
| Author | Revisions | Lines of Code | Added Lines of Code | Lines of Code per Change |
|---|---|---|---|---|
| bjoo | 103 (66.5%) | 18228 (97.6%) | 24342 (94.0%) | 176.97 |
| edwards | 52 (33.5%) | 443 (2.4%) | 1554 (6.0%) | 8.52 |
| Date | Author | File/Message |
|---|---|---|
| 7/17/07 12:56 PM | bjoo |
Made some C++ warnings go away
(3 Files changed,
26 Lines changed)
include/scalarsite_generic/generic_spin_recon_inlines.h 1.3
(+17
-17)
include/scalarsite_generic/generic_spin_proj_inlines.h 1.3
(+8
-8)
include/scalarsite_generic/qdp_generic_fused_spin_proj_evaluates.h 1.5
(+1
-1)
|
| 6/10/07 10:32 AM | edwards |
Reorganized BinaryReader/Writer and TextReader. Now, these classes are
abstract classes (just like XMLWriter) for BinaryBufferReader/Writer and BinaryFileReader/Writer . Also, removed the old QDP_BEGIN/END_NAMESPACE macro and now simply use "namespace QDP". (36 Files changed, 98 Lines changed) include/scalarsite_generic/generic_blas_local_sumsq.h 1.2
(+3
-3)
include/scalarsite_generic/qdp_scalarsite_generic_blas.h 1.23
(+3
-3)
include/scalarsite_generic/generic_blas_vaxpby3_g5.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_vaxmby3_norm.h 1.2
(+3
-3)
include/scalarsite_generic/qdp_generic_fused_spin_proj_evaluates.h 1.4
(+2
-2)
include/scalarsite_generic/generic_blas_vaxpby3.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_local_vcdot.h 1.3
(+3
-3)
include/scalarsite_generic/generic_spin_recon_inlines.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_vadd3_g5.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_vaypx3_g5.h 1.2
(+3
-3)
include/scalarsite_generic/qdp_scalarsite_generic_cblas.h 1.6
(+2
-2)
include/scalarsite_generic/generic_blas_vaxpy3_norm.h 1.2
(+3
-3)
include/scalarsite_generic/generic_spin_proj_inlines.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_vaxmy3.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_vadd.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_vcscal.h 1.2
(+3
-3)
include/scalarsite_generic/qdp_scalarsite_generic_linalg.h 1.8
(+3
-3)
include/scalarsite_generic/qdp_generic_spin_project_evaluates.h 1.4
(+2
-2)
include/scalarsite_generic/qdp_scalarsite_generic_blas_g5.h 1.7
(+3
-3)
include/scalarsite_generic/generic_blas_vsub.h 1.2
(+3
-3)
include/scalarsite_generic/generic_spin_proj.h 1.5
(+2
-2)
include/scalarsite_generic/generic_blas_vscal.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_vcaxmby3.h 1.3
(+3
-3)
include/scalarsite_generic/qdp_generic_fused_spin_recon_evaluates.h 1.4
(+2
-2)
include/scalarsite_generic/generic_blas_vscal_g5.h 1.2
(+3
-3)
include/scalarsite_generic/generic_fused_spin_recon.h 1.2
(+2
-2)
include/scalarsite_generic/generic_blas_vcaxpy3.h 1.2
(+3
-3)
include/scalarsite_generic/generic_spin_recon.h 1.4
(+2
-2)
include/scalarsite_generic/generic_blas_local_vcdot_real.h 1.3
(+3
-3)
include/scalarsite_generic/generic_blas_g5.h 1.5
(+2
-2)
include/scalarsite_generic/generic_blas_vcaxpby3.h 1.3
(+2
-2)
include/scalarsite_generic/generic_blas_vaxpy3.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_vaxmby3.h 1.2
(+3
-3)
include/scalarsite_generic/generic_fused_spin_proj.h 1.3
(+2
-2)
include/scalarsite_generic/generic_blas_vcaxmy3.h 1.2
(+3
-3)
include/scalarsite_generic/generic_blas_vaxpy3_g5.h 1.3
(+3
-3)
|
