Cycles: use packed float3 back for oneAPI
This fixes a 15% performance regression silently introduced by
79ab76e156
that aligned the compact
float3 on 16 bytes for oneAPI.
Current change is minimalist, there are further cleanup opportunities
such as removing packed_float3 definition for oneAPI but for some
reason, it cuts the recovered speedup in half, so we're starting with
this small fix for now.
Reviewed by: brecht
Differential Revision: https://developer.blender.org/D16340
This commit is contained in:
parent
633d314b75
commit
4b14b33ea8
|
@ -10,7 +10,12 @@
|
|||
CCL_NAMESPACE_BEGIN
|
||||
|
||||
#ifndef __KERNEL_NATIVE_VECTOR_TYPES__
|
||||
# ifdef __KERNEL_ONEAPI__
|
||||
/* Define float3 as packed for oneAPI. */
|
||||
struct float3
|
||||
# else
|
||||
struct ccl_try_align(16) float3
|
||||
# endif
|
||||
{
|
||||
# ifdef __KERNEL_GPU__
|
||||
/* Compact structure for GPU. */
|
||||
|
|
Loading…
Reference in New Issue