[Apache TVM Discuss] [Questions] [iOS- Auto Tvm] Auto Tuning was not happening for iOS metal target

[Morita Kazutaka via Apache TVM Discuss]

@Dileep Can you run tests/ios_rpc_test.py successfully?  Your tuning script can 
run against the llvm target?

Can you try the following patch and check if something changes or not?
```
diff --git a/python/tvm/autotvm/measure/local_executor.py 
b/python/tvm/autotvm/measure/local_executor.py
index a0a826abc..ed7e855c1 100644
--- a/python/tvm/autotvm/measure/local_executor.py
+++ b/python/tvm/autotvm/measure/local_executor.py
@@ -132,7 +132,7 @@ class LocalExecutor(executor.Executor):
         (e.g. cuda runtime, cudnn). Set this to False if you have used these 
runtime
         before submitting jobs.
     """
-    def __init__(self, timeout=None, do_fork=True):
+    def __init__(self, timeout=None, do_fork=False):
         self.timeout = timeout or executor.Executor.DEFAULT_TIMEOUT
         self.do_fork = do_fork
 
@@ -143,7 +143,11 @@ class LocalExecutor(executor.Executor):
 
     def submit(self, func, *args, **kwargs):
         if not self.do_fork:
-            return LocalFutureNoFork(func(*args, **kwargs))
+            try:
+                res = func(*args, **kwargs)
+            except Exception as e:
+                res = e
+            return LocalFutureNoFork(res)
 
         queue = Queue(2)  # Size of 2 to avoid a race condition with size 1.
         process = Process(target=call_with_timeout,
```





---
[Visit 
Topic](https://discuss.tvm.apache.org/t/ios-auto-tvm-auto-tuning-was-not-happening-for-ios-metal-target/8115/3)
 to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click 
here](https://discuss.tvm.apache.org/email/unsubscribe/4fc52cad47acf500e7ff8f7a6840bbbf7d64f610eea0e9fd0d0a854804ddcf7c).