insert memory fence to avoid AMD OpenCL compiler reordering the read/…

…writes
boostorg · Jan 18, 2019 · 81dc8c7 · 81dc8c7
1 parent 2135633
commit 81dc8c7
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/include/boost/compute/algorithm/detail/radix_sort.hpp b/include/boost/compute/algorithm/detail/radix_sort.hpp
@@ -176,8 +176,10 @@ const char radix_sort_source[] =
 " uint sum = 0;\n"
 " for(uint i = 0; i < K2_BITS; i++){\n"
 " uint x = global_offsets[i] + last_block_offsets[i];\n"
+" mem_fence(CLK_GLOBAL_MEM_FENCE);\n" // work around the RX 500/Vega bug, see #811
 " global_offsets[i] = sum;\n"
 " sum += x;\n"
+" mem_fence(CLK_GLOBAL_MEM_FENCE);\n" // work around the RX Vega bug, see #811
 " }\n"
 "}\n"