I am trying to make a B-Tree in Promela so that I can prove stuff about it, however, it seems that Promela does not support recursive data types. This doesn't work:
#define n 2
typedef BTreeNode
{
int keys[2*n-1];
BTreeNode children[2*n];
int c;
};
How can I make a B-Tree in Promela, and if I can't, which tool would you suggest? I considered QuickCheck and Prolog. However making a B-Tree in Prolog would be hard too.
You'll represent the children using an index into a statically defined array of nodes. Like this:
#define n 2
#define BTreeNodeId byte
typedef BTreeNode {
BTreeNodeId my_id;
int keys[2*n-1];
BTreeNodeId children[2*n];
int c;
};
BTreeNode nodes [10];
byte next_node_id = 0;
With this, you 'allocate' nodes by incrementing next_node_id and can access a child by referencing into nodes using the child's id.
Related
I have a question that I found many threads in, but none did explicitly answer my question.
I am trying to have a multidimensional array inside the kernel of the GPU using thrust. Flattening would be difficult, as all the dimensions are non-homogeneous and I go up to 4D. Now I know I cannot have device_vectors of device_vectors, for whichever underlying reason (explanation would be welcome), so I tried going the way over raw-pointers.
My reasoning is, a raw pointer points onto memory on the GPU, why else would I be able to access it from within the kernel. So I should technically be able to have a device_vector, which holds raw pointers, all pointers that should be accessible from within the GPU. This way I constructed the following code:
thrust::device_vector<Vector3r*> d_fluidmodelParticlePositions(nModels);
thrust::device_vector<unsigned int***> d_allFluidNeighborParticles(nModels);
thrust::device_vector<unsigned int**> d_nFluidNeighborsCrossFluids(nModels);
for(unsigned int fluidModelIndex = 0; fluidModelIndex < nModels; fluidModelIndex++)
{
FluidModel *model = sim->getFluidModelFromPointSet(fluidModelIndex);
const unsigned int numParticles = model->numActiveParticles();
thrust::device_vector<Vector3r> d_neighborPositions(model->getPositions().begin(), model->getPositions().end());
d_fluidmodelParticlePositions[fluidModelIndex] = CudaHelper::GetPointer(d_neighborPositions);
thrust::device_vector<unsigned int**> d_fluidNeighborIndexes(nModels);
thrust::device_vector<unsigned int*> d_nNeighborsFluid(nModels);
for(unsigned int pid = 0; pid < nModels; pid++)
{
FluidModel *fm_neighbor = sim->getFluidModelFromPointSet(pid);
thrust::device_vector<unsigned int> d_nNeighbors(numParticles);
thrust::device_vector<unsigned int*> d_neighborIndexesArray(numParticles);
for(unsigned int i = 0; i < numParticles; i++)
{
const unsigned int nNeighbors = sim->numberOfNeighbors(fluidModelIndex, pid, i);
d_nNeighbors[i] = nNeighbors;
thrust::device_vector<unsigned int> d_neighborIndexes(nNeighbors);
for(unsigned int j = 0; j < nNeighbors; j++)
{
d_neighborIndexes[j] = sim->getNeighbor(fluidModelIndex, pid, i, j);
}
d_neighborIndexesArray[i] = CudaHelper::GetPointer(d_neighborIndexes);
}
d_fluidNeighborIndexes[pid] = CudaHelper::GetPointer(d_neighborIndexesArray);
d_nNeighborsFluid[pid] = CudaHelper::GetPointer(d_nNeighbors);
}
d_allFluidNeighborParticles[fluidModelIndex] = CudaHelper::GetPointer(d_fluidNeighborIndexes);
d_nFluidNeighborsCrossFluids[fluidModelIndex] = CudaHelper::GetPointer(d_nNeighborsFluid);
}
Now the compiler won't complain, but accessing for example d_nFluidNeighborsCrossFluids from within the kernel will work, but return wrong values. I access it like this (again, from within a kernel):
d_nFluidNeighborsCrossFluids[iterator1][iterator2][iterator3];
// Note: out of bounds indexing guaranteed to not happen, indexing is definitely right
The question is, why does it return wrong values? The logic behind it should work in my opinion, since my indexing is correct and the pointers should be valid addresses from within the kernel.
Thank you already for your time and have a great day.
EDIT:
Here is a minimal reproducable example. For some reason the values appear right despite of having the same structure as my code, but cuda-memcheck reveals some errors. Uncommenting the two commented lines leads me to my main problem I am trying to solve. What does the cuda-memcheck here tell me?
