Per instance world matrix is 0.0f/NaN - directx

I'm trying to draw some cubes with Hardware Instancing.
However they don't get displayed. So I debugged my code, and found the source of the problem:
In my VertexShader, the var that has the per instance world matrix has a value of:
{ 0.0f, 0.0f, 0.0f, 0.0f,
0.0f, 0.0f, 0.0f, 0.0f,
0.0f, 0.0f, 0.0f, 0.0f,
0.0f, NaN, NaN, NaN }
The weirdest thing is that it outpus NaN (Not a Number). Here's how I create my instanced buffer:
XMMATRIX trans[4];
trans[0] = XMMatrixTranslation(0.0f, 0.0f, 0.0f);
trans[1] = XMMatrixTranslation(0.5f, 0.5f, 0.5f);
trans[2] = XMMatrixTranslation(-0.5, -0.5, 0.5);
trans[3] = XMMatrixTranslation(0.5, -0.5f, 0.5);
//Store world matrices
for (int i = 0; i < 4; i++)
XMStoreFloat4x4(&mIV[i].world, trans[i]);
D3D11_BUFFER_DESC instDesc;
ZeroMemory(&instDesc, sizeof(D3D11_BUFFER_DESC));
instDesc.BindFlags = D3D11_BIND_VERTEX_BUFFER;
instDesc.Usage = D3D11_USAGE_DYNAMIC;
instDesc.ByteWidth = sizeof(XMFLOAT4X4) * 4;
instDesc.CPUAccessFlags = D3D11_CPU_ACCESS_WRITE;
//Create instanced buffer
HR(mDevice->CreateBuffer(&instDesc, NULL, &mBoxInstB));
Here's how I map the instanced data to my buffer:
D3D11_MAPPED_SUBRESOURCE mapSub;
mContext->Map(mBoxInstB, 0, D3D11_MAP_WRITE_DISCARD, NULL, &mapSub);
VertexI* idata = reinterpret_cast<VertexI*>(mapSub.pData);
idata = mIV;
mContext->Unmap(mBoxInstB, 0);
Thanks for the help!
If you need some more info, write it in the comments!

idata = mIV doesn't copy any data. What you want is memcpy(mapSub.pData, &mIV[0].world, instDesc.ByteWidth) assuming the world member is the entire contents of mIV[i] and is contiguous in memory.

Related

How to copy the RTV output to the side of a cubemap?

I am currently implementing diffuse irridiance(A part of Image based lightning of PBR) in my game engine. I got to the point where I have to take an HDR Image and turn it into a cubemap. I am currently using a EquirectangularToCubemap shader and its working fine. I was able to project the HDR image to a (unit)cube. Now comes the part where I am stuck, I can't turn this cube to a cubemap. I tried using 1 TextureCube, 6 RenderTargetView's and a ShaderResourceView. My plan was to render the (unit)cube 6 times from different view projection with a FOV of 90 to capture the whole side in each of the render target, and lastly copy each of the output of the render target to the corresponding side of the Texture cube.
I don't know how to do this ^.
NOTE: I am using DirextX11 as the rendering backend.
