1
0
mirror of https://github.com/paboyle/Grid.git synced 2026-06-04 11:14:38 +01:00

Commit Graph

  • 1315d4604d Enable GRID_REDUCTION_TIMING unconditionally Peter Boyle 2026-05-18 22:14:00 -04:00
  • a31af31328 Lattice_reduction_gpu: add GRID_REDUCTION_TIMING instrumentation Peter Boyle 2026-05-18 22:13:30 -04:00
  • 26c3c7d8f9 sumD_gpu_large: radix-12 word-bundle reduction replacing radix-1 Peter Boyle 2026-05-18 21:56:45 -04:00
  • 0650d7c7eb Lattice_reduction_sycl: fix double-precision accumulation in sumD_gpu_tensor Peter Boyle 2026-05-18 21:53:40 -04:00
  • 068f95ad2d Revert to hand-rolled reduction; drop Lattice_reduction_gpu_cub.h Peter Boyle 2026-05-18 21:52:18 -04:00
  • f4fbf7c9ca sumD_gpu_direct: revert to per-lane write; CUB handles Nsimd*osites inputs Peter Boyle 2026-05-18 21:23:15 -04:00
  • 843d6497b2 sumD_gpu_direct: shared-memory lane reduction with acceleratorThreads(1) Peter Boyle 2026-05-18 21:08:10 -04:00
  • 747c167658 sumD_gpu_direct: one thread per SIMD lane using extractLane Peter Boyle 2026-05-18 16:21:50 -04:00
  • fca2c5dba0 Lattice_reduction_gpu_cub: define GRID_REDUCTION_TIMING in header Peter Boyle 2026-05-18 14:54:08 -04:00
  • e12bc7f07c Lattice_reduction_gpu_cub: add GRID_REDUCTION_TIMING instrumentation Peter Boyle 2026-05-18 14:23:44 -04:00
  • dc6ae51cab Lattice_reduction_gpu_cub: replace WordBundle4 with iVector<iScalar<scalarD>,4> Peter Boyle 2026-05-18 13:55:28 -04:00
  • baa70d8ec9 Test_reduction: add timing benchmark for new vs old reduction paths Peter Boyle 2026-05-18 12:31:13 -04:00
  • c93b338bdd skills: HPC battle-hardening skill files for GPU+MPI correctness Peter Boyle 2026-05-18 12:10:44 -04:00
  • c0472aa0ec Test_reduction: use separate float and double grids Peter Boyle 2026-05-18 12:09:35 -04:00
  • 09552cfd73 Rename scalarNorm2 to squaredSum in Test_reduction.cc Peter Boyle 2026-05-15 23:15:11 -04:00
  • 003fec509c Fix Zero() used on thrust::complex in WordBundle4 initialisation Peter Boyle 2026-05-15 18:10:17 -04:00
  • 773a82d87f Reinstate large/small dispatch in CUB reduction path; radix-4 word-bundle for large types Peter Boyle 2026-05-15 16:55:58 -04:00
  • 286c29d6fb Add Test_reduction to tests/debug Peter Boyle 2026-05-15 14:31:33 -04:00
  • 969b0a3922 Rewrite lattice GPU reduction to use CUB, hipCUB, and SYCL reduction Peter Boyle 2026-05-15 13:41:56 -04:00
  • f8b2eacf99 File list issue (Ed Bennets pull request?) Peter Boyle 2026-05-15 12:57:42 -04:00
  • 6140ac6864 Hip Happy Peter Boyle 2026-05-15 12:13:01 -04:00
  • c6c2834e03 Hip Happy Peter Boyle 2026-05-15 11:27:46 -04:00
  • 856545a1db Support ROCM 7.0.2 Peter Boyle 2026-05-15 11:25:47 -04:00
  • e2d607f6c7 Merge pull request #490 from jdmaia/hip-guard-acceleratorfor2dNB Peter Boyle 2026-05-06 14:51:30 -04:00
  • 66da4e0657 Including guard on accelerator_for2dNB against invalid kernel configurations if GRID_HIP Julio Maia 2026-05-06 11:38:57 -05:00
  • b37390bb5a 4 node usqcd run Peter Boyle 2026-04-27 14:40:11 -07:00
  • 829dc8cceb 32 node Peter Boyle 2026-04-27 14:38:02 -07:00
  • 13cc2c39f5 FOM run Peter Boyle 2026-04-27 14:20:49 -07:00
  • 66ea3b271c Merge branch 'develop' of https://github.com/paboyle/Grid into develop Peter Boyle 2026-04-27 13:55:52 -07:00
  • d293b58a20 384 node baseline run Peter Boyle 2026-04-27 13:54:40 -07:00
  • ce093b2bf3 rdtsc Peter Boyle 2026-04-27 13:54:06 -07:00
