StackRating

An Elo-based rating system for Stack Overflow

Home | About | Stats and Analysis | Get a Badge

Rating Stats for

Greg Smith

Rating
1585.55 (2,598th)

Reputation
8,623 (18,136th)

Page: 1 2 3 4

Title	Δ
How to profile the number of global memory transactions without usi...	0.00
How to evaluate CUDA performance?	-4.26
Is there a way to emulate multiple GPUs with one?	0.00
CUDA inter-kernel communication between different streams	+3.52
optimal number of CUDA parallel blocks	-4.65
Changing gpu with debugger	0.00
cuda: write to same global memory location by several threads	0.00
cuModuleGetFunction don't accepts simple kernel names, only "....	0.00
how to profile CUDA using Nvidia Visual Profile with Matlab	-4.66
Nvidia Nsight 2.2 MSVC++ 2010 Profiling - see user defined Host fun...	+3.72
CUDA: shared data member of struct and member of reference to that...	0.00
CUPTI / CUDA prof_trigger not working as expected	0.00
Equivalent of usleep() in CUDA kernel?	+3.79
CUDA Global Memory, Where is it?	+3.59
blocks, threads, warpSize	+3.46
What is the difference: DRAM Throughput vs Global Memory Throughput	+3.50
CUDA device heap memory for different applications	0.00
Deferring code in Twisted to a specific thread	+4.77
cuda code produces incorrect result in release mode	+3.84
cuda sdk example simpleStreams in SDK 4.1 not working	-0.50
NVidia CUDA Trace or Debug Function	0.00
What CUDA resources are used by the display driver itself?	+3.86
CUDA concurrent kernels serialize when using events	+3.73
How CUDA Blocks/Warps/Threads map onto CUDA Cores?	0.00
cuda infinite kernel	0.00
how does CUDA schedule its threads	+3.87
Why is the constant memory size limited in CUDA?	0.00
Diverting gpu output via c/c++ libraries	0.00
std::vector vs normal array	-0.09
WMI Win32_Process creating process that can not remotely initialize...	0.00
Scalability Analysis on GPU	+3.91
How can kernel execution time increase with better occupancy?	0.00
Debugging OpenCL with NVIDIA Nsight 2.1 and Visual Studio 2010	+3.86
CUDA profiled achieved occupany very low; how to diagnose?	+1.98
CUDA profiled achieved occupany very low; how to diagnose?	+1.98
NVIDIA Parallel Nsight Vs Visual Profiler	0.00
clock() in opencl	0.00
How to calculate Gflops of a kernel	0.00
Nvidia compute visual profiler always shows press any key to continue	0.00
Where does CUDA allocate the stack frame for kernels?	+3.92
How to profile PyCuda code with the Visual Profiler?	0.00
Debugging a clobbered static variable in C (gdb broken?)	+4.39