Here is the pseudo code about my problem(which is not working)
glm::mat4 captureProjection = glm::perspective(glm::radians(90.0f), 1.0f, 0.1f, 10.0f);
glm::mat4 captureViews[] =
{
glm::lookAt(glm::vec3(0.0f, 0.0f, 0.0f), glm::vec3(1.0f, 0.0f, 0.0f), glm::vec3(0.0f, -1.0f, 0.0f)),
glm::lookAt(glm::vec3(0.0f, 0.0f, 0.0f), glm::vec3(-1.0f, 0.0f, 0.0f), glm::vec3(0.0f, -1.0f, 0.0f)),
glm::lookAt(glm::vec3(0.0f, 0.0f, 0.0f), glm::vec3(0.0f, 1.0f, 0.0f), glm::vec3(0.0f, 0.0f, 1.0f)),
glm::lookAt(glm::vec3(0.0f, 0.0f, 0.0f), glm::vec3(0.0f, -1.0f, 0.0f), glm::vec3(0.0f, 0.0f, -1.0f)),
glm::lookAt(glm::vec3(0.0f, 0.0f, 0.0f), glm::vec3(0.0f, 0.0f, 1.0f), glm::vec3(0.0f, -1.0f, 0.0f)),
glm::lookAt(glm::vec3(0.0f, 0.0f, 0.0f), glm::vec3(0.0f, 0.0f, -1.0f), glm::vec3(0.0f, -1.0f, 0.0f))
};
//Create the TextureCube
D3D11_TEXTURE2D_DESC textureDesc = {};
textureDesc.Width = 512;
textureDesc.Height = 512;
textureDesc.MipLevels = 1;
textureDesc.ArraySize = 6;
textureDesc.Format = DXGI_FORMAT_R32G32B32A32_FLOAT;
textureDesc.CPUAccessFlags = 0;
textureDesc.SampleDesc.Count = 1;
textureDesc.SampleDesc.Quality = 0;
textureDesc.Usage = D3D11_USAGE_DEFAULT;
textureDesc.BindFlags = D3D11_BIND_SHADER_RESOURCE | D3D11_BIND_RENDER_TARGET;
textureDesc.MiscFlags = D3D11_RESOURCE_MISC_TEXTURECUBE;
ID3D11Texture2D* tex = nullptr;
DX_CALL(DX11Internal::GetDevice()->CreateTexture2D(&textureDesc, nullptr, &tex));
// Create the Shader Resource view for the texture cube
D3D11_SHADER_RESOURCE_VIEW_DESC srvDesc = {};
srvDesc.Format = textureDesc.Format;
srvDesc.ViewDimension = D3D11_SRV_DIMENSION_TEXTURECUBE;
srvDesc.Texture2D.MostDetailedMip = 0;
srvDesc.Texture2D.MipLevels = 1;
DX_CALL(DX11Internal::GetDevice()->CreateShaderResourceView(tex, &srvDesc, &mSRV));
//Create the Render target views
Vector<ID3D11RenderTargetView*> rtvs;
for (Uint i = 0; i < 6; i++)
{
D3D11_RENDER_TARGET_VIEW_DESC renderTargetViewDesc = {};
renderTargetViewDesc.Format = textureDesc.Format;
renderTargetViewDesc.ViewDimension = D3D11_RTV_DIMENSION_TEXTURE2D;
renderTargetViewDesc.Texture2D.MipSlice = 0;
ID3D11RenderTargetView* view = nullptr;
DX11Internal::GetDevice()->CreateRenderTargetView(tex, &renderTargetViewDesc, &view);
rtvs.push_back(view);
}
tex->Release();
auto deviceContext = DX11Internal::GetDeviceContext();
for (Uint i = 0; i < 6; ++i)
{
float clearColor[4] = { 1.0f, 0.1f, 0.1f, 1.0f };
deviceContext->ClearRenderTargetView(rtvs[i], clearColor);
Vault::Get<Shader>("EquirectangularToCubemap.hlsl")->Bind();
auto data = captureProjection * captureViews[i];
cbuffer->Bind();
cbuffer->SetData(&data);
texture->Bind(0);
tempPipeline->Bind();
deviceContext->OMSetRenderTargets(1, &rtvs[i], nullptr);
//I am rendering the cube here from different view projection to capture the faces, but I dont't know where to copy the data to the //side of the TextureCube :( [Note that I am doing this only once]
RenderCommand::DrawIndexed(tempPipeline, 36);
}
Thanks in advance!
You are not specifying which slices you want to write to when creating render views.
The correct description for slices is:
D3D11_RENDER_TARGET_VIEW_DESC renderTargetViewDesc = {};
renderTargetViewDesc.Format = textureDesc.Format;
renderTargetViewDesc.ViewDimension = D3D11_RTV_DIMENSION_TEXTURE2DARRAY;
renderTargetViewDesc.Texture2DArray.MipSlice = 0;
renderTargetViewDesc.Texture2DArray.FirstArraySlice =i;
renderTargetViewDesc.Texture2DArray.ArraySize = 1;
(Note : if you use MSAA, ViewDimension will become D3D11_RTV_DIMENSION_TEXTURE2DMSARRAY)
Also to create the shader view for your resource, since you want to create a default one, you can pass NULL instead of a home made D3D11_SHADER_RESOURCE_VIEW_DESC
DX_CALL(DX11Internal::GetDevice()->CreateShaderResourceView(tex, NULL, &mSRV));
You can also create another render view that maps the whole cube map in one go :
DX11Internal::GetDevice()->CreateRenderTargetView(tex, NULL, &cubeMapFullView);
But in that case you will need to use Geometry Shader to replicate geometry across slices (using SV_RenderTargetArrayIndex), or use vendor specific extensions that provide the same kind of feature.

