gcc -O2 pidigits.c -lgmp 2.56u 0.00s 2.57r
gc pidigits 55.22u 0.04s 55.29r # *** -23%
gc_B pidigits 55.49u 0.02s 55.60r # *** -23%
+
+September 3 2009
+
+# New 6g inlines slices, has a few other tweaks.
+# Complete rerun. Significant changes marked.
+
+fasta -n 25000000
+ # probably I/O library inefficiencies
+ gcc -O2 fasta.c 5.96u 0.00s 5.96r
+ gc fasta 10.63u 0.02s 10.66r
+ gc_B fasta 9.92u 0.01s 9.94r
+
+reverse-complement < output-of-fasta-25000000
+ # we don't know - memory cache behavior?
+ gcc -O2 reverse-complement.c 1.92u 0.33s 2.93r
+ gccgo -O2 reverse-complement.go 6.76u 0.72s 7.58r # +5%
+ gc reverse-complement 6.59u 0.70s 7.29r # +2%
+ gc_B reverse-complement 5.57u 0.80s 6.37r # -10%
+
+nbody 50000000
+ # math.Sqrt needs to be in assembly; inlining is probably the other 50%
+ # also loop alignment appears to be critical
+ gcc -O2 nbody.c 21.28u 0.00s 21.28r
+ gccgo -O2 nbody.go 119.21u 0.00s 119.22r # +2%
+ gc nbody 109.72u 0.00s 109.78r # + 28% *****
+ gc_B nbody 85.90u 0.00s 85.91r
+
+binary-tree 15 # too slow to use 20
+ # memory allocation and garbage collection
+ gcc -O2 binary-tree.c -lm 0.86u 0.00s 0.87r
+ gccgo -O2 binary-tree.go 1.88u 0.54s 2.42r # +17%
+ gccgo -O2 binary-tree-freelist.go 0.01u 0.01s 0.02r
+ gc binary-tree 8.94u 0.01s 8.96r # -2%
+ gc binary-tree-freelist 0.47u 0.01s 0.48r
+
+fannkuch 12
+ # bounds checking is half the difference
+ # rest might be registerization
+ gcc -O2 fannkuch.c 60.12u 0.00s 60.12r
+ gccgo -O2 fannkuch.go 92.62u 0.00s 92.66r # +41% ***
+ gc fannkuch 123.90u 0.00s 123.92r
+ gc_B fannkuch 89.71u 0.00s 89.74r # -1%
+
+regex-dna 100000
+ # regexp code is slow on trivial regexp
+ gcc -O2 regex-dna.c -lpcre 0.88u 0.00s 0.88r
+ gc regex-dna 25.77u 0.01s 25.79r # -5%
+ gc_B regex-dna 26.05u 0.02s 26.09r # -12% ***
+
+spectral-norm 5500
+ # possibly inline evalA
+ gcc -O2 spectral-norm.c -lm 11.51u 0.00s 11.51r
+ gccgo -O2 spectral-norm.go 11.95u 0.00s 11.96r
+ gc spectral-norm 24.23u 0.00s 24.23r
+ gc_B spectral-norm 23.83u 0.00s 23.84r
+
+k-nucleotide 1000000
+ # string maps are slower than glib string maps
+ gcc -O2 -I/usr/include/glib-2.0 -I/usr/lib/glib-2.0/include k-nucleotide.c -lglib-2.0 10.68u 0.04s 10.72r
+ gccgo -O2 k-nucleotide.go 23.03u 0.88s 23.92r
+ gc k-nucleotide 15.79u 0.05s 15.85r # -5% (but this one seems to vary by more than that)
+ gc_B k-nucleotide 17.88u 0.05s 17.95r # +8% (ditto)
+
+mandelbrot 16000
+ gcc -O2 mandelbrot.c 56.17u 0.02s 56.20r
+ gccgo -O2 mandelbrot.go 56.74u 0.02s 56.79r # -1%
+ gc mandelbrot 63.31u 0.01s 63.35r # -1%
+ gc_B mandelbrot 63.29u 0.00s 63.31r # -1%
+
+meteor 16000
+ # we don't know
+ gcc -O2 meteor-contest.c 0.10u 0.00s 0.10r
+ gccgo -O2 meteor-contest.go 0.11u 0.00s 0.12r
+ gc meteor-contest 0.18u 0.00s 0.19r
+ gc_B meteor-contest 0.17u 0.00s 0.18r
+
+pidigits 10000
+ # bignum is slower than gmp
+ gcc -O2 pidigits.c -lgmp 2.56u 0.00s 2.57r
+ gc pidigits 55.87u 0.03s 55.91r
+ gc_B pidigits 55.93u 0.03s 55.99r
+
+# these tests are compared using real time, since they run multiple processors
+# accuracy probably low
+threadring 50000000
+ gcc -O2 threadring.c -lpthread 26.31u 164.69s 199.92r # -2%
+ gccgo -O2 threadring.go 87.90u 487.26s 472.81r # +6%
+ gc threadring 28.89u 0.00s 28.90r # -25% ***
+
+chameneos 6000000
+ gcc -O2 chameneosredux.c -lpthread 16.41u 296.91s 81.17r # -8%
+ gc chameneosredux 19.97u 0.00s 19.97r # -8%
+