[Bug]: `total_time` more than gemm/comm time added up.

For example 20, when I do --gemm_only why is the total_ms greater than gemm_ms? Similar behavior for --comm_only.

Fix the timings in relevant examples so it accurately reflects the correct time or identify where the time is being spent?

{
    "world_size": 8,
    "m": 3840,
    "n": 3840,
    "k": 4352,
    "m_comm": 3840,
    "n_comm": 3840,
    "debug": false,
    "validate": false,
    "trace_tiles": false,
    "benchmark": true,
    "datatype": "bf16",
    "output_file": "log.json",
    "BLK_M": 256,
    "BLK_N": 64,
    "BLK_K": 64,
    "gsize_m": 6,
    "heap_size": 8589934592,
    "gemm_sms": 256,
    "comm_sms": 64,
    "num_ranks": 8,
    "csv": null,
    "only_gemm": true,
    "only_comm": false,
    "tflops": 96.64808160566294,
    "total_ms": 1.3279694771766664,
    "gemm_ms": 0.48436891938012744,
    "gemm_experiments": 126
}