#!/usr/bin/env bash
# CPU emulation of the CUDA harness, for checking a pack on a machine WITHOUT nvcc (any clang++ or g++).
# It compiles host.cu and packs/<pack>/kernel.cu as plain C++17 against the shim cuda_runtime.h in this
# directory, runs the kernels on host threads (32 threads per warp, a barrier inside __shfl_xor_sync)
# and checks the dataset self-test and the vectors. Rates it prints are meaningless; only PASS/FAIL matters.
# Usage: emu/emu.sh <pack> [host args...]     e.g. emu/emu.sh igneum-genesis --batch-log2 13 --batches 1 --block-warps 2
set -euo pipefail
HERE="$(cd "$(dirname "$0")" && pwd)"
CUDA_DIR="$(cd "$HERE/.." && pwd)"
PACK="${1:-igneum-genesis}"; shift || true
BUILD="$HERE/build-$PACK"
mkdir -p "$BUILD"
cp "$CUDA_DIR/host.cu" "$BUILD/host_emu.cpp"
# Rewrite only the launch syntax; everything else is the exact generated text.
sed -E 's/([A-Za-z_0-9]+)<<<([^,]+), ([^>]+)>>>\(/emu_launch(\1, \2, \3, /' "$CUDA_DIR/packs/$PACK/kernel.cu" > "$BUILD/kernel_emu.cpp"
CXX="${CXX:-c++}"
"$CXX" -std=c++17 -O2 -Wall -Wextra -I "$HERE" -I "$CUDA_DIR/packs/$PACK" \
  -o "$BUILD/igneum-emu" "$BUILD/host_emu.cpp" "$BUILD/kernel_emu.cpp" "$HERE/shim.cpp" -pthread
echo "compiled $BUILD/igneum-emu (CPU emulation, not a GPU build)"
exec "$BUILD/igneum-emu" "$@"