What's New: New Features in Version 24.x of Prime95
NEW FEATURES IN VERSION 24.x of PRIME95.EXE
New Features in Version 24.14 of Prime95
A bug that caused the
torture test to hang on 256K FFTs on SSE2 machines with 128K of L2 cache was
fixed.
New Features in Version 24.13 of Prime95
Celeron D (256K L2
cache) and Willamette (also 256K L2 cache) now have different implementations
for several FFT sizes. This results in an improvement of several percent for
the Celeron D.
A bug that caused some
machines to generate "Error 2252" when communicating with the server
was fixed.
SSE2 trial factoring
code had a bug when factoring very large exponents.
New Features in Version 24.12 of Prime95
For SSE2 machines the
larger FFTs have been changed to more effectively use a wide variety of L2
cache sizes. The previous version was optimized for a 256KB L2 cache only. Depending
on your CPU and FFT size, you could see an improvement of several
percent.
As a side
"benefit" even larger FFT sizes are now supported. This allows
testing of exponents up to 596 million. Not recommended.
The factoring breakeven
points have been recalculated using my 2 GHz P4. This version of prime95 will
do less trial factoring.
Since server database
crashes cause spurious error 3 messages, prime95 will now ignore error 3
messages from the server for 72 hours. This should workaround the problem
whereby a result is reported but no CPU credit is given and the reservation is
not cleared.
Faster FFTs for AMD64
using prefetchw in both 32-bit and 64-bit mode. You can expect about a 15%
speed improvement.
Prime95 now detects
support for 3DNow! instructions. See undoc.txt for overriding this detection
with CpuSupports3DNow=n in local.ini.
Factoring entries in
worktodo.ini now accept exponents up to 2 billion.
Improved checking for
memory allocation errors during a torture test. Better guessing of amount of
memory to use in a blend test.
Added timeouts to
PrimeNet communications in hopes of avoiding rare hangs when contacting the
PrimeNet server.
Fixed rare bug where
P-1's GCD could miss a factor.
Added trial factoring
to the benchmark.
Fixed bug in ECM when
using zero-padded FFTs.
SSE2 macros optimized
for an additional 1-3% improvement on P4 and AMD64 CPUs.
New Features in Version 24.10 of Prime95
64-bit version of
prime95 available for 64-bit Windows.
New Features in Version 24.9 of Prime95
Fixed crash when
running on machines with "no-execute" protection.
Fixed mis-detection of
some P3 and Celeron CPUs.
New features in Version 24.6 of Prime95
Athlon users should see
a 20% to 30% speed increase.
Pentium, Pentium II,
Pentium III users should see dramatically WORSE performance. Run version 23
instead.
P-1 and ECM now support
numbers of the form k*b^n+c. This cannot be done from the menus. Add these
entries to worktodo.ini:
Pminus1=k,b,n,c,B1,B2
ECM2=k,b,n,c,B1,B2,curves_to_do[,specific_sigma]