편집 기록

안녕하세요 파이썬에서 pycuda로 juliaSet을 만들어 보고 있습니다.

import ctypes

import pycuda.autoinit

import numpy as np

import cv2

import pycuda.driver as cuda

import numpy

from pycuda.compiler import SourceModule

bmp = np.zeros((1000,1000), dtype=np.float32)

ptr = bmp.ctypes.data_as(ctypes.c_void_p)

bmp = bmp.astype(numpy.float32)

a_gpu = cuda.mem_alloc(bmp.nbytes)

cuda.memcpy_htod(a_gpu, bmp)


mod = SourceModule(""" 

    struct cuComplex {
        float r; float i;
        __device__ cuComplex(float a, float b) : r(a),i(b) {}
        __device__ float magnitude2(void) { return r * r + i * i; }
        __device__ cuComplex operator* (const cuComplex& a){
            return cuComplex(r * a.r - i * a.i, i * a.r + r * a.i);}
        __device__ cuComplex operator+ (const cuComplex& a){
            return cuComplex(r + a.r, i + a.i);}
    };    
    __device__ int julia(int x, int y){
        const float scale = 1.5;
        float jx = scale * (float)(1000/2-x)/(1000/2);
        float jy = scale * (float)(1000/2-y)/(1000/2);

        cuComplex c(-0.8,0.156);
        cuComplex a(jx,jy);

        for (int i = 0;i<200;i++){
            a = a * a + c;
            if(a.magnitude2()>1000)
                return 0;
        }
        return 1;
    }
    __global__ void juliaSet(float *ptr)
    {
        int x = blockIdx.x;
        int y = blockIdx.y;
        int offset = x + y * gridDim.x;

        int juliaValue = julia(x,y);
        ptr[offset*4+0]=255*juliaValue;
        ptr[offset*4+1]=0;
        ptr[offset*4+2]=0;
        ptr[offset*4+3]=255;
    }
    """)
func = mod.get_function("juliaSet")

bmp_kernel = numpy.empty_like(bmp)

func(a_gpu,block=(1000,1000,1))

cuda.memcpy_dtoh(bmp_kernel, a_gpu)

cv2.imshow('bmp', bmp)

cv2.waitKey()

이런식으로 코딩을 했는데 오류가

pycuda._driver.LogicError: cuFuncSetBlockShape failed: invalid argument 

이렇게 뜹니다. 혹시 고쳐야 할 부분이 있을까요??

안녕하세요 파이썬에서 pycuda로 juliaSet을 만들어 보고 있습니다.

import ctypes

import pycuda.autoinit

import numpy as np

import cv2

import pycuda.driver as cuda

import numpy

from pycuda.compiler import SourceModule

bmp = np.zeros((1000,1000), dtype=np.float32)

ptr = bmp.ctypes.data_as(ctypes.c_void_p)

bmp = bmp.astype(numpy.float32)

a_gpu = cuda.mem_alloc(bmp.nbytes)

cuda.memcpy_htod(a_gpu, bmp)

mod = SourceModule("""

struct cuComplex {
    float r; float i;
    __device__ cuComplex(float a, float b) : r(a),i(b) {}
    __device__ float magnitude2(void) { return r * r + i * i; }
    __device__ cuComplex operator* (const cuComplex& a){
        return cuComplex(r * a.r - i * a.i, i * a.r + r * a.i);}
    __device__ cuComplex operator+ (const cuComplex& a){
        return cuComplex(r + a.r, i + a.i);}
};    
__device__ int julia(int x, int y){
    const float scale = 1.5;
    float jx = scale * (float)(1000/2-x)/(1000/2);
    float jy = scale * (float)(1000/2-y)/(1000/2);

    cuComplex c(-0.8,0.156);
    cuComplex a(jx,jy);

    for (int i = 0;i<200;i++){
        a = a * a + c;
        if(a.magnitude2()>1000)
            return 0;
    }
    return 1;
}
__global__ void juliaSet(float *ptr)
{
    int x = blockIdx.x;
    int y = blockIdx.y;
    int offset = x + y * gridDim.x;

    int juliaValue = julia(x,y);
    ptr[offset*4+0]=255*juliaValue;
    ptr[offset*4+1]=0;
    ptr[offset*4+2]=0;
    ptr[offset*4+3]=255;
}
""")

func = mod.get_function("juliaSet")

bmp_kernel = numpy.empty_like(bmp)

func(a_gpu,block=(1000,1000,1))

cuda.memcpy_dtoh(bmp_kernel, a_gpu)

cv2.imshow('bmp', bmp)

cv2.waitKey()

이런식으로 코딩을 했는데 오류가 pycuda._driver.LogicError: cuFuncSetBlockShape failed: invalid argument 이렇게 뜹니다. 혹시 고쳐야 할 부분이 있을까요??