/* Part of this example has been taken from code of Robert Crovella
in a comment below */
#include <thrust/device_vector.h>
#include <stdio.h>
template<typename T>
static T* GetPointer(thrust::device_vector<T> &vector)
{
return thrust::raw_pointer_cast(vector.data());
}
__global__
void k(unsigned int ***nFluidNeighborsCrossFluids, unsigned int ****allFluidNeighborParticles){
const unsigned int i = blockIdx.x*blockDim.x + threadIdx.x;
if(i > 49)
return;
printf("i: %d nNeighbors: %d\n", i, nFluidNeighborsCrossFluids[0][0][i]);
//for(int j = 0; j < nFluidNeighborsCrossFluids[0][0][i]; j++)
// printf("i: %d j: %d neighbors: %d\n", i, j, allFluidNeighborParticles[0][0][i][j]);
}
int main(){
const unsigned int nModels = 2;
const int numParticles = 50;
thrust::device_vector<unsigned int**> d_nFluidNeighborsCrossFluids(nModels);
thrust::device_vector<unsigned int***> d_allFluidNeighborParticles(nModels);
for(unsigned int fluidModelIndex = 0; fluidModelIndex < nModels; fluidModelIndex++)
{
thrust::device_vector<unsigned int*> d_nNeighborsFluid(nModels);
thrust::device_vector<unsigned int**> d_fluidNeighborIndexes(nModels);
for(unsigned int pid = 0; pid < nModels; pid++)
{
thrust::device_vector<unsigned int> d_nNeighbors(numParticles);
thrust::device_vector<unsigned int*> d_neighborIndexesArray(numParticles);
for(unsigned int i = 0; i < numParticles; i++)
{
const unsigned int nNeighbors = i;
d_nNeighbors[i] = nNeighbors;
thrust::device_vector<unsigned int> d_neighborIndexes(nNeighbors);
for(unsigned int j = 0; j < nNeighbors; j++)
{
d_neighborIndexes[j] = i + j;
}
d_neighborIndexesArray[i] = GetPointer(d_neighborIndexes);
}
d_nNeighborsFluid[pid] = GetPointer(d_nNeighbors);
d_fluidNeighborIndexes[pid] = GetPointer(d_neighborIndexesArray);
}
d_nFluidNeighborsCrossFluids[fluidModelIndex] = GetPointer(d_nNeighborsFluid);
d_allFluidNeighborParticles[fluidModelIndex] = GetPointer(d_fluidNeighborIndexes);
}
k<<<256, 256>>>(GetPointer(d_nFluidNeighborsCrossFluids), GetPointer(d_allFluidNeighborParticles));
if (cudaGetLastError() != cudaSuccess)
printf("Sync kernel error: %s\n", cudaGetErrorString(cudaGetLastError()));
cudaDeviceSynchronize();
}
A device_vector is a class definition. That class has various methods and operators associated with it. The thing that allows you to do this:
d_nFluidNeighborsCrossFluids[...]...;
is a square-bracket operator. That operator is a host operator (only). It is not usable in device code. Issues like this give rise to the general statements that "thrust::device_vector is not usable in device code." The device_vector object itself is generally not usable. However the data it contains is usable in device code, if you attempt to access it via a raw pointer.
Here is an example of a thrust device vector that contains an array of pointers to the data contained in other device vectors. That data is usable in device code, as long as you don't attempt to make use of the thrust::device_vector object itself:
$ cat t1509.cu
#include <thrust/device_vector.h>
#include <stdio.h>
template <typename T>
__global__ void k(T **data){
printf("the first element of vector 1 is: %d\n", (int)(data[0][0]));
printf("the first element of vector 2 is: %d\n", (int)(data[1][0]));
printf("the first element of vector 3 is: %d\n", (int)(data[2][0]));
}
int main(){
thrust::device_vector<int> vector_1(1,1);
thrust::device_vector<int> vector_2(1,2);
thrust::device_vector<int> vector_3(1,3);
thrust::device_vector<int *> pointer_vector(3);
pointer_vector[0] = thrust::raw_pointer_cast(vector_1.data());
pointer_vector[1] = thrust::raw_pointer_cast(vector_2.data());
pointer_vector[2] = thrust::raw_pointer_cast(vector_3.data());
k<<<1,1>>>(thrust::raw_pointer_cast(pointer_vector.data()));
cudaDeviceSynchronize();
}
$ nvcc -o t1509 t1509.cu
$ cuda-memcheck ./t1509
========= CUDA-MEMCHECK
the first element of vector 1 is: 1
the first element of vector 2 is: 2
the first element of vector 3 is: 3
========= ERROR SUMMARY: 0 errors
$
EDIT: In the mcve you have now posted, you point out that an ordinary run of the code appears to give correct results, but when you use cuda-memcheck, errors are reported. You have a general design problem that will cause this.
