Bug fix for add<float32x4_t>.

8 years ago · 7fe03f7b3a
parent 9e7da6799b
commit 7fe03f7b3a
1 changed files with 1 additions and 1 deletions
--- a/paddle/cuda/include/hl_tensor_ops.h
+++ b/paddle/cuda/include/hl_tensor_ops.h
@ -461,7 +461,7 @@ class add<float32x4_t> {
 public:
  INLINE float32x4_t operator()(const float32x4_t a,
                                const float32x4_t b) const {
-    return vmulq_f32(a, b);
+    return vaddq_f32(a, b);
  }
 };