我已经实现了CUDA版本的反离散余弦变换(IDCT),将MATLAB内置函数cuIDCT.cu
“转换”为CUDA:
#include <stdio.h>
#include <stdlib.h>
#include <cuda.h>
#include <cufft.h>
#include <cuComplex.h>
// round up n/m
inline int iDivUp(int n, int m)
{
return (n + m - 1) / m;
}
typedef cufftComplex complex;
#define PI 3.1415926535897932384626433832795028841971693993751
__global__
void idct_ComputeWeightsKernel(const int n, complex *ww)
{
const int pos = threadIdx.x + blockIdx.x * blockDim.x;
if (pos >= n) return;
ww[pos].x = sqrtf(2*n) * cosf(pos*PI/(2*n));
ww[pos].y = sqrtf(2*n) * sinf(pos*PI/(2*n));
}
__global__
void idct_ComputeEvenKernel(const float *b, const int n, const int m, complex *ww, complex *y)
{
const int ix = threadIdx.x + blockIdx.x * blockDim.x;
const int iy = threadIdx.y + blockIdx.y * blockDim.y;
if (ix >= n || iy >= m) return;
const int pos = ix + iy*n;
// Compute precorrection factor
ww[0].x = ww[0].x / sqrtf(2);
ww[0].y = ww[0].y / sqrtf(2);
y[iy + ix*m].x = ww[iy].x * b[pos];
y[iy + ix*m].y = ww[iy].y * b[pos];
}
__global__
void Reordering_a0_Kernel(complex *y, const int n, const int m, complex *yy)
{
const int ix = threadIdx.x + blockIdx.x * blockDim.x;
const int iy = threadIdx.y + blockIdx.y * blockDim.y;
if (ix >= n || iy >= m) return;
const int pos = ix + iy*n;
yy[iy + ix*n].x = y[pos].x / (float) n;
yy[iy + ix*n].y = y[pos].y / (float) n;
}
__global__
void Reordering_a_Kernel(complex *yy, const int n, const int m, float *a)
{
const int ix = threadIdx.x + blockIdx.x * blockDim.x;
const int iy = threadIdx.y + blockIdx.y * blockDim.y;
if (ix >= n || iy >= m) return;
const int pos = ix + iy*n;
// Re-order elements of each column according to equations (5.93) and (5.94) in Jain
if (iy < n/2)
{
a[ix + 2*iy*n] = yy[pos].x;
a[ix + (2*iy+1)*n] = yy[ix + (m-iy-1)*n].x;
}
}
/**
* a = idct(b), where a is of size [n m].
* @param b, input array
* @param n, first dimension of a
* @param m, second dimension of a
* @param a, output array
*/
void cuIDCT(float *h_in, int n, int m, float *h_out) // a is of size [n m]
{
const int data_size = n * m * sizeof(float);
// device memory allocation
float *d_in, *d_out;
cudaMalloc(&d_in, data_size);
cudaMalloc(&d_out, data_size);
// transfer data from host to device
cudaMemcpy(d_in, h_in, data_size, cudaMemcpyHostToDevice);
// compute IDCT using CUDA
// begin============================================
// Compute weights
complex *ww;
cudaMalloc(&ww, n*sizeof(complex));
dim3 threads(256);
dim3 blocks(iDivUp(n, threads.x));
idct_ComputeWeightsKernel<<<blocks, threads>>>(n, ww);
complex *y;
complex *yy;
cufftHandle plan;
dim3 threads1(32, 6);
dim3 blocks2(iDivUp(n, threads1.x), iDivUp(m, threads1.y)); // for even case
int Length[1] = {m}; // for each IFFT, the length is m
cudaMalloc(&y, n*m*sizeof(complex));
idct_ComputeEvenKernel<<<blocks2, threads1>>>(d_in, n, m, ww, y);
cufftPlanMany(&plan, 1, Length,
Length, 1, m,
Length, 1, m, CUFFT_C2C, n);
cufftExecC2C(plan, y, y, CUFFT_INVERSE); // y is of size [n m]
cudaMalloc(&yy, n*m*sizeof(complex));
Reordering_a0_Kernel<<<blocks2, threads1>>>(y, n, m, yy);
