1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650
|
/* Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of NVIDIA CORPORATION nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/* This example demonstrates how to use the CUDA Direct3D bindings to fill
* a vertex buffer with CUDA and use Direct3D to render the data.
* Host code.
*/
#pragma warning(disable : 4312)
// Windows System include files
#include <windows.h>
#include <mmsystem.h>
// This header includes all the necessary D3D10 and CUDA includes
#include <dynlink_d3d10.h>
#include <cuda_runtime_api.h>
#include <cuda_d3d10_interop.h>
// includes, project
#include <rendercheck_d3d10.h>
#include <helper_functions.h> // Helper functions for other non-cuda utilities
#include <helper_cuda.h> // CUDA Helper Functions for initialization
#define MAX_EPSILON 10
static char *sSDKSample = "simpleD3D10";
//-----------------------------------------------------------------------------
// Global variables
//-----------------------------------------------------------------------------
IDXGIAdapter *g_pCudaCapableAdapter = NULL; // Adapter to use
ID3D10Device *g_pd3dDevice = NULL; // Our rendering device
IDXGISwapChain *g_pSwapChain = NULL; // The swap chain of the window
ID3D10RenderTargetView *g_pSwapChainRTV =
NULL; // The Render target view on the swap chain ( used for clear)
ID3D10InputLayout *g_pInputLayout = NULL;
ID3D10Effect *g_pSimpleEffect = NULL;
ID3D10EffectTechnique *g_pSimpleTechnique = NULL;
ID3D10EffectMatrixVariable *g_pmWorld = NULL;
ID3D10EffectMatrixVariable *g_pmView = NULL;
ID3D10EffectMatrixVariable *g_pmProjection = NULL;
static const char g_simpleEffectSrc[] =
"matrix g_mWorld;\n"
"matrix g_mView;\n"
"matrix g_mProjection;\n"
"\n"
"struct Fragment{ \n"
" float4 Pos : SV_POSITION;\n"
" float4 Col : TEXCOORD0; };\n"
"\n"
"Fragment VS( float4 Pos : POSITION, float4 Col : COLOR )\n"
"{\n"
" Fragment f;\n"
" f.Pos = mul(Pos, g_mWorld);\n"
" f.Pos = mul(f.Pos, g_mView);\n"
" f.Pos = mul(f.Pos, g_mProjection);\n"
" f.Col = Col;\n"
" return f;\n"
"}\n"
"\n"
"float4 PS( Fragment f ) : SV_Target\n"
"{\n"
" return f.Col;\n"
"}\n"
"\n"
"technique10 Render\n"
"{\n"
" pass P0\n"
" {\n"
" SetVertexShader( CompileShader( vs_4_0, VS() ) );\n"
" SetGeometryShader( NULL );\n"
" SetPixelShader( CompileShader( ps_4_0, PS() ) );\n"
" }\n"
"}\n"
"\n";
ID3D10Buffer *g_pVB = NULL; // Buffer to hold vertices
struct cudaGraphicsResource *cuda_VB_resource; // handles D3D10-CUDA exchange
// testing/tracing function used pervasively in tests. if the condition is
// unsatisfied then spew and fail the function immediately (doing no cleanup)
#define AssertOrQuit(x) \
if (!(x)) { \
fprintf(stdout, "Assert unsatisfied in %s at %s:%d\n", __FUNCTION__, \
__FILE__, __LINE__); \
return 1; \
}
// A structure for our custom vertex type
struct CUSTOMVERTEX {
FLOAT x, y, z; // The untransformed, 3D position for the vertex
DWORD color; // The vertex color
};
const unsigned int g_WindowWidth = 1024;
const unsigned int g_WindowHeight = 1024;
const unsigned int g_MeshWidth = 512;
const unsigned int g_MeshHeight = 512;
const unsigned int g_NumVertices = g_MeshWidth * g_MeshHeight;
bool g_bPassed = true;
int g_iFrameToCompare = 10;
int *pArgc = NULL;
char **pArgv = NULL;
float anim;
//-----------------------------------------------------------------------------
// Forward declarations
//-----------------------------------------------------------------------------
void runTest(int argc, char **argv, char *ref_file);
void runCuda();
bool SaveResult(int argc, char **argv);
HRESULT InitD3D(HWND hWnd);
HRESULT InitGeometry();
VOID Cleanup();
VOID SetupMatrices();
VOID Render();
LRESULT WINAPI MsgProc(HWND hWnd, UINT msg, WPARAM wParam, LPARAM lParam);
// CUDA/D3D10 kernel
extern "C" void simpleD3DKernel(float4 *pos, unsigned int width,
unsigned int height, float time);
#define NAME_LEN 512
bool findCUDADevice() {
int nGraphicsGPU = 0;
int deviceCount = 0;
bool bFoundGraphics = false;
char devname[NAME_LEN];
// This function call returns 0 if there are no CUDA capable devices.
