diff --git a/README.md b/README.md index d63a6a1..cfef8c6 100644 --- a/README.md +++ b/README.md @@ -1,11 +1,31 @@ **University of Pennsylvania, CIS 565: GPU Programming and Architecture, Project 1 - Flocking** -* (TODO) YOUR NAME HERE - * (TODO) [LinkedIn](), [personal website](), [twitter](), etc. -* Tested on: (TODO) Windows 22, i7-2222 @ 2.22GHz 22GB, GTX 222 222MB (Moore 2222 Lab) +* Sydney Miller + * [LinkedIn](https://www.linkedin.com/in/sydney-miller-upenn/) +* Tested on: GTX 222 222MB (CETS Virtual Lab) -### (TODO: Your README) -Include screenshots, analysis, etc. (Remember, this is public, so don't put -anything here that you don't want to share with the world.) +### README + +### Boids +![boids](images/BoidsScreenShot.png) +![boidsGif](images/boids.gif) + +### Performance Analysis + +#### For each implementation, how does changing the number of boids affect performance? Why do you think this is? +My hypothesis was that performance would decrease as the number of boids increased. I saw that the performance decreased when the number of boids increased. I beleive this happened because there is more computation required when the number of boids is increased, so the program will not run as fast. +![boids](images/FPSvsNumberOfBoids.png) + + +#### For each implementation, how does changing the block count and block size affect performance? Why do you think this is? +My hypothesis was that the larger block sizes would increase performance, however the performance remained almost the same as the block size increased. This could be because the block size is considered when defining the fullBlocksPerGrid dimension, so the performance remains relatively constant with the tested block sizes. +![boids](images/FPSvsBlockSize.png) + + +#### Did you experience any performance improvements with the more coherent uniform grid? Was this the outcome you expected? Why or why not? +Yes, I experienced better performance with the coherent uniform grid, which is what, which is what I expected to happen. I expected the performance to be better because the scattered grid required an additional memory look up whereas the coherent grid uses the same index as the grid indices. The additional memory look up slows down performance. + +#### Did changing cell width and checking 27 vs 8 neighboring cells affect performance? Why or why not? +It slightly changed the performance, but not by a significant amount. I expected the performance to be better for 8 neighboring cells compared to 27 neighboring cells. For Naive, 8 neighboring cells was 480 FPS and 27 neighboring cells was 480 FPS. For Scattered, 8 neighboring cells was 512 FPS and 27 neighboring cells was 550 FPS. For Naive, 8 neighboring cells was 660 FPS and 27 neighboring cells was 650 FPS. This could be because 8 and 27 are relatively small constant numbers, and since these calculations are done in parallel the difference isn't that much greater. Each of them is still iterating over a 3D space, one is just slightly larger than the other. diff --git a/images/BoidsScreenShot.png b/images/BoidsScreenShot.png new file mode 100644 index 0000000..a7fc2ce Binary files /dev/null and b/images/BoidsScreenShot.png differ diff --git a/images/FPSvsBlockSize.png b/images/FPSvsBlockSize.png new file mode 100644 index 0000000..e688163 Binary files /dev/null and b/images/FPSvsBlockSize.png differ diff --git a/images/FPSvsNumberOfBoids.png b/images/FPSvsNumberOfBoids.png new file mode 100644 index 0000000..38b68db Binary files /dev/null and b/images/FPSvsNumberOfBoids.png differ diff --git a/images/boids.gif b/images/boids.gif new file mode 100644 index 0000000..5b0c908 Binary files /dev/null and b/images/boids.gif differ diff --git a/src/kernel.cu b/src/kernel.cu index 74dffcb..9b90bf7 100644 --- a/src/kernel.cu +++ b/src/kernel.cu @@ -20,15 +20,15 @@ /** * Check for CUDA errors; print and exit if there was a problem. */ -void checkCUDAError(const char *msg, int line = -1) { - cudaError_t err = cudaGetLastError(); - if (cudaSuccess != err) { - if (line >= 0) { - fprintf(stderr, "Line %d: ", line); - } - fprintf(stderr, "Cuda error: %s: %s.\n", msg, cudaGetErrorString(err)); - exit(EXIT_FAILURE); - } +void checkCUDAError(const char* msg, int line = -1) { + cudaError_t err = cudaGetLastError(); + if (cudaSuccess != err) { + if (line >= 0) { + fprintf(stderr, "Line %d: ", line); + } + fprintf(stderr, "Cuda error: %s: %s.\n", msg, cudaGetErrorString(err)); + exit(EXIT_FAILURE); + } } @@ -66,25 +66,27 @@ dim3 threadsPerBlock(blockSize); // Consider why you would need two velocity buffers in a simulation where each // boid cares about its neighbors' velocities. // These are called ping-pong buffers. -glm::vec3 *dev_pos; -glm::vec3 *dev_vel1; -glm::vec3 *dev_vel2; +glm::vec3* dev_pos; +glm::vec3* dev_vel1; +glm::vec3* dev_vel2; // LOOK-2.1 - these are NOT allocated for you. You'll have to set up the thrust // pointers on your own too. // For efficient sorting and the uniform grid. These should always be parallel. -int *dev_particleArrayIndices; // What index in dev_pos and dev_velX represents this particle? -int *dev_particleGridIndices; // What grid cell is this particle in? +int* dev_particleArrayIndices; // What index in dev_pos and dev_velX represents this particle? +int* dev_particleGridIndices; // What grid cell is this particle in? // needed for use with thrust thrust::device_ptr dev_thrust_particleArrayIndices; thrust::device_ptr dev_thrust_particleGridIndices; -int *dev_gridCellStartIndices; // What part of dev_particleArrayIndices belongs -int *dev_gridCellEndIndices; // to this cell? +int* dev_gridCellStartIndices; // What part of dev_particleArrayIndices belongs +int* dev_gridCellEndIndices; // to