mrheisenberg

ok I expanded it and same thing happens, it crashes on Release(), but when I remove the line afterwards that sets it to 0/NULL the other error appears.There's

<Unknown function>

Unknown
at the top of the call stack, so I guess there's something wrong in the COM?I don't think I initialized it wrong tho, just used EnumOutputs, I check the HRESULT and it's ok

edit: I tried to use IDXGIOutput1 too instead of IDXGIOutput, but I EnumOutputs() doesn't take IDXGIOutput1 as an argument, it wants an IDXGIOutput, or is IDXGIOutput1 a special case and used in a different way?

I check breakpoint by breakpoint the pointer addresses, all of the IDXGI objects seem to be getting created with valid addresses(they're not 0x00000000 or anything similar)

Ok I fixed it, DXGIOutput outputInterface = DXGIOutput(output); should have been DXGIOutput* outputInterface = new DXGIOutput(output); otherwise it gets destroyed in the end of the frame and then I do adapterOutputs.Add(&outputInterface); I was adding a pointer to an already destroyed object (facepalm).

Yes, I use the updated ones everywhere, however I don't understand this:
 

/ Create a factory to enumerate all of the hardware in the system.

    IDXGIFactory1* pFactory = 0;
    hr = CreateDXGIFactory1( __uuidof(IDXGIFactory), (void**)(&pFactory) );

Shouldn't it be IDXGIFactory1? I'm using IDXGIFactory1, maybe that's the issue?
It also worries me that the SafeRelease macro causes a crash, even if I use 0 instead of nullptr, could be a hint at the problem.

 

on a side note - I just now notice GameDev has colors for DirectX in the code tags lol

What you need is in DirectXCollision.h and DirectXCollision.inl,but there are a few functions that have changed from xnamath to DirectXMath(if I remember correctly,some xnamath functions that weren't templated are now templated in DirectXMath)  Desktop.rar   95.97K   14 downloads
Also you can still DL the Windows 8 kit on Win7:
http://msdn.microsoft.com/en-us/windows/hardware/hh852363.aspx

How do the modders,who introduce new shader effects,know what input layout they must be expecting in the vertex shader and what constant buffers are being set,etc..are they reverse engineering the shader files?
For example:Freelancer
http://www.youtube.com/watch?v=Mp6VIu4JRRQ
The game originally used a forward renderer and it didn't have bloom,how did they alter the renderer if they don't have access to the source?

Maybe I'm doing it wrong?

Profiler.hpp

#pragma once

#ifndef _PROFILER_HPP_
#define _PROFILER_HPP_

#pragma comment (lib,"Winmm.lib")

#define WIN32_LEAN_AND_MEAN
#include <windows.h>
#include <mmsystem.h>

class Profiler
{
public:
	static Profiler* Instance();
	static void Destroy();

	void operator()();
	UINT64 GetDTime()
	{
		return(DTime);
	}

private:
	Profiler();
	~Profiler();

	static Profiler *instance;
	UINT64 lastGameTime;
	UINT64 DTime;
};

#endif 

Benchmarks.hpp

#pragma once

#ifndef _TEST_FUNCTIONS_HPP_
#define _TEST_FUNCTIONS_HPP_

#include <Windows.h>
#include <iostream>
#include <cstdlib>
#include <time.h>
#include <vector>
#include <fstream>
#include <ostream>
#include <istream>
#include <DirectXMath.h>
using namespace DirectX;

namespace Benchmark
{
	XMFLOAT4X4 UnoptA(XMFLOAT4X4 inputMat, XMFLOAT4 inputVec);
	XMFLOAT4X4 UnoptB(XMFLOAT4X4 inputMat);

	XMMATRIX OptA(CXMMATRIX inputMat, FXMVECTOR inputVec);
	XMMATRIX OptB(CXMMATRIX inputMat);

	void BenchUnopt(XMFLOAT4X4 inputMat, XMFLOAT4 inputVec, UINT count, std::vector<XMFLOAT4X4> &buffer);
	void BenchOpt(XMFLOAT4X4 inputMat, XMFLOAT4 inputVec, UINT count, std::vector<XMFLOAT4X4> &buffer);
}

#endif

Profiler.cpp

#include "Profiler.hpp"

Profiler *Profiler::instance = nullptr;

Profiler *Profiler::Instance()
{
	if(instance)
	{
		return(instance);
	}
	return(instance = new Profiler);
}

void Profiler::Destroy()
{
	if(instance)
	{
		delete instance;
	}
}

Profiler::Profiler(): DTime(0)
{
	lastGameTime = (UINT64)timeGetTime();
}

Profiler::~Profiler()
{

}

void Profiler::operator()()
{
	UINT64 ticks = (UINT64)timeGetTime();

	DTime = ticks - lastGameTime;

	lastGameTime = ticks;
}

BenchmarksOpt.cpp

#include "Benchmarks.hpp"

namespace Benchmark
{
	XMMATRIX OptA(CXMMATRIX inputMat, FXMVECTOR inputVec)
	{
		return(OptB(XMMatrixMultiply(inputMat, XMMatrixRotationQuaternion(inputVec))));
	}

