我使用Linux中的GeForce GT 610卡在OpenCL中编程。我的CPU和GPU双精度结果不一致。我可以在这里发布部分代码，但我首先想知道其他人是否遇到过这个问题。当我运行具有多次迭代的循环时，GPU和CPU双精度结果之间的差异变得明显。代码真的没有什么特别之处，但如果有人有兴趣我可以在这里发布。非常感谢。这是我的代码。请原谅__和错误的格式，因为我是新来的:)正如你所看到的，我有两个循环，我的CPU代码基本上几乎是一个相同的版本。
#ifdef cl_khr_fp64
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
#elif defined(cl_amd_fp64)
#pragma OPENCL EXTENSION cl_amd_fp64 : enable
#else
#error "Double precision floating point not supported by OpenCL implementation."
#ENDIF
__kernel void simpar(__global double* fp, __global double* fp1,
__global double* fp3, __global double* fp5,
__global double* fp6, __global double* fp7,
__global double* fp8, __global double* fp8Plus,
__global double* x, __global double* v, __global double* acc,
__global double* keBuf, __global double* peBuf,
unsigned int prntstps, unsigned int nprntstps, double dt
) {
unsigned int m,i,j,k,l,t;
unsigned int chainlngth=100;
double dxi, twodxi, dxipl1, dximn1, fac, fac1, fac2, fac13, fac23;
double ke,pe,tke,tpe,te,dx;
double hdt, hdt2;
double alpha=0.16;
double beta=0.7;
double cmass;
double peTemp;
nprntstps=1001;
dt=0.01;
prntstps=100;
double alphaby4=beta/4.0;
hdt=0.5*dt;
hdt2=dt*0.5*dt;
double Xlocal,Vlocal,Acclocal;
unsigned int global_id=get_global_id(0);
if (global_id<chainlngth){
Xlocal=x[global_id];
Vlocal=v[global_id];
Acclocal=acc[global_id];
for (m=0;m<nprntstps;m++){
for(l=0;l<prntstps;l++){
Xlocal =Xlocal+dt *Vlocal+hdt2*Acclocal;
x[global_id]=Xlocal;
barrier(CLK_LOCAL_MEM_FENCE);
Vlocal =Vlocal+ hdt * Acclocal;
barrier(CLK_LOCAL_MEM_FENCE);
j = global_id - 1;
k = global_id + 1;
if (j == -1) {
dximn1 = 0.0;
} else {
dximn1 = x[j];
}
if (k == chainlngth) {
dxipl1 = 0.0;
} else {
dxipl1 = x[k];
}
dxi = Xlocal;
twodxi = 2.0 * dxi;
fac = dxipl1 + dximn1 - twodxi;
fac1 = dxipl1 - dxi;
fac2 = dxi - dximn1;
fac13 = fac1 * fac1 * fac1;
fac23 = fac2 * fac2 * fac2;
Acclocal = alpha * fac + beta * (fac13 - fac23);
barrier(CLK_GLOBAL_MEM_FENCE);
Vlocal += hdt * Acclocal;
v[global_id]=Vlocal;
acc[global_id]=Acclocal;
barrier(CLK_GLOBAL_MEM_FENCE);
}
barrier(CLK_GLOBAL_MEM_FENCE);
tke = tpe = te = dx = 0.0;
ke=0.5*Vlocal*Vlocal;//Vlocal*Vlocal;
barrier(CLK_GLOBAL_MEM_FENCE);
fp6[(m*100)+global_id]=ke;
keBuf[global_id]=ke;
ke=0.0;
barrier(CLK_GLOBAL_MEM_FENCE);
j = global_id - 1;
k = global_id + 1;
if (j == -1) {
dximn1 = 0.0;
} else {
dximn1 = x[j];
}
if (k == chainlngth) {