DX11 triangle list is not rendering at all

I have a list of 4 verts loaded into a vert buffer, and an index loaded into a index buffer.
The issue I have is that while the LineList rendermode shows a quad just fine (see below) the TriangleList shows nothing (See below)
void BLX::Model::load(std::filesystem::path path, Model* model, ID3D11Device* d3dDevice, ID3D11DeviceContext* d3dContext)
{
// tmp: just making a quad
float num = 0.5f;
std::vector<BLX::Vertex> vertices = {
BLX::Vertex { DirectX::XMFLOAT3(-num, -num, 0.0f), DirectX::XMFLOAT3(0.0f, 0.0f, 0.5f), }, // 0 = TL
BLX::Vertex { DirectX::XMFLOAT3(num, -num, 0.0f), DirectX::XMFLOAT3(0.0f, 0.5f, 0.0f), }, // 1 = TR
BLX::Vertex { DirectX::XMFLOAT3(num, num, 0.0f), DirectX::XMFLOAT3(0.5f, 0.0f, 0.0f), }, // 2 = BR
BLX::Vertex { DirectX::XMFLOAT3(-num, num, 0.0f), DirectX::XMFLOAT3(0.5f, 0.5f, 0.0f), }, // 3 = BL
};
// line list
//std::vector<unsigned int> indices = { 0, 1, 1, 2, 2, 3, 3, 0 };
// triangle list
std::vector<unsigned int> indices = { 0, 1, 3, 3, 1, 2 };
model->vertexCount = vertices.size();
model->indexCount = indices.size();
// Vertex Buffer
D3D11_BUFFER_DESC vbd = {};
vbd.BindFlags = D3D11_BIND_VERTEX_BUFFER;
vbd.Usage = D3D11_USAGE_DEFAULT;
vbd.CPUAccessFlags = 0u;
vbd.MiscFlags = 0u;
vbd.ByteWidth = sizeof(BLX::Vertex) * model->vertexCount;
vbd.StructureByteStride = sizeof(BLX::Vertex);
D3D11_SUBRESOURCE_DATA vsd = {};
vsd.pSysMem = &vertices[0];
vsd.SysMemPitch = 0;
vsd.SysMemSlicePitch = 0;
d3dDevice->CreateBuffer(&vbd, &vsd, &model->vertexBuffer);
/// Index Buffer
D3D11_BUFFER_DESC ibd = {};
ibd.Usage = D3D11_USAGE_DEFAULT;
ibd.ByteWidth = sizeof(unsigned int) * model->indexCount;
ibd.BindFlags = D3D11_BIND_INDEX_BUFFER;
ibd.CPUAccessFlags = 0;
ibd.MiscFlags = 0;
D3D11_SUBRESOURCE_DATA isd = {};
isd.pSysMem = &indices[0];
isd.SysMemPitch = 0;
isd.SysMemSlicePitch = 0;
d3dDevice->CreateBuffer(&ibd, &isd, &model->indexBuffer);
// IA = Input Assembly
// pixel shader
D3DReadFileToBlob(L"PixelShader2.cso", &model->pBlob);
d3dDevice->CreatePixelShader(model->pBlob->GetBufferPointer(), model->pBlob->GetBufferSize(), nullptr, &model->pPixelShader);
// Vertex Shader
D3DReadFileToBlob(L"VertexShader2.cso", &model->pBlob);
d3dDevice->CreateVertexShader(model->pBlob->GetBufferPointer(), model->pBlob->GetBufferSize(), nullptr, &model->pVertexShader);
const D3D11_INPUT_ELEMENT_DESC ied[] =
{
// "Position" correcponds to Vertex Shader Semantic Name
// semantic index
// data type format
// Input slot
// Aligned byte offset
// Input slot class
// Instance data step rate
{ "POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 0, D3D11_INPUT_PER_VERTEX_DATA, 0},
{ "COLOR", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 12, D3D11_INPUT_PER_VERTEX_DATA, 0 },
};
// needs vertex shader blob
d3dDevice->CreateInputLayout(ied, ARRAYSIZE(ied), model->pBlob->GetBufferPointer(), model->pBlob->GetBufferSize(), &model->pInputLayout);
}
void BLX::Model::render(ID3D11Device* d3dDevice, ID3D11DeviceContext* d3dContext, D3D11_VIEWPORT * vp)
{