cudaError_t error_id = cudaGetDeviceCount(&deviceCount);
if (error_id != cudaSuccess) {
printf("cudaGetDeviceCount returned %d\n-> %s\n", (int)error_id,
cudaGetErrorString(error_id));
exit(EXIT_FAILURE);
}
if (deviceCount == 0) {
printf("> There are no device(s) supporting CUDA\n");
return false;
} else {
printf("> Found %d CUDA Capable Device(s)\n", deviceCount);
}
// Get CUDA device properties
cudaDeviceProp deviceProp;
for (int dev = 0; dev < deviceCount; ++dev) {
cudaGetDeviceProperties(&deviceProp, dev);
STRCPY(devname, NAME_LEN, deviceProp.name);
printf("> GPU %d: %s\n", dev, devname);
}
return true;
}
bool findDXDevice(char *dev_name) {
HRESULT hr = S_OK;
cudaError cuStatus;
// Iterate through the candidate adapters
IDXGIFactory *pFactory;
hr = sFnPtr_CreateDXGIFactory(__uuidof(IDXGIFactory), (void **)(&pFactory));
if (!SUCCEEDED(hr)) {
printf("> No DXGI Factory created.\n");
return false;
}
UINT adapter = 0;
for (; !g_pCudaCapableAdapter; ++adapter) {
// Get a candidate DXGI adapter
IDXGIAdapter *pAdapter = NULL;
hr = pFactory->EnumAdapters(adapter, &pAdapter);
if (FAILED(hr)) {
break; // no compatible adapters found
}
// Query to see if there exists a corresponding compute device
int cuDevice;
cuStatus = cudaD3D10GetDevice(&cuDevice, pAdapter);
// This prints and resets the cudaError to cudaSuccess
printLastCudaError("cudaD3D10GetDevice failed");
if (cudaSuccess == cuStatus) {
// If so, mark it as the one against which to create our d3d10 device
g_pCudaCapableAdapter = pAdapter;
g_pCudaCapableAdapter->AddRef();
}
pAdapter->Release();
}
printf("> Found %d D3D10 Adapater(s).\n", (int)adapter);
pFactory->Release();
if (!g_pCudaCapableAdapter) {
printf("> Found 0 D3D10 Adapater(s) /w Compute capability.\n");
return false;
}
DXGI_ADAPTER_DESC adapterDesc;
g_pCudaCapableAdapter->GetDesc(&adapterDesc);
wcstombs(dev_name, adapterDesc.Description, 128);
printf("> Found 1 D3D10 Adapater(s) /w Compute capability.\n");
printf("> %s\n", dev_name);
return true;
}
////////////////////////////////////////////////////////////////////////////////
// Program main
////////////////////////////////////////////////////////////////////////////////
int main(int argc, char **argv) {
char device_name[256];
char *ref_file = NULL;
pArgc = &argc;
pArgv = argv;
printf("> %s starting...\n", sSDKSample);
if (!findCUDADevice()) { // Search for CUDA GPU
printf("> CUDA Device NOT found on \"%s\".. Exiting.\n", device_name);
exit(EXIT_SUCCESS);
}
// Search for D3D API (locate drivers, does not mean device is found)
if (!dynlinkLoadD3D10API()) {
printf("> D3D10 API libraries NOT found on.. Exiting.\n");