Reordering_a_Kernel<<<blocks2, threads1>>>(yy, n, m, d_out);
// end============================================
// transfer result from device to host
cudaMemcpy(h_out, d_out, data_size, cudaMemcpyDeviceToHost);
// cleanup
cufftDestroy(plan);
cudaFree(ww);
cudaFree(y);
cudaFree(yy);
cudaFree(d_in);
cudaFree(d_out);
}
,当 m = n 时, m 和 n 都是偶数。cuIDCT.cu
cuIDCT.cu
然后我使用以下代码将我的CUDA IDCT(即idct.m
)的结果与MATLAB main.cpp
进行了比较:
main.m
功能,#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <helper_functions.h>
#include <stdlib.h>
#include <stdio.h>
// N must equal to M, and both must be even numbers
#define N 256
#define M 256
void WriteDataFile(const char *name, int w, int h, const float *in, const float *out)
{
FILE *stream;
stream = fopen(name, "wb");
float data = 202021.25f;
fwrite(&data, sizeof(float), 1, stream);
fwrite(&w, sizeof(w), 1, stream);
fwrite(&h, sizeof(h), 1, stream);
for (int i = 0; i < h; i++)
for (int j = 0; j < w; j++)
{
const int pos = j + i * h;
fwrite(in + pos, sizeof(float), 1, stream);
fwrite(out + pos, sizeof(float), 1, stream);
}
fclose(stream);
}
void cuIDCT(float *b, int n, int m, float *a);
int main()
{
// host memory allocation
float *h_in = new float [N * M];
float *h_out = new float [N * M];
float *h_temp = new float [N * M];
// input data initialization
for (int i = 0; i < N * M; i++)
{
h_in[i] = (float)rand()/(float)RAND_MAX;
h_out[i] = h_in[i];
h_temp[i] = h_in[i];
}
// please comment either one case for testing
// test case 1: use cuIDCT.cu once
// cuIDCT(h_in, N, M, h_out);
// test case 2: iteratively use cuIDCT.cu
for (int i = 0; i < 4; i++)
{
if (i % 2 == 0)
cuIDCT(h_out, N, M, h_temp);
else
cuIDCT(h_temp, N, M, h_out);
}
// write data, for further visualization using MATLAB
WriteDataFile("test.flo", N, M, h_in, h_out);
// cleanup
delete [] h_in;
delete [] h_out;
delete [] h_temp;
cudaDeviceReset();
}
,用于读取CUDA的结果,并将其与MATLAB进行比较。的main.cpp
clc;clear;
% read
[h_in, h_out] = read_data('test.flo');
% MATLAB result, for test case 1, comment the for-loop
matlab_out = h_in;
for i = 1:4
matlab_out = idct(matlab_out);
end
% compare
err = matlab_out - h_out;
% show
figure(1);
subplot(221); imshow(h_in, []); title('h\_in'); colorbar
subplot(222); imshow(h_out, []); title('h\_out'); colorbar
subplot(223); imshow(matlab_out, []); title('matlab\_out'); colorbar
subplot(224); imshow(err, []); title('error map'); colorbar
disp(['maximum error between CUDA and MATLAB is ' ...
num2str(max(max(abs(err))))])
的main.m
main.cpp
我在Windows 7中使用Nvidia GPU Tesla K20c在Visual Studio 11(即VS2012)上运行代码,使用CUDA Toolkit 7.5版,我的MATLAB版本是R2015b。
我的测试步骤:
main.m
。main.m
。 我重复了第3步20次。输出结果未更改,main.cpp
的结果为:
最大误差为7.7152e-07。
main.m
。main.m
。我重复了第3步20次。输出结果已更改,结果为cuIDCT.cu
(没有足够的声誉来放置所有图像,只有错误的情况显示在下面):
one situation (the wrong one) of test case 2
最大误差为0.45341(2次),0.44898(1次),0.26186(1次),0.26301次(1次)和9.5716e-07次(15次)。
从测试结果来看,我的结论是:
idct.m
在数值上正确(错误~10 ^ -7)到cuIDCT.cu
。cuIDCT.cu
导致不稳定的结果(即每次重新运行代码时输出都会改变,有时可能在数字上错误,错误~0.1)我的问题:
从测试用例1我们知道idct.m
在cuIDCT.cu
数字上是正确的。但是,每次重新运行代码时,为什么递归使用#options br {
content: "";
}
#options br:after {
content: ", ";
}
会导致不同的输出结果?
