Atomic<T>.reduceAdd

Description

Atomically adds the given value to the stored value without returning the original value. On CUDA, maps to the PTX red instruction for potentially better performance than add().

Signature

void Atomic<T>.reduceAdd(
    T value,
    MemoryOrder order)
    where T : IArithmeticAtomicable;

Parameters

value : T

order : MemoryOrder = MemoryOrder.Relaxed

Availability and Requirements

Defined for the following targets:

hlsl

Available in all stages.

glsl

Available in all stages.

cpp

Available in all stages.

cuda

Available in all stages.

metal

Available in all stages.

wgsl

Available in all stages.

spirv

Available in all stages.

llvm

Available in all stages.