texture<float, 2, cudaReadModeElementType> tex;
void foo()
{
cudaArray* cu_array;
// Allocate array
cudaChannelFormatDesc description = cudaCreateChannelDesc<float>();
cudaMallocArray(&cu_array, &description, width, height);
// Copy image data to array
cudaMemcpyToArray(cu_array, image, width*height*sizeof(float), cudaMemcpyHostToDevice);
// Set texture parameters (default)
tex.addressMode[0] = cudaAddressModeClamp;
tex.addressMode[1] = cudaAddressModeClamp;
tex.filterMode = cudaFilterModePoint;
tex.normalized = false; // do not normalize coordinates
// Bind the array to the texture
cudaBindTextureToArray(tex, cu_array);
// Run kernel
dim3 blockDim(16, 16, 1);
dim3 gridDim((width + blockDim.x - 1)/ blockDim.x, (height + blockDim.y - 1) / blockDim.y, 1);
kernel<<< gridDim, blockDim, 0 >>>(d_data, height, width);
// Unbind the array from the texture
cudaUnbindTexture(tex);
} //end foo()
__global__ void kernel(float* odata, int height, int width)
{
unsigned int x = blockIdx.x*blockDim.x + threadIdx.x;
unsigned int y = blockIdx.y*blockDim.y + threadIdx.y;
if (x < width && y < height) {
float c = tex2D(tex, x, y);
odata[y*width+x] = c;
}
}
import pycuda.compiler as comp
import pycuda.driver as drv
import numpy
import pycuda.autoinit
mod = comp.SourceModule(
"""
__global__ void multiply_them(float *dest, float *a, float *b)
{
const int i = threadIdx.x;
dest[i] = a[i] * b[i];
}
"""
)
multiply_them = mod.get_function("multiply_them")
a = numpy.random.randn(400).astype(numpy.float32)
b = numpy.random.randn(400).astype(numpy.float32)
dest = numpy.zeros_like(a)
multiply_them(drv.Out(dest), drv.In(a), drv.In(b), block=(400, 1, 1))
print(dest - a * b)
행렬 곱셈 연산을 단순화하는 추가 파이썬 바인딩은 pycublas 프로그램에서 찾을 수 있다.
import numpy
from pycublas import CUBLASMatrix
A = CUBLASMatrix(numpy.mat([[1, 2, 3], [4, 5, 6]], numpy.float32))
B = CUBLASMatrix(numpy.mat([[2, 3], [4, 5], [6, 7]], numpy.float32))
C = A * B
print(C.np_mat())
import cupy
a = cupy.random.randn(400)
b = cupy.random.randn(400)
dest = cupy.zeros_like(a)
print(dest - a * b)
/ 2026년 9월 9일
.PNG)