const UINT stride = sizeof(Vertex);
const UINT offset[] = { 0u, 0u };
d3dContext->IASetVertexBuffers(0u, 1u, vertexBuffer.GetAddressOf(), &stride, &offset[0]);
d3dContext->IASetIndexBuffer(*indexBuffer.GetAddressOf(), DXGI_FORMAT_R32_UINT, offset[1]);
d3dContext->PSSetShader(pPixelShader.Get(), nullptr, 0u);
d3dContext->VSSetShader(pVertexShader.Get(), nullptr, 0u);
d3dContext->IASetInputLayout(pInputLayout.Get());
d3dContext->RSSetViewports(1u, vp);
//d3dContext->IASetPrimitiveTopology(D3D11_PRIMITIVE_TOPOLOGY::D3D11_PRIMITIVE_TOPOLOGY_LINELIST);
d3dContext->IASetPrimitiveTopology(D3D11_PRIMITIVE_TOPOLOGY::D3D11_PRIMITIVE_TOPOLOGY_TRIANGLELIST);
d3dContext->DrawIndexed(indexCount, 0, 0);
}
When using the LineList index and topology:
When using the TriangleList index and topology:
But when I was doing this:
// tmp: just making a quad
float num = 0.5f;
std::vector<BLX::Vertex> vertices = {
BLX::Vertex { DirectX::XMFLOAT3(0.0f, num, 0.0f), DirectX::XMFLOAT3(0.0f, 0.0f, 0.5f), },
BLX::Vertex { DirectX::XMFLOAT3(num, -num, 0.0f), DirectX::XMFLOAT3(0.0f, 0.5f, 0.0f), },
BLX::Vertex { DirectX::XMFLOAT3(-num, -num, 0.0f), DirectX::XMFLOAT3(0.5f, 0.0f, 0.0f), },
};
// triangle list
std::vector<unsigned int> indices = { 0, 1, 2 };
(everything else the exact same) I got this:
Just really curious what I'm not seeing or getting when trying to render two triangles to make up a quad
Your rectangle has indices organized in a clockwise manner, which are culled by the default rasterizer (since you do not specify one it culls clockwise primitives)
Your triangle vertices order was counter clockwise, so the primitive was not culled.
To solve it, two solutions:
Change your indices order :
std::vector<unsigned int> indices = { 0, 3, 1, 3, 2, 1 };
Disable culling in the rasterizer state :
First create one Rasterizer Description
D3D11_RASTERIZER_DESC raster_desc;
raster_desc.FillMode = D3D11_FILL_SOLID;
raster_desc.CullMode= D3D11_CULL_NONE;
raster_desc.FrontCounterClockwise = false;
raster_desc.DepthBias = 0;
raster_desc.DepthBiasClamp= 0.0f;
raster_desc.SlopeScaledDepthBias= 0.0f;
raster_desc.DepthClipEnable= true;
raster_desc.ScissorEnable= false;
raster_desc.MultisampleEnable= false;
raster_desc.AntialiasedLineEnable= false;
Then create a rasterizer state using your device:
ID3D11RasterizerState* raster_state;
HRESULT hr =d3dDevice->CreateRasterizerState(&raster_desc, &raster_state);
Before the draw, assign your rasterizer state to your context:
d3dContext->RSSetState(raster_state);
Your two meshes, triangle and quad, have opposite triangle winding order. Here’s how.
By default, D3D11 uses CullMode=Back and FrontCounterClockwise=FALSE.
This means it only renders front faces, and front face is defined as “when the vertices are counter-clockwise”.
As you see from the above illustration, your triangle indeed has counter-clockwise order, however both triangles of your quad are clockwise, GPU considers them as back faces and skips both.
You have many ways to fix, any of the following will do.
Reorder vertices in vertex buffer.
