include/oneapi/dpl/pstl/hetero/dpcpp/parallel_backend_sycl_merge.h - …

…increate chunk size on GPU to 8 Signed-off-by: Sergey Kopienko <[email protected]>
oneapi-src · Nov 18, 2024 · 129898c · 129898c
1 parent d1469c6
commit 129898c
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/include/oneapi/dpl/pstl/hetero/dpcpp/parallel_backend_sycl_merge.h b/include/oneapi/dpl/pstl/hetero/dpcpp/parallel_backend_sycl_merge.h
@@ -292,7 +292,7 @@ struct __parallel_merge_submitter_large<_IdType, _CustomName,
         _PRINT_INFO_IN_DEBUG_MODE(__exec);
 
         // Empirical number of values to process per work-item
-        const std::uint8_t __chunk = __exec.queue().get_device().is_cpu() ? 128 : 4;
+        const std::uint8_t __chunk = __exec.queue().get_device().is_cpu() ? 128 : 8;
 
         const _IdType __steps = oneapi::dpl::__internal::__dpl_ceiling_div(__n, __chunk);
         const _IdType __base_diag_count = 1'024 * 32;