pytorch with mkl-dnn backend performance on small conv with multi thread

I'm trying pytorch model with mkl-dnn backend. But i got a problem that the multi thread performance is slower than expected, runing on small conv. Please see this table. mkl-dnn performace table

Runs big conv, the performance is obvious faster on 8 threads compared with single thread. But runs small conv, the speed has no big differences with 8 threads and single thread.

So my question is: 1. why 8 threads is not obviously faster than 1 thread with small conv? 2. How to improve the 8 threads performance on small conv?

My code here

import time
import torch
import torch.nn as nn
from torch.nn.utils import weight_norm

class MyConv(nn.Module):
    def __init__(self, *args, **kwargs):
        super().__init__()
        self.cell = nn.Conv1d(*args, **kwargs)
        self.cell.weight.data.normal_(0.0, 0.02)

    def forward(self, x):
        return self.cell(x)


def main():
    #print(*torch.__config__.show().split("\n"), sep="\n")
    torch.set_num_threads(1)
    dim = 32
    kernels = 3
    seq = 100000
    MyCell = MyConv(dim, dim, kernel_size=kernels, stride=1)
    MyCell.eval()
    inputs = []
    iter = 1000
    for i in range(iter):
        inputs.append(torch.rand(1, dim, seq))

    start = time.time() * 1000
    for i in range(iter):
        print(i)
        y = MyCell(inputs[i])
        #print(y)
    end = time.time() * 1000
    print('cost %d ms per iter\n' % ((end - start) / iter))


if __name__ == "__main__":
    main()

Mkldnn verbose info (running with "export MKLDNN_VERBOSE=1")

mkldnn_verbose,exec,reorder,jit:uni,undef,in:f32_nchw out:f32_nChw8c,num:1,1x32x1x107718,2.18091
mkldnn_verbose,exec,reorder,jit:uni,undef,in:f32_oihw out:f32_OIhw8i8o,num:1,32x32x1x1,0.00195312
mkldnn_verbose,exec,convolution,jit_1x1:avx2,forward_training,fsrc:nChw8c fwei:OIhw8i8o fbia:x fdst:nChw8c,alg:convolution_direct,mb1_ic32oc32_ih1oh1kh1sh1dh0ph0_iw107718ow107718kw1sw1dw0pw0,3.87793
mkldnn_verbose,exec,reorder,jit:uni,undef,in:f32_nChw8c out:f32_nchw,num:1,1x32x1x107718,4.69116

Thanks a lot!