a00ae98 | Peter Boyle | 29 March 2023, 19:00:40 UTC | Fence propagation from SYCL | 29 March 2023, 19:00:40 UTC |
3f2fd49 | Peter Boyle | 28 March 2023, 00:29:54 UTC | Merge branch 'develop' of https://github.com/paboyle/Grid into develop | 28 March 2023, 00:29:54 UTC |
0efa107 | Peter Boyle | 28 March 2023, 00:29:43 UTC | Script update | 28 March 2023, 00:29:43 UTC |
8feedb4 | Peter Boyle | 28 March 2023, 00:29:21 UTC | Include files moved | 28 March 2023, 00:29:21 UTC |
05e562e | Peter Boyle | 28 March 2023, 00:28:38 UTC | Move the copy synch out to stencil and do one per call instead of one per packet | 28 March 2023, 00:28:38 UTC |
dd3bbb8 | Peter Boyle | 28 March 2023, 00:27:45 UTC | MOve the synchronise out to the stencil so one call instead of one call per packet | 28 March 2023, 00:27:45 UTC |
2fbcf13 | Peter Boyle | 27 March 2023, 21:25:14 UTC | SYCL fix | 27 March 2023, 21:25:14 UTC |
4ea48ef | Peter Boyle | 24 March 2023, 19:42:16 UTC | Merge pull request #419 from lehner/feature/gpt Separate rankSum from sum | 24 March 2023, 19:42:16 UTC |
546be72 | Peter Boyle | 24 March 2023, 16:04:06 UTC | Merge pull request #421 from UniOfLeicester/feature/accel_Copy_plane Populate the Cshift_table in the GPU | 24 March 2023, 16:04:06 UTC |
481bbaf | Peter Boyle | 23 March 2023, 16:55:31 UTC | Interface to query memory use | 23 March 2023, 16:55:31 UTC |
2814886 | Peter Boyle | 23 March 2023, 14:28:50 UTC | WriteDiscard on construct | 23 March 2023, 14:28:50 UTC |
bae0f8e | Peter Boyle | 21 March 2023, 12:59:08 UTC | Merge pull request #425 from rrhodgson/feature/CacheLogging Huge Cache | 21 March 2023, 12:59:08 UTC |
bbbcd36 | Peter Boyle | 21 March 2023, 12:58:40 UTC | Merge pull request #426 from rrhodgson/feature/LCDeflation Batched Local Coherence Tools | 21 March 2023, 12:58:40 UTC |
39c0815 | Peter Boyle | 21 March 2023, 12:57:29 UTC | WriteDiscard | 21 March 2023, 12:57:29 UTC |
a3e935c | Raoul Hodgson | 27 February 2023, 11:38:16 UTC | Batched block project/promote size checks | 27 February 2023, 11:38:16 UTC |
7731c7d | Raoul Hodgson | 26 February 2023, 14:15:28 UTC | Add huge cache type and allow Ncache==0 | 26 February 2023, 14:15:28 UTC |
ff97340 | Raoul Hodgson | 26 February 2023, 12:22:45 UTC | Expose cached bytes | 26 February 2023, 12:22:45 UTC |
920a514 | Raoul Hodgson | 14 February 2023, 17:04:13 UTC | Added batched Mixed precision CG | 14 February 2023, 17:04:13 UTC |
be528b6 | Raoul Hodgson | 14 February 2023, 14:37:10 UTC | Add batched block project/promote functions | 14 February 2023, 14:37:10 UTC |
796abfa | Peter Boyle | 17 January 2023, 14:34:49 UTC | Merge pull request #422 from fjosw/fix/NVCC_DIAG_PRAGMA_SUPPORT Disable diagnostic pragma warnings for CUDA 12+ | 17 January 2023, 14:34:49 UTC |
ad0270a | Fabian Joswig | 12 January 2023, 12:36:30 UTC | fix: diagnostic pragma warnings fixed for CUDA 12+ | 12 January 2023, 12:36:30 UTC |
7d62f1d | Makis Kappas | 11 January 2023, 21:26:25 UTC | Populate the Cshift_table in the GPU Cshift is allocated in Unified memory and used in the LambdaApply kernels but also populated from the host. This creates a lot of Unified HtoD and DtoH mem operations and has a negative effect in performance. With this commit we populate the Cshift table in the device with the populate_Cshift_table() kernel. | 11 January 2023, 21:26:25 UTC |
458c943 | Christoph Lehner | 31 December 2022, 09:16:21 UTC | merged upstream | 31 December 2022, 09:16:21 UTC |
