似乎達(dá)到了CUDA限制,但這有什么限制?
似乎達(dá)到了CUDA限制,但這有什么限制?我有一個(gè)CUDA程序似乎在某種資源的某種限制,但我無(wú)法弄清楚該資源是什么。這是內(nèi)核函數(shù):__global__ void DoCheck(float2* points, int* segmentToPolylineIndexMap,
int segmentCount, int* output){
int segmentIndex = threadIdx.x + blockIdx.x * blockDim.x;
int pointCount = segmentCount + 1;
if(segmentIndex >= segmentCount)
return;
int polylineIndex = segmentToPolylineIndexMap[segmentIndex];
int result = 0;
if(polylineIndex >= 0)
{
float2 p1 = points[segmentIndex];
float2 p2 = points[segmentIndex+1];
float2 A = p2;
float2 a;
a.x = p2.x - p1.x;
a.y = p2.y - p1.y;
for(int i = segmentIndex+2; i < segmentCount; i++)
{
int currentPolylineIndex = segmentToPolylineIndexMap[i];
// if not a different segment within out polyline and
// not a fake segment
bool isLegit = (currentPolylineIndex != polylineIndex &&
currentPolylineIndex >= 0);
float2 p3 = points[i];
float2 p4 = points[i+1];
float2 B = p4;
float2 b;
b.x = p4.x - p3.x;
b.y = p4.y - p3.y;
float2 c;
c.x = B.x - A.x;
c.y = B.y - A.y;
float2 b_perp;
b_perp.x = -b.y;
b_perp.y = b.x;
float numerator = dot(b_perp, c);
float denominator = dot(b_perp, a);
bool isParallel = (denominator == 0.0);
output[segmentIndex] = result;}參數(shù)的大如下:devicePoints = 22,464 float2s = 179,712字節(jié)deviceSegmentsToPolylineIndexMap = 22,463 ints = 89,852字節(jié)numSegments = 1 int = 4個(gè)字節(jié)deviceOutput = 22,463 ints = 89,852字節(jié)當(dāng)我執(zhí)行這個(gè)內(nèi)核時(shí),它會(huì)崩潰視頻卡??雌饋?lái)我正在達(dá)到某種限制,因?yàn)槿绻沂褂肈oCheck<<<300, 32>>>(...);它來(lái)執(zhí)行內(nèi)核,它就可以工作。需要明確的是,參數(shù)是相同的,只是塊數(shù)不同。知道為什么一個(gè)人崩潰了視頻驅(qū)動(dòng)程序,而另一個(gè)沒(méi)有?失敗的那個(gè)似乎仍然在卡的數(shù)量限制內(nèi)。更新 有關(guān)我的系統(tǒng)配置的更多信息:視頻卡:nVidia 8800GTCUDA版本:1.1操作系統(tǒng):Windows Server 2008 R2我也嘗試在具有以下配置的筆記本電腦上,但得到了相同的結(jié)果:視頻卡:nVidia Quadro FX 880MCUDA版本:1.2操作系統(tǒng):Windows 7 64位
查看完整描述