In C++, when an object is defined within a curly-braces region:
{
{
Object A;
// object A is in-scope here
}
// object A is out-of-scope here
}
// object A is out of scope here
k<<<...>>>(anything that points to something in object A); // is illegal
and you exit that region, the object defined within the region is now out of scope. For objects with constructors/destructors, this usually means the destructor of the object will be called when it goes out-of-scope. For a thrust::device_vector (or std::vector) this will deallocate any underlying storage associated with that vector. That does not necessarily "erase" any data, but attempts to use that data are illegal and would be considered UB (undefined behavior) in C++.
When you establish pointers to such data inside an in-scope region, and then go out-of-scope, those pointers no longer point to anything that would be legal to access, so attempts to dereference the pointer would be illegal/UB. Your code is doing this. Yes, it does appear to give the correct answer, because nothing is actually erased on deallocation, but the code design is illegal, and cuda-memcheck will highlight that.
I suppose one fix would be to pull all this stuff out of the inner curly-braces, and put it at main scope, just like the d_nFluidNeighborsCrossFluids device_vector is. But you might also want to rethink your general data organization strategy and flatten your data.
You should really provide a minimal, complete, verifiable/reproducible example; yours is neither minimal, nor complete, nor verifiable.
I will, however, answer your side-question:
I know I cannot have device_vectors of device_vectors, for whichever underlying reason (explanation would be welcome)
While a device_vector regards a bunch of data on the GPU, it's a host-side data structure - otherwise you would not have been able to use it in host-side code. On the host side, what it holds should be something like: The capacity, the size in elements, the device-side pointer to the actual data, and maybe more information. This is similar to how an std::vector variable may refer to data that's on the heap, but if you create the variable locally the fields I mentioned above will exist on the stack.
Now, those fields of the device vector that are located in host memory are not generally accessible from the device-side. In device-side code you would typically use the raw pointer to the device-side data the device_vector manages.
Also, note that if you have a thrust::device_vector<T> v, each use of operator[] means a bunch of separate CUDA calls to copy data to or from the device (unless there's some caching going on under the hoold). So you really want to avoid using square-brackets with this structure.
Finally, remember that pointer-chasing can be a performance killer, especially on a GPU. You might want to consider massaging your data structure somewhat in order to make it amenable to flattening.
The reason why I ask this is because there is some strange bug in my code and I suspect it could be some aliasing problem:
__shared__ float x[32];
__shared__ unsigned int xsum[32];
int idx=threadIdx.x;
unsigned char * xchar=(unsigned char *)x;
//...do something
if (threadIdx.x<32)
{
xchar[4*idx]&=somestring[0];
xchar[4*idx+1]&=somestring[1];
xchar[4*idx+2]&=somestring[2];
xchar[4*idx+3]&=somestring[3];
xsum[idx]+=*((unsigned int *)(x+idx));//<-Looks like the compiler sometimes fail to recongize this as the aliasing of xchar;
};
The compiler only needs to honour aliasing between compatible types. Since char and float are not compatible, the compiler is free to assume the pointers never alias.
If you want to do bitwise operations on float, firstly convert (via __float_as_int()) to unsigned integer, then operate on that, and finally convert back to float (using __int_as_float()).
I think you have a race condition here. But I don't know what is somestring. If it is the same for all threads you can do like this:
__shared__ float x[32];
unsigned char * xchar=(unsigned char *)x;
//...do something
if(threadIdx.x<4) {
xchar[threadIdx.x]&=somestring[threadIdx.x];
}
__syncthreads();
unsigned int xsum+=*((unsigned int *)x);
It means that every thread shares the same array and therefore, xsum is the same between all threads. If you want that each thread has its own array, you have to allocate an array of 32*number_of_threads_in_block and use an offset.
PS: the code above works only in 1D block. In 2D or 3D you have to compute you own threadID and be sure that only 4 threads execute the code.
I am still learning about pointers and structs, but I hoping someone might know if it is possible to access individual members sequentially by use of a pointer?
Typedef record_data {
float a;
float b;
float c;
}records,*Sptr;
records lists[5];
Sptr ptr;
Example: assign all members of the 5 lists with a value of float 1.0
// instead of this
(void)testworks(void){
int i;
float j=1.0;
ptr = &lists[i]
ptr->lists[0].a = j;
ptr->lists[0].b = j;
ptr->lists[0].c = j;
ptr->lists[1].a = j;
// ... and so on
ptr->lists[4].c = j;
}
// want to do this
(void)testwannado(void){
int a,i;
float j=1.0;
ptr = &lists[i]
for (a=0;a<5;a++){ // step through typedef structs
for (i=0;i<3;i++){ // step through members
???
}
}
Forgive my errors in this example below, but it represents the closest thing I can think of for want I am trying to accomplish.
int *mptr;
mptr = &(ptr->lists[0].a) // want to assign a pointer to members so all 3 members can be used...
