gpt4 book ai didi

c++ - OpenCL 内核访问 CL_MEM_READ_WRITE,缓冲区

转载 作者:行者123 更新时间:2023-11-28 05:45:55 27 4
gpt4 key购买 nike

我正在尝试将 float3 缓冲区 border 用于数据结构。它在使用英特尔 OpenCL SDK 4.4、英特尔 iCore7 的内核执行期间崩溃。不幸的是,我无法找出 3d-index (i, y, x) 到线性索引 adr=WIDTH2*i+WIDTH*y+x 中的任何索引错误然而。我错过了什么?

以下是缓冲区定义(使用 OpenCL C++ 包装器 v1.2):

m_numPixels(width*width),
m_inBuffer(getContext(), CL_MEM_READ_ONLY | CL_MEM_ALLOC_HOST_PTR,
sizeof(float)*(width*width), NULL),
m_inBuffer2(getContext(), CL_MEM_READ_ONLY | CL_MEM_ALLOC_HOST_PTR,
sizeof(float)*(width*width), NULL),
m_backBuffer(getContext(), CL_MEM_READ_ONLY,
sizeof(float)*(width*width), NULL),
m_borderBuffer(getContext(), CL_MEM_READ_WRITE,
(3*sizeof(float))*(10*width*width), NULL),
m_outBuffer(getContext(), CL_MEM_READ_WRITE | CL_MEM_ALLOC_HOST_PTR,
4*(width*width), NULL),

内核代码如下:

__kernel void computeMedial (__global const float* height, // input height
__global const float* height2, // input height, previous frame
__global const float* background, // input background
__global float3* border, // border datastructure
__global uchar4* output, // output image
float thres,
uint width,
uint ls,
float scale)
{
uint x = get_global_id(0);
uint y = get_global_id(1);
const uint WIDTH2 = width*width;
const uint WIDTH = width;

// access pixel (x, y)
float2 c00 = (float2)(x, y);
float h00 = array_height(height, height2, width, c00);
if (x < 4 || x > width-5 || y < 4 || y > width-5) { // border location
return;
}
if (h00 < thres-10 || h00 > thres+10) { // not in thres interval
return;
}
output[y*WIDTH+x] = colorUCHAR(0, y, x); // writing output image

// test
for (uint i=0; i<ls; ++i) { // ls<=7 ok, ls==8/9/10 crashes
uint adr = WIDTH2*i+WIDTH*y+x;
border[adr] = (float3)(0);
}
}

最佳答案

边框 中存在对齐问题。在 cl_platform.h 中声明:

/* cl_float3 is identical in size, alignment and behavior to cl_float4. See section 6.1.5. */
typedef cl_float4 cl_float3;

最好使用 cl_* 类型来避免此类问题,因此您可以按以下方式创建 border 缓冲区:

m_borderBuffer(getContext(), CL_MEM_READ_WRITE, (sizeof(cl_float3))*10*width*width), NULL),

关于c++ - OpenCL 内核访问 CL_MEM_READ_WRITE,缓冲区,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/36224071/

27 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com