import tvm
from tvm import te
n = 1024
l = 128
m = 235
bias = te.var("bias", dtype="float32")
A = te.placeholder((n, l), name="A")
B = te.placeholder((l, m), name="B")
C = te.extern(
(n, m),
[A, B],
lambda ins, outs: tvm.tir.call_packed(
"tvm.contrib.cblas.matmul", ins[0], ins[1], outs[0], False, False
),
name="C",
)
D = te.compute(C.shape, lambda i, j: C[i, j] + bias, name="D")
s = te.create_schedule(D.op)
ctx = tvm.cpu(0)
f = tvm.build(s, [A, B, D, bias], "c")
Above code always crashes when with “c” target, while it works properly with “llvm” target.
Error message:
Anyone knows whether it is a known issue or not? And is there any approaches to workaround this?
Thanks