portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2026-07-17 15:43:27 +01:00
Code Releases Activity
2,520 Commits 95 Branches 14 Tags
b9bbe5d188ca785c4fee6f8d3a3f7370b6db7aba
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
paboyle b9bbe5d188 L1p config bg/q 2017-04-22 11:33:09 +01:00
paboyle 3844bcf800 If no f16c instructions supported must use software half precision conversion. 
This will also become useful on BG/Q, so will move out from SSE4 into a general area.
Lifted the Eigen half precision from web. Looks sensible, but not extensively regressed
against the intrinsics implementation yet.
 2017-04-20 15:30:52 +01:00
paboyle e1a2319d01 Simple compressor moved out of cshift into stencil 2017-04-20 13:18:15 +01:00
paboyle 180c732b4c Move compressors out of Cshift. 
Slice iterators would help
 2017-04-20 13:17:55 +01:00
paboyle 957a706d0b Useful script 2017-04-20 13:17:44 +01:00
paboyle d2312e9874 Drop compressor entirely from Cshift to only Stencil. 2017-04-20 13:16:55 +01:00
paboyle fc4ab9ccd5 Working half precision comms 2017-04-20 11:20:26 +01:00
paboyle 4a340aa5ca Massive compressor rework to support reduced precision comms 2017-04-20 09:28:27 +01:00
paboyle 3b7de792d5 Type comparison in the traits work 2017-04-18 13:28:04 +01:00
paboyle 557c3fa109 Pretty change 2017-04-18 13:27:38 +01:00
paboyle ec18e9f7f6 Merge branch 'develop' into feature/half-prec-comms 2017-04-18 11:39:39 +01:00
paboyle a839d5bc55 Updated todo list 2017-04-18 11:22:17 +01:00
paboyle de41b84c5c Merge branch 'feature/normHP' into develop 2017-04-18 10:57:21 +01:00
paboyle 8e161152e4 MultiRHS solver improvements with slice operations moved into lattice and sped up. 
Block solver requires a lot of performance work.
 2017-04-18 10:51:55 +01:00
paboyle 3141ebac10 MultiRHS working, starting to optimise. Block doesn't and I thought it already was; puzzled. 2017-04-17 10:50:19 +01:00
paboyle 7ede696126 Non compile of tests fixed 2017-04-16 23:40:00 +01:00
paboyle bf516c3b81 higher precision reduction variables in norm and inner product 2017-04-15 12:27:28 +01:00
paboyle 441a52ee5d First cut at higher precision reduction 2017-04-15 10:57:21 +01:00
paboyle a8db024c92 Cleaning up the dense matrix and lanczos sector 2017-04-15 08:54:11 +01:00
paboyle a9c22d5f43 Verbose removal 2017-04-14 14:38:49 +01:00
paboyle 3ca41458a3 Fix to no USE_FP16 case 2017-04-14 14:20:54 +01:00
paboyle 9e2d29c644 USE_FP16 macro 2017-04-14 14:17:14 +01:00
Peter Boyle 951be75292 Half precision conversion working on AVX512 now too 2017-04-13 17:35:11 +01:00
Peter Boyle b9113ed310 Patches for knl 2017-04-13 12:02:12 -04:00
paboyle 42fb49d3fd Merge branch 'develop' of https://github.com/paboyle/Grid into develop 2017-04-13 14:12:47 +01:00
paboyle 2a54c9aaab Merge branch 'feature/block-cg' into develop 2017-04-13 14:12:24 +01:00
paboyle 0957378679 Fixing conditional ugly way 2017-04-13 13:47:56 +01:00
paboyle 2ed6c76fc5 Getting multiline if then fi working 2017-04-13 13:43:13 +01:00
paboyle d3b9a7fa14 F16c apparently requires AVX, even if the 128 bit are used. 
Seems odd.
