison for 8192x8192 BGRA8 image (256MB)
// Compiled with "clang -O2", AVX2 requires extra "-mavx2" or "/arch:AVX2" argument
//
// For libpng (compressed) uses default libpng/zlib compression settings
// For libpng (uncompressed) case following two functions are used:

d7samurai

Minimal D3D11 bonus material: pixel art antialiasing

A minimal Direct3D 11 implementation of "antialiased point sampling", useful for smooth fractional movement and non-integer scaling of pixel art AKA "fat pixel" aesthetics.

Also view below side-by-side point sampling comparison on YouTube (video is zoomed in to counter implicit downsampling & compression artifacts and make aa effect more apparent) or check out the Shadertoy.

The actual sampler is set to bilinear filtering (the default D3D11 sampler state) in order to utilize single texture-read hardware interpolation, then emulating point sampling in the shader and applying AA at the fat pixel boundaries. Use with premultiplied alpha textures* and keep a one pixel transparent border around each sprite/tile.

d7samurai

Minimal D3D11 pt2

Follow-up to Minimal D3D11, adding instanced rendering. As before: An uncluttered Direct3D 11 setup & basic rendering primer / API familiarizer. Complete, runnable Windows application contained in a single function and laid out in a linear, step-by-step fashion. No modern C++ / OOP / obscuring cruft.

The main difference here is that the hollow cube is rendered using DrawIndexedInstanced (which saves a lot of vertices compared to the original, so model data is now small enough to be included in the source without being too much in the way), but also all trigonometry and matrix math is moved to the vertex shader, further simplifying the main code.

Each instance is merely this piece of geometry, consisting of 4 triangles:

..which is then repeated 24 times, rotated and colored:

ibireme

// =============================================================================
// XNU kperf/kpc demo
// Available for 64-bit Intel/Apple Silicon, macOS/iOS, with root privileges
//
//
// Demo 1 (profile a function in current thread):
// 1. Open directory '/usr/share/kpep/', find your CPU PMC database.
//    For M1 (Pro/Max), the database file is '/usr/share/kpep/a14.plist'.
// 2. Select a few events that you are interested in,
//    add their names to the `profile_events` array below.

pervognsen

// Estimating CPU frequency...
// CPU frequency: 4.52 GHz
// sum1: value = 15182118497126522709, 0.31 secs, 5.14 cycles/elem
// sum2: value = 15182118497126522709, 0.17 secs, 2.93 cycles/elem

#define RW(x) asm("" : "+r"(x))

typedef struct Node {
	u64 value;
	struct Node *next;

NoelFB

#pragma once

namespace YourNamespace
{
	struct Routine
	{
        // Current "waiting time" before we run the next block
        float wait_for = 0;

        // Used during `rt_for`, which repeats the given block for X time

Joshua-Ashton

template <class _Ty>
_NODISCARD /* constexpr */ _Ty _Common_lerp(const _Ty _ArgA, const _Ty _ArgB, const _Ty _ArgT) noexcept {
    // on a line intersecting {(0.0, _ArgA), (1.0, _ArgB)}, return the Y value for X == _ArgT

    const int _Finite_mask = (int{isfinite(_ArgA)} << 2) | (int{isfinite(_ArgB)} << 1) | int{isfinite(_ArgT)};
    if (_Finite_mask == 0b111) {
        // 99% case, put it first; this block comes from P0811R3
        if ((_ArgA <= 0 && _ArgB >= 0) || (_ArgA >= 0 && _ArgB <= 0)) {
            // exact, monotonic, bounded, determinate, and (for _ArgA == _ArgB == 0) consistent:
            return _ArgT * _ArgB + (1 - _ArgT) * _ArgA;

native-m

#include <Windows.h>
#include <d3d11.h>
#include <iostream>
#include <vector>
#include <thread>
#include <mutex>
#include <d3dcompiler.h>

#pragma comment(lib, "dxgi.lib")
#pragma comment(lib, "d3d11.lib")

willscott

.PHONY: all
all: rot13.wasm

%.wasm.full: %.c
	clang $< -g -o $@

%.wasm.dwarf: %.wasm.full
	llvm-dwarfdump $< > $@

%.wasm: %.wasm.full %.wasm.dwarf

NickStrupat

#pragma once

#if defined(_WIN32)
#	include <Windows.h>
#elif defined(__APPLE__) || defined(LINUX)
#	include <sys/mman.h>
#endif

#include <optional>
#include "result.hpp"