	XMMATRIX OptB(CXMMATRIX inputMat)
	{
		XMVECTOR determinant;
		return(XMMatrixInverse(&determinant, inputMat));
	}

	void BenchOpt(XMFLOAT4X4 inputMat, XMFLOAT4 inputVec, UINT count, std::vector<XMFLOAT4X4> &buffer)
	{
		XMMATRIX matrixInput = XMLoadFloat4x4(&inputMat);
		XMVECTOR vectorInput = XMLoadFloat4(&inputVec);

		for(UINT i = 0; i < count; i++)
		{
			XMFLOAT4X4 bufferMat;
			XMStoreFloat4x4(&bufferMat, OptA(matrixInput, vectorInput));
			buffer.push_back(bufferMat);
		}
	}
}

BenchmarksUnopt.cpp

#include "Benchmarks.hpp"

namespace Benchmark
{
	XMFLOAT4X4 UnoptA(XMFLOAT4X4 inputMat, XMFLOAT4 inputVec)
	{
		XMMATRIX matrixInput = XMLoadFloat4x4(&inputMat);
		XMVECTOR vectorInput = XMLoadFloat4(&inputVec);
		
		matrixInput = XMMatrixMultiply(matrixInput, XMMatrixRotationQuaternion(vectorInput));

		XMFLOAT4X4 outputMat;
		XMStoreFloat4x4(&outputMat, matrixInput);

		return(UnoptB(outputMat));
	}

	XMFLOAT4X4 UnoptB(XMFLOAT4X4 inputMat)
	{
		XMMATRIX matrixInput = XMLoadFloat4x4(&inputMat);
		XMVECTOR determinant;
		matrixInput = XMMatrixInverse(&determinant, matrixInput);
		XMFLOAT4X4 outputMat;
		XMStoreFloat4x4(&outputMat, matrixInput);
		
		return(outputMat);
	}

	void BenchUnopt(XMFLOAT4X4 inputMat, XMFLOAT4 inputVec, UINT count, std::vector<XMFLOAT4X4> &buffer)
	{
		for(UINT i = 0; i < count; i++)
		{
			buffer.push_back(UnoptA(inputMat, inputVec));
		}
	}
}

main.cpp

#include "Benchmarks.hpp"
#include "Profiler.hpp"

using namespace std;
using namespace Benchmark;

int main()
{
	Profiler &ProfilerRef = *Profiler::Instance();
	UINT count;
	cout<<"Select iteration amount:";
	cin>>count;
	cout<<endl<<"Test will now begin"<<endl<<endl;

	std::vector<XMFLOAT4X4> bufferUnopt;
	std::vector<XMFLOAT4X4> bufferOpt;
	bufferUnopt.reserve(count);
	bufferOpt.reserve(count);

	XMFLOAT4 testVector = XMFLOAT4(1.0f, 3.0f, 2.0f, 4.0f);
	XMFLOAT4X4 testMatrix = XMFLOAT4X4(3.0f,3.0f,3.0f,3.0f,
									   3.0f,3.0f,3.0f,3.0f,
									   3.0f,3.0f,3.0f,3.0f,
									   3.0f,3.0f,3.0f,3.0f);

	ProfilerRef();
	BenchUnopt(testMatrix, testVector, count, bufferUnopt);
	ProfilerRef();
	cout<<"Unoptimized Benchmkar: "<<ProfilerRef.GetDTime()<<endl;

	ProfilerRef();
	BenchOpt(testMatrix, testVector, count, bufferOpt);
	ProfilerRef();
	cout<<"Optimized Benchmkar: "<<ProfilerRef.GetDTime()<<endl;

	ofstream myfile;
	myfile.open ("example.txt");
	for(UINT i = 0; i < bufferOpt.size(); i++)
	{
		myfile<<bufferOpt[i]._11;
	}
	for(UINT i = 0; i < bufferUnopt.size(); i++)
	{
		myfile<<bufferUnopt[i]._11;
	}
	myfile.close();

	return 0;
}

I split the Benchmarks# into 2 .cpp files,so I can get 2 seperate ASM/Machine code lists,the Unopt version always gets over 20 times more output,but the speed difference is almosst 0

I actualy tried to benchmark some DirectXMath code,one part was doing "unoptimized" functions,by taking XMFLOAT4X4 and XMFLOAT4 as arguments,then loading them into XMVECTOR/XMMATRIX,then doing operations,then storing again,passing again to another function that loads again and then stores again and outputs to the progra.The other test functions were doing the same operations,but with only loading/unloading when it has to output,otherwise taking CXMMATRIX and FXMVECTOR as arguments and being as fast as possible.Even with millions of calls,the "optimized" version was only slightly faster than the "unoptimized" one.

how much vRAM do your GBuffers usually take up?GPU-Z tells me with 8xMSAA that mine takes around 350mb just for a position,color,normal,specular buffer.

