cwpearson/astaroth
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into 3d-decomposition-2020-01

Browse Source
This commit is contained in:
jpekkila
2020-01-16 13:21:59 +02:00
parent 1d315732e0 bb70c660bb
commit c76c2afd5e
101 changed files with 1515 additions and 2681 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
CMakeLists.txt
View File

@@ -25,8 +25,7 @@ option(BUILD_DEBUG "Builds the program with extensive error checkin
option(BUILD_STANDALONE "Builds the standalone Astaroth" ON)
option(BUILD_UTILS "Builds the utility library" ON)
option(BUILD_RT_VISUALIZATION "Builds the module for real-time visualization using SDL2" OFF)
option(BUILD_C_API_TEST "Builds a C program to test whether the API is conformant" OFF)
option(BUILD_MPI_TEST "Builds a C program to test whether MPI works" OFF)
option(BUILD_SAMPLES "Builds projects in samples subdirectory" OFF)
option(DOUBLE_PRECISION "Generates double precision code" OFF)
option(MULTIGPU_ENABLED "If enabled, uses all the available GPUs" ON)
option(MPI_ENABLED "Enables additional functions for MPI communciation" OFF)
@@ -51,7 +50,7 @@ set(DSL_HEADERS "${PROJECT_BINARY_DIR}/user_kernels.h"
"${PROJECT_BINARY_DIR}/user_defines.h")
add_custom_command (
COMMENT "Building ACC objects ${DSL_MODULE_DIR}"
COMMAND ${CMAKE_SOURCE_DIR}/scripts/compile_acc_module.sh ${DSL_MODULE_DIR}
COMMAND ${CMAKE_SOURCE_DIR}/acc/compile_acc_module.sh ${DSL_MODULE_DIR}
DEPENDS ${DSL_SOURCES}
OUTPUT ${DSL_HEADERS}
)
@@ -93,20 +92,16 @@ include_directories(include)
include_directories(${CMAKE_BINARY_DIR})
## Subdirectories
add_subdirectory(src/core) # The core library
add_subdirectory(src/core) # The core library
if (BUILD_UTILS)
add_subdirectory(src/utils) # The utility library
endif ()
if (BUILD_STANDALONE)
add_subdirectory(src/standalone)
endif ()
if (BUILD_C_API_TEST)
add_subdirectory(src/ctest)
endif ()
if (BUILD_MPI_TEST)
add_subdirectory(src/mpitest)
endif ()
if (BUILD_UTILS)
add_subdirectory(src/utils)
if (BUILD_SAMPLES)
add_subdirectory(samples)
endif ()