this cell? // TODO-2.3 - consider what additional buffers you might need to reshuffle // the position and velocity data to be coherent within cells. +glm::vec3* dev_pos_rearrange; +glm::vec3* dev_vel1_rearrange; // LOOK-2.1 - Grid parameters based on simulation parameters. // These are automatically computed for you in Boids::initSimulation @@ -99,13 +101,13 @@ glm::vec3 gridMinimum; ******************/ __host__ __device__ unsigned int hash(unsigned int a) { - a = (a + 0x7ed55d16) + (a << 12); - a = (a ^ 0xc761c23c) ^ (a >> 19); - a = (a + 0x165667b1) + (a << 5); - a = (a + 0xd3a2646c) ^ (a << 9); - a = (a + 0xfd7046c5) + (a << 3); - a = (a ^ 0xb55a4f09) ^ (a >> 16); - return a; + a = (a + 0x7ed55d16) + (a << 12); + a = (a ^ 0xc761c23c) ^ (a >> 19); + a = (a + 0x165667b1) + (a << 5); + a = (a + 0xd3a2646c) ^ (a << 9); + a = (a + 0xfd7046c5) + (a << 3); + a = (a ^ 0xb55a4f09) ^ (a >> 16); + return a; } /** @@ -113,63 +115,82 @@ __host__ __device__ unsigned int hash(unsigned int a) { * Function for generating a random vec3. */ __host__ __device__ glm::vec3 generateRandomVec3(float time, int index) { - thrust::default_random_engine rng(hash((int)(index * time))); - thrust::uniform_real_distribution unitDistrib(-1, 1); + thrust::default_random_engine rng(hash((int)(index * time))); + thrust::uniform_real_distribution unitDistrib(-1, 1); - return glm::vec3((float)unitDistrib(rng), (float)unitDistrib(rng), (float)unitDistrib(rng)); + return glm::vec3((float)unitDistrib(rng), (float)unitDistrib(rng), (float)unitDistrib(rng)); } /** * LOOK-1.2 - This is a basic CUDA kernel. * CUDA kernel for generating boids with a specified mass randomly around the star. */ -__global__ void kernGenerateRandomPosArray(int time, int N, glm::vec3 * arr, float scale) { - int index = (blockIdx.x * blockDim.x) + threadIdx.x; - if (index < N) { - glm::vec3 rand = generateRandomVec3(time, index); - arr[index].x = scale * rand.x; - arr[index].y = scale * rand.y; - arr[index].z = scale * rand.z; - } +__global__ void kernGenerateRandomPosArray(int time, int N, glm::vec3* arr, float scale) { + int index = (blockIdx.x * blockDim.x) + threadIdx.x; + if (index < N) { + glm::vec3 rand = generateRandomVec3(time, index); + arr[index].x = scale * rand.x; + arr[index].y = scale * rand.y; + arr[index].z = scale * rand.z; + } } /** * Initialize memory, update some globals */ void Boids::initSimulation(int N) { - numObjects = N; - dim3 fullBlocksPerGrid((N + blockSize - 1) / blockSize); - - // LOOK-1.2 - This is basic CUDA memory management and error checking. - // Don't forget to cudaFree in Boids::endSimulation. - cudaMalloc((void**)&dev_pos, N * sizeof(glm::vec3)); - checkCUDAErrorWithLine("cudaMalloc dev_pos failed!"); - - cudaMalloc((void**)&dev_vel1, N * sizeof(glm::vec3)); - checkCUDAErrorWithLine("cudaMalloc dev_vel1 failed!"); - - cudaMalloc((void**)&dev_vel2, N * sizeof(glm::vec3)); - checkCUDAErrorWithLine("cudaMalloc dev_vel2 failed!"); - - // LOOK-1.2 - This is a typical CUDA kernel invocation. - kernGenerateRandomPosArray<<>>(1, numObjects, - dev_pos, scene_scale); - checkCUDAErrorWithLine("kernGenerateRandomPosArray failed!"); - - // LOOK-2.1 computing grid params - gridCellWidth = 2.0f * std::max(std::max(rule1Distance, rule2Distance), rule3Distance); - int halfSideCount = (int)(scene_scale / gridCellWidth) + 1; - gridSideCount = 2 * halfSideCount; - - gridCellCount = gridSideCount * gridSideCount * gridSideCount; - gridInverseCellWidth = 1.0f / gridCellWidth; - float halfGridWidth = gridCellWidth * halfSideCount; - gridMinimum.x -= halfGridWidth; - gridMinimum.y -= halfGridWidth; - gridMinimum.z -= halfGridWidth; - - // TODO-2.1 TODO-2.3 - Allocate additional buffers here. - cudaDeviceSynchronize(); + numObjects = N; + dim3 fullBlocksPerGrid((N + blockSize - 1) / blockSize); + + // LOOK-1.2 - This is basic CUDA memory management and error checking. + // Don't forget to cudaFree in Boids::endSimulation. + cudaMalloc((void**)&dev_pos, N * sizeof(glm::vec3)); + checkCUDAErrorWithLine("cudaMalloc dev_pos failed!"); + + cudaMalloc((void**)&dev_vel1, N * sizeof(glm::vec3)); + checkCUDAErrorWithLine("cudaMalloc dev_vel1 failed!"); + + cudaMalloc((void**)&dev_vel2, N * sizeof(glm::vec3)); + checkCUDAErrorWithLine("cudaMalloc dev_vel2 failed!"); + + // LOOK-1.2 - This is a typical CUDA kernel invocation. + kernGenerateRandomPosArray << > > (1, numObjects, + dev_pos, scene_scale); + checkCUDAErrorWithLine("kernGenerateRandomPosArray failed!"); + + // LOOK-2.1 computing grid params + gridCellWidth = 2.0f * std::max(std::max(rule1Distance, rule2Distance), rule3Distance); + int halfSideCount = (int)(scene_scale / gridCellWidth) + 1; + gridSideCount = 2 * halfSideCount; + + gridCellCount = gridSideCount * gridSideCount * gridSideCount; + gridInverseCellWidth = 1.0f / gridCellWidth; + float halfGridWidth = gridCellWidth * halfSideCount; + gridMinimum.x -= halfGridWidth; + gridMinimum.y -= halfGridWidth; + gridMinimum.z -= halfGridWidth; + + // TODO-2.1 TODO-2.3 - Allocate additional buffers here. + cudaMalloc((void**)&dev_particleArrayIndices, N * sizeof(int)); + checkCUDAErrorWithLine("cudaMalloc dev_particleArrayIndices failed!"); + + cudaMalloc((void**)&dev_particleGridIndices, N * sizeof(int)); + checkCUDAErrorWithLine("cudaMalloc dev_particleGridIndices failed!"); + + cudaMalloc((void**)&dev_gridCellStartIndices, gridCellCount * sizeof(int)); + checkCUDAErrorWithLine("cudaMalloc dev_gridCellStartIndices failed!"); + + cudaMalloc((void**)&dev_gridCellEndIndices, gridCellCount * sizeof(int)); + checkCUDAErrorWithLine("cudaMalloc dev_gridCellEndIndices failed!"); + + //2.3 + cudaMalloc((void**)&dev_pos_rearrange, N * sizeof(glm::vec3)); + checkCUDAErrorWithLine("cudaMalloc