*mptr++ = j; // so I can do something like this.
This wasn't compiled, so any other errors are unintentional.
You generally don't want to do that. Structure members should be accessed individually. You can run into a lot of portability problems by assuming the memory layout of how multiple consecutive structure members are placed in memory. And most (C-like) languages do not give you a way to "introspect" through the members of a structure.
I have to transfer a number of elements of type:
typedef struct
{
float w;
int a, b;
} edge;
to different processes, hence I am creating an MPI derived type like this:
unsigned int typecount;
MPI_Datatype PEDGE, types[2] = { MPI_FLOAT, MPI_INT };
MPI_Aint offsets[2], extent;
int blocklen[2] = { 1, 2 };
typecount = 2;
offsets[0] = 0;
MPI_Type_extent(MPI_FLOAT, &extent);
offsets[1] = (1*extent);
MPI_Type_struct (typecount, blocklen, offsets, types, &PEDGE);
MPI_Type_commit(&PEDGE);
When I do a sizeof(edge) I get 12 bytes, but I am getting only 8 bytes when I do sizeof(PEDGE)...why is that? Apart from this, my code for sending some elements of PEDGE type to arrays of edge type are failing, probably because of this mismatch.
The problem here is that an MPI_Datatype object such as PEDGE is not itself the new datatype, merely an opaque handle to some implementation-specific entity that MPI can interpret as a datatype. As such, sizeof() will not be able to return its accurate size. Use MPI_Type_size() instead.
As for the sends failing, I can't say much without seeing your code, but your datatype definition does look correct.
people, i've an issue now..
#include <stdio.h>
#include <stdlib.h>
typedef struct a
{
int *aa;
int *bb;
struct b *wakata;
}a;
typedef struct b
{
int *you;
int *me;
}b;
int main()
{
a *aq;
aq = (a*)malloc(sizeof(a*));
*aq->wakata->you = 1;
*aq->wakata->me = 2;
free(aq);
return 0;
}
and compiled, then debugged :
gcc -o tes tes.c --debug
sapajabole#cintajangankaupergi:/tmp$ gdb -q ./tes
Reading symbols from /tmp/tes...done.
(gdb) r
Starting program: /tmp/tes
Program received signal SIGSEGV, Segmentation fault.
0x08048414 in main () at tes.c:22
22 *aq->wakata->you = 1;
well, the question is, how to set the value to variable inside struct 'b' through struct 'a' ?
anyone ?
The initial allocation of a is only allocating 4 bytes (in a 32-bit architecture). It should be:
aq = (a*)malloc(sizeof(a));
And wakata has not been initialized: Maybe this:
aq->wakata = (b*)malloc(sizeof(b));
And it will need a corresponding free as well prior to the free of aq.
free(aq->wakata);
And since you have pointers to the integers, those would also need to be allocated (you and me). But it is not clear if that is your goal. You probably should remove the * from the int declarations so that they are simply int members rather than the pointers to int.
Looks like you have a few mistakes here. See the code below.
In general a few things to keep in mind. You can't access memory before you malloc it. Also, there is a difference between memory and pointers e.g. int and int *
#include <stdio.h>
#include <stdlib.h>
typedef struct a
{
int aa;
int bb;
struct b *wakata;
}a;
typedef struct b
{
int you;
int me;
}b;
int main()
{
a * aq = malloc(sizeof(a));
aq->wakata = malloc(sizeof(b))
aq->wakata->you = 1;
aq->wakata->me = 2;
free(aq->wakata)
free(aq);
return 0;
}
wakata isn't pointing to any valid memory. You have to malloc memory for it, and then also for wakata->you and wakata->me
Pointers do not contain data. They point at data. That is why they are called pointers.
When you malloc enough space to store an a instance named aq, you allocate space for the pointers contained in that structure. You do not cause them to point at anything, nor do you allocate space to contain the things that they would point at.
You're not allocating space for b in struct a. You have defined 'a' as holding pointers, not structs. Also, I think malloc(sizeof(a*)) should be malloc(sizeof(a))
aq = (a*)malloc(sizeof(a)); // You should probably use calloc here
aq->wakata = (b*)malloc(sizeof(b));
you and me don't seem to need to be pointers, just normal ints
You have some problems with your code.
When you allocate memory for the struct a, you should do
aq = (a*)malloc(sizeof(a));
You now allocated memory for the struct a, but not for the struct b pointed by the wakata member, so you need to do
aq->wakata = (b*)malloc(sizeof(b));
Finally, in the struct b there should not be int* members, but int members. This way, you'll be able to correctly assign a value to them.
Remember that you should check for the correct allocation of memory by checking if the malloc return value is not NULL.