 2017-04-13 13:19:11 +01:00
paboyle 75ea306ce9 Another try at travis 2017-04-13 13:05:32 +01:00
paboyle 4226c633c4 Default to FP16 off again 2017-04-13 12:51:39 +01:00
paboyle 5a4eafbf7e .travis 2017-04-13 12:50:43 +01:00
paboyle eb8e26018b Travis update for macos 2017-04-13 12:35:11 +01:00
paboyle db5ea001a3 Update to use Xcode 8.3 since -mfp16 causes SIGILL 2017-04-13 12:22:40 +01:00
paboyle 2846f079e5 Predicate tests on fp16 being enabled 2017-04-13 12:08:05 +01:00
paboyle 1d502e4ed6 FP16 optional compile time 2017-04-13 11:55:24 +01:00
paboyle 73cdf0fffe Drop f16c from SSE because of a macos compile error on travis 2017-04-13 11:23:41 +01:00
paboyle 1c25773319 Trap illegal instructions 2017-04-13 10:51:40 +01:00
paboyle c38400b26f Trap signals 2017-04-13 10:35:20 +01:00
paboyle 9c3065b860 Debug flags off again 2017-04-13 10:01:32 +01:00
paboyle 94eb829d08 Align cast fixed for __mm128i gcc complained 2017-04-13 08:40:44 +01:00
paboyle 68392ddb5b Exchange in generic 
Precision change in AVX, SSE, AVX512, Generic. QPX still to do.
 2017-04-13 08:38:12 +01:00
paboyle cb6b81ae82 Half precision conversion 2017-04-12 19:32:37 +01:00
paboyle b12dc89d26 Commenting and clean up 2017-04-10 20:38:20 +09:00
paboyle d80d802f9d MultiRHS solver test 2017-04-10 00:12:12 +09:00
paboyle 3d99b09dba Start of blockCG 2017-04-09 23:42:10 +09:00
paboyle db5f6d3ae3 Verbose fix 2017-04-09 23:41:30 +09:00
paboyle 683550f116 Const args improvement 2017-04-09 23:41:04 +09:00
paboyle 55d0329624 Merge branch 'develop' of https://github.com/paboyle/Grid into develop 2017-04-07 11:08:14 +09:00
paboyle 86aaa35294 Christoph needs SchurDiagTwoKappa which is mobius specific. 2017-04-07 11:07:40 +09:00
paboyle 5592f7b8c1 Creation mode better implementation 2017-04-05 02:35:34 +09:00
paboyle 35da4ece0b UID fix 2017-04-05 02:18:15 +09:00
paboyle 061b15b9e9 Merge branch 'feature/sitmo-skipahead' into develop 2017-04-05 01:24:49 +09:00
paboyle 561426f6eb Clean up 2017-04-02 23:13:48 +09:00
paboyle 83f6fab8fa Big/Small crush test, and fast SITMO rng init, faster but not ideal 
MT and Ranlux init.
 2017-04-02 12:10:51 +09:00
paboyle 0fade84ab2 No random device 2017-04-02 00:29:40 +09:00
paboyle 9dc7ca4c3b Sitmo fast init 2017-04-02 00:28:22 +09:00
paboyle 935d82f5b1 sanity checks 2017-04-02 00:27:28 +09:00
paboyle 9cbcdd65d7 No random device seed 2017-04-02 00:26:57 +09:00
paboyle f18f5ed926 Drop random device 2017-04-02 00:26:26 +09:00
paboyle d1d63a4f2d sitmo default 2017-04-02 00:26:05 +09:00
paboyle 7e5faa0f34 Multiple RNGs 2017-04-02 00:25:44 +09:00
paboyle 6af459cae4 Christoph's coefficients. 2017-03-31 17:07:43 +09:00
paboyle 1c4bc7ed38 Debugged staggered conventions 2017-03-31 14:41:48 +09:00
paboyle 93ea5d9468 Pretty code 2017-03-30 15:00:03 +09:00
paboyle 1ec5d32369 Chulwoo's test to zmobius helped me shake out 2017-03-30 13:45:13 +09:00
