forked from bartvdbraak/blender
828abaf11c
This way we can get rid of inefficient memory usage caused by BVH boundbox
part being unused by leaf nodes but still being allocated for them. Doing
such split allows to save 6 of float4 values for QBVH per leaf node and 3
of float4 values for regular BVH per leaf node.
This translates into following memory save using 01.01.01.G rendered
without hair:
Device memory size Device memory peak Global memory peak
Before the patch: 4957 5051 7668
With the patch: 4467 4562 7332
The measurements are done against current master. Still need to run speed tests
and it's hard to predict if it's faster or not: on the one hand leaf nodes are
now much more coherent in cache, on the other hand they're not so much coherent
with regular nodes anymore.
Reviewers: brecht, juicyfruit
Subscribers: venomgfx, eyecandy
Differential Revision: https://developer.blender.org/D1236
50 lines
1.6 KiB
C
50 lines
1.6 KiB
C
/*
|
|
* Adapted from code Copyright 2009-2010 NVIDIA Corporation
|
|
* Modifications Copyright 2011, Blender Foundation.
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
|
|
/* bottom-most stack entry, indicating the end of traversal */
|
|
#define ENTRYPOINT_SENTINEL 0x76543210
|
|
|
|
/* 64 object BVH + 64 mesh BVH + 64 object node splitting */
|
|
#define BVH_STACK_SIZE 192
|
|
#define BVH_QSTACK_SIZE 384
|
|
#define BVH_NODE_SIZE 4
|
|
#define BVH_NODE_LEAF_SIZE 1
|
|
#define BVH_QNODE_SIZE 7
|
|
#define BVH_QNODE_LEAF_SIZE 1
|
|
#define TRI_NODE_SIZE 3
|
|
|
|
/* silly workaround for float extended precision that happens when compiling
|
|
* without sse support on x86, it results in different results for float ops
|
|
* that you would otherwise expect to compare correctly */
|
|
#if !defined(__i386__) || defined(__SSE__)
|
|
#define NO_EXTENDED_PRECISION
|
|
#else
|
|
#define NO_EXTENDED_PRECISION volatile
|
|
#endif
|
|
|
|
#include "geom_attribute.h"
|
|
#include "geom_object.h"
|
|
#include "geom_triangle.h"
|
|
#include "geom_triangle_intersect.h"
|
|
#include "geom_motion_triangle.h"
|
|
#include "geom_motion_curve.h"
|
|
#include "geom_curve.h"
|
|
#include "geom_volume.h"
|
|
#include "geom_primitive.h"
|
|
#include "geom_bvh.h"
|
|
|