dynlinkUnloadD3D10API();
exit(EXIT_SUCCESS);
}
if (!findDXDevice(device_name)) { // Search for D3D Hardware Device
printf("> D3D10 Graphics Device NOT found.. Exiting.\n");
dynlinkUnloadD3D10API();
exit(EXIT_SUCCESS);
}
if (argc > 1) {
if (checkCmdLineFlag(argc, (const char **)argv, "file")) {
getCmdLineArgumentString(argc, (const char **)argv, "file",
(char **)&ref_file);
}
}
runTest(argc, argv, ref_file);
//
// and exit
//
printf("%s running on %s exiting...\n", sSDKSample, device_name);
printf("%s sample finished returned: %s\n", sSDKSample,
(g_bPassed ? "OK" : "ERROR!"));
exit(g_bPassed ? EXIT_SUCCESS : EXIT_FAILURE);
}
////////////////////////////////////////////////////////////////////////////////
//! Run a simple test for CUDA
////////////////////////////////////////////////////////////////////////////////
void runTest(int argc, char **argv, char *ref_file) {
// Register the window class
WNDCLASSEX wc = {sizeof(WNDCLASSEX), CS_CLASSDC, MsgProc, 0L, 0L,
GetModuleHandle(NULL), NULL, NULL, NULL, NULL,
"CUDA/D3D10 simpleD3D10", NULL};
RegisterClassEx(&wc);
// Create the application's window
int xBorder = ::GetSystemMetrics(SM_CXSIZEFRAME);
int yMenu = ::GetSystemMetrics(SM_CYMENU);
int yBorder = ::GetSystemMetrics(SM_CYSIZEFRAME);
HWND hWnd = CreateWindow(
wc.lpszClassName, "CUDA/D3D10 simpleD3D10", WS_OVERLAPPEDWINDOW, 0, 0,
g_WindowWidth + 2 * xBorder, g_WindowHeight + 2 * yBorder + yMenu, NULL,
NULL, wc.hInstance, NULL);
// Initialize Direct3D
if (SUCCEEDED(InitD3D(hWnd))) {
// Create the scene geometry
if (SUCCEEDED(InitGeometry())) {
// Initialize interoperability between CUDA and Direct3D
// Register vertex buffer with CUDA
// DEPRECATED: cudaD3D10RegisterResource(g_pVB,
// cudaD3D10RegisterFlagsNone);
cudaGraphicsD3D10RegisterResource(&cuda_VB_resource, g_pVB,
cudaD3D10RegisterFlagsNone);
getLastCudaError("cudaGraphicsD3D10RegisterResource (g_pVB) failed");
// Initialize vertex buffer with CUDA
runCuda();
// Save result
SaveResult(argc, argv);
// Show the window
ShowWindow(hWnd, SW_SHOWDEFAULT);
UpdateWindow(hWnd);
// Enter the message loop
MSG msg;
ZeroMemory(&msg, sizeof(msg));
while (msg.message != WM_QUIT) {
if (PeekMessage(&msg, NULL, 0U, 0U, PM_REMOVE)) {
TranslateMessage(&msg);
DispatchMessage(&msg);
} else {
Render();
if (ref_file != NULL) {
for (int count = 0; count < g_iFrameToCompare; count++) {
Render();
}
const char *cur_image_path = "simpleD3D10.ppm";
// Save a reference of our current test run image
CheckRenderD3D10::ActiveRenderTargetToPPM(g_pd3dDevice,
cur_image_path);
// compare to offical reference image, printing PASS or FAIL.
