nmoinvaz

/* ===========================================================================
 * Symbol buffer write/read macros.
 *
 * The symbol buffer stores literal and distance/length pairs. The storage
 * format differs based on LIT_MEM (separate buffers) vs sym_buf (interleaved),
 * and on whether the platform supports fast unaligned 32-bit access
 * (OPTIMAL_CMP >= 32), which allows packing a 3-byte symbol into a single
 * 32-bit write/read.
 *
 * SYM_WRITE_LIT and SYM_WRITE_DIST write a symbol and advance sym_next.

nmoinvaz

import re, sys

def parse_results(path):
    results = {}
    with open(path) as f:
        for line in f:
            m = re.match(r'\s+(\d+|avg\d?)\s', line)
            if not m:
                continue
            level = m.group(1)

nmoinvaz

name: Benchmark
on:
  issue_comment:
    types: [created]
  workflow_dispatch:
    inputs:
      pr_number:
        description: 'PR number to benchmark (results posted as PR comment)'
        required: false
        type: number

nmoinvaz

    // Set up generic C code fallbacks
#ifndef WITH_ALL_FALLBACKS
    // Only use necessary generic functions when no suitable simd versions are available.
    // These conditions mirror the native_* defines in arch/*_functions.h headers.
#  if (defined(X86_SSE2) && defined(__SSE2__)) || (defined(ARCH_X86) && defined(ARCH_64BIT))
    ft.adler32 = &adler32_c;
    ft.adler32_copy = &adler32_copy_c;
    ft.crc32 = &crc32_braid;
    ft.crc32_copy = &crc32_copy_braid;

nmoinvaz

/* benchmark_tally.cc -- benchmark sym_buf read/write strategies
 * Copyright (C) 2024 zlib-ng contributors
 * For conditions of distribution and use, see copyright notice in zlib.h
 *
 * Compares:
 * 1. LIT_MEM (separate d_buf/l_buf arrays)
 * 2. sym_buf with zng_memread_4/zng_memwrite_4 (batched)
 * 3. sym_buf with byte-by-byte access (original)
 */

nmoinvaz

#include <benchmark/benchmark.h>
#include <cstdint>

static inline uint32_t count_matching_bytes_ctzll(uint64_t mask) {
    return __builtin_ctzll(mask);
}

static inline uint32_t count_matching_bytes_ctz32(uint64_t mask) {
    uint32_t lo = (uint32_t)mask;
    if (lo)

nmoinvaz

/* benchmark_crc32_tail_copy.cc -- benchmark different copy strategies for CRC32 tail handling
 * Copyright (C) 2022 Nathan Moinvaziri
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

#include <benchmark/benchmark.h>
#include <cstring>
#include <cstdint>

extern "C" {

nmoinvaz

/* benchmark_tailcopy.cc -- benchmark different copy strategies for tail handling
 * Copyright (C) 2022 Nathan Moinvaziri
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

#include <benchmark/benchmark.h>
#include <cstring>
#include <cstdint>

extern "C" {

nmoinvaz

OS: Darwin 24.6.0 Darwin Kernel Version 24.6.0: Wed Nov  5 21:28:03 PST 2025; root:xnu-11417.140.69.705.2~1/RELEASE_ARM64_T8122 arm64
CPU: arm
Timing: Python perf_counter 
Levels: 0-9       
Runs: 70         Trim worst: 40        

Test 1

Develop

nmoinvaz

{
    // Use IntelliSense to learn about possible attributes.
    // Hover to view descriptions of existing attributes.
    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
    "version": "0.2.0",
    "configurations": [
        {
            "name": "fuzzer_example_small",
            "type": "lldb",
            "request": "launch",