NPRG054 Assignment - Deep Convolutional Neural Network

Deep Convolutional Neural Network

Deadline: 2026/06/30 23:59
This assignment is tested with -n 1 -c 64 Slurm settings
Points will be awarded for speed-up wrt. the public initial solution, logarithmically (400 pts for ten-fold speed-up)
Doxymentation
Layer sizes and complexity

Note: If your solution does not appear in the table, it is because it did not compile.

If it compiles well in your worktree, the difference is because your worktree is not up-to-date with respect to the asgn (upstream) repository. In this case, you should update your worktree using the following command, resolve the conflicts, make sure it compiles, and push to your (origin) repository.

git pull git@gitlab.mff.cuni.cz:teaching/nprg054/asgn.git

machine	author	commit	commit date	platform					loss	time	check	rel time	points
mpi-homo	andrejcd	9486c60	"2026-05-02 20:45:48 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.17082	OK	0.99784	0.375589
mpi-homo	andrejcd	9486c60	"2026-05-02 20:45:48 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169137	OK	1.00138	-0.239842
mpi-homo	asgn	6ef8d97	"2026-04-18 21:17:08 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168966	OK	1.00037	-0.0645065
mpi-homo	asgn	6ef8d97	"2026-04-18 21:17:08 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171312	OK	1.00072	-0.124164
mpi-homo	balkoad	4696c1d	"2026-04-25 02:42:27 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171161	OK	0.999833	0.0290745
mpi-homo	balkoad	4696c1d	"2026-04-25 02:42:27 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169069	OK	1.00098	-0.170186
mpi-homo	bambasz	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170898	OK	0.998296	0.296289
mpi-homo	bambasz	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169167	OK	1.00156	-0.271433
mpi-homo	bendaja1	6f40a23	"2026-05-11 15:27:31 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.17119	OK	1	-0.000497869
mpi-homo	bendaja1	6f40a23	"2026-05-11 15:27:31 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169224	OK	1.0019	-0.329897
mpi-homo	beranst	5f13dd8	"2026-05-10 18:47:47 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170717	OK	0.99724	0.480123
mpi-homo	beranst	5f13dd8	"2026-05-10 18:47:47 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169226	OK	1.00191	-0.33135
mpi-homo	bittnem1	131dd04	"2026-05-11 19:47:48 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168888	OK	0.999913	0.0151953
mpi-homo	bittnem1	131dd04	"2026-05-11 19:47:48 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171269	OK	1.00047	-0.0809509
mpi-homo	bitzanf	5b86a52	"2026-05-07 03:47:12 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170736	OK	0.997352	0.46064
mpi-homo	bitzanf	5b86a52	"2026-05-07 03:47:12 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168935	OK	1.00019	-0.0332297
mpi-homo	blahetad	5cbd5ea	"2026-04-27 15:02:02 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170875	OK	0.998162	0.319517
mpi-homo	blahetad	5cbd5ea	"2026-04-27 15:02:02 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169054	OK	1.0009	-0.155424
mpi-homo	bubakf	5a23c16	"2026-04-18 13:28:08 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170844	OK	0.997983	0.350788
mpi-homo	bubakf	5a23c16	"2026-04-18 13:28:08 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168934	OK	1.00018	-0.0320304
mpi-homo	cernohj3	dfa5975	"2026-03-09 17:34:49 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171078	OK	0.999347	0.113491
mpi-homo	cernohj3	dfa5975	"2026-03-09 17:34:49 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169329	OK	1.00252	-0.437067
mpi-homo	cimermmi	27ae19c	"2026-04-23 21:17:23 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170894	OK	0.998272	0.300464
mpi-homo	cimermmi	27ae19c	"2026-04-23 21:17:23 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168864	OK	0.999765	0.0407565
mpi-homo	dostama4	89ca229	"2026-05-10 21:20:02 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170977	OK	0.99876	0.215564
mpi-homo	dostama4	89ca229	"2026-05-10 21:20:02 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168971	OK	1.0004	-0.0696566
mpi-homo	farkasm2	63946d6	"2026-05-09 18:17:30 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170765	OK	0.997523	0.430838
mpi-homo	farkasm2	63946d6	"2026-05-09 18:17:30 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169002	OK	1.00058	-0.101373
mpi-homo	fedorekd	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170774	OK	0.997576	0.421613
mpi-homo	fedorekd	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169304	OK	1.00237	-0.411921
mpi-homo	havelh	5835e56	"2026-04-17 15:26:57 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171081	OK	0.999366	0.110214
mpi-homo	havelh	5835e56	"2026-04-17 15:26:57 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168908	OK	1.00003	-0.00483387
mpi-homo	hrdinap1	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170782	OK	0.99762	0.413981