g_bPassed = CheckRenderD3D10::PPMvsPPM(cur_image_path, ref_file,
argv[0], MAX_EPSILON, 0.15f);
Cleanup();
PostQuitMessage(0);
}
}
}
}
}
// Release D3D Library (after message loop)
dynlinkUnloadD3D10API();
UnregisterClass(wc.lpszClassName, wc.hInstance);
}
////////////////////////////////////////////////////////////////////////////////
//! Run the Cuda part of the computation
////////////////////////////////////////////////////////////////////////////////
void runCuda() {
// Map vertex buffer to Cuda
float4 *d_ptr;
// CUDA Map call to the Vertex Buffer and return a pointer
// DEPRECATED: cudaD3D10MapResources(1, (ID3D10Resource **)&g_pVB);
checkCudaErrors(cudaGraphicsMapResources(1, &cuda_VB_resource, 0));
getLastCudaError("cudaGraphicsMapResources failed");
// DEPRECATED: cudaD3D10ResourceGetMappedPointer( (void **)&dptr, g_pVB, 0);
size_t num_bytes;
checkCudaErrors(cudaGraphicsResourceGetMappedPointer(
(void **)&d_ptr, &num_bytes, cuda_VB_resource));
getLastCudaError("cudaGraphicsResourceGetMappedPointer failed");
// Execute kernel
simpleD3DKernel(d_ptr, g_MeshWidth, g_MeshHeight, anim);
// CUDA Map Unmap vertex buffer
// DEPRECATED: cudaD3D10UnmapResources(1, (ID3D10Resource **)&g_pVB);
checkCudaErrors(cudaGraphicsUnmapResources(1, &cuda_VB_resource, 0));
getLastCudaError("cudaGraphicsUnmapResource failed");
}
////////////////////////////////////////////////////////////////////////////////
//! Check if the result is correct or write data to file for external
//! regression testing
////////////////////////////////////////////////////////////////////////////////
bool SaveResult(int argc, char **argv) {
// Map vertex buffer
float *data;
if (FAILED(g_pVB->Map(D3D10_MAP_READ, 0,
(void **)&data))) // Lock(0, 0, (void**)&data, 0)))
return false;
// Unmap
g_pVB->Unmap();
// Save result
if (checkCmdLineFlag(argc, (const char **)argv, "regression")) {
// write file for regression test
sdkWriteFile<float>("./data/regression.dat", data, sizeof(CUSTOMVERTEX),
0.0f, false);
}
return true;
}
//-----------------------------------------------------------------------------
// Name: InitD3D()
// Desc: Initializes Direct3D
//-----------------------------------------------------------------------------
HRESULT InitD3D(HWND hWnd) {
// Set up the structure used to create the device and swapchain
DXGI_SWAP_CHAIN_DESC sd;
ZeroMemory(&sd, sizeof(sd));
sd.BufferCount = 1;
sd.BufferDesc.Width = g_WindowWidth;
sd.BufferDesc.Height = g_WindowHeight;
sd.BufferDesc.Format = DXGI_FORMAT_R8G8B8A8_UNORM;
sd.BufferDesc.RefreshRate.Numerator = 60;
sd.BufferDesc.RefreshRate.Denominator = 1;
sd.BufferUsage = DXGI_USAGE_RENDER_TARGET_OUTPUT;
sd.OutputWindow = hWnd;
sd.SampleDesc.Count = 1;
sd.SampleDesc.Quality = 0;
sd.Windowed = TRUE;
// Create device and swapchain
HRESULT hr = sFnPtr_D3D10CreateDeviceAndSwapChain(
g_pCudaCapableAdapter, D3D10_DRIVER_TYPE_HARDWARE, NULL, 0,
D3D10_SDK_VERSION, &sd, &g_pSwapChain, &g_pd3dDevice);