非常感谢任何帮助或建议。
答案 0 :(得分:1)
我相信,由于idct_ComputeEvenKernel
中的此代码,您的结果会出现变化:
// Compute precorrection factor
ww[0].x = ww[0].x / sqrtf(2);
ww[0].y = ww[0].y / sqrtf(2);
目前还没有完全清楚你的意图是什么,但是这个代码可以做你想做的事情是值得怀疑的。您可能对CUDA执行模型感到困惑。
上面的代码将由为您通过线程检查的内核启动的每个 CUDA线程执行:
if (ix >= n || iy >= m) return;
我相信这意味着65536个线程将在该内核中执行此代码。此外,线程将以或多或少的任何顺序执行该代码(并非所有CUDA线程都以锁定步骤执行)。当他们试图将他们的价值写到位置ww[0]
时,他们甚至可能互相踩踏。所以ww[0]
的最终结果将是非常不可预测的。
当我注释掉那些代码行时,结果对我来说变得稳定(尽管与那些行的结果不同),从一开始就不变。
我想指出别的东西。无论您在何处计算复杂数量的.x
和.y
值,我的建议都是从此处重新编写代码(例如):
y[iy + ix*m].x = ww[iy].x * b[pos];
y[iy + ix*m].y = ww[iy].y * b[pos];
到此:
complex temp1, temp2;
temp1 = ww[iy];
temp2.x = temp1.x * b[pos];
temp2.y = temp2.y * b[pos];
y[iy + ix*m] = temp2;
至少根据我的测试,编译器似乎没有为您进行此优化,并且一个副作用的好处是使用{{1}来测试代码要容易得多}。在第一个实现中,编译器将加载cuda-memcheck --tool initcheck ...
作为8字节数量,修改它的4或8个字节,然后将y[iy + ix*m]
存储为8字节数量。第二个实现应该更有效(它消除y[iy + ix*m]
的负载),并消除未初始化数量(y[]
)的负载,y[]
工具将报告为危险。
无论您运行代码的1遍版本还是代码的4遍版本,我都可以描述这种可变性。因此,我认为您关于1-pass版本正确的陈述是可疑的。我认为如果你足够运行1遍版本,你最终会看到可变性(虽然它可能需要不同的初始内存条件,或者在不同的GPU类型上运行)。即使在你自己的结果中,我们也看到4个密码的20次运行中有15个产生&#34;正确&#34;结果,即残余误差为~1e-7
这是我修改后的cuda-memcheck
文件,根据您发布的版本here进行了修改。我在下面做的假设是你只想在cuIDCT.cu
上计算一次缩放,在这种情况下,我们可以轻松地将该算法作为前一个ww[0]
的附录来处理:
idct_ComputeWeightsKernel
您注意我在#include <stdio.h>
#include <stdlib.h>
#include <cuda.h>
#include <cufft.h>
#include <cuComplex.h>
#include <helper_cuda.h>
#include "assert.h"
// round up n/m
inline int iDivUp(int n, int m)
{
return (n + m - 1) / m;
}
typedef cufftComplex complex;
#define PI 3.1415926535897932384626433832795028841971693993751
#define cufftSafeCall(err) __cufftSafeCall(err, __FILE__, __LINE__)
inline void __cufftSafeCall(cufftResult err, const char *file, const int line)
{
if( CUFFT_SUCCESS != err) {
fprintf(stderr, "CUFFT error in file '%s', line %d\n %s\nerror %d: %s\nterminating!\n",__FILE__, __LINE__,err, \
_cudaGetErrorEnum(err)); \
cudaDeviceReset(); assert(0); \
}
}
__global__
void idct_ComputeWeightsKernel(const int n, complex *ww)
{
const int pos = threadIdx.x + blockIdx.x * blockDim.x;
if (pos >= n) return;
complex temp;
temp.x = sqrtf(2*n) * cosf(pos*PI/(2*n));
temp.y = sqrtf(2*n) * sinf(pos*PI/(2*n));
if (pos == 0) {
temp.x /= sqrtf(2);
temp.y /= sqrtf(2);}
ww[pos] = temp;
}
__global__
void idct_ComputeEvenKernel(const float *b, const int n, const int m, complex *ww, complex *y)
{
const int ix = threadIdx.x + blockIdx.x * blockDim.x;
const int iy = threadIdx.y + blockIdx.y * blockDim.y;
if (ix >= n || iy >= m) return;
const int pos = ix + iy*n;
/* handle this in idct_ComputeWeightsKernel
// Compute precorrection factor
ww[0].x = ww[0].x / sqrtf(2);
ww[0].y = ww[0].y / sqrtf(2);
*/
complex temp1, temp2;
temp1 = ww[iy];
temp2.x = temp1.x * b[pos];
temp2.y = temp1.y * b[pos];
y[iy + ix*m] = temp2;
