[nightly] DPH Performance Test Succeeded
DPH Buildbot
dph at ouroborus.net
Thu Mar 24 15:30:32 CET 2011
Full logs at http://log.ouroborus.net/limitingfactor/dph
Environment
Platform
host: limitingfactor.cse.unsw.EDU.AU
arch: i386
processor: i386
system: Darwin 10.6.0
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 5659)
Total tests = 671
-- WINNERS (had a swing of < -10%)
dph.dotp.vectorised.par.N8
runtime (wall clock) : 2.702s ( +8) / 2.702s ( +8) / 2.703s ( +8)
kernel runtime (wall clock) : 21.00ms (----) / 21.00ms ( -6) / 21.00ms ( -12)
dph.sumsq.vectorised.par.N1
runtime (wall clock) : 400.7ms ( -20) / 400.7ms ( -20) / 400.8ms ( -20)
kernel runtime (wall clock) : 367.0ms ( -17) / 367.9ms ( -17) / 368.0ms ( -17)
dph.sumsq.vectorised.par.N2
runtime (wall clock) : 200.6ms ( -33) / 260.6ms ( -13) / 300.6ms (----)
kernel runtime (wall clock) : 184.0ms ( -17) / 184.0ms ( -17) / 184.0ms ( -17)
dph.sumsq.vectorised.par.N4
runtime (wall clock) : 200.5ms (----) / 200.6ms (----) / 200.7ms (----)
kernel runtime (wall clock) : 92.00ms ( -16) / 92.00ms ( -17) / 92.00ms ( -17)
dph.sumsq.vectorised.par.N8
runtime (wall clock) : 100.4ms (----) / 100.5ms (----) / 100.7ms (----)
kernel runtime (wall clock) : 47.00ms ( -22) / 53.40ms ( -17) / 56.00ms ( -15)
dph.sumsq.vectorised.seq.N4
runtime (wall clock) : 400.6ms ( -20) / 400.7ms ( -20) / 401.0ms ( -20)
kernel runtime (wall clock) : 367.0ms ( -15) / 367.9ms ( -15) / 368.0ms ( -15)
dph.sumsq.vector.seq.N4
runtime (wall clock) : 400.6ms ( -20) / 400.7ms ( -20) / 401.1ms ( -20)
kernel runtime (wall clock) : 367.0ms ( -11) / 367.8ms ( -11) / 368.0ms ( -11)
dph.quicksort.vectorised.par.N2
runtime (wall clock) : 600.9ms ( -14) / 691.2ms ( -1) / 701.4ms (----)
kernel runtime (wall clock) : 341.0ms ( -10) / 387.1ms ( -3) / 397.0ms ( -3)
dph.quicksort.vectorised.par.N8
runtime (wall clock) : 901.5ms (----) / 901.6ms ( -1) / 901.7ms ( -10)
kernel runtime (wall clock) : 509.0ms ( -3) / 520.7ms ( -5) / 531.0ms ( -15)
dph.quickhull.vectorised.par.N1
runtime (wall clock) : 1.201s ( -20) / 1.201s ( -20) / 1.202s ( -20)
kernel runtime (wall clock) : 758.0ms ( -29) / 762.3ms ( -29) / 765.0ms ( -29)
dph.quickhull.vectorised.par.N2
runtime (wall clock) : 901.1ms ( -10) / 901.5ms ( -13) / 902.0ms ( -18)
kernel runtime (wall clock) : 482.0ms ( -26) / 509.3ms ( -26) / 529.0ms ( -27)
dph.quickhull.vectorised.par.N4
runtime (wall clock) : 801.0ms (----) / 801.3ms ( -10) / 801.5ms ( -11)
kernel runtime (wall clock) : 388.0ms ( -26) / 395.9ms ( -31) / 415.0ms ( -32)
dph.quickhull.vectorised.par.N8
runtime (wall clock) : 801.4ms ( -11) / 802.6ms ( -11) / 806.1ms ( -11)
kernel runtime (wall clock) : 379.0ms ( -31) / 411.7ms ( -29) / 435.0ms ( -28)
dph.quickhull.vectorised.seq.N4
runtime (wall clock) : 1.001s ( -9) / 1.001s ( -9) / 1.001s ( -9)
kernel runtime (wall clock) : 547.0ms ( -20) / 548.5ms ( -21) / 550.0ms ( -21)
dph.quickhull.vector-mutable.seq.N4
runtime (wall clock) : 400.7ms ( -20) / 400.8ms ( -20) / 401.0ms ( -20)
kernel runtime (wall clock) : 50.00ms ( -41) / 51.80ms ( -39) / 58.00ms ( -33)
dph.quickhull.vector-forkIO.par.N4
