[nightly] DPH Performance Test Succeeded
DPH Buildbot
dph at ouroborus.net
Fri Aug 5 18:03:08 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 7.0.1
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.evens.vectorised.par.N1
runtime (wall clock) : 500.6ms (----) / 500.9ms (----) / 501.1ms (----)
kernel runtime (wall clock) : 181.0ms ( -11) / 182.1ms ( -11) / 183.0ms ( -11)
dph.evens.vectorised.par.N4
runtime (wall clock) : 400.6ms (----) / 400.8ms (----) / 401.0ms (----)
kernel runtime (wall clock) : 78.00ms ( -5) / 81.30ms ( -7) / 83.00ms ( -11)
dph.quicksort.vectorised.par.N1
runtime (wall clock) : 600.7ms ( -14) / 671.0ms ( -4) / 701.3ms (----)
kernel runtime (wall clock) : 364.0ms ( -11) / 378.6ms ( -10) / 386.0ms ( -10)
dph.quicksort.vectorised.par.N8
runtime (wall clock) : 801.3ms (----) / 801.4ms ( -1) / 801.5ms ( -11)
kernel runtime (wall clock) : 465.0ms ( -1) / 475.2ms ( -2) / 486.0ms ( -3)
dph.quickhull.vector-immutable.seq.N4
runtime (wall clock) : 400.7ms (----) / 400.8ms (----) / 401.0ms (----)
kernel runtime (wall clock) : 113.0ms ( -16) / 127.6ms ( -9) / 133.0ms ( -6)
repa.laplace.par.N1
runtime (wall clock) : 6.703s ( -28) / 6.714s ( -29) / 6.804s ( -29)
kernel runtime (wall clock) : 6.086s ( -11) / 6.123s ( -12) / 6.170s ( -11)
repa.laplace.par.N2
runtime (wall clock) : 4.003s ( -23) / 4.064s ( -23) / 4.104s ( -24)
kernel runtime (wall clock) : 3.482s ( -10) / 3.578s ( -9) / 3.606s ( -9)
repa.fft2d.par.N2
runtime (wall clock) : 4.903s ( -11) / 5.114s ( -8) / 5.305s ( -7)
kernel runtime (wall clock) : 4.287s ( -13) / 4.525s ( -10) / 4.696s ( -9)
noslow.dph-prim.seq.Double.filterin_r
kernel runtime (wall clock) : 36.84us ( -14) / 36.85us ( -14) / 36.86us ( -14)
-- LOSERS (had a swing of > +10%)
dph.dotp.vectorised.par.N1
runtime (wall clock) : 1.901s ( +6) / 1.902s ( +4) / 1.902s (----)
kernel runtime (wall clock) : 99.00ms (+106) / 99.00ms (+106) / 99.00ms (+102)
dph.dotp.vectorised.par.N2
runtime (wall clock) : 1.901s ( +6) / 1.902s ( +6) / 1.902s ( +5)
kernel runtime (wall clock) : 49.00ms (+104) / 50.30ms ( +55) / 51.00ms ( +24)
dph.dotp.vectorised.par.N4
runtime (wall clock) : 1.801s ( -31) / 1.802s ( -31) / 1.802s ( -33)
kernel runtime (wall clock) : 27.00ms ( +29) / 31.40ms ( +15) / 35.00ms ( +13)
dph.dotp.vectorised.par.N8
runtime (wall clock) : 1.801s (----) / 1.883s ( +4) / 1.907s ( +5)
kernel runtime (wall clock) : 21.00ms (----) / 22.10ms ( +5) / 30.00ms ( +36)
dph.dotp.vectorised.seq.N4
runtime (wall clock) : 1.802s (----) / 1.882s ( +4) / 1.902s ( +6)
kernel runtime (wall clock) : 53.00ms (----) / 92.30ms ( +73) / 102.0ms ( +85)
dph.dotp.vector.seq.N4
runtime (wall clock) : 1.901s ( +6) / 1.992s ( +11) / 2.002s ( +11)
kernel runtime (wall clock) : 53.00ms (----) / 97.10ms ( +81) / 102.0ms ( +79)
dph.sumsq.vectorised.par.N2
runtime (wall clock) : 500.6ms (+150) / 500.7ms (+150) / 500.9ms (+149)
kernel runtime (wall clock) : 418.0ms (+127) / 418.0ms (+127) / 418.0ms (+127)
dph.sumsq.vectorised.par.N4
runtime (wall clock) : 300.5ms (+199) / 300.6ms (+199) / 300.7ms (+199)
kernel runtime (wall clock) : 209.0ms (+127) / 209.0ms (+127) / 209.0ms (+127)
dph.sumsq.vectorised.par.N8
runtime (wall clock) : 200.5ms (+100) / 200.6ms (+100) / 200.7ms ( +99)
kernel runtime (wall clock) : 105.0ms (+128) / 105.0ms (+126) / 105.0ms (+110)
dph.sumsq.vectorised.seq.N4
runtime (wall clock) : 1.201s (+200) / 1.201s (+200) / 1.201s (+200)
