ekalda commented on code in PR #10862:
URL: https://github.com/apache/tvm/pull/10862#discussion_r857437609
##########
python/tvm/relay/backend/contrib/ethosu/codegen.py:
##########
@@ -362,9 +406,30 @@ def relay_to_tir(mod: tvm.ir.IRModule) -> tvm.ir.IRModule:
gv: "ethos-u" for gv, _ in filter(lambda x: util.is_npu_func(x[1]),
mod.functions.items())
}
mod = mod.with_attr("device_contexts", device_contexts)
- mod = LowerToTIR(SCHEDULER)(mod)
- return mod
+ # Use the cascader if it is enabled for the U55 accelerator, otherwise use
copy_constants
+ # scheduler
+ if util.is_cascader_enabled():
+ assert (
+ util.get_accelerator_config() != "ethos-u65-256"
+ ), "Cascading is not supported for the U65 accelerator"
+
+ workspace_memory_pools = mod.attrs["workspace_memory_pools"]
+
+ assert (
+ workspace_memory_pools
+ ), "Workspace memory pool needs to be provided for the U55 cascader"
+
+ assert (
+ len(workspace_memory_pools.pools) == 1
+ ), "Exactly one workspace pool needs to be provided for the U55
cascader"
+
+ sram = extract_memory_info(workspace_memory_pools.pools[0])
+ tir_mod = LowerToTIR(_ethos_u55_cascader(sram))(mod)
Review Comment:
I agree that this would be the right way to go about it. Let's do it in a
follow up!
--
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]
