================
@@ -484,4 +536,8 @@ def generate_float_conversion(src, dst, size, mode, sat):
     for dst in float_types:
         for size in vector_sizes:
             for mode in rounding_modes:
+                # Do not generate "_rte" conversion for clspv as they are
+                # handle natively
----------------
kpet wrote:
```suggestion
                # handled natively
```

https://github.com/llvm/llvm-project/pull/66902
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to