Update on "Convert mul to use opmath_gpu_kernel_with_scalars"

ezyang · ezyang · commit aa0789f0a113 · 2021-08-26T07:41:40.000-07:00
Note that previously the functor operated on scalar_t and
this modifies it to operate on opmath_t, but this is not
a problem as half precision was implemented by performing the
compute in float anyway.

Signed-off-by: Edward Z. Yang &lt;ezyang@fb.com&gt;

[ghstack-poisoned]
diff --git a/aten/src/ATen/native/cuda/Loops.cuh b/aten/src/ATen/native/cuda/Loops.cuh
@@ -5,6 +5,7 @@
 #include <ATen/native/TensorIterator.h>
 #include <ATen/native/TensorIteratorDynamicCasting.h>
 #include <ATen/cuda/detail/OffsetCalculator.cuh>
+#include <ATen/OpMathType.h>
 
 #include <thrust/tuple.h>
 