127
CONTRIBUTING.md Normal file
View File

@@ -0,0 +1,127 @@
# Contributing
Contributions to Astaroth are very welcome!
This document details how to create good contributions. There are two primary concerns:
1. The codebase should stay maintainable and commits should adhere to a consistent style.
2. New additions should not disrupt the work of others.
## Basic workflow
> "There is something that needs fixing"
1. Create your work. See [Programming](#markdown-header-programming) and [Committing](#markdown-header-committing) .
2. When done, check that autotests still pass by running `./ac_run -t`.
3. **[Recommended]:** Autoformat your code. See [Formatting](#markdown-header-formatting).
4. Create a pull request.
## Programming
* **Strive for code clarity over micro-optimizations.**
* Readability and simplicity should always be preferred over anything else outside of performance-critical parts.
* Give variables meaningful names and add comments to parts that are not immediately clear from context.
* **Avoid breaking existing functionality.**
* Do not modify existing interface functions in any way. Bugfixes are exceptions. If you need new functionality, create a new function.
* Do not rename or redefine global variables or constants.
## Committing
* Prefer multiple small commits over few large ones.
* Provide meaningful commit messages.
* If a feature consists of multiple commits, consider creating a new branch. See [Managing feature branches](#markdown-header-managing-feature-branches) and [About branches in general](#markdown-header-about-branches-in-general) for more details. When done, issue the pull request to the new branch.
## Formatting
If you have `clang-format`, you may run `scripts/fix_style.sh`. This script will recursively fix style of all the source files down from the current working directory. The script will ask for a confirmation before making any changes.
> **WARNING** The script will replace old source files with new formatted versions. Ensure that you have committed your changes before running `fix_style.sh` to be safe.
Basic rules:
- Use [K&R indentation style](https://en.wikipedia.org/wiki/Indentation_style#K&R_style) and 4 space tabs.
- Line width is 100 characters.
- Start function names after a linebreak in source files.
- [Be generous with `const` type qualifiers](https://isocpp.org/wiki/faq/const-correctness).
- When in doubt, see [Google C++ Style Guide](https://google.github.io/styleguide/cppguide.html).
## Header example:
```cpp
// Licence notice and doxygen description here
#pragma once
#include "avoid_including_headers_here.h"
/** Doxygen comments */
void globalFunction(void);
```
## Source example:
```cpp
#include "parent_header.h"
#include <standard_library_headers.h>
#include "other_headers.h"
#include "more_headers.h"
typedef struct {
int data;
} SomeStruct;
static inline int small_function(const SomeStruct& stuff) { return stuff.data; }
// Pass constant structs always by reference (&) and use const type qualifier.
// Modified structs are always passed as pointers (*), never as references.
// Constant parameters should be on the left-hand side, while non-consts go to the right.
static void
local_function(const SomeStruct& constant_struct, SomeStruct* modified_struct)
{
modified_struct->data = constant_struct.data;
}
void
globalFunction(void)
{
return;
}
```
## Managing feature branches
1. Ensure that you're on the latest version of master. `git checkout master && git pull`
2. Create a feature branch with `git checkout -b <feature_name_year-month-date>`, f.ex. `git checkout -b forcingtests_2019-01-01`
3. Do your commits in that branch until your new feature works
4. Merge master with your feature branch `git merge master`
5. Resolve the conflicts and test that the code compiles and still works by running `./ac_run -t`
6. If everything is OK, commit your final changes to the feature branch and merge it to master `git commit && git checkout master && git merge <your feature branch> && git push`
7. Unless you really have to keep your feature branch around for historical/other reasons, remove it from remote by calling `git push origin --delete <your feature branch>`
A flowchart is available at [doc/commitflowchart.png](https://bitbucket.org/jpekkila/astaroth/src/2d91df19dcb3/doc/commitflowchart.png?at=master).
## About branches in general
* Unused branches should not kept around after merging them into master in order to avoid cluttering the repository.
* `git branch -a --merged` shows a list of branches that have been merged to master and are likely not needed any more.
* `git push origin --delete <feature branch>` deletes a remote branch while `git branch -d <feature branch>` deletes a local branch
* If you think that you have messed up and lost work, run `git reflog` which lists the latests commits. All work that has been committed should be accessible with the hashes listed by this command with `git checkout <reflog hash>`.