dev_pos_rearrange failed!"); + + cudaMalloc((void**)&dev_vel1_rearrange, N * sizeof(glm::vec3)); + checkCUDAErrorWithLine("cudaMalloc dev_vel1_rearrange failed!"); + + cudaDeviceSynchronize(); } @@ -180,42 +201,42 @@ void Boids::initSimulation(int N) { /** * Copy the boid positions into the VBO so that they can be drawn by OpenGL. */ -__global__ void kernCopyPositionsToVBO(int N, glm::vec3 *pos, float *vbo, float s_scale) { - int index = threadIdx.x + (blockIdx.x * blockDim.x); +__global__ void kernCopyPositionsToVBO(int N, glm::vec3* pos, float* vbo, float s_scale) { + int index = threadIdx.x + (blockIdx.x * blockDim.x); - float c_scale = -1.0f / s_scale; + float c_scale = -1.0f / s_scale; - if (index < N) { - vbo[4 * index + 0] = pos[index].x * c_scale; - vbo[4 * index + 1] = pos[index].y * c_scale; - vbo[4 * index + 2] = pos[index].z * c_scale; - vbo[4 * index + 3] = 1.0f; - } + if (index < N) { + vbo[4 * index + 0] = pos[index].x * c_scale; + vbo[4 * index + 1] = pos[index].y * c_scale; + vbo[4 * index + 2] = pos[index].z * c_scale; + vbo[4 * index + 3] = 1.0f; + } } -__global__ void kernCopyVelocitiesToVBO(int N, glm::vec3 *vel, float *vbo, float s_scale) { - int index = threadIdx.x + (blockIdx.x * blockDim.x); +__global__ void kernCopyVelocitiesToVBO(int N, glm::vec3* vel, float* vbo, float s_scale) { + int index = threadIdx.x + (blockIdx.x * blockDim.x); - if (index < N) { - vbo[4 * index + 0] = vel[index].x + 0.3f; - vbo[4 * index + 1] = vel[index].y + 0.3f; - vbo[4 * index + 2] = vel[index].z + 0.3f; - vbo[4 * index + 3] = 1.0f; - } + if (index < N) { + vbo[4 * index + 0] = vel[index].x + 0.3f; + vbo[4 * index + 1] = vel[index].y + 0.3f; + vbo[4 * index + 2] = vel[index].z + 0.3f; + vbo[4 * index + 3] = 1.0f; + } } /** * Wrapper for call to the kernCopyboidsToVBO CUDA kernel. */ -void Boids::copyBoidsToVBO(float *vbodptr_positions, float *vbodptr_velocities) { - dim3 fullBlocksPerGrid((numObjects + blockSize - 1) / blockSize); +void Boids::copyBoidsToVBO(float* vbodptr_positions, float* vbodptr_velocities) { + dim3 fullBlocksPerGrid((numObjects + blockSize - 1) / blockSize); - kernCopyPositionsToVBO << > >(numObjects, dev_pos, vbodptr_positions, scene_scale); - kernCopyVelocitiesToVBO << > >(numObjects, dev_vel1, vbodptr_velocities, scene_scale); + kernCopyPositionsToVBO << > > (numObjects, dev_pos, vbodptr_positions, scene_scale); + kernCopyVelocitiesToVBO << > > (numObjects, dev_vel1, vbodptr_velocities, scene_scale); - checkCUDAErrorWithLine("copyBoidsToVBO failed!"); + checkCUDAErrorWithLine("copyBoidsToVBO failed!"); - cudaDeviceSynchronize(); + cudaDeviceSynchronize(); } @@ -229,47 +250,102 @@ void Boids::copyBoidsToVBO(float *vbodptr_positions, float *vbodptr_velocities) * Compute the new velocity on the body with index `iSelf` due to the `N` boids * in the `pos` and `vel` arrays. */ -__device__ glm::vec3 computeVelocityChange(int N, int iSelf, const glm::vec3 *pos, const glm::vec3 *vel) { - // Rule 1: boids fly towards their local perceived center of mass, which excludes themselves - // Rule 2: boids try to stay a distance d away from each other - // Rule 3: boids try to match the speed of surrounding boids - return glm::vec3(0.0f, 0.0f, 0.0f); +__device__ glm::vec3 computeVelocityChange(int N, int iSelf, const glm::vec3* pos, const glm::vec3* vel) { + glm::vec3 thisPos = pos[iSelf]; + + glm::vec3 center(0.f); + glm::vec3 separate(0.f); + glm::vec3 cohesion(0.f); + + float numNeighbors1 = 0; + float numNeighbors3 = 0; + + for (int i = 0; i < N; i++) { + if (i == iSelf) { + continue; + } + + glm::vec3 currPos = pos[i]; + glm::vec3 currVel = vel[i]; + float distance = glm::length(thisPos - currPos); + + // Rule 1: boids fly towards their local perceived center of mass, which excludes themselves + if (distance < rule1Distance) { + center += currPos; + numNeighbors1 += 1.f; + } + + // Rule 2: boids try to stay a distance d away from each other + if (distance < rule2Distance) { + separate -= currPos - thisPos; + } + + // Rule 3: boids try to match the speed of surrounding boids + if (distance < rule3Distance) { + cohesion += currVel; + numNeighbors3 += 1.f; + } + } + + glm::vec3 change(0.f); + + if (numNeighbors1 > 0) { + center /= numNeighbors1; + change += (center - thisPos) * rule1Scale; + } + + if (numNeighbors3 > 0) { + cohesion /= numNeighbors3; + change += cohesion * rule3Scale; + } + + change += separate * rule2Scale; + + return change; } /** * TODO-1.2 implement basic flocking * For each of the `N` bodies, update its position based on its current velocity. */ -__global__ void kernUpdateVelocityBruteForce(int N, glm::vec3 *pos, - glm::vec3 *vel1, glm::vec3 *vel2) { - // Compute a new velocity based on pos and vel1 - // Clamp the speed - // Record the new velocity into vel2. Question: why NOT vel1? +__global__ void kernUpdateVelocityBruteForce(int N, glm::vec3* pos, + glm::vec3* vel1, glm::vec3* vel2) { + // Compute a new velocity based on pos and vel1 + int index = threadIdx.x + (blockIdx.x * blockDim.x); + glm::vec3 newVel = vel1[index] + computeVelocityChange(N, index, pos, vel1); + + // Clamp the speed + if (glm::length(newVel) > maxSpeed) { + newVel = glm::normalize(newVel); + } + + // Record the new velocity into vel2. Question: why NOT vel1? + vel2[index] = newVel; } /** * LOOK-1.2 Since this is pretty trivial, we implemented it for you. * For each of the `N` bodies, update its position based on its current velocity. */ -__global__ void kernUpdatePos(int N, float dt, glm::vec3 *pos, glm::vec3 *vel) { - // Update position by velocity - int index = threadIdx.x + (blockIdx.x * blockDim.x); - if (index >= N) { - return; - } - glm::vec3 thisPos = pos[index]; - thisPos += vel[index] * dt; +__global__ void kernUpdatePos(int N, float dt, glm::vec3* pos, glm::vec3* vel) { + // Update position by velocity + int index = threadIdx.x + (blockIdx.x * blockDim.x); + if (index >= N) { + return; + } + glm::vec3 thisPos = pos[index]; + thisPos += vel[index] * dt; - // Wrap the boids around so we don't lose them - thisPos.x = thisPos.x < -scene_scale ? scene_scale : thisPos.x; - thisPos.y = thisPos.y < -scene_scale ? scene_scale : thisPos.y; - thisPos.z = thisPos.z < -scene_scale ? scene_scale : thisPos.z; + // Wrap the boids around so we don't lose them + thisPos.x = thisPos.x < -scene_scale ? scene_scale : thisPos.x; + thisPos.y = thisPos.y < -scene_scale ? scene_scale : thisPos.y; + thisPos.z = thisPos.z < -scene_scale ? scene_scale : thisPos.z; - thisPos.x = thisPos.x > scene_scale ? -scene_scale : thisPos.x; - thisPos.y = thisPos.y > scene_scale ? -scene_scale : thisPos.y; - thisPos.z = thisPos.z > scene_scale ? -scene_scale : thisPos.z; + thisPos.x = thisPos.x > scene_scale ? -scene_scale : thisPos.x; + thisPos.y = thisPos.y > scene_scale ? -scene_scale : thisPos.y; + thisPos.z = thisPos.z > scene_scale ? -scene_scale : thisPos.z; - pos[index] = thisPos; + pos[index] = thisPos; } // LOOK-2.1 Consider this method of computing a 1D index from a 3D grid index. @@ -279,179 +355,574 @@ __global__ void kernUpdatePos(int N, float dt, glm::vec3 *pos, glm::vec3 *vel) { // for(y) // for(z)? Or some other order? __device__ int gridIndex3Dto1D(int x, int y, int z, int gridResolution) { - return x + y * gridResolution + z * gridResolution * gridResolution; + return x + y * gridResolution + z * gridResolution * gridResolution; } __global__ void kernComputeIndices(int N, int gridResolution, - glm::vec3 gridMin, float inverseCellWidth, - glm::vec3 *pos, int *indices, int *gridIndices) { + glm::vec3 gridMin, float inverseCellWidth, + glm::vec3* pos, int* indices, int* gridIndices) { // TODO-2.1 // - Label each boid with the index of its grid cell. + int index = threadIdx.x + (blockIdx.x * blockDim.x); + if (index >= N) { + return; + } + + glm::vec3 currPos = pos[index]; + glm::vec3 gridCell = floor((currPos - gridMin) * inverseCellWidth); + int gridCellIndex = gridIndex3Dto1D(gridCell.x, gridCell.y, gridCell.z, gridResolution); + gridIndices[index] = gridCellIndex; + // - Set up a parallel array of integer indices as pointers to the actual // boid data in pos and vel1/vel2 + indices[index] = index; + gridIndices[index] = gridCellIndex; } // LOOK-2.1 Consider how this could be useful for indicating that a cell // does not enclose any boids -__global__ void kernResetIntBuffer(int N, int *intBuffer, int value) { - int index = (blockIdx.x * blockDim.x) + threadIdx.x; - if (index < N) { - intBuffer[index] = value; - } +__global__ void kernResetIntBuffer(int N, int* intBuffer, int value) { + int index = (blockIdx.x * blockDim.x) + threadIdx.x; + if (index < N) { + intBuffer[index] = value; + } +} + +__global__ void kernRearrangePosAndVel(int N, int* particleArrayIndices, + glm::vec3* pos, glm::vec3* vel, glm::vec3* pos_rearrange, glm::vec3* vel_rearrange) { + // TODO-2.1 + // Identify the start point of each cell in the gridIndices array. + int index = threadIdx.x + (blockIdx.x * blockDim.x); + if (index >= N) { + return; + } + + int boidIndex = particleArrayIndices[index]; + pos_rearrange[index] = pos[boidIndex]; + vel_rearrange[index] = vel[boidIndex]; +} + +__global__ void kernIdentifyCellStartEnd(int N, int* particleGridIndices, + int* gridCellStartIndices, int* gridCellEndIndices) { + // TODO-2.1 + // Identify the start point of each cell in the gridIndices array. + int index = threadIdx.x + (blockIdx.x * blockDim.x); + if (index >= N) { + return; + } + + int start = -1; + int end = -1; + int gridIndex = particleGridIndices[index]; + + for (int i = 0; i < N; i++) { + if (particleGridIndices[i] == gridIndex) { + start = i; + while (i < N && particleGridIndices[i] == gridIndex) { + i++; + } + end = i - 1; + break; + } + } + gridCellStartIndices[gridIndex] = start; + gridCellEndIndices[gridIndex] = end; +} + +__device__ glm::vec3 computeVelocityChangeGivenCell(int N, int gridResolution, int gridCellIndex, int iSelf, + int* gridCellStartIndices, int* gridCellEndIndices, int* particleArrayIndices, glm::vec3* pos, glm::vec3* vel) { + if (gridCellIndex < 0 || gridCellIndex >= gridResolution * gridResolution * gridResolution) { + return glm::vec3(0.f); + } + else { + int start = gridCellStartIndices[gridCellIndex]; + int end = gridCellEndIndices[gridCellIndex]; + + // no boids in grid cell + if (start < 0) { + return glm::vec3(0.f); + } + + glm::vec3 thisPos = pos[iSelf]; + + glm::vec3 center(0.f); + glm::vec3 separate(0.f); + glm::vec3 cohesion(0.f); + + float numNeighbors1 = 0; + float numNeighbors3 = 0; + + for (int i = start; i <= end; i++) { + int location = particleArrayIndices[i]; + if (location == iSelf) { + continue; + } + + glm::vec3 currPos = pos[location]; + glm::vec3 currVel = vel[location]; + + float distance = glm::length(thisPos - currPos); + + // Rule 1: boids fly towards their local perceived center of mass, which excludes themselves + if (distance < rule1Distance) { + center += currPos; + numNeighbors1 += 1.f; + } + + // Rule 2: boids try to stay a distance d away from each other + if (distance < rule2Distance) { + separate -= currPos - thisPos; + } + + // Rule 3: boids try to match the speed of surrounding boids + if (distance < rule3Distance) { + cohesion += currVel; + numNeighbors3 += 1.f; + } + } + + glm::vec3 change(0.f); + + if (numNeighbors1 > 0) { + center /= numNeighbors1; + change += (center - thisPos) * rule1Scale; + } + + if (numNeighbors3 > 0) { + cohesion /= numNeighbors3; + change += cohesion * rule3Scale; + } + + change += separate * rule2Scale; + + return change; + } +} + +__device__ glm::vec3 computeVelocityChangeGivenCellCoherent(int N, int gridResolution, int gridCellIndex, int iSelf, + int* gridCellStartIndices, int* gridCellEndIndices, glm::vec3* pos, glm::vec3* vel) { + if (gridCellIndex < 0 || gridCellIndex >= gridResolution * gridResolution * gridResolution) { + return glm::vec3(0.f); + } + else { + int start = gridCellStartIndices[gridCellIndex]; + int end = gridCellEndIndices[gridCellIndex]; + + // no boids in grid cell + if (start < 0) { + return glm::vec3(0.f); + } + + glm::vec3 thisPos = pos[iSelf]; + + glm::vec3 center(0.f); + glm::vec3 separate(0.f); + glm::vec3 cohesion(0.f); + + float numNeighbors1 = 0; + float numNeighbors3 = 0; + + for (int i = start; i <= end; i++) { + if (i == iSelf) { + continue; + } + + glm::vec3 currPos = pos[i]; + glm::vec3 currVel = vel[i]; + + float distance = glm::length(thisPos - currPos); + + // Rule 1: boids fly towards their local perceived center of mass, which excludes themselves + if (distance < rule1Distance) { + center += currPos; + numNeighbors1 += 1.f; + } + + // Rule 2: boids try to stay a distance d away from each other + if (distance < rule2Distance) { + separate -= currPos - thisPos; + } + + // Rule 3: boids try to match the speed of surrounding boids + if (distance < rule3Distance) { + cohesion += currVel; + numNeighbors3 += 1.f; + } + } + + glm::vec3 change(0.f); + + if (numNeighbors1 > 0) { + center /= numNeighbors1; + change += (center - thisPos) * rule1Scale; + } + + if (numNeighbors3 > 0) { + cohesion /= numNeighbors3; + change += cohesion * rule3Scale; + } + + change += separate * rule2Scale; + + return change; + } +} + +__device__ glm::vec3 velChangeSmallGrid(int N, int iSelf, int gridResolution, glm::vec3 gridMin, + float inverseCellWidth, float cellWidth, int* gridCellStartIndices, int* gridCellEndIndices, + int* particleArrayIndices, glm::vec3* pos, glm::vec3* vel1, glm::vec3* vel2) { + glm::vec3 currPos = pos[iSelf]; + glm::ivec3 gridCell = floor((currPos - gridMin) * inverseCellWidth); + glm::ivec3 gridCellRound = round((currPos - gridMin) * inverseCellWidth); + + int gridCellIndex = gridIndex3Dto1D(gridCell.x, gridCell.y, gridCell.z, gridResolution); + + int xMin = gridCell.x == gridCellRound.x ? gridCell.x - 1 : gridCell.x; + int yMin = gridCell.y == gridCellRound.y ? gridCell.y - 1 : gridCell.y; + int zMin = gridCell.z == gridCellRound.z ? gridCell.z - 1 : gridCell.z; + + int xMax = gridCell.x == gridCellRound.x ? gridCell.x : gridCell.x + 1; + int yMax = gridCell.y == gridCellRound.y ? gridCell.y : gridCell.y + 1; + int zMax = gridCell.z == gridCellRound.z ? gridCell.z : gridCell.z + 1; + + glm::vec3 change(0.f); + for (int k = zMin; k <= zMax; k++) { + for (int j = yMin; j <= yMax; j++) { + for (int i = xMin; i <= xMax; i++) { + int gridCellIndex = gridIndex3Dto1D(i, j, k, gridResolution); + glm::vec3 c = computeVelocityChangeGivenCell(N, gridResolution, gridCellIndex, iSelf, + gridCellStartIndices, gridCellEndIndices, particleArrayIndices, pos, vel1); + change += c; + } + } + } + return change; +} + +__device__ glm::vec3 velChangeSmallGridCoherent(int N, int iSelf, int gridResolution, glm::vec3 gridMin, + float inverseCellWidth, float cellWidth, int* gridCellStartIndices, int* gridCellEndIndices, + glm::vec3* pos, glm::vec3* vel1, glm::vec3* vel2) { + glm::vec3 currPos = pos[iSelf]; + glm::ivec3 gridCell = floor((currPos - gridMin) * inverseCellWidth); + glm::ivec3 gridCellRound = round((currPos - gridMin) * inverseCellWidth); + + int gridCellIndex = gridIndex3Dto1D(gridCell.x, gridCell.y, gridCell.z, gridResolution); + + int xMin = gridCell.x == gridCellRound.x ? gridCell.x - 1 : gridCell.x; + int yMin = gridCell.y == gridCellRound.y ? gridCell.y - 1 : gridCell.y; + int zMin = gridCell.z == gridCellRound.z ? gridCell.z - 1 : gridCell.z; + + int xMax = gridCell.x == gridCellRound.x ? gridCell.x : gridCell.x + 1; + int yMax = gridCell.y == gridCellRound.y ? gridCell.y : gridCell.y + 1; + int zMax = gridCell.z == gridCellRound.z ? gridCell.z : gridCell.z + 1; + + glm::vec3 change(0.f); + for (int k = zMin; k <= zMax; k++) { + for (int j = yMin; j <= yMax; j++) { + for (int i = xMin; i <= xMax; i++) { + int gridCellIndex = gridIndex3Dto1D(i, j, k, gridResolution); + glm::vec3 c = computeVelocityChangeGivenCellCoherent(N, gridResolution, gridCellIndex, iSelf, + gridCellStartIndices, gridCellEndIndices, pos, vel1); + change += c; + } + } + } + return change; +} + +__device__ glm::vec3 velChangeLargeGrid(int N, int iSelf, int gridResolution, glm::vec3 gridMin, + float inverseCellWidth, float cellWidth, int* gridCellStartIndices, int* gridCellEndIndices, + int* particleArrayIndices, + glm::vec3* pos, glm::vec3* vel1, glm::vec3* vel2) { + glm::vec3 currPos = pos[iSelf]; + glm::ivec3 gridCell = floor((currPos - gridMin) * inverseCellWidth); + + int gridCellIndex = gridIndex3Dto1D(gridCell.x, gridCell.y, gridCell.z, gridResolution); + + glm::vec3 change(0.f); + for (int i = gridCell.x - 1; i <= gridCell.x + 1; i++) { + for (int j = gridCell.y - 1; j <= gridCell.y + 1; j++) { + for (int k = gridCell.z - 1; k <= gridCell.z + 1; k++) { + int gridCellIndex = gridIndex3Dto1D(i, j, k, gridResolution); + glm::vec3 c = computeVelocityChangeGivenCell(N, gridResolution, gridCellIndex, iSelf, + gridCellStartIndices, gridCellEndIndices, particleArrayIndices, pos, vel1); + change += c; + } + } + } + return change; } -__global__ void kernIdentifyCellStartEnd(int N, int *particleGridIndices, - int *gridCellStartIndices, int *gridCellEndIndices) { - // TODO-2.1 - // Identify the start point of each cell in the gridIndices array. - // This is basically