Flip triangles in index buffer to { 0, 3, 1, 1, 3, 2 }
Change rasterizer state to disable back face culling, CullMode=D3D11_CULL_NONE
Change rasterizer state to switch front face winding direction, FrontCounterClockwise=TRUE
Change matrix passed to vertex shader to include mirroring component, e.g. scale with vector [ -1, 1, 1 ] represents a mirror transform that flips X, this will flip winding order of the whole mesh.

How to fill the texture within a reactangle and fill (0.0,0.0,0.0) outside reactangle in a destination texture.?

There are 2 textures.
Destination texture - 7201080
source texture - 300300
Help required:
We need to put source texture onto destination texure at a given location (x center, y center, height and width) and fill the remaining destination texture with 0,0.
Challenge we are facing is that source texture is getting enlarged to the size of destination texture.
I tried this to do in it in shader coder as follows.
// Texture Coordinates
static const GLfloat square_vertices[] = {
-1.0f, -1.0f, // bottom left
1.0f, -1.0f, // bottom right
-1.0f, 1.0f, // top left
1.0f, 1.0f, // top right
};
static const GLfloat texture_vertices[] = {
0.0f, 0.0f, // bottom left
1.0f, 0.0f, // bottom right
0.0f, 1.0f, // top left
1.0f, 1.0f, // top right
};
// program
glUseProgram(upsample_program_);
// vertex storage
GLuint vbo[2];
glGenBuffers(2, vbo);
GLuint vao;
glGenVertexArrays(1, &vao);
glBindVertexArray(vao);
// vbo 0
glBindBuffer(GL_ARRAY_BUFFER, vbo[0]);
glBufferData(GL_ARRAY_BUFFER, 4 * 2 * sizeof(GLfloat), square_vertices,
GL_STATIC_DRAW);
glEnableVertexAttribArray(ATTRIB_VERTEX);
glVertexAttribPointer(ATTRIB_VERTEX, 2, GL_FLOAT, 0, 0, nullptr);
// vbo 1
glBindBuffer(GL_ARRAY_BUFFER, vbo[1]);
glBufferData(GL_ARRAY_BUFFER, 4 * 2 * sizeof(GLfloat), texture_vertices,
GL_STATIC_DRAW);
glEnableVertexAttribArray(ATTRIB_TEXTURE_POSITION);
glVertexAttribPointer(ATTRIB_TEXTURE_POSITION, 2, GL_FLOAT, 0, 0, nullptr);
// draw
glDrawArrays(GL_TRIANGLE_STRIP, 0, 4);
// cleanup
glDisableVertexAttribArray(ATTRIB_VERTEX);
glDisableVertexAttribArray(ATTRIB_TEXTURE_POSITION);
glBindBuffer(GL_ARRAY_BUFFER, 0);
glBindVertexArray(0);
glDeleteVertexArrays(1, &vao);
glDeleteBuffers(2, vbo);
// Frame drawing
output_width=720;
output_height=1080;
// Upsample small mask into output.
GlTexture output_texture = CreateDestinationTexture(
output_width, output_height,GpuBufferFormat::kBGRA32);
{
gpu_helper_.BindFramebuffer(output_texture); // GL_TEXTURE0
glActiveTexture(GL_TEXTURE1);
//small_mask_texture is the texture need to render inside the react.
glBindTexture(GL_TEXTURE_2D, small_mask_texture.id());
GlRender();
glBindTexture(GL_TEXTURE_2D, 0);
glUniform2f(glGetUniformLocation(upsample_program_, "rcenters"),normx_center,normy_center);
glUniform2f(glGetUniformLocation(upsample_program_, "rhw"),normalized_width,normalized_height);
glFlush();
}
Here is my shader code;
#if __VERSION__ < 130
#define in varying
#endif // __VERSION__ < 130
#ifdef GL_ES
#define fragColor gl_FragColor
precision highp float;
#else
#define lowp
#define mediump
#define highp
#define texture2D texture
out vec4 fragColor;
#endif // defined(GL_ES)
in vec2 sample_coordinate;
uniform sampler2D input_data;
uniform vec2 rcenters;
uniform vec2 rhw;
void main() {
vec4 pix = texture2D(input_data, sample_coordinate);
float xcenter = rcenters.s;
float ycenter = rcenters.t;
float rwidth = rhw.s;
float rheight = rhw.t;
if(rwidth != 0.0 && rheight != 0.0){
float cox = sample_coordinate.s;
float coy = sample_coordinate.t;
float xmin = xcenter-(rwidth/2.0);
float ymin = ycenter-(rheight/2.0);
float xmax = xcenter+(rwidth/2.0);
float ymax = ycenter+(rheight/2.0);
if((xmin<cox && xmax>cox) && (ymin<coy && ymax>coy)){
fragColor = pix;
}
else{
fragColor = vec4(0.0,0.0,0.0,1.0);
}
}
else{
fragColor = vec4(0.0,0.0,0.0,1.0);
}
}
With this solution I am getting source texture enlarge equal to destination texture. I understand that I need to do something with texture coordinates in vertex but don't know what.