675
LICENCE.md Normal file
View File

@@ -0,0 +1,675 @@
### GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc.
<https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies of this
license document, but changing it is not allowed.
### Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom
to share and change all versions of a program--to make sure it remains
free software for all its users. We, the Free Software Foundation, use
the GNU General Public License for most of our software; it applies
also to any other work released this way by its authors. You can apply
it to your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you
have certain responsibilities if you distribute copies of the
software, or if you modify it: responsibilities to respect the freedom
of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the
manufacturer can do so. This is fundamentally incompatible with the
aim of protecting users' freedom to change the software. The
systematic pattern of such abuse occurs in the area of products for
individuals to use, which is precisely where it is most unacceptable.
Therefore, we have designed this version of the GPL to prohibit the
practice for those products. If such problems arise substantially in
other domains, we stand ready to extend this provision to those
domains in future versions of the GPL, as needed to protect the
freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish
to avoid the special danger that patents applied to a free program
could make it effectively proprietary. To prevent this, the GPL
assures that patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
### TERMS AND CONDITIONS
#### 0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds
of works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of
an exact copy. The resulting work is called a "modified version" of
the earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user
through a computer network, with no transfer of a copy, is not
conveying.
An interactive user interface displays "Appropriate Legal Notices" to
the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
#### 1. Source Code.
The "source code" for a work means the preferred form of the work for
making modifications to it. "Object code" means any non-source form of
a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users can
regenerate automatically from other parts of the Corresponding Source.
The Corresponding Source for a work in source code form is that same
work.
#### 2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not convey,
without conditions so long as your license otherwise remains in force.
You may convey covered works to others for the sole purpose of having
them make modifications exclusively for you, or provide you with
facilities for running those works, provided that you comply with the
terms of this License in conveying all material for which you do not
control copyright. Those thus making or running the covered works for
you must do so exclusively on your behalf, under your direction and
control, on terms that prohibit them from making any copies of your
copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under the
conditions stated below. Sublicensing is not allowed; section 10 makes
it unnecessary.
#### 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such
circumvention is effected by exercising rights under this License with
respect to the covered work, and you disclaim any intention to limit
operation or modification of the work as a means of enforcing, against
the work's users, your or third parties' legal rights to forbid
circumvention of technological measures.
#### 4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
#### 5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these
conditions:
- a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
- b) The work must carry prominent notices stating that it is
released under this License and any conditions added under
section 7. This requirement modifies the requirement in section 4
to "keep intact all notices".
- c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
- d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
#### 6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms of
sections 4 and 5, provided that you also convey the machine-readable
Corresponding Source under the terms of this License, in one of these
ways:
- a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
- b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the Corresponding
Source from a network server at no charge.
- c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
- d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
- e) Convey the object code using peer-to-peer transmission,
provided you inform other peers where the object code and
Corresponding Source of the work are being offered to the general
public at no charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal,
family, or household purposes, or (2) anything designed or sold for
incorporation into a dwelling. In determining whether a product is a
consumer product, doubtful cases shall be resolved in favor of
coverage. For a particular product received by a particular user,
"normally used" refers to a typical or common use of that class of
product, regardless of the status of the particular user or of the way
in which the particular user actually uses, or expects or is expected
to use, the product. A product is a consumer product regardless of
whether the product has substantial commercial, industrial or
non-consumer uses, unless such uses represent the only significant
mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to
install and execute modified versions of a covered work in that User
Product from a modified version of its Corresponding Source. The
information must suffice to ensure that the continued functioning of
the modified object code is in no case prevented or interfered with
solely because modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or
updates for a work that has been modified or installed by the
recipient, or for the User Product in which it has been modified or
installed. Access to a network may be denied when the modification
itself materially and adversely affects the operation of the network
or violates the rules and protocols for communication across the
network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
#### 7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders
of that material) supplement the terms of this License with terms:
- a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
- b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
- c) Prohibiting misrepresentation of the origin of that material,
or requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
- d) Limiting the use for publicity purposes of names of licensors
or authors of the material; or
- e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
- f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions
of it) with contractual assumptions of liability to the recipient,
for any liability that these contractual assumptions directly
impose on those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions; the
above requirements apply either way.
#### 8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your license
from a particular copyright holder is reinstated (a) provisionally,
unless and until the copyright holder explicitly and finally
terminates your license, and (b) permanently, if the copyright holder
fails to notify you of the violation by some reasonable means prior to
60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
#### 9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or run
a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
#### 10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
#### 11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims owned
or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within the
scope of its coverage, prohibits the exercise of, or is conditioned on
the non-exercise of one or more of the rights that are specifically
granted under this License. You may not convey a covered work if you
are a party to an arrangement with a third party that is in the
business of distributing software, under which you make payment to the
third party based on the extent of your activity of conveying the
work, and under which the third party grants, to any of the parties
who would receive the covered work from you, a discriminatory patent
license (a) in connection with copies of the covered work conveyed by
you (or copies made from those copies), or (b) primarily for and in
connection with specific products or compilations that contain the
covered work, unless you entered into that arrangement, or that patent
license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
#### 12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under
this License and any other pertinent obligations, then as a
consequence you may not convey it at all. For example, if you agree to
terms that obligate you to collect a royalty for further conveying
from those to whom you convey the Program, the only way you could
satisfy both those terms and this License would be to refrain entirely
from conveying the Program.
#### 13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
#### 14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions
of the GNU General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in
detail to address new problems or concerns.
Each version is given a distinguishing version number. If the Program
specifies that a certain numbered version of the GNU General Public
License "or any later version" applies to it, you have the option of
following the terms and conditions either of that numbered version or
of any later version published by the Free Software Foundation. If the
Program does not specify a version number of the GNU General Public
License, you may choose any version ever published by the Free
Software Foundation.
If the Program specifies that a proxy can decide which future versions
of the GNU General Public License can be used, that proxy's public
statement of acceptance of a version permanently authorizes you to
choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
#### 15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT
WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND
PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE
DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR
CORRECTION.
#### 16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR
CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES
ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT
NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR
LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM
TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER
PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
#### 17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
### How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these
terms.
To do so, attach the following notices to the program. It is safest to
attach them to the start of each source file to most effectively state
the exclusion of warranty; and each file should have at least the
"copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper
mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands \`show w' and \`show c' should show the
appropriate parts of the General Public License. Of course, your
program's commands might be different; for a GUI interface, you would
use an "about box".
You should also get your employer (if you work as a programmer) or
school, if any, to sign a "copyright disclaimer" for the program, if
necessary. For more information on this, and how to apply and follow
the GNU GPL, see <https://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your
program into proprietary programs. If your program is a subroutine
library, you may consider it more useful to permit linking proprietary
applications with the library. If this is what you want to do, use the
GNU Lesser General Public License instead of this License. But first,
please read <https://www.gnu.org/licenses/why-not-lgpl.html>.

