HIP: use build-in atomicAdd(double)

HIP is providing for HIP 4.2+ native atomicAdd interfaces for double precision. Use always the build-in atomicAdd so speedup atomic add.
alpaka-group · Jul 27, 2022 · 0b96515 · 0b96515
1 parent 8acfbe4
commit 0b96515
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/include/alpaka/atomic/AtomicUniformCudaHipBuiltIn.hpp b/include/alpaka/atomic/AtomicUniformCudaHipBuiltIn.hpp
@@ -124,7 +124,7 @@ namespace alpaka
                 double* const addr,
                 double const& value) -> double
             {
-#        if BOOST_ARCH_PTX >= BOOST_VERSION_NUMBER(6, 0, 0)
+#        if BOOST_ARCH_PTX >= BOOST_VERSION_NUMBER(6, 0, 0) || BOOST_LANG_HIP
                 return ::atomicAdd(addr, value);
 #        else
                 // Code from: http://docs.nvidia.com/cuda/cuda-c-programming-guide/#atomic-functions