kernel runtime (wall clock) : 1.103s (+201) / 1.104s (+200) / 1.105s (+200)
dph.sumsq.vector.seq.N4
runtime (wall clock) : 1.201s (+200) / 1.201s (+200) / 1.201s (+200)
kernel runtime (wall clock) : 1.103s (+201) / 1.103s (+200) / 1.105s (+200)
dph.evens.vectorised.par.N8
runtime (wall clock) : 500.9ms ( +25) / 500.9ms ( +22) / 501.1ms (----)
kernel runtime (wall clock) : 77.00ms ( +13) / 79.40ms ( +11) / 86.00ms (----)
dph.evens.vectorised.seq.N4
runtime (wall clock) : 500.7ms (----) / 590.8ms ( +18) / 601.0ms ( +20)
kernel runtime (wall clock) : 199.0ms ( +5) / 199.4ms ( +5) / 200.0ms ( +5)
dph.quicksort.vectorised.par.N2
runtime (wall clock) : 600.9ms ( +20) / 601.1ms ( -9) / 601.3ms ( -14)
kernel runtime (wall clock) : 324.0ms ( +7) / 347.2ms ( -6) / 366.0ms ( -6)
dph.quicksort.vectorised.par.N4
runtime (wall clock) : 600.9ms ( +20) / 621.2ms ( -2) / 701.3ms (----)
kernel runtime (wall clock) : 339.0ms ( +10) / 353.1ms (----) / 363.0ms ( -4)
dph.smvm.vectorised.par.N2
runtime (wall clock) : 100.5ms (----) / 100.6ms (----) / 100.9ms (----)
kernel runtime (wall clock) : 19.00ms ( +12) / 20.30ms ( +6) / 22.00ms ( +5)
dph.smvm.vectorised.par.N4
runtime (wall clock) : 100.4ms (----) / 100.6ms (----) / 100.9ms (----)
kernel runtime (wall clock) : 10.00ms ( +11) / 12.20ms ( -19) / 18.00ms (----)
dph.smvm.vectorised.seq.N4
runtime (wall clock) : 100.4ms (----) / 100.5ms (----) / 100.7ms (----)
kernel runtime (wall clock) : 23.00ms ( +35) / 23.00ms ( +35) / 23.00ms ( +35)
dph.quickhull.vectorised.par.N2
runtime (wall clock) : 800.9ms ( +14) / 841.4ms ( +6) / 901.6ms ( +12)
kernel runtime (wall clock) : 477.0ms ( +8) / 519.3ms ( +10) / 557.0ms ( +12)
dph.quickhull.vectorised.par.N4
runtime (wall clock) : 701.0ms ( +17) / 701.2ms ( +11) / 701.4ms (----)
kernel runtime (wall clock) : 366.0ms ( +7) / 379.4ms ( +6) / 398.0ms ( +1)
dph.quickhull.vectorised.seq.N4
runtime (wall clock) : 900.8ms ( +12) / 901.1ms ( +6) / 901.3ms (----)
kernel runtime (wall clock) : 559.0ms ( +10) / 568.9ms ( +9) / 575.0ms ( +10)
dph.quickhull.vector-mutable.seq.N4
runtime (wall clock) : 400.7ms ( +33) / 400.8ms ( +29) / 401.0ms (----)
kernel runtime (wall clock) : 54.00ms ( +2) / 58.30ms ( +9) / 61.00ms ( +9)
dph.quickhull.vector-forkIO.par.N4
runtime (wall clock) : 300.6ms (----) / 300.8ms (----) / 301.0ms (----)
kernel runtime (wall clock) : 32.00ms ( +3) / 36.90ms ( +9) / 50.00ms ( +22)
dph.quickhull.vector-forkIO.par.N8
runtime (wall clock) : 300.7ms ( -25) / 300.8ms ( -25) / 301.1ms ( -25)
kernel runtime (wall clock) : 39.00ms ( +3) / 47.20ms ( +19) / 56.00ms ( +37)
repa.mmult.par.N1
runtime (wall clock) : 21.91s (+155) / 21.93s (+154) / 22.02s (+150)
kernel runtime (wall clock) : 21.61s (+155) / 21.66s (+155) / 21.71s (+155)
repa.mmult.par.N2
runtime (wall clock) : 11.11s (+158) / 11.14s (+155) / 11.21s (+155)
kernel runtime (wall clock) : 10.85s (+156) / 10.88s (+156) / 10.91s (+156)
repa.mmult.par.N4
runtime (wall clock) : 5.703s (+200) / 5.705s (+200) / 5.706s (+200)
kernel runtime (wall clock) : 5.449s (+204) / 5.463s (+205) / 5.471s (+205)
repa.mmult.par.N8
runtime (wall clock) : 2.937s (+144) / 3.021s (+147) / 3.123s (+137)
kernel runtime (wall clock) : 2.725s (+152) / 2.745s (+150) / 2.859s (+143)
repa.laplace.par.N4
runtime (wall clock) : 3.003s (----) / 3.353s ( +12) / 3.703s ( +23)
kernel runtime (wall clock) : 2.603s ( +29) / 2.942s ( +46) / 3.338s ( +65)
