Roger Dahl

Roger Dahl has asked 22 questions and find answers to 72 problems.

Stats

About

Need a computation accelerated with CUDA C? I may be available for consulting in the areas of:

Parallelization
Implementation
Optimization

Roger Dahl questions

In NVIDIA GPU profiling, what are sub-partitions, sectors and units?
IEEE-754 floating point: Divide first or multiply first for best precision?
Understanding the symbol parameter of cudaMemcpyFromSymbol()
CUDA: In which memory space is a fixed size array stored?
What are "Other" Issue Stall Reasons displayed by the Nsight profiler?
In Python, how do I determine if an object still exists?
boost::filesystem and Unicode under Linux and Windows
cudaMallocManaged() returns "operation not supported"
Decoding an ASN.1 DER OCTET STRING with OpenSSL
Timing different sections in CUDA kernel

Roger Dahl answers

CUDA. Shared Memory vs Constant
Can string data types be used in C++ CUDA kernels?
how to free device_vector<int>
How do I enable syntax highlighting of CUDA .cu files in Visual Studio 2010?
Is there an equivalent to memcpy() that works inside a CUDA kernel?
segmented reduction with scattered segments
Difference between kernels construct and parallel construct
Difference between memcpy_htod and to_gpu in Pycuda?
Load/Store Units (LD/ST) and Special Function Units (SFUs) for the Kepler architecture
Accessing class data members from within cuda kernel - how to design proper host/device interaction?