[nightly] DPH Performance Test Succeeded
DPH Buildbot
dph at ouroborus.net
Fri Jun 3 07:55:19 CEST 2011
Full logs at http://log.ouroborus.net/limitingfactor/dph
Environment
Platform
host: limitingfactor.cse.unsw.EDU.AU
arch: i386
processor: i386
system: Darwin 10.7.0
Versions
GHC The Glorious Glasgow Haskell Compilation System, version 7.1.20110602
GCC i686-apple-darwin10-gcc-4.2.1 (GCC) 4.2.1 (Apple Inc. build 5666) (dot 3)
Total tests = 708
-- WINNERS (had a swing of < -10%)
dph.quicksort.vectorised.par.N8
runtime (wall clock) : 801.3ms (----) / 801.5ms ( -1) / 801.7ms ( -11)
kernel runtime (wall clock) : 462.0ms ( -2) / 477.6ms ( -2) / 492.0ms ( -2)
dph.quickhull.vectorised.par.N1
runtime (wall clock) : 1.001s ( -9) / 1.031s ( -13) / 1.102s ( -8)
kernel runtime (wall clock) : 708.0ms ( -5) / 710.7ms ( -5) / 719.0ms ( -4)
dph.quickhull.vectorised.par.N2
runtime (wall clock) : 701.0ms (----) / 731.2ms ( -8) / 801.5ms (----)
kernel runtime (wall clock) : 390.0ms ( -12) / 418.3ms ( -11) / 453.0ms ( -9)
dph.quickhull.vectorised.par.N4
runtime (wall clock) : 600.9ms (----) / 601.1ms ( -5) / 601.3ms ( -14)
kernel runtime (wall clock) : 296.0ms ( -14) / 310.3ms ( -14) / 327.0ms ( -17)
dph.quickhull.vectorised.par.N8
runtime (wall clock) : 601.0ms (----) / 601.9ms (----) / 605.3ms (----)
kernel runtime (wall clock) : 293.0ms ( -11) / 308.3ms ( -8) / 335.0ms ( -5)
repa.laplace.par.N1
runtime (wall clock) : 5.803s ( -38) / 5.813s ( -38) / 5.905s ( -39)
kernel runtime (wall clock) : 5.179s ( -25) / 5.214s ( -25) / 5.279s ( -24)
repa.laplace.par.N2
runtime (wall clock) : 3.402s ( -35) / 3.493s ( -34) / 3.604s ( -33)
kernel runtime (wall clock) : 2.930s ( -24) / 3.041s ( -22) / 3.141s ( -21)
repa.laplace.par.N8
runtime (wall clock) : 2.203s ( -15) / 2.253s ( -15) / 2.304s ( -15)
kernel runtime (wall clock) : 1.841s ( -13) / 1.868s ( -12) / 1.877s ( -14)
repa.canny.par.N1
runtime (wall clock) : 400.6ms (----) / 400.6ms (----) / 400.8ms (----)
kernel runtime (wall clock) : 21.00ms ( -12) / 21.00ms ( -12) / 21.00ms ( -12)
repa.canny.par.N2
runtime (wall clock) : 300.5ms (----) / 300.6ms (----) / 300.8ms (----)
kernel runtime (wall clock) : 16.00ms ( -6) / 17.80ms ( -5) / 18.00ms ( -10)
noslow.list.*Double.count_filter
kernel runtime (wall clock) : 216.7us ( -11) / 217.0us ( -11) / 217.4us ( -11)
-- LOSERS (had a swing of > +10%)
dph.dotp.vectorised.par.N4
runtime (wall clock) : 1.801s ( -31) / 1.802s ( -31) / 1.802s ( -33)
kernel runtime (wall clock) : 27.00ms ( +29) / 30.50ms ( +12) / 32.00ms ( +3)
dph.sumsq.vectorised.par.N1
runtime (wall clock) : 1.101s (+175) / 1.101s (+175) / 1.101s (+175)
kernel runtime (wall clock) : 1.036s (+182) / 1.036s (+182) / 1.038s (+182)
dph.sumsq.vectorised.par.N2
runtime (wall clock) : 600.6ms (+200) / 600.7ms (+200) / 600.8ms (+199)
kernel runtime (wall clock) : 518.0ms (+182) / 518.2ms (+182) / 519.0ms (+182)
dph.sumsq.vectorised.par.N4
runtime (wall clock) : 300.5ms (+199) / 300.6ms (+199) / 300.8ms (+199)
kernel runtime (wall clock) : 259.0ms (+182) / 259.0ms (+182) / 259.0ms (+182)
dph.sumsq.vectorised.par.N8