AssertOrQuit(SUCCEEDED(hr));
g_pCudaCapableAdapter->Release();
// Create a render target view of the swapchain
ID3D10Texture2D *pBuffer;
hr =
g_pSwapChain->GetBuffer(0, __uuidof(ID3D10Texture2D), (LPVOID *)&pBuffer);
AssertOrQuit(SUCCEEDED(hr));
hr = g_pd3dDevice->CreateRenderTargetView(pBuffer, NULL, &g_pSwapChainRTV);
AssertOrQuit(SUCCEEDED(hr));
pBuffer->Release();
g_pd3dDevice->OMSetRenderTargets(1, &g_pSwapChainRTV, NULL);
// Setup the viewport
D3D10_VIEWPORT vp;
vp.Width = g_WindowWidth;
vp.Height = g_WindowHeight;
vp.MinDepth = 0.0f;
vp.MaxDepth = 1.0f;
vp.TopLeftX = 0;
vp.TopLeftY = 0;
g_pd3dDevice->RSSetViewports(1, &vp);
// Setup the effect
{
ID3D10Blob *pCompiledEffect;
hr = sFnPtr_D3D10CompileEffectFromMemory((void *)g_simpleEffectSrc,
sizeof(g_simpleEffectSrc), NULL,
NULL, // pDefines
NULL, // pIncludes
0, // HLSL flags
0, // FXFlags
&pCompiledEffect, NULL);
AssertOrQuit(SUCCEEDED(hr));
hr = sFnPtr_D3D10CreateEffectFromMemory(
pCompiledEffect->GetBufferPointer(), pCompiledEffect->GetBufferSize(),
0, // FXFlags
g_pd3dDevice, NULL, &g_pSimpleEffect);
pCompiledEffect->Release();
g_pSimpleTechnique = g_pSimpleEffect->GetTechniqueByName("Render");
// g_pmWorldViewProjection =
// g_pSimpleEffect->GetVariableByName("g_mWorldViewProjection")->AsMatrix();
g_pmWorld = g_pSimpleEffect->GetVariableByName("g_mWorld")->AsMatrix();
g_pmView = g_pSimpleEffect->GetVariableByName("g_mView")->AsMatrix();
g_pmProjection =
g_pSimpleEffect->GetVariableByName("g_mProjection")->AsMatrix();
// Define the input layout
D3D10_INPUT_ELEMENT_DESC layout[] = {
{"POSITION", 0, DXGI_FORMAT_R32G32B32_FLOAT, 0, 0,
D3D10_INPUT_PER_VERTEX_DATA, 0},
{"COLOR", 0, DXGI_FORMAT_R8G8B8A8_UNORM, 0, 12,
D3D10_INPUT_PER_VERTEX_DATA, 0},
};
UINT numElements = sizeof(layout) / sizeof(layout[0]);
// Create the input layout
D3D10_PASS_DESC PassDesc;
g_pSimpleTechnique->GetPassByIndex(0)->GetDesc(&PassDesc);
hr = g_pd3dDevice->CreateInputLayout(
layout, numElements, PassDesc.pIAInputSignature,
PassDesc.IAInputSignatureSize, &g_pInputLayout);
AssertOrQuit(SUCCEEDED(hr));
// Setup Input Layout, apply effect and draw points
g_pd3dDevice->IASetInputLayout(g_pInputLayout);
g_pSimpleTechnique->GetPassByIndex(0)->Apply(0);
g_pd3dDevice->IASetPrimitiveTopology(D3D10_PRIMITIVE_TOPOLOGY_POINTLIST);
}
return S_OK;
}
//-----------------------------------------------------------------------------
// Name: InitGeometry()
// Desc: Creates the scene geometry
//-----------------------------------------------------------------------------
HRESULT InitGeometry() {
// Setup buffer desc
D3D10_BUFFER_DESC bufferDesc;
bufferDesc.Usage = D3D10_USAGE_DEFAULT;
bufferDesc.ByteWidth = sizeof(CUSTOMVERTEX) * g_NumVertices;
bufferDesc.BindFlags = D3D10_BIND_VERTEX_BUFFER;
bufferDesc.CPUAccessFlags = 0;
bufferDesc.MiscFlags = 0;
// Create the buffer, no need for sub resource data struct since everything
// will be defined from cuda
