From 487ec8d4102f11a18b665dbc7a8314adc8fa155f Mon Sep 17 00:00:00 2001 From: Julio Maia Date: Fri, 11 Sep 2026 10:56:02 -0500 Subject: [PATCH] Fix alignment on StencilEntry struct for HIP CUDA neatly aligns the StencilEntry struct to 16-bytes, which is not used on HIP. Mapping the StencilEntry struct to 16-bytes on HIP yields around 5% better performance on MI355X-class GPUs. --- Grid/stencil/Stencil.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Grid/stencil/Stencil.h b/Grid/stencil/Stencil.h index c1243657e..918888fd7 100644 --- a/Grid/stencil/Stencil.h +++ b/Grid/stencil/Stencil.h @@ -82,7 +82,7 @@ void DslashLogPartial(void); void DslashLogDirichlet(void); struct StencilEntry { -#ifdef GRID_CUDA +#if defined(GRID_CUDA) || defined(GRID_HIP) uint64_t _byte_offset; // 8 bytes uint32_t _offset; // 4 bytes #else