mpi-homo	hrdinap1	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169008	OK	1.00062	-0.10754
mpi-homo	hubatama	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171077	OK	0.999344	0.113978
mpi-homo	hubatama	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169016	OK	1.00067	-0.115973
mpi-homo	huzickam	e949a67	"2026-05-06 15:33:07 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171164	OK	0.999849	0.026318
mpi-homo	huzickam	e949a67	"2026-05-06 15:33:07 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169267	OK	1.00216	-0.37406
mpi-homo	janicej	33941a5	"2026-05-11 14:11:58 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170786	OK	0.997643	0.409928
mpi-homo	janicej	33941a5	"2026-05-11 14:11:58 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169268	OK	1.00216	-0.374887
mpi-homo	jaworskr	8e480a3	"2026-05-29 10:02:49 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	4	0.129051	OK	0.75385	49.086
mpi-homo	jaworskr	8e480a3	"2026-05-29 10:02:49 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	4	0.136654	OK	0.809068	36.8059
mpi-homo	kanev	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170724	OK	0.997279	0.473416
mpi-homo	kanev	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168851	OK	0.999693	0.0533115
mpi-homo	kapylouma	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170709	OK	0.997191	0.48868
mpi-homo	kapylouma	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169206	OK	1.00179	-0.311056
mpi-homo	karaseto	d0a3297	"2026-05-11 17:14:22 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168951	OK	1.00029	-0.0495114
mpi-homo	karaseto	d0a3297	"2026-05-11 17:14:22 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171243	OK	1.00031	-0.0540235
mpi-homo	khotchai	dcafdc3	"2026-04-26 14:05:29 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168835	OK	0.999598	0.0698008
mpi-homo	khotchai	dcafdc3	"2026-04-26 14:05:29 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171156	OK	0.999802	0.0344541
mpi-homo	kleckama	d505976	"2026-04-25 15:35:49 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170778	OK	0.997598	0.4177
mpi-homo	kleckama	d505976	"2026-04-25 15:35:49 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168816	OK	0.999485	0.0894786
mpi-homo	kolnika	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168801	OK	0.999396	0.104894
mpi-homo	kolnika	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171126	OK	0.999631	0.0640933
mpi-homo	komarem4	fea02b5	"2026-05-20 00:52:25 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0883581	OK	0.516142	114.892
mpi-homo	komarem4	fea02b5	"2026-05-20 00:52:25 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.096932	OK	0.573891	96.4683
mpi-homo	koribans	c2085eb	"2026-05-24 05:53:38 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0776424	OK	0.453547	137.351
mpi-homo	koribans	c2085eb	"2026-05-24 05:53:38 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0811635	OK	0.480532	127.311
mpi-homo	kotlint	bc9c84c	"2026-05-10 21:11:44 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170773	OK	0.997568	0.423007
mpi-homo	kotlint	bc9c84c	"2026-05-10 21:11:44 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168953	OK	1.00029	-0.050805
mpi-homo	kotvami	eb04cc0	"2026-05-11 23:55:25 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.17074	OK	0.997373	0.456958
mpi-homo	kotvami	eb04cc0	"2026-05-11 23:55:25 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168944	OK	1.00024	-0.0415673
mpi-homo	krenmar	d1c7bbb	"2026-05-17 13:06:43 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170809	OK	0.997775	0.386888
mpi-homo	krenmar	d1c7bbb	"2026-05-17 13:06:43 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169153	OK	1.00148	-0.256785
mpi-homo	kroupad1	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170587	OK	0.996479	0.612658
mpi-homo	kroupad1	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168715	OK	0.998883	0.1941
mpi-homo	kruchij	c44f416	"2026-05-11 00:25:26 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170982	OK	0.998791	0.210174
mpi-homo	kruchij	c44f416	"2026-05-11 00:25:26 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168924	OK	1.00012	-0.0214681
mpi-homo	kunovaer	695f8ac	"2026-06-08 12:33:46 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.110175	OK	0.643586	76.5573
mpi-homo	kunovaer	695f8ac	"2026-06-08 12:33:46 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.141617	OK	0.838453	30.6084
mpi-homo	kurzs	ec83dbb	"2026-05-17 12:18:20 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0781705	OK	0.456631	136.174
mpi-homo	kurzs	ec83dbb	"2026-05-17 12:18:20 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169087	OK	1.00109	-0.18864
mpi-homo	kyselaj1	d2f74d4	"2026-05-25 23:15:07 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170741	OK	0.997381	0.455508
mpi-homo	kyselaj1	d2f74d4	"2026-05-25 23:15:07 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169041	OK	1.00082	-0.141713
mpi-homo	lamplotm	47e373f	"2026-05-08 14:14:57 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170828	OK	0.99789	0.366902
