jpekkila
|
263a1d23a3
|
Added a function for loading ScalarArrays to the GPU
|
2019-09-05 16:35:08 +03:00 |
|
jpekkila
|
9e57aba9b7
|
New feature: ScalarArray. ScalarArrays are read-only 1D arrays containing max(mx, max(my, mz)) elements. ScalarArray is a new type of uniform and can be used for storing f.ex. forcing profiles. The DSL now also supports complex numbers and some basic arithmetic (exp, multiplication)
|
2019-09-02 21:26:57 +03:00 |
|
jpekkila
|
6ea02fa28e
|
DSL now 'feature complete' with respect to what I had in mind before the summer. Users can now create multiple kernels and the library functions are generated automatically for them. The generated library functions are of the form acDeviceKernel_<name> and acNodeKernel_<name>. More features are needed though. The next features to be added at some point are 1D and 2D device constant arrays in order to support profiles for f.ex. forcing.
|
2019-08-27 18:19:20 +03:00 |
|
jpekkila
|
20138263f4
|
The previous attempt (dsl_feature_completeness_2019-08-23) to enable arbitrary kernel functions was a failure: we get significant performance loss (25-100%) if step_number is not passed as a template parameter to the integration kernel. Apparently the CUDA compiler cannot perform some optimizations if there is a if/else construct in a performance-critical part which cannot be evaluated at compile time. This branch keeps step_number as a template parameter but takes rest of the user parameters as uniforms (dt is no longer passed as a function parameter but as an uniform with the DSL instead).
|
2019-08-27 17:36:33 +03:00 |
|
jpekkila
|
022e46f2e7
|
Merge branch 'master' into dsl_parameter_overhaul_2019-08-19
|
2019-08-23 13:13:57 +03:00 |
|
jpekkila
|
f6040f89dc
|
Added acPrintMeshInfo for printing all mesh parameters
|
2019-08-21 16:24:48 +03:00 |
|
jpekkila
|
39dcda4a04
|
Made warnings about unused functions go away (this is intended functionality and not all programs will use all types of device constants, thus unnecessary warning)
|
2019-08-21 14:28:46 +03:00 |
|
jpekkila
|
51cf1f1068
|
The C header is now generated from the DSL, stashing the changes just to be sure since I might overwrite something when updating the compilation scripts to work with this new scheme
|
2019-08-19 18:19:28 +03:00 |
|
jpekkila
|
d801ebdd41
|
Now parameters and vertexbuffers (fields) can be declared with the DSL only. TODO: translation from the DSL header to C
|
2019-08-19 17:35:03 +03:00 |
|
jpekkila
|
bcdd827a4f
|
Added a proper declarations for all user-specified uniform. Note: built-in uniforms are not correctly translated into CUDA
|
2019-08-19 17:05:56 +03:00 |
|
jpekkila
|
0208d55e4e
|
Moved STENCIL_ORDER and NGHOST out of user-defined parameter as these are actually internal defines used to configure the built-in functions. Additionally, renamed all explicitly declared uniforms from dsx -> AC_dsx in the DSL in preparation for having clear connection between DSL uniforms and the library parameter handles created by the user (AcRealParam etc)
|
2019-08-19 16:40:47 +03:00 |
|
jpekkila
|
787363226b
|
Added functions for loading int, int3, scalar and vector constants to the device layer (acDeviceLoad...Constant)
|
2019-08-19 15:28:16 +03:00 |
|
jpekkila
|
41805dcb68
|
Added some error checking for the case where user supplies an incomplete meshinfo to acDeviceLoadMeshInfo
|
2019-08-19 15:17:51 +03:00 |
|
jpekkila
|
598799d7c3
|
Added a new function to the device interface: acDeviceLoadMeshInfo
|
2019-08-19 15:14:00 +03:00 |
|
jpekkila
|
e89897985e
|
Battled with math.h and cmath. We probably should move from C standard libraries to C++ ones internally (in places which are not visible via the interface)
|
2019-08-19 14:02:30 +03:00 |
|
jpekkila
|
6d4d53342e
|
Removed old comments
|
2019-08-15 11:14:52 +03:00 |
|
jpekkila
|
36fea70560
|
Moved basic built-in functions for vector operations to math_utils.h from integration.cuh so that they are shared with the CPU and GPU
|
2019-08-15 11:04:22 +03:00 |
|
jpekkila
|
d5b2e5bb42
|
Added placeholders for new built-in variables in the DSL. Also overloads to DCONST_INT etc. Naming still pending and old DCONST_REAL etc calls still work.
|
2019-08-12 14:05:35 +03:00 |
|
jpekkila
|
b8c4d07de2
|
Removed unnecessary comments
|
2019-08-12 13:31:24 +03:00 |
|
jpekkila
|
e027f7e548
|
Removed grid_n in astaroth.cu and replaced it with the new acNodeQueryDeviceConfiguration call
|
2019-08-12 13:25:47 +03:00 |
|
jpekkila
|
bba9ec7c3b
|
Implemented acNodeQueryDeviceConfiguration
|
2019-08-12 11:40:38 +03:00 |
|
jpekkila
|
b5daf22c26
|
Added interface function acSynchronizeMesh
|
2019-08-12 10:25:05 +03:00 |
|
jpekkila
|
8bbb2cd5df
|
Now prints device info before trying to run the dummy kernel
|
2019-08-12 09:46:37 +03:00 |
|
jpekkila
|
b53cabbc44
|
Made the DSL syntax less confusing: Input and output arrays are now ScalarField and VectorFields instead of scalars and vectors. C++ initializers are now also possible, removing the need to declare Fields as int or int3 which was very confusing, like "what, you assing an int value to a real, what the &^%@?"
