From 768930a73a43e48172df00b6c934de582bd9422b Mon Sep 17 00:00:00 2001 From: Lionel Landwerlin Date: Wed, 16 Feb 2022 23:14:15 +0200 Subject: [PATCH] nir: fix lower_memcpy memcpy is divided into chunks that are vec4 sized max. The problem here happens with a structure of 24 bytes : struct { float3 a; float3 b; } If you memcpy that struct, the lowering will emit 2 load/store, one of sized 8, next one sized 16. But both end up located at offset 0, so we effectively drop 2 floats. Signed-off-by: Lionel Landwerlin Fixes: a3177cca996145 ("nir: Add a lowering pass to lower memcpy") Reviewed-by: Jason Ekstrand Part-of: --- src/compiler/nir/nir_lower_memcpy.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/src/compiler/nir/nir_lower_memcpy.c b/src/compiler/nir/nir_lower_memcpy.c index b7a3f1752cb..768537a3478 100644 --- a/src/compiler/nir/nir_lower_memcpy.c +++ b/src/compiler/nir/nir_lower_memcpy.c @@ -111,11 +111,14 @@ lower_memcpy_impl(nir_function_impl *impl) uint64_t size = nir_src_as_uint(cpy->src[2]); uint64_t offset = 0; while (offset < size) { - uint64_t remaining = offset - size; - /* For our chunk size, we choose the largest power-of-two that - * divides size with a maximum of 16B (a vec4). + uint64_t remaining = size - offset; + /* Find the largest chunk size power-of-two (MSB in remaining) + * and limit our chunk to 16B (a vec4). It's important to do as + * many 16B chunks as possible first so that the index + * computation is correct for + * memcpy_(load|store)_deref_elem_imm. */ - unsigned copy_size = 1u << MIN2(ffsll(remaining) - 1, 4); + unsigned copy_size = 1u << MIN2(util_last_bit64(remaining) - 1, 4); const struct glsl_type *copy_type = copy_type_for_byte_size(copy_size);