runtime (wall clock) : 200.5ms (+100) / 200.5ms (+100) / 200.7ms ( +99)
kernel runtime (wall clock) : 130.0ms (+183) / 130.0ms (+180) / 130.0ms (+160)
dph.evens.vectorised.par.N4
runtime (wall clock) : 400.6ms (----) / 410.8ms ( +3) / 500.9ms ( +25)
kernel runtime (wall clock) : 79.00ms ( -4) / 84.00ms ( -4) / 89.00ms ( -4)
dph.evens.vectorised.par.N8
runtime (wall clock) : 400.8ms (----) / 481.0ms ( +17) / 501.3ms (----)
kernel runtime (wall clock) : 68.00ms (----) / 77.20ms ( +8) / 86.00ms (----)
dph.quicksort.vectorised.par.N2
runtime (wall clock) : 600.8ms ( +20) / 611.0ms ( -8) / 701.2ms (----)
kernel runtime (wall clock) : 349.0ms ( +15) / 364.8ms ( -2) / 384.0ms ( -2)
dph.quicksort.vectorised.par.N4
runtime (wall clock) : 601.1ms ( +20) / 621.2ms ( -2) / 701.2ms (----)
kernel runtime (wall clock) : 341.0ms ( +11) / 360.7ms ( +1) / 380.0ms (----)
dph.smvm.vectorised.par.N4
runtime (wall clock) : 100.5ms (----) / 100.6ms (----) / 100.8ms (----)
kernel runtime (wall clock) : 10.00ms ( +11) / 14.40ms ( -5) / 19.00ms ( +6)
dph.quickhull.vector-forkIO.par.N4
runtime (wall clock) : 300.7ms (----) / 300.8ms (----) / 301.0ms (----)
kernel runtime (wall clock) : 30.00ms ( -3) / 37.80ms ( +12) / 47.00ms ( +15)
dph.quickhull.vector-forkIO.par.N8
runtime (wall clock) : 300.7ms ( -25) / 300.8ms ( -25) / 301.0ms ( -25)
kernel runtime (wall clock) : 44.00ms ( +16) / 46.80ms ( +18) / 52.00ms ( +27)
repa.mmult.par.N2
runtime (wall clock) : 4.803s ( +12) / 4.804s ( +10) / 4.805s ( +9)
kernel runtime (wall clock) : 4.490s ( +6) / 4.499s ( +6) / 4.505s ( +6)
repa.mmult.par.N4
runtime (wall clock) : 2.502s ( +32) / 2.573s ( +35) / 2.604s ( +37)
kernel runtime (wall clock) : 2.252s ( +26) / 2.264s ( +26) / 2.282s ( +27)
repa.mmult.par.N8
runtime (wall clock) : 1.402s ( +17) / 1.420s ( +16) / 1.507s ( +14)
kernel runtime (wall clock) : 1.131s ( +4) / 1.139s ( +4) / 1.159s ( -2)
repa.laplace.par.N4
runtime (wall clock) : 2.403s ( -20) / 2.853s ( -5) / 3.404s ( +13)
kernel runtime (wall clock) : 1.974s ( -2) / 2.448s ( +21) / 2.964s ( +47)
repa.blur.par.N2
runtime (wall clock) : 800.9ms ( +14) / 801.0ms ( +13) / 801.2ms (----)
kernel runtime (wall clock) : 497.0ms ( +12) / 499.2ms ( +11) / 502.0ms ( +6)
repa.canny.par.N6
runtime (wall clock) : 300.5ms ( +50) / 300.7ms ( +50) / 300.8ms ( +50)
kernel runtime (wall clock) : 12.00ms (----) / 13.10ms ( +4) / 15.00ms ( +15)
repa.fft3d.par.N2
runtime (wall clock) : 18.01s ( +7) / 18.93s ( +9) / 19.52s ( +11)
kernel runtime (wall clock) : 14.69s ( +6) / 15.60s ( +9) / 16.21s ( +10)
repa.fft3d.par.N4
runtime (wall clock) : 10.91s ( +36) / 11.03s ( +38) / 11.21s ( +40)
kernel runtime (wall clock) : 9.007s ( +45) / 9.167s ( +48) / 9.264s ( +49)
noslow.list.*Double.find_indices
kernel runtime (wall clock) : 436.9us ( +13) / 438.5us ( +13) / 439.6us ( +13)
noslow.vector.Primitive.*Double.filterin_r
kernel runtime (wall clock) : 412.0us ( +14) / 413.5us ( +14) / 414.5us ( +14)
noslow.vector-unsafe.Primitive.*Double.filterin_r
kernel runtime (wall clock) : 409.4us ( +13) / 411.0us ( +13) / 412.0us ( +13)
More information about the Cvs-ghc
mailing list