Parallel Reduction CUDA Implementations

Eliminating Unnecessary Inf and NaN Checks in Floating Point Computation

An Example Approach

Disabling Optimization on Purpose

Algorithms for Finding the Top $K$ Largest or Smallest Elements in an Unsorted Array on CPU

An $O(N)$ Heap Building Algorithm and Its Asymptotic Complexity Analysis

An $O(N)$ Selection Algorithm for Finding the $i$-th Smallest Element in an Unsorted Array

TensorRT Custom Plugin Implementation and Integration

General Matrix Multiplication CUDA Performance Optimization

Quick Function for Padding and Centering a String in C++

Compare Floating-Point Numbers Empirically

Performance Caveats of Passing Functions as Arguments in C++