forked from bartvdbraak/blender
42557f90bd
This commit extend the technique of dynamic linked list to the mesh
slots so as to eliminate dumb scan or map lookup. It provides massive
performance improvement in the culling and in the rasterizer when
the majority of objects are static.
Other improvements:
- Compute the opengl matrix only for objects that are visible.
- Simplify hash function for GEN_HasedPtr
- Scan light list instead of general object list to render shadows
- Remove redundant opengl calls to set specularity, shinyness and diffuse
between each mesh slots.
- Cache GPU material to avoid frequent call to GPU_material_from_blender
- Only set once the fixed elements of mesh slot
- Use more inline function
The following table shows the performance increase between 2.48, 1st round
and this round of improvement. The test was done with a scene containing
40000 objects, of which 1000 are in the view frustrum approximately. The
object are simple textured cube to make sure the GPU is not the bottleneck.
As some of the rasterizer processing time has moved under culling, I present
the sum of scenegraph(includes culling)+rasterizer time
Scenegraph+rasterizer(ms) 2.48 1st round 3rd round
All objects static, 323.0 86.0 7.2
all visible, 1000 in
the view frustrum
All objects static, 219.0 49.7 N/A(*)
all invisible.
All objects moving, 323.0 105.6 34.7
all visible, 1000 in
the view frustrum
Scene destruction 40min 40min 4s
(*) : this time is not representative because the frame rate was at 60fps.
In that case, the GPU holds down the GE by frame sync. By design, the
overhead of the rasterizer is 0 when the the objects are invisible.
This table shows a global speed up between 9x and 45x compared to 2.48a
for scenegraph, culling and rasterizer overhead. The speed up goes much
higher when objects are invisible.
An additional 2-4x speed up is possible in the scenegraph by upgrading
the Moto library to use Eigen2 BLAS library instead of C++ classes but
the scenegraph is already so fast that it is not a priority right now.
Next speed up in logic: many things to do there...
148 lines
3.4 KiB
C++
148 lines
3.4 KiB
C++
#ifndef __KX_BLENDER_MATERIAL_H__
|
|
#define __KX_BLENDER_MATERIAL_H__
|
|
|
|
#include <vector>
|
|
|
|
|
|
#include "RAS_IPolygonMaterial.h"
|
|
#include "BL_Material.h"
|
|
#include "BL_Texture.h"
|
|
#include "BL_Shader.h"
|
|
#include "BL_BlenderShader.h"
|
|
|
|
#include "PyObjectPlus.h"
|
|
|
|
#include "MT_Vector3.h"
|
|
#include "MT_Vector4.h"
|
|
|
|
struct MTFace;
|
|
class KX_Scene;
|
|
|
|
class KX_BlenderMaterial : public PyObjectPlus, public RAS_IPolyMaterial
|
|
{
|
|
Py_Header;
|
|
public:
|
|
// --------------------------------
|
|
KX_BlenderMaterial(
|
|
PyTypeObject* T=&Type
|
|
);
|
|
void Initialize(
|
|
class KX_Scene* scene,
|
|
BL_Material* mat,
|
|
bool skin,
|
|
int lightlayer
|
|
);
|
|
|
|
virtual ~KX_BlenderMaterial();
|
|
|
|
// --------------------------------
|
|
virtual TCachingInfo GetCachingInfo(void) const {
|
