add inline for __half2float_warp (apache#20152)

chinakook · May 2, 2021 · f1a5c49 · f1a5c49
1 parent fdd6133
commit f1a5c49
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/3rdparty/mshadow/mshadow/half.h b/3rdparty/mshadow/mshadow/half.h
@@ -43,7 +43,7 @@
   #include <cuda_fp16.h>
   #if defined(__CUDA_ARCH__)
     /*! \brief __half2float_warp */
-    __host__ __device__ float __half2float_warp(const volatile __half& h) { /* NOLINT(*) */
+    MSHADOW_XINLINE float __half2float_warp(const volatile __half& h) { /* NOLINT(*) */
       __half val;
 #if CUDA_VERSION >= 9000
       val = const_cast<__half&>(h);