 Dhairya Malhotra
|
a016a3bc43
Update examples, SetupFMM, MemoryManager
|
há 10 anos atrás |
|
Dhairya Malhotra
|
d9ab22a021
Different kernels for each FMM interaction type
|
há 10 anos atrás |
|
Dhairya Malhotra
|
ae7120bf79
Fix error in cheb_div(), optimize FMM setup.
|
há 10 anos atrás |
|
Dhairya Malhotra
|
a690819165
Fix errors in EvalListGPU, SSE Kernel declarations
|
há 10 anos atrás |
|
Dhairya Malhotra
|
d550de6c0e
Merge branch 'develop' into feature/cuda
|
há 10 anos atrás |
|
Dhairya Malhotra
|
06f5575582
Cleanup MemoryManager, merge mem_utils and mem_mgr
|
há 10 anos atrás |
|
Dhairya Malhotra
|
c2ce2a66c9
Create feature/dbg-tools
|
há 10 anos atrás |
|
Dhairya Malhotra
|
0c263bdf85
Fix errors.
|
há 10 anos atrás |
|
Dhairya Malhotra
|
d6607e6236
Auto detect scale-invariance and symmetry
|
há 10 anos atrás |
|
Dhairya Malhotra
|
5b461dd3b6
Compiler support for default template arguments
|
há 10 anos atrás |
|
Dhairya Malhotra
|
8c2b816f95
Fix multiply defined symbols.
|
há 10 anos atrás |
|
Dhairya Malhotra
|
01430964b3
Fix Phi compilation errors; add m4 script to detect quadruple precision support.
|
há 10 anos atrás |
|
Dhairya Malhotra
|
deacf73ca2
- Update Stokes double-layer potential to symmetric part of Stokes-dipole.
|
há 10 anos atrás |
|
Dhairya Malhotra
|
15eeec9134
fix errors.
|
há 10 anos atrás |
|
Dhairya Malhotra
|
b8dbad698b
Quadruple precision support.
|
há 10 anos atrás |
|
Dhairya Malhotra
|
03de09b5df
Add single-precision SSE support for V-list
|
há 10 anos atrás |
|
Dhairya Malhotra
|
64e0edc334
load balancing, bug fixes.
|
há 11 anos atrás |
|
Dhairya Malhotra
|
60d0823440
Merge branch 'feature/mpi-sparse' into develop
|
há 11 anos atrás |
|
Dhairya Malhotra
|
5e3a02609c
clean up
|
há 11 anos atrás |
|
Dhairya Malhotra
|
a05dc803a5
Changes for Intel Phi native build.
|
há 11 anos atrás |
|
Dhairya Malhotra
|
075cfdda7d
Clean up.
|
há 11 anos atrás |
|
Chenhan D. Yu
|
1cc35372fb
Last commit of feature/cuda from Chenhan
|
há 11 anos atrás |
|
Dhairya Malhotra
|
28f272943b
Permutations using shared memory.
|
há 11 anos atrás |
|
Chenhan D. Yu
|
069f848388
Bug fixed, counter, tmp_a, tmp_b.
|
há 11 anos atrás |
|
Chenhan D. Yu
|
36c01fec95
Optimize kernels in_perm_2d_k and out_perm_2d_k.
|
há 11 anos atrás |
|
Chenhan D. Yu
|
5f94b322e3
Eventually, this is a bug free version!!
|
há 11 anos atrás |
|
Chenhan D. Yu
|
0c7134e0dd
This is bug-version. GPU address wrap-over.
|
há 11 anos atrás |
|
Dhairya Malhotra
|
1cce181fe9
allow MultipoleOrder()==0
|
há 11 anos atrás |
|
Chenhan D. Yu
|
43da9649d0
Feature CUDA completed, yet hasn't debugged yet.
|
há 11 anos atrás |
|
Chenhan D. Yu
|
ff3a4bfaf4
Create EvalList_cuda();
|
há 11 anos atrás |
