Full logs at http://log.ouroborus.net/limitingfactor/dph
Environment
Platform
host: limitingfactor.cse.unsw.EDU.AU
arch: i386
processor: i386
system: Darwin 10.5.0
Versions
GHC The Glorious Glasgow Haskell Compilation System, version 7.1.20101202
GCC i686-apple-darwin10-gcc-4.2.1 (GCC) 4.2.1 (Apple Inc. build 5659)
Total tests = 707
-- WINNERS (had a swing of < -10%)
noslow.vector-unsafe.Primitive.*Double.filterin_r
kernel runtime (wall clock) : 365.0us ( -11) / 365.0us ( -11) /
365.1us ( -11)
noslow.dph-prim.seq.Double.axpy
kernel runtime (wall clock) : 82.33us ( -10) / 82.34us ( -10) /
82.36us ( -10)
noslow.vector.Primitive.Double.scale_r
kernel runtime (wall clock) : 61.54us ( -11) / 61.55us ( -11) /
61.57us ( -11)
noslow.vector.Primitive.Double.axpy
kernel runtime (wall clock) : 82.02us ( -10) / 82.03us ( -10) /
82.05us ( -10)
-- LOSERS (had a swing of > +10%)
dph.evens.vector.seq.N4
runtime (wall clock) : 400.6ms (----) / 430.7ms ( +7) /
500.8ms ( +25)
kernel runtime (wall clock) : 97.00ms (----) / 97.20ms (----) /
98.00ms (----)
dph.quickhull.vectorised.par.N4
runtime (wall clock) : 900.9ms ( +12) / 901.3ms ( +1) /
901.5ms (----)
kernel runtime (wall clock) : 554.0ms ( +5) / 581.6ms ( +2) /
603.0ms ( -2)
dph.quickhull.vectorised.par.N8
runtime (wall clock) : 901.4ms (----) / 925.0ms ( +2) /
1.007s ( +11)
kernel runtime (wall clock) : 536.0ms ( -2) / 598.1ms ( +3) /
638.0ms ( +5)
dph.quickhull.vector-forkIO.par.N8
runtime (wall clock) : 400.7ms (----) / 410.8ms ( +3) /
500.8ms ( +25)
kernel runtime (wall clock) : 59.00ms ( +5) / 61.80ms ( -2) /
66.00ms ( -10)
dph.nbody.vectorised.par.N2
runtime (wall clock) : 3.303s ( +10) / 3.804s ( +1) /
4.205s ( -2)
kernel runtime (wall clock) : 3.267s ( +12) / 3.734s ( +1) /
4.118s ( -2)
repa.mmult.par.N4
runtime (wall clock) : 2.202s ( +16) / 2.422s ( +27) /
4.203s (+121)
kernel runtime (wall clock) : 2.133s ( +19) / 2.341s ( +31) /
4.104s (+129)
repa.laplace.par.N4
runtime (wall clock) : 3.402s ( +13) / 3.413s ( +14) /
3.503s ( +17)
kernel runtime (wall clock) : 2.513s ( +24) / 2.559s ( +27) /
2.602s ( +29)
repa.fft2d.par.N4
runtime (wall clock) : 4.104s ( +11) / 4.194s ( +13) /
4.204s ( +14)
kernel runtime (wall clock) : 3.775s ( +14) / 3.824s ( +16) /
3.881s ( +17)
repa.fft3d.par.N4
runtime (wall clock) : 10.41s ( +30) / 10.51s ( +31) /
10.61s ( +32)
kernel runtime (wall clock) : 8.560s ( +38) / 8.654s ( +40) /
8.770s ( +41)
noslow.list.*Double.find_indices
kernel runtime (wall clock) : 436.9us ( +13) / 438.5us ( +13) /
439.6us ( +13)
noslow.list.*Double.count_filter
kernel runtime (wall clock) : 241.9us ( +11) / 242.8us ( +11) /
243.5us ( +12)
noslow.vector.Primitive.*Double.filterin_r
kernel runtime (wall clock) : 412.8us ( +13) / 414.4us ( +14) /
415.4us ( +14)
noslow.dph-prim.seq.Double.filterin_r
kernel runtime (wall clock) : 48.46us ( +32) / 48.52us ( +32) /
48.58us ( +32)
noslow.vector.Unboxed.Double.filterin_r
kernel runtime (wall clock) : 46.81us ( +35) / 46.85us ( +35) /
46.89us ( +35)
_______________________________________________
Cvs-ghc mailing list
[email protected]
http://www.haskell.org/mailman/listinfo/cvs-ghc