if (FAILED(g_pd3dDevice->CreateBuffer(&bufferDesc, NULL, &g_pVB)))
return E_FAIL;
return S_OK;
}
//-----------------------------------------------------------------------------
// Name: Cleanup()
// Desc: Releases all previously initialized objects
//-----------------------------------------------------------------------------
VOID Cleanup() {
if (g_pVB != NULL) {
// Unregister vertex buffer
// DEPRECATED: checkCudaErrors(cudaD3D10UnregisterResource(g_pVB));
cudaGraphicsUnregisterResource(cuda_VB_resource);
getLastCudaError("cudaGraphicsUnregisterResource failed");
g_pVB->Release();
}
if (g_pInputLayout != NULL) g_pInputLayout->Release();
if (g_pSimpleEffect != NULL) g_pSimpleEffect->Release();
if (g_pSwapChainRTV != NULL) g_pSwapChainRTV->Release();
if (g_pSwapChain != NULL) g_pSwapChain->Release();
if (g_pd3dDevice != NULL) g_pd3dDevice->Release();
}
//-----------------------------------------------------------------------------
// Name: SetupMatrices()
// Desc: Sets up the world, view, and projection transform matrices.
//-----------------------------------------------------------------------------
VOID SetupMatrices() {
XMMATRIX matWorld;
matWorld = XMMatrixIdentity();
XMVECTOR vEyePt = {0.0f, 3.0f, -2.0f};
XMVECTOR vLookatPt = {0.0f, 0.0f, 0.0f};
XMVECTOR vUpVec = {0.0f, 1.0f, 0.0f};
XMMATRIX matView;
matView = XMMatrixLookAtLH(vEyePt, vLookatPt, vUpVec);
XMMATRIX matProj;
matProj = XMMatrixPerspectiveFovLH((float)XM_PI / 4.f, 1.0f, 0.01f, 10.0f);
g_pmWorld->SetMatrix((float *)&matWorld);
g_pmView->SetMatrix((float *)&matView);
g_pmProjection->SetMatrix((float *)&matProj);
}
//-----------------------------------------------------------------------------
// Name: Render()
// Desc: Draws the scene
//-----------------------------------------------------------------------------
VOID Render() {
// Clear the backbuffer to a black color
float ClearColor[4] = {0, 0, 0, 0};
g_pd3dDevice->ClearRenderTargetView(g_pSwapChainRTV, ClearColor);
// Run CUDA to update vertex positions
runCuda();
// Draw frame
{
// Setup the world, view, and projection matrices
SetupMatrices();
// Render the vertex buffer contents
UINT stride = sizeof(CUSTOMVERTEX);
UINT offset = 0;
g_pd3dDevice->IASetVertexBuffers(0, 1, &g_pVB, &stride, &offset);
g_pSimpleTechnique->GetPassByIndex(0)->Apply(0);
g_pd3dDevice->Draw(g_NumVertices, 0);
}
// Present the backbuffer contents to the display
g_pSwapChain->Present(0, 0);
anim += 0.01f;
}
//-----------------------------------------------------------------------------
// Name: MsgProc()
// Desc: The window's message handler
//-----------------------------------------------------------------------------
LRESULT WINAPI MsgProc(HWND hWnd, UINT msg, WPARAM wParam, LPARAM lParam) {
switch (msg) {
case WM_DESTROY:
case WM_KEYDOWN:
if (msg != WM_KEYDOWN || wParam == 27) {
Cleanup();
PostQuitMessage(0);
return 0;
}
}
return DefWindowProc(hWnd, msg, wParam, lParam);
}
|