88015b0 | Christoph Lehner | 26 December 2022, 09:01:32 UTC | Split sum in rankSum and GlobalSum | 26 December 2022, 09:01:32 UTC |
4ca1bf7 | Peter Boyle | 21 December 2022, 12:23:16 UTC | Added gauge invariance test | 21 December 2022, 12:23:16 UTC |
2ff868f | Peter Boyle | 01 December 2022, 05:35:05 UTC | CPU open doesn't need to free space | 20 December 2022, 10:10:23 UTC |
ede02b6 | Peter Boyle | 01 December 2022, 05:25:04 UTC | Memory manager debug Felix case | 20 December 2022, 10:10:23 UTC |
1822ced | Peter Boyle | 01 December 2022, 05:24:08 UTC | Bug fix | 20 December 2022, 10:10:23 UTC |
37ba327 | Peter Boyle | 01 December 2022, 05:19:42 UTC | More logging | 20 December 2022, 10:10:23 UTC |
99b3697 | Peter Boyle | 01 December 2022, 05:19:33 UTC | More loggin | 20 December 2022, 10:10:23 UTC |
43a45ec | Peter Boyle | 01 December 2022, 05:18:43 UTC | SSC_START | 20 December 2022, 10:10:23 UTC |
b00a414 | Peter Boyle | 01 December 2022, 05:18:11 UTC | A=A fix | 20 December 2022, 10:10:23 UTC |
3791bc5 | Peter Boyle | 30 November 2022, 20:55:17 UTC | Logging pulled in from dirichlet branch | 20 December 2022, 10:10:23 UTC |
d8c29f5 | Peter Boyle | 18 December 2022, 17:05:00 UTC | Updated FFT test for PETSc | 18 December 2022, 17:05:00 UTC |
281f810 | Peter Boyle | 18 December 2022, 01:35:33 UTC | Matt FFT test | 18 December 2022, 01:35:33 UTC |
07acfe8 | Peter Boyle | 06 December 2022, 17:45:03 UTC | Merge pull request #417 from rrhodgson/feature/fermtoprop Feature/fermtoprop | 06 December 2022, 17:45:03 UTC |
40234f5 | Raoul Hodgson | 06 December 2022, 17:34:51 UTC | FermToProp accelerator_for -> thread_for | 06 December 2022, 17:34:51 UTC |
d49694f | Raoul Hodgson | 06 December 2022, 15:48:54 UTC | PropToFerm fix | 06 December 2022, 15:48:54 UTC |
97a0986 | Peter Boyle | 30 November 2022, 20:36:35 UTC | FermToProp | 30 November 2022, 20:36:35 UTC |
e13930c | Peter Boyle | 30 November 2022, 20:11:29 UTC | Faster fermtoprop case | 30 November 2022, 20:11:29 UTC |
0655dab | Peter Boyle | 08 November 2022, 21:38:54 UTC | Open MP on host enabled | 08 November 2022, 21:38:54 UTC |
7f097bc | Peter Boyle | 08 November 2022, 21:23:40 UTC | Merge branch 'develop' of https://github.com/paboyle/Grid into develop | 08 November 2022, 21:23:40 UTC |
5c75aa5 | Peter Boyle | 08 November 2022, 21:22:57 UTC | Device mem | 08 November 2022, 21:22:57 UTC |
1873101 | Peter Boyle | 08 November 2022, 21:22:45 UTC | PVC | 08 November 2022, 21:22:45 UTC |
63fd1df | Peter Boyle | 08 November 2022, 21:22:09 UTC | Config on PVC | 08 November 2022, 21:22:09 UTC |
bd68861 | Peter Boyle | 08 November 2022, 20:49:26 UTC | SYCL sum | 08 November 2022, 20:49:26 UTC |
82e959f | Peter Boyle | 08 November 2022, 20:45:25 UTC | SYCL reduction | 08 November 2022, 20:45:25 UTC |
62e52de | Peter Boyle | 01 November 2022, 13:15:44 UTC | Merge pull request #414 from fjosw/feat/eCloverGPU Compact Exponential Cloverterm on GPU | 01 November 2022, 13:15:44 UTC |
184adee | Fabian Joswig | 26 October 2022, 11:53:46 UTC | feat: renamed open_boundaries to fixedBoundaries | 26 October 2022, 11:53:46 UTC |
5fa6a8b | Fabian Joswig | 26 October 2022, 11:40:28 UTC | docs: CompactClover debug info generalized. | 26 October 2022, 11:41:14 UTC |
a2a879b | Fabian Joswig | 25 October 2022, 16:20:42 UTC | docs: CompactClover Debug Info improved. | 25 October 2022, 16:20:42 UTC |
9317d89 | Fabian Joswig | 25 October 2022, 16:10:06 UTC | docs: details about inversion of CompactClover term added. | 25 October 2022, 16:10:06 UTC |
