// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only

#pragma once

#include <bitshuffle/bitshuffle_internals.h>
#include <bitshuffle_hperf/bitshuffle.h>

// One bitshuffle block, transformed by whichever of the two vendored implementations is SIMD on
// this architecture. The two write byte-identical output and each decodes the other's, so the file
// format does not depend on the build host.
//
// bitshuffle_hperf is x86-only: outside SSE2 its whole vector body is compiled out and what remains
// is a scalar fallback. The classic bitshuffle has an aarch64 NEON path (bitshuffle_core.c,
// USEARMNEON), so aarch64 encodes with that instead - measured against the hperf scalar fallback it
// is ~2.5x on encode and ~1.7x on decode. Decode, which is what rugnux spends its time on, goes on
// aarch64 through a NEON port of hperf's decoder (bitshuffle_hperf/bitshuffle_neon.c) for the
// element sizes it covers (1, 2, 4 bytes), and through the classic NEON stages for the rest.
// Everywhere else hperf wins outright (~2x over classic SSE2), so it stays the default.
//
// The condition mirrors USEARMNEON in bitshuffle_core.c exactly. With NEON off the classic path
// falls back to a scalar of its own that is slower than hperf's, so it must not be selected then.
// It is a preprocessor test rather than a CMake one on purpose: Apple Silicon defines the same two
// macros as aarch64 Linux, and a macOS universal build compiles this header once per architecture,
// which a single configure-time answer could not follow.
#if (defined(__ARM_NEON__) || (__ARM_NEON)) && defined(__aarch64__)

#include <bitshuffle_hperf/bitshuffle_neon.h>

// The two stages of bshuf_untrans_bit_elem_NEON, which bitshuffle_core.c defines but no header
// declares. Calling them directly lets the decode use the caller's scratch instead of the block-sized
// buffer the classic entry point mallocs and frees for every block.
extern "C" {
    int64_t bshuf_trans_byte_bitrow_NEON(const void *in, void *out, size_t size, size_t elem_size);
    int64_t bshuf_shuffle_bit_eightelem_NEON(const void *in, void *out, size_t size, size_t elem_size);
}

// The classic encode entry point allocates its own block-sized scratch, so the caller's goes unused.
inline int64_t JFJochBitShuffleBlock(char *out, const char *in, char *, size_t size, size_t elem_size) {
    return bshuf_trans_bit_elem(in, out, size, elem_size);
}

inline int64_t JFJochBitUnshuffleBlock(char *out, const char *in, char *scratch, size_t size, size_t elem_size) {
    if (elem_size == 1 || elem_size == 2 || elem_size == 4)
        return bitshuf_decode_block_neon(out, in, scratch, size, elem_size);

    const int64_t count = bshuf_trans_byte_bitrow_NEON(in, scratch, size, elem_size);
    if (count < 0)
        return count;
    return bshuf_shuffle_bit_eightelem_NEON(scratch, out, size, elem_size);
}

#else

inline int64_t JFJochBitShuffleBlock(char *out, const char *in, char *scratch, size_t size, size_t elem_size) {
    return bitshuf_encode_block(out, in, scratch, size, elem_size);
}

inline int64_t JFJochBitUnshuffleBlock(char *out, const char *in, char *scratch, size_t size, size_t elem_size) {
    return bitshuf_decode_block(out, in, scratch, size, elem_size);
}

#endif