[Perf]Call cublas.Gemm instead of cublasGemmStridedBatched

[Aurelius84]

what's New?

复现代码：

#!/usr/bin/env python3
# Please set "export PYTHONPATH=${CINN_ROOT}/build/python:${PYTHONPATH}" first
import paddle
import unittest
import numpy as np
import cinn
from cinn.frontend import *
from cinn.common import *
from op_test import OpTest

class TestGroup(unittest.TestCase):
  def test_group(self):
    builder = NetBuilder("matmul")
    x_shape = [128, 128, 768]
    y_shape = [768, 768]

    x = builder.create_input(Float16(),x_shape, "x")
    y = builder.create_input(Float16(), y_shape, "y")
    out = builder.matmul(
            x, y, transpose_x=False, transpose_y=False)

    feed_list = [x, y]
    fetch_list = [out]

    prog = builder.build()

    feed_data = [OpTest.random(shape=var.shape(), dtype=var.type()) for var in feed_list]
    result = prog.build_and_get_output(DefaultNVGPUTarget(), feed_list, feed_data, fetch_list)

    result = [res.numpy(DefaultNVGPUTarget()) for res in result]
    for i in range(len(result)):
      info_str = fetch_list[i].name()
      info_str += ", shape=" + str(result[i].shape)
      info_str += ", dtype=" + str(result[i].dtype) + ":\n"
      print(info_str)

if __name__ == "__main__":
  unittest.main()

生效日志：

[paddle-bot]

Thanks for your contribution!

[thisjiang]

麻烦顺便在python/tests/ops/test_matmul_op.py 下加上对应的测试用例吧

[Aurelius84]

麻烦顺便在python/tests/ops/test_matmul_op.py 下加上对应的测试用例吧

好的

[thisjiang]

LGTM