  • e4404efe5a Perlmutter compile update Peter Boyle 2026-04-27 13:53:28 -07:00
  • 5ce270f1de Adding Claude related files Peter Boyle 2026-04-21 10:41:18 -04:00
  • af43b067a0 New CLAUDE controllable visualiser Peter Boyle 2026-04-10 11:23:25 -04:00
  • 34b44d1fee New file for animation in MD time direction Quadro 2026-04-02 13:55:38 -04:00
  • 09aa843984 Changed batchedInnerProduct for portability KS_shifted Chulwoo Jung 2026-03-17 18:54:18 -04:00
  • 24752002fa Verbosity reduction batched inner product for reorthogonalization Chulwoo Jung 2026-03-17 13:02:16 -04:00
  • f3223021fd RestartedLanczosBidiagonalization seems to have been fixed Chulwoo Jung 2026-03-16 14:34:56 -04:00
  • 4e1d95d3bb Claude implementation of Thick Restarted Lanczos Bidiagonalization Chulwoo Jung 2026-03-13 19:12:54 -04:00
  • 2ed38f63ca Merge branch 'develop' of https://github.com/paboyle/Grid into KS_shifted Chulwoo Jung 2026-03-12 10:49:21 -04:00
  • 80d2a8d88d wqMerge branch 'develop' of https://github.com/paboyle/Grid into KS_shifted Chulwoo Jung 2026-03-11 21:49:26 -04:00
  • 595ceaac37 Include grid header and make the ENABLE correct Peter Boyle 2026-03-11 17:24:44 -04:00
  • daf5834e8e Fixing incorrect PR about disable fermion instantiations Peter Boyle 2026-03-11 17:05:46 -04:00
  • 2ac5431401 Turning of NERSC header checking Chulwoo Jung 2026-03-06 14:16:20 -05:00
  • 0d8658a039 Optimised Peter Boyle 2026-03-05 06:06:22 -05:00
  • 095e004d01 Setup change GCR Peter Boyle 2026-03-05 06:05:50 -05:00
  • 0acabee7f6 Modest change Peter Boyle 2026-03-05 06:04:26 -05:00
  • 76fbcffb60 Improvement to 16^3 hdcg Peter Boyle 2026-03-05 06:02:38 -05:00
  • a0a62d7ead Merge pull request #478 from vataspro/PolyakovUpstream Peter Boyle 2026-02-24 20:45:42 -05:00
  • c5038ea6a5 Merge pull request #483 from cmcknigh/bugfix/rocm7-rocblas-type-refactor Peter Boyle 2026-02-24 20:45:03 -05:00
  • a5120903eb Merge pull request #486 from RChrHill/fix/sp4-fp32 Peter Boyle 2026-02-24 20:44:08 -05:00
  • 00b286a08a Merge pull request #488 from RChrHill/feature/additional-ET-traces Peter Boyle 2026-02-24 20:43:45 -05:00
  • 24a9759353 Merge pull request #485 from edbennett/skip-fermion-instantiations Peter Boyle 2026-02-24 20:43:20 -05:00
  • 1b56f6f46d be able to skip compiling fermion instantiations altogether edbennett 2025-11-15 00:52:38 +00:00
  • 2a8084d569 Subspace setup Peter Boyle 2026-02-13 17:26:11 -05:00
  • 6ff29f9d4f Alternate multigrids Peter Boyle 2026-02-13 17:25:45 -05:00
  • c4d3e79193 Add ET support for Lattice spin- and colour-traces RChHill 2026-01-29 14:46:52 +00:00
  • 3e71cac7ae Merge branch 'specflow2' of github.com:chulwoo1/Grid into KS_shifted Chulwoo Jung 2026-01-15 03:40:52 +00:00
  • e8e7ef08fc KrylovSchur and spectral flow updates Chulwoo Jung 2026-01-15 03:20:01 +00:00
  • 5c00fe6bef Merge branch 'develop' of github.com:poare/Grid into KS_shifted Chulwoo Jung 2026-01-12 06:26:15 +00:00
  • 3175788f97 Added explicit shift before pulling Chulwoo Jung 2026-01-12 06:25:09 +00:00
  • 6f1788bb38 modified Givens rotation to implement a sparse multiplication Patrick Oare 2026-01-06 16:19:48 -05:00
  • 7cd3f21e6b preserving a bunch of experiments on setup and g5 subspace doubling Peter Boyle 2026-01-06 05:56:54 -05:00
  • dcda74f924 Timing info for schurReorder,etc Chulwoo Jung 2025-12-18 18:23:50 +00:00
  • df4c2a082b Reducing comments Chulwoo Jung 2025-12-09 14:23:22 +00:00