| 2/23/07 8:00 PM | bjoo |
Generics now work on lexico layout
(4 Files changed,
737 Lines changed)
include/scalarsite_generic/qdp_scalarsite_generic_blas.h 1.22
(+5
-5)
include/scalarsite_generic/qdp_generic_fused_spin_recon_evaluates.h 1.3
(+471
-223)
include/scalarsite_generic/qdp_generic_fused_spin_proj_evaluates.h 1.3
(+232
-102)
include/scalarsite_generic/qdp_scalarsite_generic_linalg.h 1.7
(+29
-11)
|
| 2/22/07 10:58 AM | bjoo |
OK make check now works too. Also tests seem to pass in cb2 and lexico mode for generics and sse. But I dont trust it so I need to do the chroma build. Still commit this
(1 Files changed,
67 Lines changed)
include/scalarsite_generic/qdp_scalarsite_generic_blas.h 1.21
(+67
-6)
|
| 2/21/07 10:30 PM | bjoo |
Added changes to make the scalar normal and scalar sse targets compile
(4 Files changed,
17 Lines changed)
include/scalarsite_generic/qdp_scalarsite_generic_blas.h 1.20
(+10
-10)
include/scalarsite_generic/qdp_scalarsite_generic_cblas.h 1.5
(+2
-2)
include/scalarsite_generic/qdp_scalarsite_generic_blas_g5.h 1.6
(+4
-4)
include/scalarsite_generic/qdp_generic_spin_project_evaluates.h 1.3
(+1
-0)
|
| 2/21/07 5:17 PM | bjoo |
First stage of removing ordered subset. Code is UNSTABLE
(7 Files changed,
2405 Lines changed)
include/scalarsite_generic/qdp_scalarsite_generic_cblas.h 1.4
(+561
-175)
include/scalarsite_generic/qdp_generic_fused_spin_recon_evaluates.h 1.2
(+77
-58)
include/scalarsite_generic/qdp_scalarsite_generic_linalg.h 1.6
(+7
-21)
include/scalarsite_generic/qdp_scalarsite_generic_blas.h 1.19
(+612
-299)
include/scalarsite_generic/qdp_generic_spin_project_evaluates.h 1.2
(+445
-136)
include/scalarsite_generic/qdp_scalarsite_generic_blas_g5.h 1.5
(+666
-245)
include/scalarsite_generic/qdp_generic_fused_spin_proj_evaluates.h 1.2
(+37
-26)
|
| 2/9/07 3:35 PM | bjoo |
SSE SPin Projectors. Dont seem to win me much... More work needed. But at least the hooks are there.
(2 Files changed,
16 Lines changed)
include/scalarsite_generic/generic_spin_proj.h 1.4
(+8
-8)
include/scalarsite_generic/generic_spin_recon.h 1.3
(+8
-8)
|
| 2/7/07 3:45 PM | bjoo |
Added SSE Stuff. Moved proj names around for non_sse
(9 Files changed,
1571 Lines changed)
include/scalarsite_generic/generic_spin_recon.h 1.2
(+42
-0)
include/scalarsite_generic/generic_spin_aggregate.h 1.2
(+3
-3)
include/scalarsite_generic/qdp_generic_fused_spin_recon_evaluates.h 1.1 added 597
include/scalarsite_generic/qdp_generic_fused_spin_recon.h 1.2 removed
include/scalarsite_generic/qdp_scalarsite_spin_project.h 1.3 removed
include/scalarsite_generic/generic_spin_proj.h 1.3
(+45
-2)
include/scalarsite_generic/qdp_generic_spin_project_evaluates.h 1.1 added 558
include/scalarsite_generic/qdp_generic_fused_spin_proj_evaluates.h 1.1 added 326
include/scalarsite_generic/qdp_generic_fused_spin_proj.h 1.3 removed
|
| 2/6/07 10:01 AM | bjoo |
Added more spin ops and hooks. Next step to do the projections in SSE
(14 Files changed,
3575 Lines changed)
include/scalarsite_generic/qdp_scalarsite_spin_project.h 1.2
(+54
-1136)
include/scalarsite_generic/generic_spin_proj_inlines.h 1.1 added 500
include/scalarsite_generic/qdp_generic_fused_spin_recon.h 1.1 added
include/scalarsite_generic/generic_adj_mat_vec.h 1.2
(+4
-0)
include/scalarsite_generic/generic_fused_spin_proj.h 1.2