}
__global__
void Reordering_a0_Kernel(complex *y, const int n, const int m, complex *yy)
{
const int ix = threadIdx.x + blockIdx.x * blockDim.x;
const int iy = threadIdx.y + blockIdx.y * blockDim.y;
if (ix >= n || iy >= m) return;
const int pos = ix + iy*n;
complex temp1, temp2;
temp1 = y[pos];
temp2.x = temp1.x / (float) n;
temp2.y = temp1.y / (float) n;
yy[iy + ix*n] = temp2;
}
__global__
void Reordering_a_Kernel(complex *yy, const int n, const int m, float *a)
{
const int ix = threadIdx.x + blockIdx.x * blockDim.x;
const int iy = threadIdx.y + blockIdx.y * blockDim.y;
if (ix >= n || iy >= m) return;
const int pos = ix + iy*n;
// Re-order elements of each column according to equations (5.93) and (5.94) in Jain
if (iy < n/2)
{
a[ix + 2*iy*n] = yy[pos].x;
a[ix + (2*iy+1)*n] = yy[ix + (m-iy-1)*n].x;
}
}
/**
* a = idct(b), where a is of size [n m].
* @param b, input array
* @param n, first dimension of a
* @param m, second dimension of a
* @param a, output array
*/
void cuIDCT(float *h_in, int n, int m, float *h_out) // a is of size [n m]
{
const int data_size = n * m * sizeof(float);
// device memory allocation
float *d_in, *d_out;
checkCudaErrors(cudaMalloc(&d_in, data_size));
checkCudaErrors(cudaMalloc(&d_out, data_size));
// transfer data from host to device
checkCudaErrors(cudaMemcpy(d_in, h_in, data_size, cudaMemcpyHostToDevice));
// compute IDCT using CUDA
// begin============================================
// Compute weights
complex *ww;
checkCudaErrors(cudaMalloc(&ww, n*sizeof(complex)));
dim3 threads(256);
dim3 blocks(iDivUp(n, threads.x));
idct_ComputeWeightsKernel<<<blocks, threads>>>(n, ww);
complex *y;
complex *yy;
cufftHandle plan;
dim3 threads1(32, 6);
dim3 blocks2(iDivUp(n, threads1.x), iDivUp(m, threads1.y)); // for even case
int Length[1] = {m}; // for each IFFT, the length is m
checkCudaErrors(cudaMalloc(&y, n*m*sizeof(complex)));
idct_ComputeEvenKernel<<<blocks2, threads1>>>(d_in, n, m, ww, y);
cufftSafeCall(cufftPlanMany(&plan, 1, Length,
Length, 1, m,
Length, 1, m, CUFFT_C2C, n));
cufftSafeCall(cufftExecC2C(plan, y, y, CUFFT_INVERSE)); // y is of size [n m]
checkCudaErrors(cudaMalloc(&yy, n*m*sizeof(complex)));
Reordering_a0_Kernel<<<blocks2, threads1>>>(y, n, m, yy);
cudaMemset(d_out, 0, data_size);
Reordering_a_Kernel<<<blocks2, threads1>>>(yy, n, m, d_out);
// end============================================
// transfer result from device to host
checkCudaErrors(cudaMemcpy(h_out, d_out, data_size, cudaMemcpyDeviceToHost));
// cleanup
cufftDestroy(plan);
checkCudaErrors(cudaFree(ww));
checkCudaErrors(cudaFree(y));
checkCudaErrors(cudaFree(yy));
checkCudaErrors(cudaFree(d_in));
checkCudaErrors(cudaFree(d_out));
}
上加了cudaMemset
,因为它帮助我清除了d_out
的问题。它不应该是必要的,你可以删除它。