Files
fastwc/benchmarks/std.sh
T
huntedbytheirs 6aa461f053 bench: rub it in — monsters, stdin wins, busybox retired
Suites split into benchmarks/files/{lines,words} and
benchmarks/stdin/piping, with the monsters bolted onto the lines suite:
100M lines raced against coreutils (~2x win), 1B lines solo (~6-8s,
11 GB in one pass). Stdin redirects from regular files are now mmap'd
in count_stream, so the stdin suite wins too — up to 12.00x on words.

The ratio column now reports how many times faster fastwc is, not how
much of GNU's time it used. busybox was removed from the suite: it
stopped being a challenge and started being a participation trophy.
GNU wc's lone win — 1M lines by one millisecond on hand-tuned AVX-512
assembly — is now a historical footnote, and the README says so.
2026-08-29 15:52:24 -04:00

326 lines
11 KiB
Bash
Executable File

#!/usr/bin/env bash
#
# std.sh — shared "standard library" for the fastwc benchmark scripts.
#
# Every benchmark script lives in its own directory (benchmarks/files/words,
# benchmarks/files/lines, benchmarks/stdin/piping) and sets two variables
# before sourcing this file:
# SCRIPT_DIR — the benchmark script's own directory (test data lives here)
# REPO_DIR — the repository root (release binary and tools live here)
#
# Provides the helpers every benchmark script needs:
# checkfastwc() verify a release build of fastwc exists
# checkwc() locate the coreutils wc implementation
# createtxt() create (or reuse) a text file with N such lines
# time_ms() run a command once, print elapsed wall time in ms
# capture_count() print the first whitespace-separated field of output
# run_case() race fastwc against the reference on a file argument
# run_stdin_case() same, but feeding the file through standard input
# run_solo_case() time fastwc alone (no reference) and print throughput
# run_cases() run run_case for a list of sizes, fail-fast
# run_stdin_cases() run run_stdin_case for a list of sizes, fail-fast
# write_failed_report() write the human readable failure report
#
# The suites fail fast: the moment fastwc is slower than (or disagrees
# with) the reference wc, a human readable report is written to
# FAILED-benchmark.txt next to the suite and it returns non-zero.
set -u
FASTWC="$REPO_DIR/bin/release/fastwc"
DATA_DIR="$SCRIPT_DIR/.data"
GENFILE="$REPO_DIR/benchmarks/tools/genfile" # optional C helper, built by test-all.sh
BENCH_NAME="${BENCH_NAME:-wc}" # set by the caller: coreutils
BENCH_REPS="${BENCH_REPS:-3}" # interleaved runs per case; minimum is kept
RESULT_ROWS="" # accumulated results table
WC_CMD=() # filled by checkwc()
TEXT_FILE="" # filled by createtxt()
if [[ -z "$BENCH_REPS" || "$BENCH_REPS" -lt 1 ]]; then
BENCH_REPS=1
fi
# checkfastwc — make sure the release build exists and is executable.
checkfastwc() {
printf 'checking for release build fastwc... '
if [[ -x "$FASTWC" ]]; then
printf 'yes\n'
return 0
fi
printf 'no\n'
printf 'configure: error: no release build of fastwc found at %s\n' "$FASTWC" >&2
printf 'configure: error: run "make release" first to generate one\n' >&2
exit 1
}
# checkwc — locate the coreutils wc implementation and store its invocation
# in $WC_CMD. Exits on failure.
checkwc() {
printf 'checking for coreutils wc... '
if command -v wc >/dev/null 2>&1 \
&& wc --version 2>/dev/null | head -n1 | grep -qi 'GNU coreutils'; then
printf 'yes\n'
WC_CMD=(wc)
else
printf 'no\n'
printf 'configure: error: GNU Coreutils wc not found in PATH\n' >&2
exit 1
fi
}
# createrandstr — print one random 10-character alphanumeric string.
createrandstr() {
local chars='abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789'
local out='' i
for ((i = 0; i < 10; i++)); do
out+="${chars:$((RANDOM % ${#chars})):1}"
done
printf '%s\n' "$out"
