Aurélien Delval
eb71a752f5
Fixed naive GPU kernels and ignored variable issue
2022-04-05 14:28:35 +02:00
Aurélien Delval
bc43113b6f
Merge branch 'gpu' into master
2022-04-05 11:46:12 +02:00
94035929e4
Fixed cppcheck
2022-04-05 11:45:02 +02:00
Aurélien Delval
0e43d33a1d
Merge branch 'gpu' into master
2022-04-05 11:39:16 +02:00
6fb261d635
warnings
2022-04-05 11:15:42 +02:00
Aurélien Delval
98097e8fa7
Convert GPU implementations to C
...
TODO : Fix naive implementation which seems to be incorrect (probably an
issue with indexing)
2022-04-05 11:02:08 +02:00
511eba5843
Fixed dgemm bug
2022-04-05 09:56:13 +02:00
bcdbc49d5f
Cleaning
2022-04-04 23:53:58 +02:00
dd045452f6
Fixed documentation
2022-04-04 17:30:38 +02:00
1f9ea610d4
Moved C version of Jastrow into HPC
2022-04-04 16:56:33 +02:00
Aurélien Delval
84013a5f76
Cleanup before merging into QMCkl's GPU branch
2022-04-04 12:12:11 +02:00
Aurélien Delval
26bbd6f341
Start work on cuBLAS implementation
...
TODO Replace CPU BLAS calls by cuBLAS calls (will probably require to write a Fortran to the functions we're interested in, at least DGEMMs)
2022-04-01 09:19:56 +02:00
Aurélien Delval
9428eaa19e
Implement computation of tmp_c and dtmp_c in OpenACC
...
These 2 kernels seem to give good speedup compared to the CPU BLAS
versions. However, the current GPU implementation of factor_een_deriv seems to
be slightly slower (on the tested machine).
TODO:
- Try to improve factor_een_deriv GPU implem
- Try out a cuBLAS implementation of tmp_c and dtmp_c
2022-03-30 16:16:06 +02:00
Aurelien Delval
99306473a4
Start OpenACC implementation in Jastro, including compute_dtmp_c
2022-03-30 09:01:32 +02:00
Aurelien Delval
383c6ac78a
Add OFFLOAD_FLAGS, OFFLOAD_CFLAGS and OFFLOAD_FCFLAGS vars to configure
2022-03-28 07:58:01 +02:00
Aurelien Delval
bcc49ca312
Minor fixes to previous commit
...
TODO Start modifying dedicated function to implement offloading
Also, as of now, Fortran preprocessor flags should be passed manually,
we need to manage this in the configure.ac in the future. For now, when
using gfortran, you should pass FCFLAGS="-cpp -DWITH_OPENMP_OFFLOAD" to
enable offloading.
2022-03-25 13:03:35 +01:00
Aurelien Delval
5e3231e7e3
Add selection mechanism for offload mode in Jastrow
...
This system adds an additional field to the QMCkl context to store the
offload mode currently in use for each kernel (in this commit, this has
been implemented for Jastrow as an example). This will be useful to test
different offloading versions that can be easily toggled on/off at
compilation and at runtime.
2022-03-24 16:35:29 +01:00
Gianfranco Abrusci
3ce162a384
dtmp_c done
2022-03-17 22:27:10 +01:00
Gianfranco Abrusci
6b45157212
tmp_c done
2022-03-17 17:46:21 +01:00
Gianfranco Abrusci
b222ee3156
lkpm works
2022-03-14 11:21:31 +01:00
Gianfranco Abrusci
a4ba5deac4
compute_dim_cord_vect done
2022-03-09 11:15:15 +01:00
Gianfranco Abrusci
d13693a822
to be cleaned from print
2022-03-02 10:18:45 +01:00
Gianfranco Abrusci
4fac9f06c9
to be checked
2022-02-28 17:47:24 +01:00
Gianfranco Abrusci
3bd249176f
Merge branch 'jastrow_c' into qmckl_compute_een_rescaled_n
2022-02-22 14:55:55 +01:00
Gianfranco Abrusci
5151f1bd36
Merge branch 'master' into jastrow_c
2022-02-22 14:53:00 +01:00
Gianfranco Abrusci
2427d1b56e
working qmckl_compute_een_rescaled_n
2022-02-22 14:52:21 +01:00
Gianfranco Abrusci
bb2e8384e8
fix reorder of nex function
2022-02-16 18:13:57 +01:00
Gianfranco Abrusci
bf8cec7f3c
reordered index in ee_distance_rescaled that makes sense
2022-02-16 18:09:02 +01:00
e90e9a531c
Added HPC version of polynomials
2022-02-16 15:14:41 +01:00
Gianfranco Abrusci
05cfd10cc4
completed qmckl_compute_factor_en
2022-02-16 14:14:05 +01:00
685b7201fc
Accelerated AOs
2022-02-15 00:44:47 +01:00
Gianfranco Abrusci
85e0a6e8e0
Merge branch 'master' into jastrow_c
2022-02-14 12:30:02 +01:00
v1j4y
8ed7a8b672
Added dim to factor_een and factor_een_deriv_e.
2022-02-11 17:35:07 +01:00
v1j4y
e2a678cc5c
Cleaned tmp_c and dtmp_c.
2022-02-11 17:31:17 +01:00
v1j4y
2f05df5109
Fixed een_rescaled_n_deriv_e.
2022-02-11 17:30:15 +01:00
v1j4y
367d0ff108
Fixed een_rescaled_n.
2022-02-11 17:19:36 +01:00
v1j4y
cf005084f1
Fixed een_rescaled_e_deriv_d.
2022-02-11 17:06:17 +01:00
v1j4y
a7ec3585a7
reorder indices for een_rescaled_e.
2022-02-11 16:19:31 +01:00
v1j4y
2c7a1eb2c6
Fix factor_en_deriv_e.
2022-02-11 16:06:19 +01:00
v1j4y
f22e2b1d72
Working on factor_en.
2022-02-11 15:45:16 +01:00
v1j4y
3348781cc2
Fixed ee_distances_rescaled_deriv_e.
2022-02-11 15:37:55 +01:00
v1j4y
88e2f62d7f
Fixed ee_distance_rescaled index order.
2022-02-11 15:36:08 +01:00
v1j4y
da3c8c7cf9
Working on ee_distance_deriv_e.
2022-02-11 15:27:18 +01:00
v1j4y
fa535bdcd1
Added size to factor_ee.
2022-02-11 15:17:57 +01:00
v1j4y
757d81324a
Added size in setters.
2022-02-11 15:09:18 +01:00
v1j4y
04624171f0
Added size dimensions to aord, cord, and bord.
2022-02-11 14:45:20 +01:00
Gianfranco Abrusci
c3889340eb
Merge branch 'master' into jastrow_c
2022-02-09 17:45:37 +01:00
e9f79c144a
Merge branch 'master' of github.com:TREX-CoE/qmckl
2022-02-09 14:37:45 +01:00
484c0a7d5c
Documentation of Jastrow
2022-02-09 14:37:38 +01:00
Gianfranco Abrusci
2332007a7c
fixed qmckl_compute_factor_ee
2022-02-07 13:53:50 +01:00