dxipl1 = 0.0;
} else {
dxipl1 = x[k];
}
dxi = Xlocal;
twodxi = 2.0 * dxi;
fac = dxipl1 + dximn1 - twodxi;
fac1 = dxipl1 - dxi;
fac2 = dxi - dximn1;
fac13 = fac1 * fac1 * fac1;
fac23 = fac2 * fac2 * fac2;
Acclocal = alpha * fac + beta * (fac13 - fac23);
barrier(CLK_GLOBAL_MEM_FENCE);
Vlocal += hdt * Acclocal;
v[global_id]=Vlocal;
acc[global_id]=Acclocal;
barrier(CLK_GLOBAL_MEM_FENCE);
}
barrier(CLK_GLOBAL_MEM_FENCE);
tke = tpe = te = dx = 0.0;
ke=0.5*Vlocal*Vlocal;//Vlocal*Vlocal;
barrier(CLK_GLOBAL_MEM_FENCE);
fp6[(m*100)+global_id]=ke;
keBuf[global_id]=ke;
ke=0.0;
barrier(CLK_GLOBAL_MEM_FENCE);
j = global_id - 1;
k = global_id + 1;
if (j == -1) {
dximn1 = 0.0;
} else {
dximn1 = x[j];
}
if (k == chainlngth) {
dxipl1 = 0.0;
} else {
dxipl1 = x[k];
}
dxi = Xlocal;
twodxi = 2.0 * dxi;
fac = dxipl1 + dximn1 - twodxi;
fac1 = dxipl1 - dxi;
fac2 = dxi - dximn1;
fac13 = fac1 * fac1 * fac1;
fac23 = fac2 * fac2 * fac2;
Acclocal = alpha * fac + beta * (fac13 - fac23);
barrier(CLK_GLOBAL_MEM_FENCE);
Vlocal += hdt * Acclocal;
v[global_id]=Vlocal;
acc[global_id]=Acclocal;
barrier(CLK_GLOBAL_MEM_FENCE);
}
barrier(CLK_GLOBAL_MEM_FENCE);
tke = tpe = te = dx = 0.0;
ke=0.5*Vlocal*Vlocal;//Vlocal*Vlocal;
barrier(CLK_GLOBAL_MEM_FENCE);
fp6[(m*100)+global_id]=ke;
keBuf[global_id]=ke;
ke=0.0;
barrier(CLK_GLOBAL_MEM_FENCE);
if (global_id ==0){
for(t=0;t<100;t++)
tke+=keBuf[t];
}
barrier(CLK_GLOBAL_MEM_FENCE);
k = global_id-1;
if (k == -1) {
dx = Xlocal;
}else{
dx = Xlocal-x[k];
}
fac = dx * dx;
peTemp = alpha * 0.5 * fac + alphaby4 * fac * fac;
fp8[global_id*m]=peTemp;
if (global_id == 0)
tpe+=peTemp;
barrier(CLK_GLOBAL_MEM_FENCE);
cmass=0.0;
dx = -x[100-1];
fac = dx*dx;
pe=alpha*0.5*fac+alphaby4*fac*fac;
if (global_id==0){
fp8Plus[m]=pe;
tpe+=peBuf[0];
fp5[m*2]=i;
fp5[m*2+1]=cmass;
te=tke+tpe;
fp[m*2]=m;
fp[m*2+1]=te;
}
barrier(CLK_GLOBAL_MEM_FENCE);
//cmass /=100;
fp1[(m*chainlngth)+global_id]=Xlocal-cmass;
// barrier(CLK_GLOBAL_MEM_FENCE);
fp3[(m*chainlngth)+global_id]=Vlocal;
// barrier(CLK_GLOBAL_MEM_FENCE);
fp7[(m*chainlngth)+global_id]=Acclocal;
barrier(CLK_GLOBAL_MEM_FENCE);
}
}
}
答案 0 :(得分：6)
实际上，这是一种预期的行为。
在较旧的x86 CPU上，浮点数为80位（英特尔"long double"），仅在需要时被截断为64位。 当用于浮点算术的SIMD单元/指令到达x86 CPU时，浮点双精度默认为64位;但是，仍然可以使用80位，具体取决于您的编译器设置。有很多关于此的内容：Wikipedia: Floating Point。
在浮点“魔术”上检查OpenCL 和主机代码的编译器设置，以便更好地同意您的结果。计算值的absolute和relative error，并检查此错误边距对您的应用程序是否安全。