5276 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Peter Boyle	c0d89a2dbb	TODO updates	2019-07-12 17:11:15 +01:00
Peter Boyle	78ebd93281	Cuda 9.1 happy	2019-07-12 17:11:00 +01:00
Peter Boyle	3d58daf70f	Safety check	2019-07-12 17:10:35 +01:00
Peter Boyle	bd155ca5c0	Overlap comms with comput now supported	2019-07-12 09:09:40 +01:00
Peter Boyle	91e2cf9b40	All axes can be used for comms now	2019-07-12 09:08:26 +01:00
Peter Boyle	3cc9947731	Better welcome printing	2019-07-12 06:47:51 +01:00
Peter Boyle	f15eeb0283	localise scope of variables declared in macro	2019-07-12 06:47:01 +01:00
Peter Boyle	0996ba9396	Pretty messaging	2019-07-12 06:45:31 +01:00
Peter Boyle	966a203dcb	Interactions with GPU compilation	2019-07-11 03:16:17 +01:00
Peter Boyle	44170cc15f	Initialise CUDA device prior to entering MPI. ... This may or may not interact with Summit which configures MPI - CUDA mapping with jsrun. TBD Cases of OpenMPI and MVAPICH are covered, and default to cudaSetDevice(0) otherwise	2019-07-11 03:14:23 +01:00
Antonin Portelli	c3d0c176ab	cleaning up Kl2 contraction	2019-07-05 16:29:46 +01:00
Antonin Portelli	0a71f8bb10	Merge pull request #222 from guelpers/feature/kl2QEDseq ... EMLepton: Multiple source-sink separations at once	2019-07-05 16:22:34 +01:00
Vera Guelpers	3a31ba2ea2	Merge remote-tracking branch 'upstream/develop' into feature/kl2QEDseq	2019-07-03 14:37:56 +01:00
Vera Guelpers	eac6337466	Hadrons: EMLepton: multiple source-sink separations at once	2019-07-03 14:36:34 +01:00
Antonin Portelli	ab7537e002	Merge pull request #221 from fionnoh/bugfix/A2ALoop ... Bugfix for A2ALoop module	2019-07-03 14:13:51 +01:00
Peter Boyle	6e3c3214a3	Offload loops	2019-07-02 17:25:40 +01:00
Peter Boyle	d6ffadb33b	Coalesced write	2019-07-02 17:25:13 +01:00
Peter Boyle	4c3225412b	Drop 5dVEC	2019-07-01 07:31:26 +01:00
Peter Boyle	b8f7bfbb26	Dont stream as poor perf in some cases	2019-07-01 07:30:25 +01:00
Peter Boyle	7b7c470917	Accelerator loop	2019-07-01 07:29:51 +01:00
Peter Boyle	532e226b22	cuda 9.1 fixes	2019-07-01 07:29:22 +01:00
Peter Boyle	6a13731818	Move GPU cuda call earlier	2019-07-01 07:28:41 +01:00
fionnoh	67690df3bd	Changes nedded to have a current insertion on every second time slice - avoids unnecessary contractions	2019-06-28 15:18:28 +08:00
fionnoh	1059189abf	Bugfix for A2ALoop module	2019-06-27 13:49:55 +08:00
fionnoh	ce29b18dc9	New modules for loading in MFs as diskvectors and producing propagaotrs from 4 quark contractions	2019-06-27 13:46:06 +08:00
fionnoh	421a0a8a36	Changes to A2Autils, A2AMatirx and DiskVector code that is needed for Hadrons 4 quark contraction module	2019-06-27 13:45:20 +08:00
fionnoh	ac530636ca	A2Aloop bugfix	2019-06-27 13:44:47 +08:00
Peter Boyle	1cd4ee0706	Thrust used on GPU builds	2019-06-18 12:50:35 +01:00
Peter Boyle	b8f71b6777	Fix NVCC warning unused variable	2019-06-17 13:58:45 +01:00
Peter Boyle	703dc20377	Compile tests fix	2019-06-16 13:59:29 +01:00
Peter Boyle	d976e5c514	Pow is being awkward in thrust for reasons I don't understand. Possible thrust bug.	2019-06-16 12:05:11 +01:00
Peter Boyle	d7b3efe893	Compile fix	2019-06-15 17:03:15 +01:00
Peter Boyle	f710d7bd45	TODO list update	2019-06-15 12:54:27 +01:00
Peter Boyle	cb336aa8f8	Thread loop constructs changing a little	2019-06-15 12:54:11 +01:00
Peter Boyle	462900b48d	Modified entire test directory to suit new GPU constructs for looping	2019-06-15 12:53:27 +01:00
Peter Boyle	0561c2edeb	Benchmarks modified for new GPU constructs	2019-06-15 12:52:56 +01:00
Peter Boyle	0184719216	Change to predicate type	2019-06-15 12:52:26 +01:00
Peter Boyle	24202dbc51	Thread loop construct change	2019-06-15 12:52:07 +01:00
Peter Boyle	d763c303c5	Clean acceleerator barrier	2019-06-15 12:51:45 +01:00
Peter Boyle	8e394d3bf9	New loop construct	2019-06-15 12:51:15 +01:00
Peter Boyle	b881d5489b	Move SchurDiagTwoKappa to Algorithms	2019-06-15 12:50:45 +01:00
Peter Boyle	82306913a8	Move Schur operator into correct place	2019-06-15 12:49:22 +01:00
Peter Boyle	49f90cc7eb	use pragma once	2019-06-15 12:45:22 +01:00
Peter Boyle	b77af0210b	Thread loop. Probably deprecate this impl	2019-06-15 12:44:56 +01:00
Peter Boyle	5254ede2d8	New loops. Revisit as accelerator loop in future audit	2019-06-15 12:44:29 +01:00
Peter Boyle	16e5d7945e	Hard to make 5D vec work with GPU code	2019-06-15 12:43:43 +01:00
Peter Boyle	decc99ca76	Accelerator version	2019-06-15 12:43:00 +01:00
Peter Boyle	464cd65931	Still to test this fully	2019-06-15 12:35:14 +01:00
Peter Boyle	a1ec2f4723	Still to test this routine fully	2019-06-15 12:33:55 +01:00
Peter Boyle	ea9662ec85	Thread loop changes	2019-06-15 09:09:57 +01:00