mpi-homo	lamplotm	47e373f	"2026-05-08 14:14:57 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169545	OK	1.0038	-0.658619
mpi-homo	lejkom	e71a7e2	"2026-05-29 15:20:25 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0748247	OK	0.437087	143.773
mpi-homo	lejkom	e71a7e2	"2026-05-29 15:20:25 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0745007	OK	0.441085	142.191
mpi-homo	lipovss	675f9e4	"2026-05-10 16:06:33 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170946	OK	0.99858	0.246802
mpi-homo	lipovss	675f9e4	"2026-05-10 16:06:33 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169055	OK	1.0009	-0.155714
mpi-homo	lopatad	5173af2	"2026-05-04 21:38:11 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170961	OK	0.998667	0.231663
mpi-homo	lopatad	5173af2	"2026-05-04 21:38:11 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168822	OK	0.999522	0.0830575
mpi-homo	lovisekd	6ef8d97	"2026-04-18 21:17:08 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170799	OK	0.997717	0.397064
mpi-homo	lovisekd	6ef8d97	"2026-04-18 21:17:08 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168822	OK	0.999518	0.0836685
mpi-homo	lukasej1	bd3c5a3	"2026-05-11 23:20:45 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170828	OK	0.997887	0.367429
mpi-homo	lukasej1	bd3c5a3	"2026-05-11 23:20:45 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168956	OK	1.00031	-0.0538141
mpi-homo	machhy	119f180	"2026-05-16 08:09:45 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171155	OK	0.9998	0.0346955
mpi-homo	machhy	119f180	"2026-05-16 08:09:45 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168977	OK	1.00044	-0.0757483
mpi-homo	machotao	a67b323	"2026-05-29 11:36:13 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0825059	OK	0.481957	126.797
mpi-homo	machotao	a67b323	"2026-05-29 11:36:13 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0906797	OK	0.536874	108.051
mpi-homo	maliarm	f248943	"2026-03-11 03:09:48 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170869	OK	0.998131	0.325063
mpi-homo	maliarm	f248943	"2026-03-11 03:09:48 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168878	OK	0.999851	0.0258136
mpi-homo	malydo	7b79608	"2026-05-09 14:30:55 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171032	OK	0.999078	0.160226
mpi-homo	malydo	7b79608	"2026-05-09 14:30:55 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169268	OK	1.00216	-0.374691
mpi-homo	masekmi2	0d4b782	"2026-04-27 15:45:15 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170759	OK	0.997483	0.437854
mpi-homo	masekmi2	0d4b782	"2026-04-27 15:45:15 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168967	OK	1.00038	-0.0653527
mpi-homo	meszard	f18c879	"2026-05-11 09:35:54 +0000"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170742	OK	0.997385	0.454824
mpi-homo	meszard	f18c879	"2026-05-11 09:35:54 +0000"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168896	OK	0.999959	0.00719837
mpi-homo	mojikm	861a978	"2026-05-11 23:53:01 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171162	OK	0.999842	0.0274009
mpi-homo	mojikm	861a978	"2026-05-11 23:53:01 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168929	OK	1.00015	-0.0261537
mpi-homo	mudraja1	3624aee	"2026-04-15 13:50:02 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171081	OK	0.999367	0.110047
mpi-homo	mudraja1	3624aee	"2026-04-15 13:50:02 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169368	OK	1.00275	-0.477374
mpi-homo	novakj80	70710b0	"2026-05-11 23:24:54 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170846	OK	0.997995	0.348739
mpi-homo	novakj80	70710b0	"2026-05-11 23:24:54 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169041	OK	1.00082	-0.142051
mpi-homo	pajonkf	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171069	OK	0.999294	0.122676
mpi-homo	pajonkf	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168973	OK	1.00042	-0.0721924
mpi-homo	pelikam3	52b02c6	"2026-05-11 23:59:26 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.17076	OK	0.997489	0.436709
mpi-homo	pelikam3	52b02c6	"2026-05-11 23:59:26 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169162	OK	1.00153	-0.265795
mpi-homo	petruchm	6337ec6	"2026-05-02 11:13:12 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170889	OK	0.998245	0.30516
mpi-homo	petruchm	6337ec6	"2026-05-02 11:13:12 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.16922	OK	1.00187	-0.325377
mpi-homo	popovaks	2fafde9	"2026-05-16 21:42:30 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170846	OK	0.997994	0.348826
mpi-homo	popovaks	2fafde9	"2026-05-16 21:42:30 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168888	OK	0.999911	0.0154074
mpi-homo	posaa	0a7cbc3	"2026-05-08 17:43:16 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170889	OK	0.998247	0.304798
mpi-homo	posaa	0a7cbc3	"2026-05-08 17:43:16 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169042	OK	1.00082	-0.143126
