Workaround for tensorize failure


#1

Hi TVM community,

I am new to TVM. For the current master version, if we use “llvm -mcpu=skylake-avx512” or “llvm -mcpu=cascadelake” instead of “llvm” as the target device,
e.g.,



it reports the error like the following:
TVMError: Check failed: is_one(e.region[i]->extent): Tensorize tensor_intrin: Input dimension mismatch with tensor intrin expected shape=[16, 4], given region=[range(min=((j.outer16)/16), ext=(((((j.outer16) + 15)/16) + 1) - j.outer)), range(min=(((((k.outer.outer4) + k.outer.inner)4)/4)16), ext=((((((((k.outer.outer16) + (k.outer.inner4)) + 3)/4)16) + 16) - (k.outer.inner16)) - (k.outer.outer64))), range(min=0, ext=4)]

The same issue is reported here:

Is there any workaround to solve this issue?