86075fd | Fabian Joswig | 25 October 2022, 16:05:34 UTC | feat: MassTerm and ExponentiateClover merged into InstantiateClover | 25 October 2022, 16:05:34 UTC |
b36442e | Fabian Joswig | 25 October 2022, 15:57:01 UTC | feat: CloverHelpers::InvertClover implemented which handles the inversion of the Clover term depending on clover type and the boundary conditions. | 25 October 2022, 15:57:01 UTC |
513d797 | Fabian Joswig | 25 October 2022, 15:17:22 UTC | fix: signature of CompactWilsonCloverHelpers::Exponentiate fixed. | 25 October 2022, 15:17:22 UTC |
9e4835a | Fabian Joswig | 25 October 2022, 14:19:43 UTC | feat: changed CompactWilsonExpClover exponentiation to Taylor expansion with Horner scheme. | 25 October 2022, 14:19:43 UTC |
477ebf2 | Peter Boyle | 04 October 2022, 18:19:43 UTC | Merge branch 'develop' of https://github.com/paboyle/Grid into develop | 04 October 2022, 18:19:43 UTC |
0d5639f | Peter Boyle | 04 October 2022, 18:13:41 UTC | Run script update | 04 October 2022, 18:13:41 UTC |
413312f | Peter Boyle | 04 October 2022, 18:12:59 UTC | Benchmark the halo construction. THe bye counts are out and should be doubled for SIMD directions | 04 October 2022, 18:12:59 UTC |
0350844 | Peter Boyle | 04 October 2022, 18:12:15 UTC | Remove verbose | 04 October 2022, 18:12:15 UTC |
e1e5c75 | Peter Boyle | 04 October 2022, 18:11:10 UTC | Stencil gather improvements - SVM was running slow and used for a pointer array that wasn't needed to be in SVM | 04 October 2022, 18:11:10 UTC |
9296299 | Peter Boyle | 04 October 2022, 18:10:34 UTC | Better commenting | 04 October 2022, 18:10:34 UTC |
913fbca | Peter Boyle | 31 August 2022, 22:01:45 UTC | Merge pull request #410 from gkanwar/photon_and_sha_patches Photon.h and SHA256 patches | 31 August 2022, 22:01:45 UTC |
60dfb49 | Gurtej Kanwar | 21 August 2022, 15:29:55 UTC | Remove FP16 tests when FP16 is disabled | 21 August 2022, 15:29:55 UTC |
554c238 | Gurtej Kanwar | 21 August 2022, 15:28:57 UTC | Update OpenSSL digest to use high-level methods This avoids deprecation warnings when compiling against OpenSSL 3.0 but should still be backwards compatible. It is the recommended way to use the digest API going forward. | 21 August 2022, 15:28:57 UTC |
f922adf | Gurtej Kanwar | 21 August 2022, 14:16:18 UTC | Fix Photon ComplexField type | 21 August 2022, 14:16:18 UTC |
188d2c7 | Peter Boyle | 02 August 2022, 15:38:53 UTC | PVC default, ignore ATS | 02 August 2022, 15:38:53 UTC |
17d7177 | Peter Boyle | 02 August 2022, 15:33:39 UTC | Files for SYCL | 02 August 2022, 15:33:39 UTC |
bb0a0da | Peter Boyle | 02 August 2022, 15:09:43 UTC | inon blocking caution due to SYCL | 02 August 2022, 15:09:43 UTC |
8411016 | Peter Boyle | 02 August 2022, 15:00:43 UTC | Fix the fence | 02 August 2022, 15:00:43 UTC |
d32b923 | Peter Boyle | 02 August 2022, 14:58:04 UTC | Fencing on a stream in SYCL is needed. Didn't know that ... gulp | 02 August 2022, 14:58:04 UTC |
2ab1af5 | Peter Boyle | 19 July 2022, 16:51:06 UTC | Ensure no synchronize and not optoin dependent | 19 July 2022, 16:51:06 UTC |
5f8892b | Peter Boyle | 19 July 2022, 16:31:51 UTC | Mistake pointed out by Camilo | 19 July 2022, 16:31:51 UTC |
f14e7e5 | Peter Boyle | 12 July 2022, 17:56:22 UTC | Grid accelerator | 12 July 2022, 17:56:22 UTC |
042ab1a | Peter Boyle | 27 June 2022, 17:21:39 UTC | Update GridStd.h | 27 June 2022, 17:21:39 UTC |
2df98a9 | Peter Boyle | 14 June 2022, 21:46:25 UTC | Merge pull request #406 from giordano/patch-1 Update default value of gen-simd-width in README | 14 June 2022, 21:46:25 UTC |
