StackRating

An Elo-based rating system for Stack Overflow
Home   |   About   |   Stats and Analysis   |   Get a Badge
Rating Stats for

Jez

Rating
1496.60 (4,024,946th) 		Reputation
1,451 (112,322nd)
Page: 1
Title Δ
Is warp shuffling with less than a full warp safe? 0.00
Eliminate cudaMemcpy between kernel calls 0.00
CUDA 32 bit integer operations faster on Kepler than Maxwell? 0.00
CUDA performance with Computer Vision Algorithm 0.00
CUDA Matrix Addition Timing with varying block size -4.07
Use cudaDeviceSynchronize() inside kernel for global synchronisation 0.00
Is it good practice to run different kernel variants for 'full&... -0.01
Cuda Programming in comparision with C Programming -4.05
Launching a CUDA stream from each host thread, will each stream run... 0.00
CUDA by example program GPU version runs slower or almost the same... 0.00
Converting from AoS to SoA - Write performance and Optimal packing 0.00
Faster Matrix Multiplication in CUDA +3.99
Amount of cores per SM and threads per block in CUDA 0.00
Understanding CUDA profiler output (nvprof) 0.00
Cuda grid size limitations 0.00
Avoiding CudaMemcpy in an iterative loop 0.00
CUDA loop unrolling on triangular region 0.00
CUDA variables inside global kernel 0.00
Optimizing specific memory usage for CUDA 0.00
Loading from global memory -3.18
How bad is it to launch many small kernels in CUDA? -0.05
Is there a penalty to using char variables in CUDA kernels? -1.46
Difference between MP and SP (or is it Cuda Core) in thread paralle... -0.07
How does the compiler generate the instance of the function when I&... -3.66
Cuda illegal memory access error when using array indexes stored in... 0.00
GTX Titan Z Global Memory 0.00
What is the best way to make an application have CPU and GPU comput... -3.59
loop unrolling with dynamic parallelism decrease the time performance 0.00
cuda: shared 'constants' amongst thread block 0.00
Normal Cuda Vs CuBLAS? +3.90
slow cuda computing time 0.00
Can we use cuFFT for processing multiple files of different sizes? 0.00
Defining MACRO depending on GPU compute capability +4.29
It's slower to calculate integral image using CUDA than CPU code +4.56
GPU Tridiagonal Solver (CUDA) : Non base 2 tridiagonal system 0.00
Understanding GPU architecture (NVIDIA) 0.00
Need help explaining some CUDA performance results 0.00