SuperCache breaks the disk I/O
bottleneck by using the computer's RAM to hold or contain the most frequently
used disk data. This 'container' is referred to as a cache. With SuperCache,
as a program sends and receives disk data, the most frequently used data
is read from and written to RAM – not the hard drive – thus
accelerating the program's performance. SuperCache implements our patented
block-level cache technology to increase performance above that
of the operating system’s file-level cache.
SuperCache is an excellent choice for these scenarios:
The data files are located on a disk partition or disk volume
that is too large to fit into available physical
memory, and cannot be moved to one where they will fit. (For
example: Dragon Naturally Speaking v7.3 cannot be configured to
place its data on a different drive.)
3.
Minimum risk of lost data.
Unlike our RamDisk or SuperVolume
products not all the data will be available in RAM all the time. Some
will come from the hard drive. Nonetheless, depending upon the size of
the cache and the nature of the disk I/O demands, performance accelerations
can be significant and often dramatic.
Deferred-write mode
By enabling its lazy-write mechanism, SuperCache can
also accelerate writing data to disk. This mechanism delays writes to
the hard drive. This can 'smooth out' I/O activity on the hard drive.
It is important to note that enabling lazy-write increases the risk
of data loss in the event of a system crash or power failure. SuperSpeed
Software recommends that enabling the lazy-write feature ONLY on systems
equipped with an Uninterruptible Power Supply (UPS).
SuperCache can be used to cache an entire system drive (e.g. drive
C:) including the system pagefile. SuperCache is the appropriate choice
when a particular program (e.g. database, game, etc.) needs to access
very large amounts data.
Support for NUMA
Windows XP x64 provides special support for machines with a non-uniform memory architecture (NUMA). When active on such platforms, the memory manager for SuperCache 3 examines the processor and memory affinities reported by Windows and the ACPI SRAT, and then optimizes physical memory allocations across the described NUMA nodes. The NUMA support in SuperCache 3 greatly improves the speed of memory allocations and equalizes the distribution of cache allocations among the NUMA nodes. Currently, NUMA support does not include the ability to build caches on specific nodes.
SuperSpeed LLC is the owner of the following U.S. Patents 5577226, 5606681, 5918244,
6370615, 6629201, 6651136, 7017013, 7039767, 7111129, and other patents
are pending.
Buy
Here
Top
