// SPDX-License-Identifier: Apache-2.0
// Split-matmul operand build (tt/kcat_kernel.py), reader (RISCV_0): this core's contiguous range of x tiles.
// CT args: [0] per-core RT-arg count (P3), then the TensorAccessorArgs of x.
// Common RT args: [x_addr]. Per-core RT args: [t0, n] (flattened x tile indices).
#include <cstdint>

#include "api/dataflow/dataflow_api.h"

constexpr auto x_args = TensorAccessorArgs<1>();
constexpr uint32_t cb_x = 0;
constexpr uint32_t TB = 4096;

void kernel_main() {
    const uint32_t x_addr = get_common_arg_val<uint32_t>(0);
    const uint32_t t0 = get_arg_val<uint32_t>(0);
    const uint32_t n = get_arg_val<uint32_t>(1);
    const auto x = TensorAccessor(x_args, x_addr, TB);
    for (uint32_t t = t0; t < t0 + n; ++t) {
        cb_reserve_back(cb_x, 1);
        noc_async_read(x.get_noc_addr(t), get_write_ptr(cb_x), TB);
        noc_async_read_barrier();
        cb_push_back(cb_x, 1);
    }
}