No transparency with simple OpenGL ES2.0 stencils

I am attempting to make a stencil mask in OpenGL. I have been following the model from this source (http://open.gl/depthstencils and more specifically, http://open.gl/content/code/c5_reflection.txt), and as far as I can tell, I have followed the example properly. My code is drawing one square stencil, and then another square on top of it. I expected to see only the parts of the second rotating green square that are covering the same space as the first. What I actually see is the two overlapping squares, one rotating with no transparency. One notable difference from the example is that I am not using a texture. Is that a problem? I figured that this would be a simpler example.
I'm fairly new to ES2.0, so if I'm doing something obviously stupid, please let me know.
Initialization:
GLuint attributes[] = { GLKVertexAttribPosition, GLKVertexAttribColor, GLKVertexAttribTexCoord0 };
const char *attributeNames[] = { "position", "color", "texcoord0" };
// These are all global GLuint variables
// vshSrc and fshSrc are const char* filenames (the files are found properly)
_myProgram = loadProgram(vshSrc, fshSrc, 3, attributes, attributeNames);
_myProgramUniformMVP = glGetUniformLocation(_myProgram, "modelViewProjectionMatrix");
_myProgramUniformTex = glGetUniformLocation(_myProgram, "tex");
_myProgramUniformOverrideColor = glGetUniformLocation(_myProgram, "overrideColor");
The draw loop:
glEnable(GL_DEPTH_TEST);
glUseProgram(_myProgram);
glDisable(GL_BLEND);
glClearColor(1.0, 1.0, 1.0, 1.0);
glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
GLfloat gSquare[20] = { // not using the textures currently
// posX, posY, posZ, texX, texY,
-0.5f, -0.5f, 0, 0.0f, 0.0f,
0.5f, -0.5f, 0, 1.0f, 0.0f,
-0.5f, 0.5f, 0, 0.0f, 1.0f,
0.5f, 0.5f, 0, 1.0f, 1.0f
};
// Projection matrix
float aspect = fabsf(self.view.bounds.size.width / self.view.bounds.size.height);
GLKMatrix4 projectionMatrix = GLKMatrix4MakePerspective(GLKMathDegreesToRadians(65.0f), aspect, 0.1f, 100.0f);
// Put the squares where they can be seen
GLKMatrix4 baseModelViewMatrix = GLKMatrix4MakeTranslation(0.0f, 0.0f, -4.0f);
glEnable(GL_STENCIL_TEST);
// Build the stencil
glStencilFunc(GL_ALWAYS, 1, 0xFF); // Set any stencil to 1
glStencilOp(GL_KEEP, GL_KEEP, GL_REPLACE);
glStencilMask(0xFF); // Write to stencil buffer
glDepthMask(GL_FALSE); // Don't write to depth buffer
glClear(GL_STENCIL_BUFFER_BIT); // Clear stencil buffer (0 by default)
GLKMatrix4 mvp = GLKMatrix4Multiply(projectionMatrix, baseModelViewMatrix);
// Draw a stationary red square for the stencil (though the color shouldn't matter)
glUniformMatrix4fv(_chetProgramUniformMVP, 1, 0, mvp.m);
glUniform1i(_chetProgramUniformTex, 0);
glUniform4f(_chetProgramUniformOverrideColor, 1.0f, 1.0f, 1.0f,0.0f);
glVertexAttrib4f(GLKVertexAttribColor, 1, 0, 0, 1);
