#!/bin/bash
set -e
# byte-load loop, timed on a run-only image so the resident compiler is not
# in the process. the slope between 1 repetition and N drops startup.
# prints: backend  ms/rep  checksum
cd "$(dirname "$0")/../.."
CC=${CC:-$(sh src/tools/findcc.sh)} || exit 1
make -s build/core/genome.bin || exit 1
T=$(mktemp -d)
trap 'rm -rf "$T"' EXIT
$CC -O2 -w src/tools/genmap.c -o "$T/genmap" || exit 1
GENMAP="$T/genmap" bash src/tools/automap.sh run "$T/run" src/runtime/run.zc tests/programs/bench_bytes.zc >/dev/null || exit 1
cp src/micro/micro.c src/micro/micro_port.h src/micro/port_linux.c src/core/core.c src/core/io_linux.c src/core/fops.h src/core/bops.h src/core/stack.h src/core/genome.h "$T/run/"
$CC -O2 -w -DJTYPE=int "$T/run/core.c" "$T/run/io_linux.c" -o "$T/zy" || exit 1
$CC -O2 -w "$T/run/micro.c" "$T/run/port_linux.c" -o "$T/zym" || exit 1
vms=("$T/zy" "$T/zym"); names=("interp" "micro")
if command -v llvm-config >/dev/null; then
	$CC -O2 -w -DJTYPE=int -DZYLLVM $(llvm-config --cflags) "$T/run/core.c" "$T/run/io_linux.c" -o "$T/zyl" $(llvm-config --ldflags --libs) \
		&& { vms+=("$T/zyl"); names+=("llvm"); }
fi
if command -v aarch64-linux-gnu-gcc >/dev/null && command -v qemu-aarch64 >/dev/null; then
	aarch64-linux-gnu-gcc -O2 -w -DJTYPE=int -static "$T/run/core.c" "$T/run/io_linux.c" -o "$T/zyj" \
		&& { vms+=("qemu-aarch64 $T/zyj"); names+=("arm64"); }
fi
# seconds for $2 repetitions on vm $1
once(){ python3 -c 'import shlex, statistics, subprocess, sys, time; samples=[]; output=b""; cmd=shlex.split(sys.argv[1]); data=sys.argv[2].encode();
for _ in range(5):
 start=time.perf_counter(); p=subprocess.run(cmd, input=data, stdout=subprocess.PIPE); p.check_returncode(); samples.append(time.perf_counter()-start); output=p.stdout
open("/tmp/bench_bytes.out", "wb").write(output); print(statistics.median(samples))' "$1" "$2"; }
printf "%-10s %12s %s\n" backend "ms/rep" checksum
for i in "${!vms[@]}"; do
	one=$(once "${vms[$i]}" 1)
	many=$(once "${vms[$i]}" 1000)
	ms=$(python3 -c "print(round(($many - $one) / 999 * 1000, 3))")
	sum=$(tr -d '\n' < /tmp/bench_bytes.out)
	printf "%-10s %12s %s\n" "${names[$i]}" "$ms" "$sum"
done