atomicAdd와 관련 연산

An atomic operation reads, modifies, and writes a value as a single step that no other thread can interrupt. That kills the race. ⚛️

atomicAdd takes a pointer and a value, adds safely, and returns the old value. Many threads can hit the same address with no lost updates.

Swap the plain increment for atomicAdd and the count becomes correct every single time, no matter how many threads run.

atomicAdd returns the value held before your add. That old value is a unique slot you can use as an index or a ticket number.

atomicAdd has many friends: atomicSub, atomicMax, atomicMin, atomicExch, atomicAnd, atomicOr, and atomicXor all work the same atomic way.

atomicExch stores a new value and returns the old one in one step. It is handy for claiming flags or grabbing a previous state safely.

atomicMax updates the target only if your value is larger. It is perfect for finding a global maximum across all threads without races.

Atomics cover int, unsigned, and on newer hardware float and double too. Always check that your type and arch support the call you want.

Atomics serialize threads that target the same address. Heavy contention on one spot becomes a bottleneck, so use them only where needed.

Reduce contention by having threads update different addresses, then combine results. Fewer collisions means atomics stay fast.

For summing huge arrays, a tree reduction often beats a flood of atomics. Reach for atomics when updates are sparse or irregular.

Test your grip on atomicAdd's behavior.

You met the atomic family, fixed the racy counter, and learned atomics return the old value but cost time under contention. ✅