glEnableVertexAttribArray(GLKVertexAttribPosition);
glVertexAttribPointer(GLKVertexAttribPosition, 3, GL_FLOAT, GL_FALSE, 20, gSquare);
glDrawArrays(GL_TRIANGLE_STRIP, 0, 4);
// Prepare the mask
glStencilFunc(GL_EQUAL, 1, 0xFF); // Pass test if stencil value is 1
glStencilMask(0x00); // Don't write anything to stencil buffer
glDepthMask(GL_TRUE); // Write to depth buffer
glUniform4f(_myProgramUniformOverrideColor, 0.3f, 0.3f, 0.3f,1.0f);
// A slow rotating green square to be masked by the stencil
static float rotation = 0;
rotation += 0.01;
baseModelViewMatrix = GLKMatrix4Rotate(baseModelViewMatrix, rotation, 0, 0, 1);
mvp = GLKMatrix4Multiply(projectionMatrix, baseModelViewMatrix);
glUniformMatrix4fv(_myProgramUniformMVP, 1, 0, mvp.m);//The transformation matrix
glUniform1i(_myProgramUniformTex, 0); // The texture
glVertexAttrib4f(GLKVertexAttribColor, 0, 1, 0, 1);
glEnableVertexAttribArray(GLKVertexAttribPosition);
glVertexAttribPointer(GLKVertexAttribPosition, 3, GL_FLOAT, GL_FALSE, 20, gSquare);
glDrawArrays(GL_TRIANGLE_STRIP, 0, 4);
glDisable(GL_STENCIL_TEST);
EDIT: The following shader stuff is irrelevant to the problem I was having. The stenciling does not take place in the shader.
Vertex Shader:
attribute vec4 position;
attribute vec4 color;
attribute vec2 texcoord0;
varying lowp vec4 colorVarying;
varying lowp vec2 texcoord;
uniform mat4 modelViewProjectionMatrix;
uniform vec4 overrideColor;
void main()
{
colorVarying = overrideColor * color;
texcoord = texcoord0;
gl_Position = modelViewProjectionMatrix * position;
}
Fragment Shader:
varying lowp vec4 colorVarying;
varying lowp vec2 texcoord;
uniform sampler2D tex;
void main()
{
gl_FragColor = colorVarying * texture2D(tex, texcoord);
}
It was necessary to initialize a stencil buffer. Here is the code that fixed it.
glGenRenderbuffersOES(1, &depthStencilRenderbuffer);
glBindRenderbufferOES(GL_RENDERBUFFER_OES, depthStencilRenderbuffer);
glRenderbufferStorageOES(GL_RENDERBUFFER_OES, GL_DEPTH24_STENCIL8_OES, framebufferWidth, framebufferHeight);
glFramebufferRenderbufferOES(GL_FRAMEBUFFER_OES, GL_DEPTH_ATTACHMENT_OES, GL_RENDERBUFFER_OES, depthStencilRenderbuffer);
glFramebufferRenderbufferOES(GL_FRAMEBUFFER_OES, GL_STENCIL_ATTACHMENT_OES, GL_RENDERBUFFER_OES, depthStencilRenderbuffer);

2D Programming with Direct3D 9 - Test image is distorted

I am trying to build a simple 2D game using 2D sprites with DirectX 9, and I'm having problems getting the images to come out cleanly. I'd like to load bmp images and display them on the screen as is (no interpolation, no magnification, no filtering or anti-aliasing, etc).
I'm sure I'm missing something, but when I try and render a 100x100 bmp to the screen, it looks choppy and distorted, like a pixel art image would normally look when shrunken slightly. I want the bmp to look exactly as it does when loaded in MS Paint.