  • 88611659a3 Appear to be working Chulwoo Jung 2025-12-08 21:08:14 -05:00
  • 504b85dfc0 Restarting and adding codes back in Chulwoo Jung 2025-12-08 13:27:06 -05:00
  • 43ea83e5e1 Checking in to move back to genoa Chulwoo Jung 2025-12-05 23:56:40 +00:00
  • 376150c3df Adding Chulwoo Jung 2025-12-04 21:29:31 -05:00
  • 842e0391e7 Checking in to move back to aurora Chulwoo Jung 2025-12-04 20:13:44 -05:00
  • 17e3799bcc Necessary code for Harmonic KS added Chulwoo Jung 2025-12-03 19:38:45 -05:00
  • 985ab70f85 Checking in without adjusting Nk Chulwoo Jung 2025-12-03 14:46:34 -05:00
  • 1e85081986 Adding shift and debugging Chulwoo Jung 2025-12-03 00:16:51 -05:00
  • 7132a4fd28 Update feature/verify-checksum-host paboyle 2025-12-02 23:22:42 +00:00
  • e8057d6b4a Updated for verbose on host vs. device side csum paboyle 2025-12-02 23:15:32 +00:00
  • 3876fe5a29 Merge branch 'KrylovSchur' of github.com:chulwoo1/Grid into KS_shifted Chulwoo Jung 2025-12-02 17:46:40 -05:00
  • 973584e039 Update on aurora paboyle 2025-12-02 22:24:54 +00:00
  • ea46c2dc3c config command Peter Boyle 2025-12-02 16:01:37 -05:00
  • 50bcd76fc1 Changes to help with error logging on aurora -- triage MPI / Slingshot vs. host-device / SYCL on checksum error Peter Boyle 2025-12-02 15:51:29 -05:00
  • 6692425aa2 Checking in before pulling Chulwoo Jung 2025-11-26 17:17:22 -05:00
  • d5ac4fc67f Starting to modified KS Chulwoo Jung 2025-11-26 22:13:27 +00:00
  • 3538faf449 Starting Harmonic (shift and inverse) Chulwoo Jung 2025-11-24 17:05:35 -05:00
  • 4a0aaf0786 Fix issue with Aurora compilers paboyle 2025-11-21 21:40:28 +00:00
  • 9c3835524c Fix compile warn paboyle 2025-11-21 21:36:38 +00:00
  • 549351bb8a Stag verbose clean up paboyle 2025-11-20 18:22:57 +00:00
  • b650b89682 Define Sp4 ProjectOnGeneralGroup for generic vtype RChHill 2025-11-19 13:26:52 +00:00
  • 74e6b19f83 Looks like the reuse of xfers in staggered has bugs or corner cases depending on volume Peter Boyle 2025-11-17 22:29:06 -05:00
  • 2e684028de Improvements Peter Boyle 2025-11-14 18:12:27 -05:00
  • c6e88d9a11 T-direction terms done feature/S2xR Peter Boyle 2025-11-11 08:36:57 -05:00
  • 0b457b9d52 fixed ritz estimate bug Patrick Oare 2025-11-07 18:56:08 +00:00
  • fe0ab5f1a9 Merge branch 'develop' of github.com:poare/Grid into develop Chulwoo Jung 2025-11-07 15:50:22 +00:00
  • caa66418bd Checking in before pulling Chulwoo Jung 2025-11-06 22:44:05 +00:00
  • d5c0d54f89 Gauge staples for temporal direction added (ico-T staples and T-ico staples). Passes gauge covariance test, requiring the link x its staples = 1 on a random gauge transform. Peter Boyle 2025-11-06 13:54:39 -05:00
  • c54d87a472 Aurora compile fix for new compiler paboyle 2025-11-06 18:17:33 +00:00
  • 4304245c1b Merge branch 'develop' into bugfix/rocm7-rocblas-type-refactor Allen McKnight 2025-11-04 08:50:11 -06:00
  • 786496f22e Checking in before pulling KrylovSchur Chulwoo Jung 2025-11-03 21:18:56 +00:00
  • 68af1bba67 commented some slow code out Patrick R Oare 2025-10-31 11:47:29 -04:00
  • bf2a715ef7 bug in wilson eigenvectors: ritz estimates not equalling deviation from being an evec Patrick Oare 2025-10-31 15:31:46 +00:00
  • 6e40e22004 aarch64 libunwind compatibility fix hotfix/unwind-aarch64 portelli 2025-10-30 16:45:43 +01:00
  • d3ca16c76d Updated Peter Boyle 2025-10-27 21:09:02 -04:00