Tianqi Chen
Tianqi Chen
I think we should actually avoid running exccessive integration tests across platforms. The unit tests of frontend should only cover the ingestion part ideally (via some lightweight structural equality check)....
Thanks @Jiawei-Shao ! contribution is more than welcomed
@Jiawei-Shao , in this case. i think we can go with directly creating an array of "int8x4"(aka the vector type), so all loading and store are vectorized. and we lower...
Another simpler approach(which could be one step easier) would be to simply first take dp4a as an intrinsic that takes in uint32 and produces the i32. That does mean that...
```python import tvm import numpy as np from tvm.script import tir as T @tvm.script.ir_module class MyModule: @T.prim_func def vector_copy(A: T.Buffer((4,), "int8x4"), B: T.Buffer((4,), "int8x4")): T.func_attr({"global_symbol": "vector_copy", "tir.noalias": True}) for i...
here is a simple example writing program directly in int8x4, note that the array of (4,) in int8x4 will be represented as extra dimension `(4, 4)` in this case, where...
Can we first update to make it cxx17 compatible?
This seems to relates to the way a reduction order is formed(rfactor) and the current schedule dense. Would be useful to directly invoke the topi schedule and take a look...
we close the issue due to the staleness, the latest llvm18 should work