}
# createtxt <lines> — make sure a text file with <lines> rows of random
# 10-character alphanumeric strings exists in this suite's .data directory.
# A copy generated by a previous run is reused (checked by exact byte size:
# 10 chars + '\n' per line), so repeated benchmark runs are cheap.
# Prints the path and sets $TEXT_FILE; returns non-zero if generation fails.
createtxt() {
local lines="$1"
local expect=$((lines * 11))
local have=0
TEXT_FILE="$DATA_DIR/words-$lines.txt"
if [[ -f "$TEXT_FILE" ]]; then
have=$(stat -c '%s' "$TEXT_FILE" 2>/dev/null || printf '0')
fi
if [[ "$have" -ne "$expect" ]]; then
mkdir -p "$DATA_DIR"
if [[ -x "$GENFILE" ]]; then
"$GENFILE" "$lines" > "$TEXT_FILE" || {
printf 'createtxt: error: failed to generate %s\n' "$TEXT_FILE" >&2
return 1
}
else
printf 'createtxt: warning: %s not built, using slow shell fallback\n' "$GENFILE" >&2
printf 'createtxt: warning: run ./test-all.sh to build the helper tools\n' >&2
: > "$TEXT_FILE"
for ((i = 0; i < lines; i++)); do
createrandstr >> "$TEXT_FILE"
done
fi
fi
printf '%s\n' "$TEXT_FILE"
}
# time_ms <cmd...> — run a command once and print elapsed wall time in ms.
time_ms() {
local s e
s=$(date +%s%N)
"$@" >/dev/null 2>&1
e=$(date +%s%N)
printf '%s\n' "$(( (e - s) / 1000000 ))"
}
# capture_count <cmd...> — print the first whitespace-separated field of a
# command's output, i.e. the count reported by `wc -w/-l` or `fastwc -w/-l`.
capture_count() {
"$@" 2>/dev/null | awk 'NR == 1 { print $1 }'
}
# write_failed_report <label> <reason> <wc_ms> <fast_ms> — write the
# human readable failure report to FAILED-benchmark.txt next to the suite.
write_failed_report() {
local label="$1" reason="$2" wc_ms="$3" fast_ms="$4"
local report="$SCRIPT_DIR/FAILED-benchmark.txt"
{
printf 'fastwc benchmark FAILED\n'
printf '=======================\n'
printf 'implementation : %s wc\n' "$BENCH_NAME"
printf 'failed test : %s\n' "$label"
printf 'failure : %s\n' "$reason"
printf '\nresults\n'
printf '%s\n' '-------'
printf '%-28s %10s %10s %8s %s\n' 'test' 'wc' 'fastwc' 'ratio' 'status'
printf '%s' "$RESULT_ROWS"
printf '\nfastwc must never be slower than %s wc — benchmark aborted.\n' "$BENCH_NAME"
} > "$report"
printf '\nbenchmark FAILED (%s): %s\n' "$BENCH_NAME" "$reason" >&2
printf 'full results written to %s\n' "$report" >&2
}
# run_case <words|lines> <n-lines> <-w|-l> — race the reference wc against
# fastwc on a file argument. Fails the benchmark the moment fastwc is
# slower or reports a different count.
run_case() {
local mode="$1" lines="$2" flag="$3"
local noun='lines'; [[ "$lines" -eq 1 ]] && noun='line'
local label="${mode} (${lines} ${noun})"
local file wc_count fast_count wc_ms fast_ms ratio verdict reason row
local i d
file=$(createtxt "$lines") || return 1
# correctness: fastwc must report the same count as the reference wc
wc_count=$(capture_count "${WC_CMD[@]}" "$flag" "$file")
fast_count=$(capture_count "$FASTWC" "$flag" "$file")
# speed: interleaved timing so both commands see identical cache warmth;
# keep the minimum of $BENCH_REPS runs each to reduce noise
wc_ms=''
fast_ms=''
for ((i = 0; i < BENCH_REPS; i++)); do
d=$(time_ms "${WC_CMD[@]}" "$flag" "$file")
[[ -z "$wc_ms" || "$d" -lt "$wc_ms" ]] && wc_ms="$d"
d=$(time_ms "$FASTWC" "$flag" "$file")
[[ -z "$fast_ms" || "$d" -lt "$fast_ms" ]] && fast_ms="$d"
done
# ratio: how many times faster fastwc is than the reference (wc / fastwc)
if [[ -n "$wc_ms" && "$wc_ms" -gt 0 ]]; then
if [[ "$fast_ms" -gt 0 ]]; then
ratio=$(awk -v f="$fast_ms" -v w="$wc_ms" 'BEGIN { printf "%.2fx", w / f }')
else
ratio='infx'
fi
else
ratio='-'
fi
verdict='PASS'
reason=''
if [[ "$fast_count" != "$wc_count" ]]; then
verdict='FAIL'
reason="output mismatch (fastwc: ${fast_count}, ${BENCH_NAME} wc: ${wc_count})"
elif (( fast_ms > wc_ms )); then
verdict='FAIL'
reason="fastwc was slower (fastwc: ${fast_ms}ms vs ${BENCH_NAME} wc: ${wc_ms}ms)"
fi
row=$(printf '%-28s %10s %10s %8s %s\n' \
"$label" "wc: ${wc_ms}ms" "fastwc: ${fast_ms}ms" "$ratio" "$verdict")
RESULT_ROWS+="${row}"$'\n'
printf '%s\n' "$row"
if [[ "$verdict" == 'FAIL' ]]; then
write_failed_report "$label" "$reason" "$wc_ms" "$fast_ms"
