Lines Matching refs:memory

15 This section describes some key memory considerations when developing applications in the DPDK envi…
35 Other functions of libc, such as malloc(), provide a flexible way to allocate and free memory.
40 If you really need dynamic allocation in the data plane, it is better to use a memory pool of fixed…
42 This data structure provides several services that increase performance, such as memory alignment o…
49 Read-Write (RW) access operations by several lcores to the same memory area can generate a lot of d…
63 On a NUMA system, it is preferable to access local memory since remote memory access is slower.
73 Modern memory controllers have several memory channels that can load or store data in parallel.
74 Depending on the memory controller and its configuration,
75 the number of channels and the way the memory is distributed across the channels varies.
77 meaning that if all memory access operations are done on the first channel only, there is a potenti…
79 …e  :ref:`Mempool Library <Mempool_Library>` spreads the addresses of objects among memory channels.
81 Locking memory pages
84 The underlying operating system is allowed to load/unload memory pages at its own discretion.
87 To avoid these you could pre-load, and lock them into memory with the ``mlockall()`` call.
129 When PCI devices write to system memory through DMA,
192 the C11 memory model and provide finer memory order control.
202 Some use cases require atomicity alone, the ordering of the memory operations
204 incremented atomically but do not need any particular memory ordering.
205 So, RELAXED memory ordering is sufficient.
210 Some use cases allow for memory reordering in one way while requiring memory
213 For example, the memory operations before the spinlock lock are allowed to
214 move to the critical section, but the memory operations in the critical section
215 are not allowed to move above the lock. In this case, the full memory barrier
216 in the compare-and-swap operation can be replaced with ACQUIRE memory order.
217 On the other hand, the memory operations after the spinlock unlock are allowed
218 to move to the critical section, but the memory operations in the critical
220 store operation can use RELEASE memory order.
228 can be written with RELAXED memory order. However, the guard variable should
229 be written with RELEASE memory order. This ensures that the store to guard
233 with ACQUIRE memory order. The payload or the data the writer communicated,
234 can be read with RELAXED memory order. This ensures that, if the store to