the Z-prepass worries me,does that mean I have to do the tessellation twice as well?(tessellation already hits my FPS big time)

http://www.cse.chalmers.se/~olaolss/get_file.php?filename=clustered_forward_demo.zip here's the demo,if you don't trust the direct link you can get it here http://www.cse.chalmers.se/~olaolss/main_frame.php?contents=publication&id=tiled_clustered_forward_talk

I'm referring to this: http://www.cse.chalmers.se/~uffe/clustered_shading_preprint.pdf there is also a video avaliable http://www.youtube.com/watch?v=6DyTk7917ZI the performance of this technique seems to scale perfectly for huge amounts of lights,but on lower amounts performs a little worse than the less advanced tiled culling method.The thing is - has there ever been a case where you will need 30 thousand lights in a scene?Plus,won't it get bottlenecked by generating shadow maps for all the lights(in the youtube video the lights just pass trough the bridge and under it).Unfortunately I couldn't test it's performance,because for some reason the provided demo won't start up(even tho I support OpenGL 3 and higher) and I've never done GLSL,so it might take time to get it to work.

This is pretty much my input handler:

Input* gInput = 0;
Input::Input()
{
   raw = 0;
}
Input::~Input()
{
}
void Input::Release()
{

}
void Input::Initialize()
{
Rid[0].usUsagePage = 1;
Rid[0].usUsage = 6;
Rid[0].dwFlags = 0;
Rid[0].hwndTarget=NULL;
Rid[1].usUsagePage = 1;
Rid[1].usUsage = 2;
Rid[1].dwFlags = 0;
Rid[1].hwndTarget=NULL;
RegisterRawInputDevices(Rid, 2, sizeof(Rid[0]));
}
void Input::Update()
{
if (raw->header.dwType== RIM_TYPEMOUSE)
{
  lastMouseX = raw->data.mouse.lLastX;
  lastMouseY = raw->data.mouse.lLastY;
  mouseFlags = raw->data.mouse.usFlags;
  mouseButtonFlags = raw->data.mouse.usButtonFlags;
  leftButtonDown = raw->data.mouse.ulButtons & RI_MOUSE_LEFT_BUTTON_DOWN;
  rightButtonDown = raw->data.mouse.ulButtons & RI_MOUSE_RIGHT_BUTTON_DOWN;
  middleButtonDown = raw->data.mouse.ulButtons & RI_MOUSE_MIDDLE_BUTTON_DOWN;
  if(raw->data.mouse.ulButtons & RI_MOUSE_WHEEL)
  {
   wheelZ = raw->data.mouse.usButtonData;
  }
}
if (raw->header.dwType== RIM_TYPEKEYBOARD)
{
  keyCode=raw->data.keyboard.VKey;
  bool keyPressed=raw->data.keyboard.Flags & RI_KEY_BREAK;
}
}

class Input
{
#pragma region REGION:INPUT_METHODS
public:
Input();
~Input();

void Release();
void Initialize();
void Update();
#pragma endregion
#pragma region REGION:INPUT_MEMBERS
public:
RAWINPUTDEVICE Rid[2];
RAWINPUT *raw;
long lastMouseX;
long lastMouseY;
USHORT mouseFlags;
USHORT mouseButtonFlags;
USHORT wheelZ;
bool leftButtonDown;
bool rightButtonDown;
bool middleButtonDown;
USHORT keyCode;
#pragma endregion
};
extern Input* gInput;


#endif

When I initialize it in the main function like this:

gInput = new Input();
gInput->Initialize();

The window starts lagging and all 4 cores of my CPU show increased load,as much as 20% - 40% !!
I tried to read input with Enter and LeftMouseButton,but it doesn't respond:

while(!done)
    {
	    if(PeekMessage(&msg, NULL, 0, 0, PM_REMOVE))
	    {
		    TranslateMessage(&msg);
		    DispatchMessage(&msg);
	    }
	    if(msg.message == WM_QUIT)
	    {
		    done = true;
	    }
 
  if(msg.message == WM_INPUT)
  {
  UINT bufferSize;
  GetRawInputData((HRAWINPUT)msg.lParam, RID_INPUT, NULL, &bufferSize, sizeof (RAWINPUTHEADER));
  BYTE *buffer=new BYTE[bufferSize];
  GetRawInputData((HRAWINPUT)msg.lParam, RID_INPUT, (LPVOID)buffer, &bufferSize, sizeof (RAWINPUTHEADER));
  SafeDelete(gInput->raw);
  gInput->raw = (RAWINPUT*)buffer;
  gInput->Update();
  if(gInput->keyCode = VK_RETURN)
  {
   done = true;
  }
  if(gInput->leftButtonDown)
  {
   done = true;
  }
  }
	    else
	    {
   gGraphics->Render();
	    }
}

What am I doing wrong?Did I initialize with the wrong flags?I also tried it like this:

Rid[0].usUsagePage = 0x01;
Rid[0].usUsage = 0x02;
Rid[0].dwFlags = RIDEV_NOLEGACY;  
Rid[0].hwndTarget = 0;


Rid[1].usUsagePage = 0x01;
Rid[1].usUsage = 0x06;
Rid[1].dwFlags = RIDEV_NOLEGACY; 
Rid[1].hwndTarget = 0;

Same thing happens..