|
2019-08-08 21:07:36 +03:00 |
|
jpekkila
|
5397495496
|
Added acLoadWithOffset
|
2019-08-08 20:43:01 +03:00 |
|
jpekkila
|
e79e1207f2
|
Added a function for checking whether CUDA-capable devices are available
|
2019-08-08 20:35:02 +03:00 |
|
jpekkila
|
8a9099d75e
|
Added missing functions to fix backwards compatibility with the version interfaced with Pencil Code
|
2019-08-08 19:49:57 +03:00 |
|
jpekkila
|
322cdce52c
|
Added some new comments + some helpful old comments from a time before the interface revision
|
2019-08-07 20:05:54 +03:00 |
|
jpekkila
|
1525e0603f
|
Added some preliminary pragma omps and verified that acIntegrate works as it should.
|
2019-08-07 19:08:52 +03:00 |
|
jpekkila
|
c2bd5ae3e6
|
Simplified the optimized multi-GPU integration function
|
2019-08-07 18:17:03 +03:00 |
|
jpekkila
|
a930864f42
|
Merge branch 'master' into node_device_interface_revision_07-23
|
2019-08-07 07:43:28 +03:00 |
|
jpekkila
|
cf6b75f82a
|
Merged in cmakelist_rewrite_and_C_API_conformity_07-26 (pull request #1)
|
2019-08-07 06:53:17 +03:00 |
|
jpekkila
|
6b53eb31ef
|
Errors with forcing now down from 3 to 1 after switching from fast & inaccurate trig functions to more accurate ones
|
2019-08-06 19:29:40 +03:00 |
|
jpekkila
|
daee456660
|
Merge branch 'cmakelist_rewrite_and_C_API_conformity_07-26' into node_device_interface_revision_07-23
|
2019-08-06 17:57:30 +03:00 |
|
jpekkila
|
abf4815174
|
Merge branch 'master' into cmakelist_rewrite_and_C_API_conformity_07-26
|
2019-08-06 17:53:53 +03:00 |
|
jpekkila
|
5870081645
|
Split kernels.cuh into bounconds.cuh, integration.cuh and reductions.cuh
|
2019-08-06 17:50:41 +03:00 |
|
jpekkila
|
405fa4d6d6
|
Moved old kernels to kernels/deprecated
|
2019-08-06 17:46:52 +03:00 |
|
jpekkila
|
3726847683
|
Made globalGridN and d_multigpu_offsets built-in parameters. Note the renaming from globalGrid.n to globalGridN.
|
2019-08-06 16:39:15 +03:00 |
|
jpekkila
|
1dd9975528
|
Formatting
|
2019-08-06 15:44:51 +03:00 |
|
jpekkila
|
b2632c87b4
|
Merge branch 'cmakelist_rewrite_and_C_API_conformity_07-26' into node_device_interface_revision_07-23
|
2019-08-06 15:18:33 +03:00 |
|
jpekkila
|
280804a438
|
Merge branch 'master' into cmakelist_rewrite_and_C_API_conformity_07-26
|
2019-08-06 15:14:33 +03:00 |
|
jpekkila
|
5f4246fb42
|
Standalone now uses O2 optimization level instead of O3. Also removed -march=native since this causes issues if the program is compiled on a different architecture than it is run on. Since we do not do heavy arithmetic on the host side and the host code is not performance-critical part of the code, -march-native is not very useful anyways
|
2019-08-06 14:46:13 +03:00 |
|
jpekkila
|
b73c2675e8
|
Added the optimized implementation of acNodeIntegrate where boundconds are done before integration instead of after
|
2019-08-05 20:10:13 +03:00 |
|
jpekkila
|
8df49370c8
|
Cleanup
|
2019-08-05 19:08:05 +03:00 |
|
jpekkila
|
fa6e1116cb
|
The interface revision now actually works. The issue was incorrect order of src and dst indices when storing the mesh.
|
2019-08-05 17:26:05 +03:00 |
|
jpekkila
|
5232d987c1
|
Added acStoreWithOffset to the revised interface
|
2019-08-05 16:18:22 +03:00 |
|
jpekkila
|
f3de2fa03c
|
Made globalVertexIdx available during preprocessing. NOTE: potentially dangerous. globalVertexIdx should never be used for reading data from the vertex buffers.
|
2019-08-05 15:03:02 +03:00 |
|
jpekkila
|
6dfd03664d
|
Still does not work. I'm starting to think that instead of this one huge revision, we should modify the existing interface step-by-step.
|
2019-08-02 15:31:24 +03:00 |
|
jpekkila
|
5f2378e91b
|
Now compiles (does not work though)
|
2019-08-02 15:15:18 +03:00 |
|
jpekkila
|
567ad61465
|
Multinode MPI implementation should be done later in its own branch. The focus of this branch is to revise the node and device layers. Commented out references to the Grid layer.
|
2019-08-02 13:54:54 +03:00 |
|