benchmarks/dlrm/ootb/dlrm_data_caffe2.py [700:729]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    if enable_padding:
        # WARNING: notice that as the ratio between the number of samples (l)
        # and cardinality (c) of a sample increases the probability of
        # generating a sample gets smaller and smaller because there are
        # few new samples compared to repeated samples. This means that for a
        # long trace with relatively small cardinality it will take longer to
        # generate all new samples and therefore obtain full distribution support
        # and hence it takes longer for distribution to resemble the original.
        # Therefore, we may pad the number of new samples to be on par with
        # average number of samples l/c artificially.
        l = len(stack_distances)
        c = max(stack_distances)
        padding = int(np.ceil(l / c))
        stack_distances = stack_distances + [0] * padding

    return (rstack, stack_distances, line_accesses)


# auxiliary read/write routines
def read_trace_from_file(file_path):
    try:
        with open(file_path) as f:
            if args.trace_file_binary_type:
                array = np.fromfile(f, dtype=np.uint64)
                trace = array.astype(np.uint64).tolist()
            else:
                line = f.readline()
                trace = list(map(lambda x: np.uint64(x), line.split(", ")))
            return trace
    except Exception:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



benchmarks/dlrm/ootb/dlrm_data_pytorch.py [1167:1196]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    if enable_padding:
        # WARNING: notice that as the ratio between the number of samples (l)
        # and cardinality (c) of a sample increases the probability of
        # generating a sample gets smaller and smaller because there are
        # few new samples compared to repeated samples. This means that for a
        # long trace with relatively small cardinality it will take longer to
        # generate all new samples and therefore obtain full distribution support
        # and hence it takes longer for distribution to resemble the original.
        # Therefore, we may pad the number of new samples to be on par with
        # average number of samples l/c artificially.
        l = len(stack_distances)
        c = max(stack_distances)
        padding = int(np.ceil(l / c))
        stack_distances = stack_distances + [0] * padding

    return (rstack, stack_distances, line_accesses)


# auxiliary read/write routines
def read_trace_from_file(file_path):
    try:
        with open(file_path) as f:
            if args.trace_file_binary_type:
                array = np.fromfile(f, dtype=np.uint64)
                trace = array.astype(np.uint64).tolist()
            else:
                line = f.readline()
                trace = list(map(lambda x: np.uint64(x), line.split(", ")))
            return trace
    except Exception:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -