fix shape in te matmul workload

Author: masahi

python/tvm/meta_schedule/postproc/rewrite_tensorize.py

@@ -29,7 +29,6 @@ class RewriteTensorize(Postproc):
     ----------
     vectorize_init_loop : bool
        Whether or not vectorize the initialization loop produced by DecomposeReduction
-
     """
 
     def __init__(self, vectorize_init_loop=False) -> None:

python/tvm/meta_schedule/testing/te_workload.py

@@ -607,7 +607,7 @@ def f_compute(i, j):
 
 def matmul_relu(n: int, m: int, k: int) -> Tuple[te.Tensor, te.Tensor, te.Tensor]:
     a = te.placeholder((n, k), name="A")
-    b = te.placeholder((m, k), name="B")
+    b = te.placeholder((k, m), name="B")
     k = te.reduce_axis((0, k), name="k")
     c = te.compute(
         (n, m),