4: Pioneering Specialized Hardware Flashcards
Most Al projects that you create will at least begin with ____________ because modern off-the-shelf components actually
provide significant processing power, especially when compared to components from the 1980s when AI first began to produce usable results.
standard hardware
The architecture (structure) of the standard PC hasn’t changed since ___________ first proposed it in 1946.
John von Neumann
It connects to memory and peripheral devices through a bus in PC products as early as 1981 (and long before).
The processor
The modularity provided by the Von Neumann architecture comes with some serious deficiencies
Von Neumann bottleneck
Single points of failure
Single-mindedness
Tasking
the most serious when considering the requirements of disciplines such as Al, machine learning, and even data science.
Von Neumann bottleneck
Any loss of connectivity with the bus necessarily means that the computer fails immediately, rather than gracefully.
Single points of failure
The Von Neumann bus can either retrieve an instruction or retrieve the data required to execute the instruction, but it can’t do both.
Single-mindedness
When the brain performs a task, a number of synapses fire at one time, allowing simultaneous execution of multiple operations.
Tasking
The original Von Neumann design allowed just ____ operation at a time, and only after the system retrieved both the required instruction and data.
one
Many ways are available to provide such processing power, but a common way is to use _________ in addition to the central processor of a machine.
Graphic Processing Units (GPUs)
a natural result of using a bus to transfer data between the processor, memory, long-term storage, and peripheral devices.
Von Neumann bottleneck
When problems with obtaining data from memory fast enough with the Von Neumann Architecture became evident, hardware vendors quickly responded by adding localized memory that didn’t require bus access.
Caching
Unfortunately, external caches still don’t provide enough speed. Even using the fastest RAM available and cutting out the bus access completely doesn’t meet the processing capacity needs of the processor.
Processor caching
The problem with caches is that they prove useful only when they contain the correct data. Unfortunately, cache hits prove low in applications that use a lot of data and perform a wide variety of tasks.
Prefetching
You can get buried by RAM alphabet soup because there are more kinds of RAM than most people imagine. Each kind of RAM purports to solve at least part of the Von Neumann bottleneck problem, and they do work within limits.
Using specialty RAM
