
6.42
IDT70V05S/L
High-Speed 8K x 8 Dual-Port Static RAM Military, Industrial and Commercial Temperature Ranges
D
0
2941 drw 19
D
Q
WRITE
D
0
WRITE
D
Q
SEMAPHORE
REQUEST FLIP FLOP
SEMAPHORE
REQUEST FLIP FLOP
L PORT
R PORT
SEMAPHORE
READ
SEMAPHORE
READ
,
The critical case of semaphore timng is when both sides request a
single token by attempting to write a zero into it at the same time. The
semaphore logic is specially designed to resolve this problem If
simultaneous requests are made, the logic guarantees that only one
side receives the token. If one side is earlier than the other in making
the request, the first side to make the request will receive the token. If
both requests arrive at the same time, the assignment will be arbitrarily
made to one port or the other.
One caution that should be noted when using semaphores is that
semaphores alone do not guarantee that access to a resource is
secure. As with any powerful programmng technique, if semaphores
are msused or msinterpreted, a software error can easily happen.
Initialization of the semaphores is not automatic and must be
handled via the initialization programat power-up. Since any sema-
phore request flag which contains a zero must be reset to a one, all
semaphores on both sides should have a one written into themat
initialization fromboth sides to assure that they will be free when
needed.
<.&@./6
Perhaps the simplest application of semaphores is their applica-
tion as resource markers for the IDT70V05
’
s Dual-Port SRAM. Say the
8K x 8 SRAMwas to be divided into two 4K x 8 blocks which were to be
dedicated at any one time to servicing either the left or right port.
Semaphore 0 could be used to indicate the side which would control
the lower section of memory, and Semaphore 1 could be defined as the
indicator for the upper section of memory.
To take a resource, in this example the lower 4K of Dual-Port
SRAM the processor on the left port could write and then read a
zero in to Semaphore 0. If this task were successfully completed
(a zero was read back rather than a one), the left processor would
assume control of the lower 4K. Meanwhile the right processor was
attempting to gain control of the resource after the left processor, it
would read back a one in response to the zero it had attempted to
write into Semaphore 0. At this point, the software could choose to try
and gain control of the second 4K section by writing, then reading a zero
into Semaphore 1. If it succeeded in gaining control, it would lock out
the left side.
Once the left side was finished with its task, it would write a one to
Semaphore 0 and may then try to gain access to Semaphore 1. If
Semaphore 1 was still occupied by the right side, the left side could undo
its semaphore request and performother tasks until it was able to write, then
read a zero into Semaphore 1. If the right processor performs a simlar task
with Semaphore 0, this protocol would allow the two processors to swap
4K blocks of Dual-Port SRAMwith each other.
The blocks do not have to be any particular size and can even be
variable, depending upon the complexity of the software using the
semaphore flags. All eight semaphores could be used to divide the
Dual-Port SRAMor other shared resources into eight parts. Semaphores
can even be assigned different meanings on different sides rather than
being given a common meaning as was shown in the example above.
Semaphores are a useful formof arbitration in systems like disk
interfaces where the CPU must be locked out of a section of memory
during a transfer and the I/O device cannot tolerate any wait states.
With the use of semaphores, once the two devices has determned
which memory area was
“
off-limts
”
to the CPU, both the CPU and the
I/O devices could access their assigned portions of memory continu-
ously without any wait states.
Semaphores are also useful in applications where no memory
“
WAIT
”
state is available on one or both sides. Once a semaphore
handshake has been performed, both processors can access their
assigned SRAMsegments at full speed.
Another application is in the area of complex data structures. In this
case, block arbitration is very important. For this application one
processor may be responsible for building and updating a data
structure. The other processor then reads and interprets that data
structure. If the interpreting processor reads an incomplete data
structure, a major error condition may exist. Therefore, some sort of
arbitration must be used between the two different processors. The
building processor arbitrates for the block, locks it and then is able to
go in and update the data structure. When the update is completed, the
data structure block is released. This allows the interpreting processor
to come back and read the complete data structure, thereby guaran-
teeing a consistent data structure.
Figure 4. IDT70V05 Semaphore Logic