|
return (void*) this;
|
|
}
|
|
|
|
virtual
|
|
bool Activate(
|
|
RAS_IRasterizer* rasty,
|
|
TCachingInfo& cachingInfo
|
|
) const;
|
|
|
|
virtual
|
|
void ActivateMeshSlot(
|
|
const RAS_MeshSlot & ms,
|
|
RAS_IRasterizer* rasty
|
|
) const;
|
|
|
|
void ActivateMat(
|
|
RAS_IRasterizer* rasty,
|
|
TCachingInfo& cachingInfo
|
|
)const;
|
|
|
|
void ActivatShaders(
|
|
RAS_IRasterizer* rasty,
|
|
TCachingInfo& cachingInfo
|
|
)const;
|
|
|
|
void ActivateBlenderShaders(
|
|
RAS_IRasterizer* rasty,
|
|
TCachingInfo& cachingInfo
|
|
)const;
|
|
|
|
MTFace* GetMTFace(void) const;
|
|
unsigned int* GetMCol(void) const;
|
|
BL_Texture * getTex (unsigned int idx) {
|
|
return (idx < MAXTEX) ? mTextures + idx : NULL;
|
|
}
|
|
Image * getImage (unsigned int idx) {
|
|
return (idx < MAXTEX && mMaterial) ? mMaterial->img[idx] : NULL;
|
|
}
|
|
// for ipos
|
|
void UpdateIPO(
|
|
MT_Vector4 rgba, MT_Vector3 specrgb,
|
|
MT_Scalar hard, MT_Scalar spec,
|
|
MT_Scalar ref, MT_Scalar emit, MT_Scalar alpha
|
|
);
|
|
|
|
// --------------------------------
|
|
virtual PyObject* py_getattro(PyObject *attr);
|
|
virtual PyObject* py_getattro_dict();
|
|
virtual int py_setattro(PyObject *attr, PyObject *pyvalue);
|
|
virtual PyObject* py_repr(void) { return PyString_FromString(mMaterial->matname.ReadPtr()); }
|
|
|
|
KX_PYMETHOD_DOC( KX_BlenderMaterial, getShader );
|
|
KX_PYMETHOD_DOC( KX_BlenderMaterial, getMaterialIndex );
|
|
KX_PYMETHOD_DOC( KX_BlenderMaterial, getTexture );
|
|
KX_PYMETHOD_DOC( KX_BlenderMaterial, setTexture );
|
|
|
|
KX_PYMETHOD_DOC( KX_BlenderMaterial, setBlending );
|
|
|
|
// --------------------------------
|
|
// pre calculate to avoid pops/lag at startup
|
|
virtual void OnConstruction( );
|
|
|
|
static void EndFrame();
|
|
|
|
private:
|
|
BL_Material* mMaterial;
|
|
BL_Shader* mShader;
|
|
BL_BlenderShader* mBlenderShader;
|
|
KX_Scene* mScene;
|
|
BL_Texture mTextures[MAXTEX]; // texture array
|
|
bool mUserDefBlend;
|
|
unsigned int mBlendFunc[2];
|
|
bool mModified;
|
|
bool mConstructed; // if false, don't clean on exit
|
|
|
|
void SetBlenderGLSLShader();
|
|
|
|
void ActivatGLMaterials( RAS_IRasterizer* rasty )const;
|
|
void ActivateTexGen( RAS_IRasterizer *ras ) const;
|
|
|
|
bool UsesLighting(RAS_IRasterizer *rasty) const;
|
|
void GetMaterialRGBAColor(unsigned char *rgba) const;
|
|
Material* GetBlenderMaterial() const;
|
|
Scene* GetBlenderScene() const;
|
|
void ReleaseMaterial();
|
|
|
|
// message centers
|
|
void setTexData( bool enable,RAS_IRasterizer *ras);
|
|
void setBlenderShaderData( bool enable, RAS_IRasterizer *ras);
|
|
void setShaderData( bool enable, RAS_IRasterizer *ras);
|
|
|
|
void setObjectMatrixData(int i, RAS_IRasterizer *ras);
|
|
void setTexMatrixData(int i);
|
|
|
|
void setLightData();
|
|
|
|
// cleanup stuff
|
|
void OnExit();
|
|
|
|
// shader chacing
|
|
static BL_BlenderShader *mLastBlenderShader;
|
|
static BL_Shader *mLastShader;
|
|
|
|
mutable int mPass;
|
|
};
|
|
|
|
|
|
#endif
|