return 1
fi
return 0
}
# run_stdin_case <words|lines> <n-lines> <-w|-l|...> — same race, but the
# data is fed through standard input with a redirect instead of a file
# argument. Counts must also agree with the reference's stdin behavior.
run_stdin_case() {
local mode="$1" lines="$2" flag="$3"
local noun='lines'; [[ "$lines" -eq 1 ]] && noun='line'
local label="stdin ${mode} (${lines} ${noun})"
local file wc_count fast_count wc_ms fast_ms ratio verdict reason row
local i d
file=$(createtxt "$lines") || return 1
wc_count=$(capture_count "${WC_CMD[@]}" "$flag" < "$file")
fast_count=$(capture_count "$FASTWC" "$flag" < "$file")
wc_ms=''
fast_ms=''
for ((i = 0; i < BENCH_REPS; i++)); do
d=$(time_ms "${WC_CMD[@]}" "$flag" < "$file")
[[ -z "$wc_ms" || "$d" -lt "$wc_ms" ]] && wc_ms="$d"
d=$(time_ms "$FASTWC" "$flag" < "$file")
[[ -z "$fast_ms" || "$d" -lt "$fast_ms" ]] && fast_ms="$d"
done
# ratio: how many times faster fastwc is than the reference (wc / fastwc)
if [[ -n "$wc_ms" && "$wc_ms" -gt 0 ]]; then
if [[ "$fast_ms" -gt 0 ]]; then
ratio=$(awk -v f="$fast_ms" -v w="$wc_ms" 'BEGIN { printf "%.2fx", w / f }')
else
ratio='infx'
fi
else
ratio='-'
fi
verdict='PASS'
reason=''
if [[ "$fast_count" != "$wc_count" ]]; then
verdict='FAIL'
reason="output mismatch (fastwc: ${fast_count}, ${BENCH_NAME} wc: ${wc_count})"
elif (( fast_ms > wc_ms )); then
verdict='FAIL'
reason="fastwc was slower (fastwc: ${fast_ms}ms vs ${BENCH_NAME} wc: ${wc_ms}ms)"
fi
row=$(printf '%-28s %10s %10s %8s %s\n' \
"$label" "wc: ${wc_ms}ms" "fastwc: ${fast_ms}ms" "$ratio" "$verdict")
RESULT_ROWS+="${row}"$'\n'
printf '%s\n' "$row"
if [[ "$verdict" == 'FAIL' ]]; then
write_failed_report "$label" "$reason" "$wc_ms" "$fast_ms"
return 1
fi
return 0
}
# run_solo_case <n-lines> <-l|...> — time fastwc alone on <n-lines> of data,
# no reference to beat. Prints the best time and throughput. A failure to
# create the data (disk, say) skips the case instead of failing the suite.
run_solo_case() {
local lines="$1" flag="$2"
local noun='lines'; [[ "$lines" -eq 1 ]] && noun='line'
local label="solo ${lines} ${noun}"
local file ms best='' bytes gbps mlps i d
file=$(createtxt "$lines") || {
printf '%-28s %s\n' "$label" 'SKIP (could not create test data)'
return 0
}
for ((i = 0; i < BENCH_REPS; i++)); do
d=$(time_ms "$FASTWC" "$flag" "$file")
[[ -z "$best" || "$d" -lt "$best" ]] && best="$d"
done
bytes=$((lines * 11))
gbps=$(awk -v b="$bytes" -v ms="$best" 'BEGIN { printf "%.2f", b / ms / 1e6 }')
mlps=$(awk -v l="$lines" -v ms="$best" 'BEGIN { printf "%.1f", l / ms / 1e3 }')
printf '%-28s %12s %12s %14s\n' \
"$label" "fastwc: ${best}ms" "${gbps} GB/s" "${mlps} Mlines/s"
}
# run_cases <words|lines> <-w|-l> <size...> — run run_case for every size,
# stopping at the first failure. Returns non-zero if any case failed.
run_cases() {
local mode="$1" flag="$2"
shift 2
local rc=0 size
for size in "$@"; do
run_case "$mode" "$size" "$flag" || { rc=1; break; }
done
return $rc
}
# run_stdin_cases <words|lines> <-w|-l|...> <size...> — run run_stdin_case
# for every size, stopping at the first failure.
run_stdin_cases() {
local mode="$1" flag="$2"
shift 2
local rc=0 size
for size in "$@"; do
run_stdin_case "$mode" "$size" "$flag" || { rc=1; break; }
done
return $rc
}