From 129898ce6b1c079d68e8366e0a232457790bb5ea Mon Sep 17 00:00:00 2001 From: Sergey Kopienko Date: Mon, 18 Nov 2024 16:08:27 +0100 Subject: [PATCH] include/oneapi/dpl/pstl/hetero/dpcpp/parallel_backend_sycl_merge.h - increate chunk size on GPU to 8 Signed-off-by: Sergey Kopienko --- .../oneapi/dpl/pstl/hetero/dpcpp/parallel_backend_sycl_merge.h | 2 +- 1 file changed, 1 insertion(+), 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 index 0c341f31de6..929ee5a79db 100644 --- 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;