(+863
-693)
include/scalarsite_generic/generic_spin_aggregate.h 1.1 added 22
include/scalarsite_generic/qdp_generic_fused_spin_proj.h 1.2
(+82
-1441)
include/scalarsite_generic/generic_spin_recon_inlines.h 1.1 added 1091
include/scalarsite_generic/generic_spin_recon.h 1.1 added 127
include/scalarsite_generic/qdp_scalarsite_generic_linalg.h 1.5
(+2
-2)
include/scalarsite_generic/generic_spin_proj.h 1.2
(+37
-249)
include/scalarsite_generic/generic_fused_spin_recon.h 1.1 added 783
include/scalarsite_generic/generic_mat_vec.h 1.3
(+5
-1)
include/scalarsite_generic/generic_mv_switchbox.h 1.2
(+5
-0)
|
| 1/30/07 7:32 PM | bjoo |
Added fused spin proj/recon and su3 hsu3 multiplies with evaluate. Dslash now runs about 700 Mflops on my laptop
(4 Files changed,
2289 Lines changed)
include/scalarsite_generic/generic_mv_switchbox.h 1.1 added 12
include/scalarsite_generic/generic_fused_spin_proj.h 1.1 added 702
include/scalarsite_generic/generic_mat_vec.h 1.2
(+134
-4)
include/scalarsite_generic/qdp_generic_fused_spin_proj.h 1.1 added
|
| 1/29/07 5:22 PM | bjoo |
Site by site spin projection unrolling
(1 Files changed,
675 Lines changed)
include/scalarsite_generic/generic_spin_proj.h 1.1 added 675
|
| 1/26/07 2:32 PM | bjoo |
Added spin projections over ordered subsets as C generics
(1 Files changed,
1136 Lines changed)
include/scalarsite_generic/qdp_scalarsite_spin_project.h 1.1 added
|
| 6/22/06 4:17 PM | bjoo |
Touched up some issues to do with precision. I disabled for example the SSE local sumsq because it accumulated in SINGLE precision which is lousy - we really need DP there. Blas tests are now much better on the laptop. I have lost speed because of this change -- essentially the SSE sum is not now like the generic one
(1 Files changed,
14 Lines changed)
include/scalarsite_generic/qdp_scalarsite_generic_blas.h 1.18
(+14
-14)
|
| 6/13/06 1:47 PM | bjoo |
Removed unused variable to quieten compiler
(1 Files changed,
2 Lines changed)
include/scalarsite_generic/generic_blas_g5.h 1.4
(+2
-2)
|
| 11/3/05 5:17 PM | bjoo |
Generic BLAS routines for twisted mass and hooks added
(2 Files changed,
1201 Lines changed)
include/scalarsite_generic/generic_blas_g5.h 1.3
(+736
-0)
include/scalarsite_generic/qdp_scalarsite_generic_blas_g5.h 1.4
(+465
-1)
|
| 5/26/05 9:46 AM | bjoo |
Fixed 5D sum
(1 Files changed,
21 Lines changed)
include/scalarsite_generic/qdp_scalarsite_generic_blas.h 1.17
(+21
-21)
|
| 5/25/05 11:42 PM | edwards |
Fixes.
(1 Files changed,
233 Lines changed)
include/scalarsite_generic/qdp_scalarsite_generic_blas.h 1.16
(+233
-110)
|
| 5/25/05 12:21 AM | edwards |
Added norm2,innerProduct,innerProductReal of multi1d.
(1 Files changed,
88 Lines changed)
include/scalarsite_generic/qdp_scalarsite_generic_blas.h 1.15
(+88
-1)
|
| 5/19/05 7:22 AM | bjoo |
Added another gamma5 specialisation
(2 Files changed,
269 Lines changed)
include/scalarsite_generic/qdp_scalarsite_generic_blas_g5.h 1.3
(+70
-1)
include/scalarsite_generic/generic_blas_g5.h 1.2
(+199
-0)
|
| 5/18/05 9:42 AM | bjoo |
Added some more gamma5 ops to generics to make the CF operator faster
(2 Files changed,
689 Lines changed)
include/scalarsite_generic/generic_blas_g5.h 1.1 added 506
include/scalarsite_generic/qdp_scalarsite_generic_blas_g5.h 1.2
(+183
-1)
|