Chapel versus Julia

How the programs are written matters! Always look at the source code.

If the fastest programs are flagged * possible hand-written vector instructions or "unsafe" or naked ffi, does the host language matter? You might be more interested in the less optimised programs — more seconds, less gz source code.

fannkuch-redux
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
* Julia #2	8.59	31.99	333,136	1077	0.12
Chapel #2	8.48	33.63—33.69	9,699	737	21.01
* Julia #3	9.44	35.60—35.68	333,103	896	0.12
Julia	42.56	42.61	309,703	441	0.10
n-body
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
Chapel #3	3.61	3.58	9,720	983	20.46
Julia #5	3.80	3.84—3.96	345,936	1129	0.11
Chapel #4	4.68	4.66	9,568	1027	20.35
Chapel #2	5.74	5.72	9,929	977	20.76
Julia #4	7.17	7.23	415,039	1168	0.13
Julia #3	8.05	8.10—8.14	415,158	1548	0.11
Julia #2	28.79	29.10—29.76	415,015	1084	0.09
spectral-norm
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
Chapel #2	0.79	2.91	9,916	348	20.86
Julia #4	1.30	3.72	315,802	435	0.14
Julia #2	2.83	5.80—5.84	414,999	377	0.09
Chapel	1.50	5.78	10,109	322	20.65
mandelbrot
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
Chapel #3	1.18	4.52	42,295	582	21.29
Julia #7	1.53	4.86	357,155	629	0.10
Julia #2	1.56	4.96	356,286	634	0.12
Julia #3	1.61	5.16—5.20	376,521	589	0.13
Julia #4	2.07	5.19	368,177	583	0.12
Julia #5	1.76	5.84	381,854	580	0.12
Julia #6	2.25	5.88	368,796	571	0.08
Chapel	6.68	26.49	41,964	447	20.87
Julia	26.66	26.72	339,251	379	0.09
fasta
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
Chapel #6	0.84	0.81	10,310	1108	21.24
Julia #2	1.28	1.32	317,960	1094	0.06
Julia #5	2.67	2.72	334,729	957	0.12
Julia #4	2.73	2.77	320,463	1053	0.12
Chapel #5	1.01	3.54—3.60	11,284	1391	22.88
Chapel #3	4.07	4.05	9,597	1219	22.91
* Julia #7	1.98	4.86—5.21	405,914	1189	0.10
* Julia #6	2.25	4.70—4.91	391,623	1213	0.13
Julia #3	11.67	11.72—11.76	318,525	901	0.10
k-nucleotide
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
Julia #6	6.82	14.29—14.70	524,403	965	0.08
Chapel #4	5.02	16.99—17.77	197,980	1074	28.32
Chapel #3	5.99	20.72—21.61	190,841	1044	28.35
Julia #7	9.91	24.02—24.48	576,082	1379	0.10
Julia	132.16	133.46—134.30	1,696,596	703	0.13
reverse-complement
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
Julia #7	1.75	1.83	1,128,034	531	0.12
Julia #9	2.08	2.17	1,330,057	456	0.12
Chapel #9	1.00	2.82—2.88	1,087,742	1260	21.34
Chapel #5	1.83	3.23—3.45	1,442,632	554	20.72
Chapel #3	1.84	3.27—3.41	1,669,767	709	20.76
Julia #2	29.38	29.83—30.87	2,259,771	464	0.13
binary-trees [ Contentious. Different approaches. ]
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
Chapel #5	2.06	7.24	1,825,448	646	19.88
Julia #2	12.60	13.45—14.61	552,776	430	0.11
Julia #4	14.42	15.81—15.87	551,617	378	0.07
Julia #3	7.34	19.54—21.11	569,876	640	0.12
Chapel #3	8.61	26.00—26.04	314,032	494	20.69
Chapel #4	7.29	26.60—26.71	495,673	489	20.08
Julia #5	22.15	60.91—62.04	1,392,615	396	0.08
pidigits [ Contentious. Different libraries. ]
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
* Chapel #4	0.80	0.78	11,416	515	19.88
Chapel #2	0.80	0.78	11,543	423	20.04
* Julia #3	1.13	1.24	307,601	512	0.12
* Julia #2	1.24	1.31	315,621	686	0.13
Julia #4	3.76	3.86—3.92	414,806	531	0.11
regex-redux [ Contentious. Different libraries. ]
	elapsed	Mean or 95% CI
source	secs	cpu secs	mem	gz	make
* Julia #5	1.91	3.18	519,856	766	0.12
* Julia #4	2.00	3.26—3.33	522,338	772	0.09
* Julia #3	2.18	3.58	671,347	630	0.12
Chapel #3	3.17	4.07—4.13	392,372	503	22.24
Chapel #2	3.58	4.51	391,442	498	21.16
Julia	5.19	5.26—5.35	714,330	414	0.11
Chapel	chpl version 2.3.0 built with LLVM version 19.1.1 Copyright 2020-2024 Hewlett Packard Enterprise Development LP Copyright 2004-2019 Cray Inc.
Julia	julia version 1.11.1