patschmidt2 commented on issue #16889:
URL: https://github.com/apache/tvm/issues/16889#issuecomment-2074426456
I think you are supposed to call `decompose_reduction `before `blockize`:
```
import tvm
from tvm.script import ir as I
from tvm.script import tir as T
@I.ir_module
class Module:
@T.prim_func
def main():
# with T.block("root"):
A_sum = T.alloc_buffer((1,), "float32")
A = T.alloc_buffer((1, 16), "float32")
for nn, ff in T.grid(1, 16):
with T.block("A"):
v_nn, v_ff = T.axis.remap("SR", [nn, ff])
T.reads(A[v_nn, v_ff])
T.writes(A_sum[v_nn])
with T.init():
A_sum[v_nn] = T.float32(0)
A_sum[v_nn] = A_sum[v_nn] + A[v_nn, v_ff]
sch = tvm.tir.Schedule(Module)
a = sch.get_block("A")
loop_n, loop_f = sch.get_loops(a)
sch.decompose_reduction("A", loop_n)
sch.blockize(loop_f)
init_block = sch.get_block("A_init")
print(sch.mod) # <-- A_init exists
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
