Chapel versus Go fastest performance Always look at the source code. If the fastest programs are hand-written vector instructions, does the host language matter? You might be more interested in the less optimised programs — more seconds, less gz source code. fannkuch-redux source secs mem gz cpu secs Chapel #2 8.09 10,932 731 32.18 Go #3 8.25 10,936 969 32.92 Go 11.83 11,128 900 47.26 Go #2 11.89 12,708 896 47.47 n-body source secs mem gz cpu secs Chapel #3 5.60 10,940 960 5.61 Chapel #2 6.10 10,940 971 6.11 Go #3 6.36 11,244 1200 6.37 Go 6.55 11,244 1310 6.56 Go #2 6.94 11,244 1215 6.95 spectral-norm source secs mem gz cpu secs Chapel #2 0.73 10,948 335 2.89 Go 5.31 11,244 411 5.32 Go #4 1.42 11,244 548 5.67 Go #2 1.44 11,244 668 5.67 Chapel 1.45 10,948 310 5.75 mandelbrot source secs mem gz cpu secs Chapel #3 1.90 37,372 591 7.55 Go #3 3.73 36,140 894 14.86 Go #4 3.73 36,116 905 14.87 Go 4.92 33,624 823 19.65 Chapel 6.61 37,436 460 26.38 Go #2 6.76 33,928 837 26.97 Go #6 6.83 33,632 700 27.22 pidigits source secs mem gz cpu secs Chapel #2 0.75 10,940 423 0.76 Chapel #4 0.75 10,940 509 0.76 Go #4 1.01 11,244 683 1.02 Go 1.37 11,244 708 1.38 Go #3 1.63 11,244 603 1.66 Go #2 1.97 11,244 733 2.00 Go #8 2.46 11,244 720 2.46 Go #7 4.80 23,844 696 5.31 regex-redux source secs mem gz cpu secs Chapel #3 3.63 551,844 492 4.57 Chapel #2 4.50 551,924 489 5.43 Go #5 4.14 302,280 810 6.25 Go #4 14.80 360,260 829 34.62 Go #3 27.89 368,528 829 67.15 Go 28.35 317,752 741 67.40 fasta source secs mem gz cpu secs Chapel #6 0.79 10,880 1104 0.80 Chapel #5 0.94 10,880 1391 3.47 Go 3.78 11,128 1053 3.78 Go #3 1.49 11,136 1358 4.10 Chapel #3 4.12 10,880 1229 4.13 Go #2 1.26 11,136 1404 4.26 k-nucleotide source secs mem gz cpu secs Chapel #4 5.66 192,092 1031 20.12 Chapel #3 6.50 198,044 1007 23.41 Go #7 7.48 166,412 1607 28.68 Go #6 7.96 148,080 1590 29.25 Go #3 8.28 148,412 1722 29.93 Go #4 9.50 142,624 1543 31.55 reverse-complement source secs mem gz cpu secs Go #2 1.76 814,544 611 1.80 Go #3 1.96 814,352 605 2.00 Go #6 1.33 1,278,596 1338 2.46 Chapel #8 0.91 1,056,436 1298 2.70 Chapel #3 1.57 1,884,484 764 2.93 Chapel #5 1.69 1,884,480 610 2.99 Go #5 Bad Output Go Failed binary-trees source secs mem gz cpu secs Chapel #3 8.09 300,444 488 24.60 Go #6 27.82 410,808 611 28.59 Go #5 14.70 406,544 950 57.87 Go #2 14.69 642,688 666 58.49 Go #3 15.07 342,008 799 58.61 Go #7 33.37 247,824 525 60.85 Go 34.62 236,728 482 61.41 Chapel chpl version 1.29.0 built with LLVM version 14.0.0 Copyright 2020-2022 Hewlett Packard Enterprise Development LP Copyright 2004-2019 Cray Inc. Go go version go1.20 linux/amd64 GOAMD64=v2 all Chapel programs & measurements all Go programs & measurements