mpi-homo	ref	83d4b77	"2026-04-18 21:35:42 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0680516	OK	0.397522	160.255
mpi-homo	ref	83d4b77	"2026-04-18 21:35:42 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0730303	OK	0.432379	145.654
mpi-homo	reznico	b087bd6	"2026-05-08 13:38:29 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.17106	OK	0.999245	0.131258
mpi-homo	reznico	b087bd6	"2026-05-08 13:38:29 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168816	OK	0.999485	0.0895195
mpi-homo	sadovskv	5bacd1a	"2026-05-11 13:49:50 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171084	OK	0.999385	0.106928
mpi-homo	sadovskv	5bacd1a	"2026-05-11 13:49:50 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168937	OK	1.0002	-0.0349017
mpi-homo	schrodm	85d095e	"2026-05-10 09:23:11 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170726	OK	0.997291	0.471302
mpi-homo	schrodm	85d095e	"2026-05-10 09:23:11 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.16902	OK	1.00069	-0.120359
mpi-homo	sebaned	223517d	"2026-05-03 14:51:39 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170831	OK	0.997904	0.36457
mpi-homo	sebaned	223517d	"2026-05-03 14:51:39 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.16881	OK	0.999449	0.095767
mpi-homo	shtabovv	240339b	"2026-05-30 21:48:46 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.121761	OK	0.720891	56.8522
mpi-homo	shtabovv	240339b	"2026-05-30 21:48:46 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.142216	OK	0.830753	32.2112
mpi-homo	snajdrvl	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.17092	OK	0.998427	0.273481
mpi-homo	snajdrvl	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168849	OK	0.999679	0.0557082
mpi-homo	stefanm4	df73f4b	"2026-05-12 11:40:06 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170945	OK	0.998569	0.248698
mpi-homo	stefanm4	df73f4b	"2026-05-12 11:40:06 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168997	OK	1.00056	-0.0969218
mpi-homo	stehlisi	a00b80d	"2026-04-24 20:16:41 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170697	OK	0.997122	0.500628
mpi-homo	stehlisi	a00b80d	"2026-04-24 20:16:41 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168921	OK	1.00011	-0.0188249
mpi-homo	strecans	8445aeb	"2026-06-01 18:43:33 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0681144	OK	0.397889	160.095
mpi-homo	strecans	8445aeb	"2026-06-01 18:43:33 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0725476	OK	0.429522	146.806
mpi-homo	svojanoj	de4a5d0	"2026-05-06 14:08:24 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170701	OK	0.997149	0.495969
mpi-homo	svojanoj	de4a5d0	"2026-05-06 14:08:24 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169318	OK	1.00245	-0.425901
mpi-homo	tomam	1ce1671	"2026-05-22 01:18:08 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0731566	OK	0.427343	147.689
mpi-homo	tomam	1ce1671	"2026-05-22 01:18:08 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.0902451	OK	0.534301	108.886
mpi-homo	tomisz	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170813	OK	0.9978	0.382597
mpi-homo	tomisz	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169217	OK	1.00186	-0.32267
mpi-homo	vernem	29c6656	"2026-04-22 03:11:01 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171212	OK	1.00013	-0.0231604
mpi-homo	vernem	29c6656	"2026-04-22 03:11:01 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168968	OK	1.00038	-0.066523
mpi-homo	vireakt	d1d89eb	"2026-04-12 11:50:15 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170794	OK	0.99769	0.401729
mpi-homo	vireakt	d1d89eb	"2026-04-12 11:50:15 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168986	OK	1.00049	-0.0852592
mpi-homo	vivtonea	15996de	"2026-05-10 17:24:04 +0000"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170871	OK	0.998142	0.323107
mpi-homo	vivtonea	15996de	"2026-05-10 17:24:04 +0000"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168865	OK	0.999777	0.038789
mpi-homo	yuriicho	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170667	OK	0.996946	0.531316
mpi-homo	yuriicho	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.169277	OK	1.00221	-0.383741
mpi-homo	zatloum1	e9f312c	"2026-04-20 20:19:44 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170882	OK	0.998205	0.312058
mpi-homo	zatloum1	e9f312c	"2026-04-20 20:19:44 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.16929	OK	1.00229	-0.397148
mpi-homo	zavodsv	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.171093	OK	0.999436	0.0979551
mpi-homo	zavodsv	4d2e6c0	"2026-03-07 14:47:14 +0100"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.168899	OK	0.999977	0.00405793
mpi-homo	zelezno	f6b9e0b	"2026-04-25 11:28:12 +0200"	avx512	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.170841	OK	0.997965	0.353888
mpi-homo	zelezno	f6b9e0b	"2026-04-25 11:28:12 +0200"	avx	(16,16,5)	(2048,2048,2)	(8,8,2)	all	6	0.16898	OK	1.00045	-0.0789581

