thrust

问题 I am using thrust::sequence(myvector.begin(), myvector.end(), 0, 1) and achieve good ordered list like: 0, 1, 2, 3, 4 My question is how can I achieve such a list below (the best way?) 0, 0, 0, 1, 1, 1, 2, 2 ,2, 3, 3, 3 I know how to make it with functors, so please do not try to answer it with functor. I want to learn if there is an optimized way for it in Thrust, or am I missing a simple way.. 回答1: Something like this: thrust::device_vector<int> myvector(N); thrust::transform( thrust::make

问题 Its mentioned that CUDA 5 allows library calls from kernel Does that mean CUDA 5 can use thrust or STL inside device code then ? 回答1: CUDA 5 has a device code linker for the first time. It means you can have separate object files of device functions and link against them rather than having to declare them at compilation unit scope. It also adds the ability for kernels to call other kernels (but only on compute 3.5 Kepler devices). None of this means that C++ standard library templates or

问题 I have a 2d array and I want to sort it by row meaning that if the array is 3 2 2 3 2 2 3 3 3 3 3 3 2 2 2 2 3 3 2 2 3 2 2 3 2 2 3 3 3 2 2 2 2 2 2 2 2 2 2 2 3 2 2 2 2 2 3 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 2 3 2 2 3 3 2 3 3 3 2 2 2 2 3 3 3 3 3 2 2 3 2 2 3 3 2 3 3 3 2 3 2 2 3 3 3 3 I want to take the array 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 2 2 2 2 2 3 2 2 2 3 2 2 3 2 2 3 3 2 3 3 2 2 3 2 2 3 3 3 2 3 2 2 3 2 2 3 3 3 3 3 3 2 2 2 2 3 3 2 2 3 3 2 2 2 2 3 3 3 3 3 3 2 3 2 2 3 3 2 3 3 3 2 3 2 2 3 3

问题 I have a pair of arrays of equal size, I will call them keys and values. For example: K: V 1: 99 1: 100 1: 100 1: 100 1: 103 2: 103 2: 105 3: 45 3: 67 The keys are sorted and the values associated with each key are sorted. How do I remove the value duplicates associated with each key and its corresponding key? That is, I want to compact the above to: 1: 99 1: 100 1: 103 2: 103 <-- This should remain, since key is different 2: 105 3: 45 3: 67 I looked at the stream compaction functions

问题 I was wondering if it is possible to sort by keys using Thrust Library without the need of creating a Vector to store the keys (on the fly). For example I have the following two vectors: Keys and Values: vectorKeys: 0, 1, 2, 0, 1, 2, 0, 1, 2 VectorValues: 10, 20, 30, 40, 50, 60, 70, 80, 90 After sort by keys: thrust::sort_by_key(vKeys.begin(), vKeys.end(), vValues.begin()); The Resulting vectors are: vectorKeys: 0, 0, 0, 1, 1, 1, 2, 2, 2 VectorValues: 10, 40, 70, 20, 50, 80, 30, 60, 90 What I

问题 I am using CUDA/Thrust/CUDPP. As I understand, in Stream compaction, certain items in an array are marked as invalid and then "removed". Now what does "removal" really mean here? Suppose the original array A and has length 6. If 2 elements are invalid (by whatever condition we may provide) then Does the system create a new array of size 4 in GPU-memory to store the valid elements to get the final result? OR does it physically remove the invalid elements from memory and shrink the original

问题 I have two arrays of integers dmap and dflag on the device of the same length and I have wrapped them with thrust device pointers, dmapt and dflagt There are some elements in the dmap array with value -1. I want to remove these -1's and the corresponding values from the dflag array. I am using the remove_if function to do this, but I cannot figure out what the return value of this call is or how I should use this returned value to get . ( I want to pass these reduced arrays to the reduce_by

问题 I have following thrust::transform call. my_functor *f_1 = new my_functor(); thrust::transform(data.begin(), data.end(), data.begin(),*f_1); I want to detect it's corresponding kernel in PTX file. But there are many kernels containing my_functor in their mangled names. For example- _ZN6thrust6system4cuda6detail6detail23launch_closure_by_valueINS2_17for_each_n_detail18for_each_n_closureINS_12zip_iteratorINS_5tupleINS_6detail15normal_iteratorINS_10device_ptrIiEEEESD_NS_9null_typeESE_SE_SE_SE_SE

问题 I have following thrust::transform call. my_functor *f_1 = new my_functor(); thrust::transform(data.begin(), data.end(), data.begin(),*f_1); I want to detect it's corresponding kernel in PTX file. But there are many kernels containing my_functor in their mangled names. For example- _ZN6thrust6system4cuda6detail6detail23launch_closure_by_valueINS2_17for_each_n_detail18for_each_n_closureINS_12zip_iteratorINS_5tupleINS_6detail15normal_iteratorINS_10device_ptrIiEEEESD_NS_9null_typeESE_SE_SE_SE_SE

问题 I have a 5000x500 matrix and I want to sort each row separately with cuda. I can use arrayfire but this is just a for loop over the thrust::sort, which should not be efficient. https://github.com/arrayfire/arrayfire/blob/devel/src/backend/cuda/kernel/sort.hpp for(dim_type w = 0; w < val.dims[3]; w++) { dim_type valW = w * val.strides[3]; for(dim_type z = 0; z < val.dims[2]; z++) { dim_type valWZ = valW + z * val.strides[2]; for(dim_type y = 0; y < val.dims[1]; y++) { dim_type valOffset =