[Openmcl-devel] Alpha-testing 0.14
Sven Van Caekenberghe
sven at beta9.be
Fri Feb 28 14:49:25 PST 2003
I did some test of 0.14 (latest CVS update of today).
My xml-rpc code all compiled and ran fine (as far as I could tell): this means that simple MP usage has remained unchanged.
I also ran Eric Marsden's cl-bench Benchmarks, comparing 0.13.4 to 0.14, on my PowerBook G4 / 667 (Gigabit Ethernet, thus no L3 cache). All benchmark code compiled and ran OK (or so it seemed).
All this seems quite nice for an alpha version: I was trying to find some bugs ;-)
Benchmark Reference OpenM
-------------------------------------------------------------------------------------
BOYER 5.45 1.43
BROWSE 1.76 1.44
DDerviv 2.85 1.89
Deriv 4.79 1.94
DESTRUCTIVE 2.46 1.51
DIV2-TEST-1 3.45 2.11
DIV2-TEST-2 1.67 2.10
FFT 10.99 1.77
FRPOLY/FIXNUM 3.26 0.81
FRPOLY/BIGNUM 3.96 1.56
FRPOLY/FLOAT 2.33 1.30
PUZZLE 14.32 1.15
CTAK 2.28 1.13
TAK 1.92 0.95
RTAK 1.92 0.97
TAKL 5.62 0.98
STAK 2.28 2.06
FPRINT 4.76 1.43
TRAVERSE 6.67 0.99
TRIANGLE 4.91 1.11
CASCOR 54.37 5.93
RICHARDS 1.87 1.33
FACTORIAL 2.02 1.70
FIB 0.33 0.94
BIGNUM/ELEM-100-1000 2.62 1.05
BIGNUM/ELEM-1000-100 13.08 0.98
BIGNUM/ELEM-10000-1 19.17 1.04
BIGNUM/PARI-100-10 3.61 0.92
BIGNUM/PARI-200-5 42.37 0.95
HASH-STRINGS 4.12 2.02
HASH-INTEGERS 1.53 3.36
BOEHM-GC 30.28 2.04
CLOS/defclass 0.88 1.10
CLOS/defmethod 0.30 1.47
CLOS/instantiate 23.85 1.15
CLOS/methodcalls 22.54 1.61
CLOS/method+after 9.56 1.57
CLOS/complex-methods 1.95 0.97
1D-ARRAYS 5.59 1.65
2D-ARRAYS 53.78 1.10
BITVECTORS 7.04 1.30
FILL-STRINGS 20.13 1.18
fill-strings/adjustable 24.58 1.10
Reference implementation: OpenMCL Version (Beta: Darwin) 0.13.4
Impl OpenM: OpenMCL Version (Alpha: Darwin) 0.14-030225
More information about the Openmcl-devel
mailing list