a parallel unrolling of a loop that goes - // "this index doesn't match the one before it, must be a new cell!" +__device__ glm::vec3 velChangeLargeGridCoherent(int N, int iSelf, int gridResolution, glm::vec3 gridMin, + float inverseCellWidth, float cellWidth, int* gridCellStartIndices, int* gridCellEndIndices, + glm::vec3* pos, glm::vec3* vel1, glm::vec3* vel2) { + glm::vec3 currPos = pos[iSelf]; + glm::ivec3 gridCell = floor((currPos - gridMin) * inverseCellWidth); + + int gridCellIndex = gridIndex3Dto1D(gridCell.x, gridCell.y, gridCell.z, gridResolution); + + glm::vec3 change(0.f); + for (int i = gridCell.x - 1; i <= gridCell.x + 1; i++) { + for (int j = gridCell.y - 1; j <= gridCell.y + 1; j++) { + for (int k = gridCell.z - 1; k <= gridCell.z + 1; k++) { + int gridCellIndex = gridIndex3Dto1D(i, j, k, gridResolution); + glm::vec3 c = computeVelocityChangeGivenCellCoherent(N, gridResolution, gridCellIndex, iSelf, + gridCellStartIndices, gridCellEndIndices, pos, vel1); + change += c; + } + } + } + return change; } __global__ void kernUpdateVelNeighborSearchScattered( - int N, int gridResolution, glm::vec3 gridMin, - float inverseCellWidth, float cellWidth, - int *gridCellStartIndices, int *gridCellEndIndices, - int *particleArrayIndices, - glm::vec3 *pos, glm::vec3 *vel1, glm::vec3 *vel2) { - // TODO-2.1 - Update a boid's velocity using the uniform grid to reduce - // the number of boids that need to be checked. - // - Identify the grid cell that this particle is in - // - Identify which cells may contain neighbors. This isn't always 8. - // - For each cell, read the start/end indices in the boid pointer array. - // - Access each boid in the cell and compute velocity change from - // the boids rules, if this boid is within the neighborhood distance. - // - Clamp the speed change before putting the new speed in vel2 + int N, int gridResolution, glm::vec3 gridMin, + float inverseCellWidth, float cellWidth, + int* gridCellStartIndices, int* gridCellEndIndices, + int* particleArrayIndices, + glm::vec3* pos, glm::vec3* vel1, glm::vec3* vel2) { + // TODO-2.1 - Update a boid's velocity using the uniform grid to reduce + // the number of boids that need to be checked. + // - Identify the grid cell that this particle is in + // - Identify which cells may contain neighbors. This isn't always 8. + // - For each cell, read the start/end indices in the boid pointer array. + // - Access each boid in the cell and compute velocity change from + // the boids rules, if this boid is within the neighborhood distance. + int index = threadIdx.x + (blockIdx.x * blockDim.x); + if (index >= N) { + return; + } + + glm::vec3 change(0.f); + if (cellWidth > glm::max(glm::max(rule1Distance, rule2Distance), rule3Distance)) { + change += velChangeSmallGrid(N, index, gridResolution, gridMin,inverseCellWidth, cellWidth, + gridCellStartIndices, gridCellEndIndices, particleArrayIndices, pos, vel1, vel2); + } + else { + change += velChangeLargeGrid(N, index, gridResolution, gridMin, inverseCellWidth, cellWidth, + gridCellStartIndices, gridCellEndIndices, particleArrayIndices, pos, vel1, vel2); + } + + glm::vec3 newVel = vel1[index] + change; + + // - Clamp the speed change before putting the new speed in vel2 + if (glm::length(newVel) > maxSpeed) { + newVel = glm::normalize(newVel); + } + + // Record the new velocity into vel2. + vel2[index] = newVel; } __global__ void kernUpdateVelNeighborSearchCoherent( - int N, int gridResolution, glm::vec3 gridMin, - float inverseCellWidth, float cellWidth, - int *gridCellStartIndices, int *gridCellEndIndices, - glm::vec3 *pos, glm::vec3 *vel1, glm::vec3 *vel2) { - // TODO-2.3 - This should be very similar to kernUpdateVelNeighborSearchScattered, - // except with one less level of indirection. - // This should expect gridCellStartIndices and gridCellEndIndices to refer - // directly to pos and vel1. - // - Identify the grid cell that this particle is in - // - Identify which cells may contain neighbors. This isn't always 8. - // - For each cell, read the start/end indices in the boid pointer array. - // DIFFERENCE: For best results, consider what order the cells should be - // checked in to maximize the memory benefits of reordering the boids data. - // - Access each boid in the cell and compute velocity change from - // the boids rules, if this boid is within the neighborhood distance. - // - Clamp the speed change before putting the new speed in vel2 + int N, int gridResolution, glm::vec3 gridMin, + float inverseCellWidth, float cellWidth, + int* gridCellStartIndices, int* gridCellEndIndices, + glm::vec3* pos, glm::vec3* vel1, glm::vec3* vel2) { + // TODO-2.3 - This should be very similar to kernUpdateVelNeighborSearchScattered, + // except with one less level of indirection. + // This should expect gridCellStartIndices and gridCellEndIndices to refer + // directly to pos and vel1. + // - Identify the grid cell that this particle is in + // - Identify which cells may contain neighbors. This isn't always 8. + // - For each cell, read the start/end indices in the boid pointer array. + // DIFFERENCE: For best results, consider what order the cells should be + // checked in to maximize the memory benefits of reordering the boids data. + // - Access each boid in the cell and compute velocity change from + // the boids rules, if this boid is within the neighborhood distance. + // - Clamp the speed change before putting the new speed in vel2 + int index = threadIdx.x + (blockIdx.x * blockDim.x); + if (index >= N) { + return; + } + + glm::vec3 change(0.f); + if (cellWidth > glm::max(glm::max(rule1Distance, rule2Distance), rule3Distance)) { + change += velChangeSmallGridCoherent(N, index, gridResolution, gridMin, inverseCellWidth, cellWidth, + gridCellStartIndices, gridCellEndIndices, pos, vel1, vel2); + } + else { + change += velChangeLargeGridCoherent(N, index, gridResolution, gridMin, inverseCellWidth, cellWidth, + gridCellStartIndices, gridCellEndIndices, pos, vel1, vel2); + } + + glm::vec3 newVel = vel1[index] + change; + + // - Clamp the speed change before putting the new speed in vel2 + if (glm::length(newVel) > maxSpeed) { + newVel = glm::normalize(newVel); + } + + // Record the new velocity into vel2. + vel2[index] = newVel; } /** * Step the entire N-body simulation by `dt` seconds. */ void Boids::stepSimulationNaive(float dt) { - // TODO-1.2 - use the kernels you wrote to step the simulation forward in time. - // TODO-1.2 ping-pong the velocity buffers + // TODO-1.2 - use the kernels you wrote to step the simulation forward in time. + dim3 fullBlocksPerGrid((numObjects + blockSize - 1) / blockSize); + kernUpdateVelocityBruteForce << > > (numObjects, dev_pos, dev_vel1, dev_vel2); + kernUpdatePos << > > (numObjects, dt, dev_pos, dev_vel1); + + // TODO-1.2 ping-pong the velocity buffers + dev_vel1 = dev_vel2; } void Boids::stepSimulationScatteredGrid(float dt) { - // TODO-2.1 - // Uniform Grid Neighbor search using Thrust sort. - // In Parallel: - // - label each particle with its array index as well as its grid index. - // Use 2x width grids. - // - Unstable key sort using Thrust. A stable sort isn't necessary, but you - // are welcome to do a performance comparison. - // - Naively unroll the loop for finding the start and end indices of each - // cell's data pointers in the array of boid indices - // - Perform velocity updates using neighbor search - // - Update positions - // - Ping-pong buffers as needed + // TODO-2.1 + // Uniform Grid Neighbor search using Thrust sort. + // In Parallel: + // - label each particle with its array index as well as its grid index. + // Use 2x width grids. + int N = numObjects; + + dim3 fullBlocksPerGrid((numObjects + blockSize - 1) / blockSize); + kernComputeIndices << > > (N, gridSideCount, gridMinimum, + gridInverseCellWidth, dev_pos, dev_particleArrayIndices, dev_particleGridIndices); + // - Unstable key sort using Thrust. A stable sort isn't necessary, but you + // are welcome to do a performance comparison. + + // Wrap device vectors in thrust iterators for use with thrust. + thrust::device_ptr dev_thrust_particleArrayIndices(dev_particleArrayIndices); + thrust::device_ptr dev_thrust_particleGridIndices(dev_particleGridIndices); + thrust::sort_by_key(dev_thrust_particleGridIndices, dev_thrust_particleGridIndices + N, dev_thrust_particleArrayIndices); + + // - Naively unroll the loop for finding the start and end indices of each + // cell's data pointers in the array of boid indices + kernIdentifyCellStartEnd << > > (N, dev_particleGridIndices, dev_gridCellStartIndices, dev_gridCellEndIndices); + + // - Perform velocity updates using neighbor search + kernUpdateVelNeighborSearchScattered << > > (N, gridSideCount, gridMinimum, + gridInverseCellWidth, gridCellWidth, dev_gridCellStartIndices, dev_gridCellEndIndices, dev_particleArrayIndices, + dev_pos, dev_vel1, dev_vel2); + + // - Update positions + kernUpdatePos << > > (numObjects, dt, dev_pos, dev_vel1); + + // - Ping-pong buffers as needed + dev_vel1 = dev_vel2; } void Boids::stepSimulationCoherentGrid(float dt) { - // TODO-2.3 - start by copying Boids::stepSimulationNaiveGrid - // Uniform Grid Neighbor search using Thrust sort on cell-coherent data. - // In Parallel: - // - Label each particle with its array index as well as its grid index. - // Use 2x width grids - // - Unstable key sort using Thrust. A stable sort isn't necessary, but you - // are welcome to do a performance comparison. - // - Naively unroll the loop for finding the start and end indices of each - // cell's data pointers in the array of boid indices - // - BIG DIFFERENCE: use the rearranged array index buffer to reshuffle all - // the particle data in the simulation array. - // CONSIDER WHAT ADDITIONAL BUFFERS YOU NEED - // - Perform velocity updates using neighbor search - // - Update positions - // - Ping-pong buffers as needed. THIS MAY BE DIFFERENT FROM BEFORE. + // TODO-2.3 - start by copying Boids::stepSimulationNaiveGrid + // Uniform Grid Neighbor search using Thrust sort on cell-coherent data. + // In Parallel: + // - label each particle with its array index as well as its grid index. + // Use 2x width grids. + int N = numObjects; + + dim3 fullBlocksPerGrid((numObjects + blockSize - 1) / blockSize); + kernComputeIndices << > > (N, gridSideCount, gridMinimum, + gridInverseCellWidth, dev_pos, dev_particleArrayIndices, dev_particleGridIndices); + // - Unstable key sort using Thrust. A stable sort isn't necessary, but you + // are welcome to do a performance comparison. + + // Wrap device vectors in thrust iterators for use with thrust. + thrust::device_ptr dev_thrust_particleArrayIndices(dev_particleArrayIndices); + thrust::device_ptr dev_thrust_particleGridIndices(dev_particleGridIndices); + thrust::sort_by_key(dev_thrust_particleGridIndices, dev_thrust_particleGridIndices + N, dev_thrust_particleArrayIndices); + + // - Naively unroll the loop for finding the start and end indices of each + // cell's data pointers in the array of boid indices + kernIdentifyCellStartEnd << > > (N, dev_particleGridIndices, dev_gridCellStartIndices, dev_gridCellEndIndices); + + // - BIG DIFFERENCE: use the rearranged array index buffer to reshuffle all + // the particle data in the simulation array. + // CONSIDER WHAT ADDITIONAL BUFFERS YOU NEED + kernRearrangePosAndVel << > > (N, dev_particleArrayIndices, dev_pos, dev_vel1, + dev_pos_rearrange, dev_vel1_rearrange); + + // - Perform