paboyle 9fd23faadf Pretty layout 2017-03-30 13:44:45 +09:00
paboyle 10e4fa0dc8 Template instantiation improvements 2017-03-30 13:44:25 +09:00
paboyle c4aca1dde4 Conjugate coefficients on adjoint 2017-03-30 13:44:05 +09:00
paboyle b9e8ea3aaa conjugate coefficient on the dagger 2017-03-30 13:43:13 +09:00
paboyle 077aa728b9 Fix the ZMobius (I think) 2017-03-30 13:42:09 +09:00
paboyle a8d83d886e Macro controls 2017-03-30 13:31:34 +09:00
paboyle 7fd46eeec4 Trailing whitespace removal 2017-03-30 13:31:10 +09:00
paboyle e0c4eeb3ec Compiles again 2017-03-30 13:30:45 +09:00
paboyle cb9a297a0a Chulwoo's Zmobius test 2017-03-30 13:30:25 +09:00
paboyle 2b115929dc Small AVX512 asm ifdef patch 2017-03-29 18:51:23 +09:00
paboyle 5c6571dab1 Merge branch 'feature/bgq-asm' into develop 2017-03-29 18:48:55 +09:00
paboyle 417ec56cca Release candidate 2017-03-29 05:45:33 -04:00
paboyle 756bc25008 Verbose header print by default 2017-03-29 04:44:17 -04:00
paboyle 35695ba57a Bug fix in MPI3 2017-03-29 04:43:55 -04:00
paboyle 81ead48850 Log any errors to a file 2017-03-29 04:39:52 -04:00
paboyle d805867e02 Better init 2017-03-28 13:25:05 -04:00
paboyle e55a751e23 Merge branch 'feature/bgq-asm' of https://github.com/paboyle/Grid into feature/bgq-asm 2017-03-28 12:20:12 -04:00
paboyle 358eb75995 Shorten loop 2017-03-28 12:20:02 -04:00
paboyle 98f9318279 Build on AVX2 and MPI passing with clang++ 2017-03-28 23:16:04 +09:00
paboyle 4b17e8eba8 Merge branch 'develop' into feature/bgq-asm 
Conflicts:
	lib/qcd/action/fermion/Fermion.h
	lib/qcd/action/fermion/WilsonFermion.cc
	lib/util/Init.cc
	tests/Test_cayley_even_odd_vec.cc
 2017-03-28 04:49:30 -04:00
paboyle 75112a632a IO improvements to fail on IO error 2017-03-28 02:28:04 -04:00
paboyle 18bde08d1b Merge branch 'feature/staggering' into develop 2017-03-28 15:25:55 +09:00
paboyle d45cd7e677 Adding a simple read of NERSC test 2017-03-26 09:24:26 -04:00
paboyle 4e96679797 Added a bnl log 2017-03-25 09:25:46 -04:00
paboyle fc93f0b2ec Save some code for static huge tlb's. It is ifdef'ed out but an interesting root only experiment. 
No gain from it.
 2017-03-21 22:30:29 -04:00
paboyle 8c8473998d Average over whole cluster the comm time. 2017-03-21 22:29:51 -04:00
paboyle e7c36771ed ZMobius prep for asm 2017-03-15 14:23:33 -04:00
paboyle 8dc57a1e25 Layout change 2017-03-13 11:11:46 +00:00
paboyle f57bd770b0 Merge branch 'bugfix/dminus' into feature/bgq-asm 2017-03-13 11:11:03 +00:00
paboyle 4ed10a3d06 Merge branch 'develop' into feature/bgq-asm 2017-03-13 11:10:10 +00:00
paboyle b64e004555 MPI run fail on macos 2017-03-13 01:59:01 +00:00
paboyle 447c5e6cd7 Z mobius hermiticity correction 2017-03-13 01:30:43 +00:00
paboyle 8b99d80d8c Merge branch 'bgq-asm-shmemfixes' into feature/bgq-asm 2017-03-12 23:30:09 +00:00
paboyle 3901b17ade timeings from BNL 2017-02-28 17:06:45 -05:00