// 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 uses that instead - measured against the hperf scalar fallback it is
// ~2.5x on encode and ~1.7x on decode. 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.
#if (defined(__ARM_NEON__) || (__ARM_NEON)) && defined(__aarch64__)

// The classic entry points allocate their 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 *, size_t size, size_t elem_size) {
    return bshuf_untrans_bit_elem(in, 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