velocity updates using neighbor search + kernUpdateVelNeighborSearchCoherent << > > (N, gridSideCount, gridMinimum, + gridInverseCellWidth, gridCellWidth, dev_gridCellStartIndices, dev_gridCellEndIndices, + dev_pos_rearrange, dev_vel1_rearrange, dev_vel2); + + // - Update positions + kernUpdatePos << > > (numObjects, dt, dev_pos_rearrange, dev_vel1_rearrange); + + // - Ping-pong buffers as needed + dev_vel1 = dev_vel2; + dev_pos = dev_pos_rearrange; } void Boids::endSimulation() { - cudaFree(dev_vel1); - cudaFree(dev_vel2); - cudaFree(dev_pos); - - // TODO-2.1 TODO-2.3 - Free any additional buffers here. + cudaFree(dev_vel1); + cudaFree(dev_vel2); + cudaFree(dev_pos); + + // TODO-2.1 TODO-2.3 - Free any additional buffers here. + cudaFree(dev_particleArrayIndices); + cudaFree(dev_particleGridIndices); + cudaFree(dev_gridCellStartIndices); + cudaFree(dev_gridCellEndIndices); + + //2.3 + cudaFree(dev_vel1_rearrange); + cudaFree(dev_pos_rearrange); } void Boids::unitTest() { - // LOOK-1.2 Feel free to write additional tests here. - - // test unstable sort - int *dev_intKeys; - int *dev_intValues; - int N = 10; - - std::unique_ptrintKeys{ new int[N] }; - std::unique_ptrintValues{ new int[N] }; - - intKeys[0] = 0; intValues[0] = 0; - intKeys[1] = 1; intValues[1] = 1; - intKeys[2] = 0; intValues[2] = 2; - intKeys[3] = 3; intValues[3] = 3; - intKeys[4] = 0; intValues[4] = 4; - intKeys[5] = 2; intValues[5] = 5; - intKeys[6] = 2; intValues[6] = 6; - intKeys[7] = 0; intValues[7] = 7; - intKeys[8] = 5; intValues[8] = 8; - intKeys[9] = 6; intValues[9] = 9; - - cudaMalloc((void**)&dev_intKeys, N * sizeof(int)); - checkCUDAErrorWithLine("cudaMalloc dev_intKeys failed!"); - - cudaMalloc((void**)&dev_intValues, N * sizeof(int)); - checkCUDAErrorWithLine("cudaMalloc dev_intValues failed!"); - - dim3 fullBlocksPerGrid((N + blockSize - 1) / blockSize); - - std::cout << "before unstable sort: " << std::endl; - for (int i = 0; i < N; i++) { - std::cout << " key: " << intKeys[i]; - std::cout << " value: " << intValues[i] << std::endl; - } - - // How to copy data to the GPU - cudaMemcpy(dev_intKeys, intKeys.get(), sizeof(int) * N, cudaMemcpyHostToDevice); - cudaMemcpy(dev_intValues, intValues.get(), sizeof(int) * N, cudaMemcpyHostToDevice); - - // Wrap device vectors in thrust iterators for use with thrust. - thrust::device_ptr dev_thrust_keys(dev_intKeys); - thrust::device_ptr dev_thrust_values(dev_intValues); - // LOOK-2.1 Example for using thrust::sort_by_key - thrust::sort_by_key(dev_thrust_keys, dev_thrust_keys + N, dev_thrust_values); - - // How to copy data back to the CPU side from the GPU - cudaMemcpy(intKeys.get(), dev_intKeys, sizeof(int) * N, cudaMemcpyDeviceToHost); - cudaMemcpy(intValues.get(), dev_intValues, sizeof(int) * N, cudaMemcpyDeviceToHost); - checkCUDAErrorWithLine("memcpy back failed!"); - - std::cout << "after unstable sort: " << std::endl; - for (int i = 0; i < N; i++) { - std::cout << " key: " << intKeys[i]; - std::cout << " value: " << intValues[i] << std::endl; - } - - // cleanup - cudaFree(dev_intKeys); - cudaFree(dev_intValues); - checkCUDAErrorWithLine("cudaFree failed!"); - return; + // LOOK-1.2 Feel free to write additional tests here. + + // test unstable sort + int* dev_intKeys; + int* dev_intValues; + int N = 10; + + std::unique_ptrintKeys{ new int[N] }; + std::unique_ptrintValues{ new int[N] }; + + intKeys[0] = 0; intValues[0] = 0; + intKeys[1] = 1; intValues[1] = 1; + intKeys[2] = 0; intValues[2] = 2; + intKeys[3] = 3; intValues[3] = 3; + intKeys[4] = 0; intValues[4] = 4; + intKeys[5] = 2; intValues[5] = 5; + intKeys[6] = 2; intValues[6] = 6; + intKeys[7] = 0; intValues[7] = 7; + intKeys[8] = 5; intValues[8] = 8; + intKeys[9] = 6; intValues[9] = 9; + + cudaMalloc((void**)&dev_intKeys, N * sizeof(int)); + checkCUDAErrorWithLine("cudaMalloc dev_intKeys failed!"); + + cudaMalloc((void**)&dev_intValues, N * sizeof(int)); + checkCUDAErrorWithLine("cudaMalloc dev_intValues failed!"); + + dim3 fullBlocksPerGrid((N + blockSize - 1) / blockSize); + + std::cout << "before unstable sort: " << std::endl; + for (int i = 0; i < N; i++) { + std::cout << " key: " << intKeys[i]; + std::cout << " value: " << intValues[i] << std::endl; + } + + // How to copy data to the GPU + cudaMemcpy(dev_intKeys, intKeys.get(), sizeof(int) * N, cudaMemcpyHostToDevice); + cudaMemcpy(dev_intValues, intValues.get(), sizeof(int) * N, cudaMemcpyHostToDevice); + + // Wrap device vectors in thrust iterators for use with thrust. + thrust::device_ptr dev_thrust_keys(dev_intKeys); + thrust::device_ptr dev_thrust_values(dev_intValues); + // LOOK-2.1 Example for using thrust::sort_by_key + thrust::sort_by_key(dev_thrust_keys, dev_thrust_keys + N, dev_thrust_values); + + // How to copy data back to the CPU side from the GPU + cudaMemcpy(intKeys.get(), dev_intKeys, sizeof(int) * N, cudaMemcpyDeviceToHost); + cudaMemcpy(intValues.get(), dev_intValues, sizeof(int) * N, cudaMemcpyDeviceToHost); + checkCUDAErrorWithLine("memcpy back failed!"); + + std::cout << "after unstable sort: " << std::endl; + for (int i = 0; i < N; i++) { + std::cout << " key: " << intKeys[i]; + std::cout << " value: " << intValues[i] << std::endl; + } + + // cleanup + cudaFree(dev_intKeys); + cudaFree(dev_intValues); + checkCUDAErrorWithLine("cudaFree failed!"); + return; } diff --git a/src/main.cpp b/src/main.cpp index b82c8c6..ddd0e3b 100644 --- a/src/main.cpp +++ b/src/main.cpp @@ -14,8 +14,8 @@ // LOOK-2.1 LOOK-2.3 - toggles for UNIFORM_GRID and COHERENT_GRID #define VISUALIZE 1 -#define UNIFORM_GRID 0 -#define COHERENT_GRID 0 +#define UNIFORM_GRID 1 +#define COHERENT_GRID 1 // LOOK-1.2 - change this to adjust particle count in the simulation const int N_FOR_VIS = 5000;