runtime (wall clock) : 400.7ms (----) / 400.9ms (----) / 401.3ms (----)
kernel runtime (wall clock) : 31.00ms ( -45) / 35.20ms ( -41) / 44.00ms ( -29)
dph.quickhull.vector-forkIO.par.N8
runtime (wall clock) : 400.8ms (----) / 400.9ms (----) / 401.0ms (----)
kernel runtime (wall clock) : 34.00ms ( -39) / 38.70ms ( -39) / 42.00ms ( -42)
-- LOSERS (had a swing of > +10%)
dph.dotp.vectorised.par.N1
runtime (wall clock) : 2.602s ( +18) / 2.602s ( +18) / 2.602s ( +18)
kernel runtime (wall clock) : 47.00ms ( -15) / 48.10ms ( -14) / 50.00ms ( -11)
dph.dotp.vectorised.par.N2
runtime (wall clock) : 2.602s ( +18) / 2.602s ( +18) / 2.603s ( +18)
kernel runtime (wall clock) : 24.00ms ( -11) / 34.70ms ( +1) / 43.00ms ( -2)
dph.dotp.vectorised.par.N4
runtime (wall clock) : 2.602s ( +13) / 2.602s ( +13) / 2.603s ( +13)
kernel runtime (wall clock) : 21.00ms ( -5) / 25.50ms ( -7) / 31.00ms (----)
dph.dotp.vectorised.seq.N4
runtime (wall clock) : 2.602s ( +13) / 2.672s ( +16) / 2.703s ( +17)
kernel runtime (wall clock) : 53.00ms ( -7) / 53.00ms ( -9) / 53.00ms ( -15)
dph.dotp.vector.seq.N4
runtime (wall clock) : 2.602s ( +13) / 2.602s ( +13) / 2.603s ( +13)
kernel runtime (wall clock) : 53.00ms ( -9) / 53.20ms ( -11) / 54.00ms ( -16)
dph.evens.vectorised.par.N1
runtime (wall clock) : 500.8ms (----) / 500.9ms (----) / 501.2ms (----)
kernel runtime (wall clock) : 205.0ms ( +13) / 205.8ms ( +13) / 206.0ms ( +12)
dph.evens.vectorised.par.N2
runtime (wall clock) : 500.8ms ( +25) / 501.0ms ( +25) / 501.1ms ( +25)
kernel runtime (wall clock) : 115.0ms ( +14) / 119.6ms ( +12) / 124.0ms ( +12)
dph.evens.vectorised.par.N4
runtime (wall clock) : 400.8ms (----) / 441.0ms ( +10) / 501.4ms ( +25)
kernel runtime (wall clock) : 85.00ms ( +18) / 88.00ms ( +10) / 91.00ms ( +7)
dph.evens.vectorised.seq.N4
runtime (wall clock) : 500.8ms (----) / 581.0ms ( +16) / 601.4ms ( +20)
kernel runtime (wall clock) : 191.0ms ( +19) / 191.4ms ( +10) / 192.0ms (----)
dph.evens.vector.seq.N4
runtime (wall clock) : 500.7ms ( +25) / 500.9ms ( +25) / 501.2ms ( +25)
kernel runtime (wall clock) : 144.0ms ( +48) / 144.9ms ( +49) / 147.0ms ( +50)
noslow.list.*Double.find_indices
kernel runtime (wall clock) : 436.7us ( +13) / 438.4us ( +13) / 439.5us ( +13)
noslow.list.*Double.count_filter
kernel runtime (wall clock) : 242.3us ( +11) / 243.3us ( +12) / 244.0us ( +12)
noslow.vector.Primitive.*Double.filterin_r
kernel runtime (wall clock) : 408.0us ( +12) / 409.6us ( +12) / 410.6us ( +13)
noslow.vector-unsafe.Primitive.*Double.dotp
kernel runtime (wall clock) : 1.038ms ( +10) / 1.040ms ( +10) / 1.041ms ( +9)
noslow.vector.Unboxed.Double.filterin_r
kernel runtime (wall clock) : 45.15us ( +30) / 45.18us ( +30) / 45.20us ( +30)
noslow.vector-unsafe.Primitive.Double.scale_r
kernel runtime (wall clock) : 65.66us ( +11) / 65.68us ( +11) / 65.69us ( +11)
noslow.vector-unsafe.Unboxed.Double.scale_r
kernel runtime (wall clock) : 70.16us ( +13) / 70.18us ( +13) / 70.19us ( +13)
noslow.vector-unsafe.boxed.mini.tridiagonal
kernel runtime (wall clock) : 3.600ms ( +15) / 3.602ms ( +15) / 3.604ms ( +15)
More information about the Cvs-ghc
mailing list