repa.laplace.par.N6
runtime (wall clock) : 2.903s ( +4) / 2.963s ( +6) / 3.003s ( +7)
kernel runtime (wall clock) : 2.536s ( +19) / 2.573s ( +19) / 2.607s ( +18)
repa.blur.par.N1
runtime (wall clock) : 6.603s (+450) / 6.603s (+450) / 6.604s (+450)
kernel runtime (wall clock) : 6.215s (+670) / 6.227s (+670) / 6.240s (+670)
repa.blur.par.N2
runtime (wall clock) : 3.902s (+457) / 3.973s (+459) / 4.303s (+437)
kernel runtime (wall clock) : 3.579s (+710) / 3.659s (+716) / 3.958s (+737)
repa.blur.par.N4
runtime (wall clock) : 2.602s (+420) / 2.672s (+434) / 2.702s (+440)
kernel runtime (wall clock) : 2.376s (+761) / 2.436s (+762) / 2.491s (+756)
repa.blur.par.N6
runtime (wall clock) : 2.002s (+400) / 2.002s (+400) / 2.002s (+399)
kernel runtime (wall clock) : 1.788s (+790) / 1.799s (+777) / 1.810s (+754)
repa.blur.par.N8
runtime (wall clock) : 1.703s (+325) / 1.774s (+342) / 2.004s (+399)
kernel runtime (wall clock) : 1.515s (+766) / 1.556s (+756) / 1.733s (+822)
repa.canny.par.N1
runtime (wall clock) : 2.101s (+425) / 2.101s (+424) / 2.102s (+424)
kernel runtime (wall clock) : 1.670s (+6858) / 1.672s (+6865) / 1.674s (+6875)
repa.canny.par.N2
runtime (wall clock) : 1.201s (+300) / 1.231s (+309) / 1.401s (+366)
kernel runtime (wall clock) : 934.0ms (+5394) / 950.6ms (+4983) / 1.083s (+5315)
repa.canny.par.N4
runtime (wall clock) : 900.9ms (+200) / 901.0ms (+200) / 901.1ms (+200)
kernel runtime (wall clock) : 602.0ms (+4531) / 608.6ms (+4442) / 622.0ms (+4047)
repa.canny.par.N6
runtime (wall clock) : 700.8ms (+250) / 701.0ms (+249) / 701.4ms (+249)
kernel runtime (wall clock) : 440.0ms (+3567) / 451.6ms (+3484) / 457.0ms (+3415)
repa.canny.par.N8
runtime (wall clock) : 600.8ms (+200) / 611.2ms (+205) / 701.4ms (+249)
kernel runtime (wall clock) : 373.0ms (+2769) / 391.3ms (+2887) / 502.0ms (+3486)
repa.fft3d.par.N2
runtime (wall clock) : 18.22s ( +8) / 19.34s ( +11) / 19.91s ( +13)
kernel runtime (wall clock) : 15.16s ( +9) / 16.11s ( +13) / 16.60s ( +13)
repa.fft3d.par.N4
runtime (wall clock) : 11.11s ( +39) / 11.21s ( +40) / 11.31s ( +41)
kernel runtime (wall clock) : 9.252s ( +49) / 9.365s ( +51) / 9.530s ( +54)
noslow.vector.Primitive.*Double.filterin_r
kernel runtime (wall clock) : 408.8us ( +13) / 410.3us ( +13) / 411.3us ( +13)
noslow.vector-unsafe.Primitive.*Double.filterin_r
kernel runtime (wall clock) : 410.8us ( +13) / 412.3us ( +13) / 413.3us ( +14)
noslow.dph-prim.seq.Double.scale_r
kernel runtime (wall clock) : 69.17us ( +10) / 69.19us ( +10) / 69.21us ( +10)
noslow.dph-prim.seq.Double.axpy
kernel runtime (wall clock) : 91.44us ( +11) / 91.46us ( +11) / 91.47us ( +11)
noslow.vector.Primitive.Double.scale_r
kernel runtime (wall clock) : 69.34us ( +13) / 69.36us ( +13) / 69.38us ( +13)
noslow.vector.Primitive.Double.axpy
kernel runtime (wall clock) : 91.34us ( +11) / 91.36us ( +11) / 91.38us ( +11)
noslow.vector.Unboxed.Double.scale_r
kernel runtime (wall clock) : 69.24us ( +11) / 69.27us ( +11) / 69.30us ( +11)
noslow.vector.Unboxed.Double.axpy
kernel runtime (wall clock) : 91.19us ( +10) / 91.25us ( +10) / 91.31us ( +10)
noslow.vector-unsafe.Primitive.Double.scale_r
kernel runtime (wall clock) : 65.80us ( +11) / 65.81us ( +11) / 65.83us ( +11)
noslow.vector-unsafe.Unboxed.Double.scale_r
kernel runtime (wall clock) : 70.27us ( +12) / 70.29us ( +12) / 70.30us ( +12)
More information about the Cvs-ghc
mailing list