Does anyone have any idea why this might be the case? My code is shown below:
Initialization code:
g_DxCom = Direct3DCreate9( D3D_SDK_VERSION );
if ( g_DxCom == NULL )
{
return false;
}
D3DDISPLAYMODE d3dDisplayMode;
if ( FAILED( g_DxCom->GetAdapterDisplayMode( D3DADAPTER_DEFAULT, &d3dDisplayMode ) ) )
{
return false;
}
D3DPRESENT_PARAMETERS d3dPresentParameters;
::ZeroMemory( &d3dPresentParameters, sizeof(D3DPRESENT_PARAMETERS) );
d3dPresentParameters.Windowed = FALSE;
d3dPresentParameters.SwapEffect = D3DSWAPEFFECT_DISCARD;
d3dPresentParameters.BackBufferFormat = d3dDisplayMode.Format; // D3DFMT_X8R8G8B8
d3dPresentParameters.BackBufferWidth = d3dDisplayMode.Width;
d3dPresentParameters.BackBufferHeight = d3dDisplayMode.Height;
d3dPresentParameters.PresentationInterval = D3DPRESENT_INTERVAL_ONE;
if ( FAILED( g_DxCom->CreateDevice( D3DADAPTER_DEFAULT,
D3DDEVTYPE_HAL,
this->hWnd,
D3DCREATE_HARDWARE_VERTEXPROCESSING,
&d3dPresentParameters,
&pd3dDevice ) ) )
{
if ( FAILED( g_DxCom->CreateDevice( D3DADAPTER_DEFAULT,
D3DDEVTYPE_HAL,
this->hWnd,
D3DCREATE_SOFTWARE_VERTEXPROCESSING,
&d3dPresentParameters,
&pd3dDevice ) ) )
{
return false;
}
}
texture = NULL;
bg_texture = NULL;
Render code:
LPDIRECT3DDEVICE9 g_dxDevice;
float float1 = 99.5f; // I'd like to render my 100x100 sprite from screen coordinates 100, 100 to 200, 200
float float2 = 198.5f;
CUSTOMVERTEX OurVertices[] =
{
{ float1, float2, 1.0f, 1.0f, 0.0f, 1.0f },
{ float1, float1, 1.0f, 1.0f, 0.0f, 0.0f },
{ float2, float1, 1.0f, 1.0f, 1.0f, 0.0f },
{ float1, float2, 1.0f, 1.0f, 0.0f, 1.0f },
{ float2, float1, 1.0f, 1.0f, 1.0f, 0.0f },
{ float2, float2, 1.0f, 1.0f, 1.0f, 1.0f }
};
LPDIRECT3DVERTEXBUFFER9 v_buffer;
g_dxDevice->CreateVertexBuffer( 6 * sizeof(CUSTOMVERTEX),
0,
CUSTOMFVF,
D3DPOOL_MANAGED,
&v_buffer,
NULL );
VOID* pVoid;
// Lock the vertex buffer into memory
v_buffer->Lock( 0, 0, &pVoid, 0 );
// Copy our vertex buffer to memory
::memcpy( pVoid, OurVertices, sizeof(OurVertices) );
// Unlock buffer
v_buffer->Unlock();
LPDIRECT3DTEXTURE9 g_texture;
HRESULT hError;
DWORD dwTextureFilter = D3DTEXF_NONE;
g_dxDevice->SetSamplerState( 0, D3DSAMP_MINFILTER, dwTextureFilter );
g_dxDevice->SetSamplerState( 0, D3DSAMP_MAGFILTER, dwTextureFilter );
g_dxDevice->SetSamplerState( 0, D3DSAMP_MIPFILTER, dwTextureFilter );
g_dxDevice->SetTextureStageState(0,D3DTSS_COLOROP,D3DTOP_SELECTARG1);
g_dxDevice->SetTextureStageState(0,D3DTSS_COLORARG1,D3DTA_TEXTURE);
g_dxDevice->SetTextureStageState(0,D3DTSS_COLORARG2,D3DTA_DIFFUSE);
hError = D3DXCreateTextureFromFile( g_dxDevice, L"Test.bmp", &g_texture ); // 100x100 sprite
g_dxDevice->SetTexture( 0, g_texture );
g_dxDevice->Clear( 0,
NULL,
D3DCLEAR_TARGET,
D3DCOLOR_XRGB( 0, 40, 100 ),
1.0f,
0 );
g_dxDevice->BeginScene();
// Do rendering on the back buffer here
g_dxDevice->SetFVF( CUSTOMFVF );
g_dxDevice->SetStreamSource( 0, v_buffer, 0, sizeof(CUSTOMVERTEX) );
g_dxDevice->DrawPrimitive( D3DPT_TRIANGLELIST, 0, 6 );
g_dxDevice->EndScene();
g_dxDevice->Present( NULL, NULL, NULL, NULL );
g_texture->Release();
v_buffer->Release();
Okay, so I've finally figured it out, and I should have known this was the case.
It looks like DirectX9 only works with textures with sizes that are multiples of 2. If I change the texture so that the sprite square is 128 x 128 (just adding some transparency) and run the application with float2 changed appropriately, there is no distortion in the rendered image.
Hurrah...

Resources