Your job is to improve the performance of the existing code, by altering the code in sol/dcnnsol.hpp. (You may also write some code in sol/dcnnsol.cpp; however, all the existing code is templated and must remain in the header file.)

Input data

The folder containing input data is set by the command-line parameter --data-folder.

The input data are already available at parlab, in the folder /home/_teaching/hiperf/dcnndata. Therefore, the program shall be invoked as:

srun -p mpi-homo-short -n 1 -c 64 ./dcnn --data-folder=/home/_teaching/hiperf/dcnndata

The input data may be downloaded from parlab via scp or compressed from here:

simplenet.model.tgz (5.3 MB) - Pretrained weights

imagenet.input.tgz (307.9 MB) - Test images and expected results

Test parameters

data-folder - the folder containing the input data files (default: data).

minibatch - the number of images in a testing minibatch (processed in one call to the forward functions). Default: 16.

superbatch - the number of minibatches in a testing batch (each minibatch is assigned to a different thread). Default: 8 (1 in Debug mode).

total - the total number of images submitted into testing (shall be divisible by minibatch*superbatch). Default: 2048 (16 in Debug mode).

Credits

The DCNN architecture was taken from [Hasanpour 2016]. The original implementation used the Caffe framework and was later converted to Pytorch.

Both the pretrained weights and the test images were converted from publicly available data:

SimpleNet - ImageNet pretrained weights

ILSVRC2012 - ImageNet Object Localization Challenge

References

[Hasanpour 2016] Hasanpour, Seyyed Hossein, et al. Lets keep it simple, using simple architectures to outperform deeper and more complex architectures. arXiv:1608.06037.