Abstract: A method for accessing a memory includes receiving a first address wherein the first address corresponds to a demand fetch, receiving a second address wherein the second address corresponds to a speculative prefetch, providing first data from the memory in response to the demand fetch in which the first data is accessed asynchronous to a system clock, and providing second data from the memory in response to the speculative prefetch in which the second data is accessed synchronous to the system clock. The memory may include a plurality of pipeline stages in which providing the first data in response to the demand fetch is performed such that each pipeline stage is self-timed independent of the system clock and providing the second data in response to the speculative prefetch is performed such that each pipeline stage is timed based on the system clock to be synchronous with the system clock.

Abstract: A memory controller performs a read test for each of a plurality of memory devices to generate a read delay time of each memory device. There is a prime memory device and a subset of memory devices. For each memory device of the subset, the read delay time for the prime memory device is compared with the read delay time of each memory device of the subset of memory devices to generate a differential delay for each memory device of the subset. For each subset memory device, a write test start time of the prime memory device is combined with a differential delay of each memory device to generate a write test start time for the each memory device. A write test for each memory device uses the write test start time for each subset memory device to generate a write launch time for each subset memory device.