315ea18 | Mosè Giordano | 14 June 2022, 21:41:05 UTC | Update default value of gen-simd-width in README | 14 June 2022, 21:41:05 UTC |
a9c2e1d | Peter Boyle | 25 May 2022, 17:30:11 UTC | Merge pull request #404 from rrhodgson/feature/json_nvcc Feature/json nvcc | 25 May 2022, 17:30:11 UTC |
da4daea | Raoul Hodgson | 24 May 2022, 15:16:06 UTC | Updated json to latest release 3.10.5 | 24 May 2022, 15:16:06 UTC |
af3b065 | Peter Boyle | 24 May 2022, 15:10:02 UTC | Merge pull request #403 from fjosw/fix/cuda_11_5_warnings Fixed nvcc 11.5+ warnings | 24 May 2022, 15:10:02 UTC |
e346154 | Raoul Hodgson | 24 May 2022, 14:47:01 UTC | Updated json CUDA compile guards | 24 May 2022, 14:48:01 UTC |
7937ac2 | Fabian Joswig | 24 May 2022, 14:31:03 UTC | fix: conditional pragmas according to new NVCC_DIAG_PRAGMA_SUPPORT standard in pugixml/pugixml.cc | 24 May 2022, 14:31:03 UTC |
e909aee | Fabian Joswig | 24 May 2022, 14:29:42 UTC | fix: conditional pragmas according to new NVCC_DIAG_PRAGMA_SUPPORT standard in Grid_Eigen_Dense.h | 24 May 2022, 14:29:42 UTC |
bab8aa8 | Fabian Joswig | 24 May 2022, 14:27:40 UTC | fix: conditional pragmas according to new NVCC_DIAG_PRAGMA_SUPPORT standard in DisableWarnings.h | 24 May 2022, 14:27:40 UTC |
38b22f0 | Peter Boyle | 24 May 2022, 14:05:27 UTC | Merge pull request #402 from fjosw/fix/clover_warnings fixed clover warnings | 24 May 2022, 14:05:27 UTC |
3ca0de1 | Raoul Hodgson | 24 May 2022, 13:37:33 UTC | Fix json write for vector<string> | 24 May 2022, 13:37:33 UTC |
c7205d2 | Raoul Hodgson | 24 May 2022, 13:30:26 UTC | Removed nvcc guards for json | 24 May 2022, 13:30:26 UTC |
617c536 | Fabian Joswig | 24 May 2022, 10:37:33 UTC | fix: fixed warning: missing return statement at end of non-void function in CloverHelpers | 24 May 2022, 10:37:33 UTC |
083b58e | Peter Boyle | 20 May 2022, 15:44:22 UTC | Merge pull request #401 from JPRichings/LocalCoheranceDeflation Local coherance batch deflation | 20 May 2022, 15:44:22 UTC |
633427a | Peter Boyle | 20 May 2022, 15:43:40 UTC | Merge pull request #400 from JPRichings/wilson_sweep bench wilson sweep fix | 20 May 2022, 15:43:40 UTC |
2031d69 | JPRichings | 20 May 2022, 15:20:23 UTC | Merge branch 'paboyle:develop' into wilson_sweep | 20 May 2022, 15:20:23 UTC |
79e34b3 | JPRichings | 19 May 2022, 13:53:17 UTC | Local Coherence batch deflation | 19 May 2022, 13:53:17 UTC |
4f3d581 | JPRichings | 19 May 2022, 13:46:17 UTC | Merge branch 'paboyle:develop' into LocalCoheranceDeflation | 19 May 2022, 13:46:17 UTC |
d16427b | Peter Boyle | 17 May 2022, 13:03:42 UTC | Merge pull request #399 from fjosw/fix/Nc_neq_3 fix: assert for dimensions of compact Wilson clover moved to constructor | 17 May 2022, 13:03:42 UTC |
4b1997e | James Richings | 16 May 2022, 14:58:33 UTC | wilson sweep test | 16 May 2022, 14:58:33 UTC |
8939d5d | James Richings | 15 May 2022, 23:28:28 UTC | bugfix: eo operator called in correct location | 15 May 2022, 23:28:28 UTC |
b051e00 | James Richings | 15 May 2022, 23:25:13 UTC | Additional Local Coherance Deflation operator() | 15 May 2022, 23:25:13 UTC |
8aa75b4 | Fabian Joswig | 10 May 2022, 13:22:03 UTC | Merge branch 'develop' into fix/Nc_neq_3 | 10 May 2022, 13:22:03 UTC |
0274f40 | Peter Boyle | 10 May 2022, 13:18:19 UTC | Merge pull request #389 from mbruno46/mbruno-eclover Feature/expClover | 10 May 2022, 13:18:19 UTC |
77aa147 | Peter Boyle | 10 May 2022, 13:16:53 UTC | Merge branch 'develop' into mbruno-eclover | 10 May 2022, 13:16:53 UTC |