18
LICENCE.txt
View File

@@ -1,18 +0,0 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
This file is part of Astaroth.
Astaroth is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Astaroth is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with Astaroth. If not, see <http://www.gnu.org/licenses/>.
*/

210
README.md
View File

@@ -1,170 +1,90 @@
![astaroth_logo](./doc/astaroth_logo.svg "Astaroth Sigil")
# Astaroth - A Multi-GPU Library for Generic Stencil Computations {#mainpage}
# Astaroth - A Multi-GPU library for generic stencil computations
[Specification](doc/Astaroth_API_specification_and_user_manual/API_specification_and_user_manual.md) | [Contributing](CONTRIBUTING.md) | [Licence](LICENCE.md) | [Issue Tracker](https://bitbucket.org/jpekkila/astaroth/issues?status=new&status=open) | [Wiki](https://bitbucket.org/jpekkila/astaroth/wiki/Home)
Astaroth is a single-node multi-GPU library for multiphysics and other problems, which involve stencil computations in a discrete mesh. It's licenced under the terms of the GNU General Public Licence, version 3, or later (see [LICENCE.txt](https://bitbucket.org/miikkavaisala/astaroth-code/src/master/astaroth_2.0/LICENCE.txt)). Astaroth ships with a domain-specific language that can be used to translate high-level representations of various stencil operations into efficient CUDA kernels.
Astaroth is a multi-GPU library for three-dimensional stencil computations. It is designed especially for performing high-order stencil
computations in structured grids, where several coupled fields are updated each time step. Astaroth consists of a multi-GPU and single-GPU
APIs and provides a domain-specific language for translating high-level descriptions of stencil computations into efficient GPU code. This
makes Astaroth especially suitable for multiphysics simulations.
## System requirements
Astaroth is licenced under the terms of the GNU General Public Licence, version 3, or later
(see [LICENCE.txt](LICENCE.md)). For contributing guidelines,
see [Contributing](CONTRIBUTING.md).
NVIDIA GPU with >= 3.0 compute capability. See https://en.wikipedia.org/wiki/CUDA#GPUs_supported.
## Building (3rd party libraries for real-time visualization)
## System Requirements
* An NVIDIA GPU with support for compute capability 3.0 or higher (Kepler architecture or newer)
1. `cd 3rdparty`
1. `./setup_dependencies.sh` Note: this may take some time.
## Dependencies
Relative recent versions of
`gcc cmake cuda flex bison`.
## Building
There are two ways to build the code as instructed below.
In the base directory, run
If you encounter issues, recheck that the 3rd party libraries were successfully built during the previous step.
1. `mkdir build`
2. `cd build`
3. `cmake ..`
4. `make -j`
> **Optional:** Documentation can be generated by running `doxygen` in the base directory. The
generated documentation can be found in `doc/doxygen`.
> **Tip:** The library is configured by passing [options](#markdown-header-cmake-options) to CMake with `-D[option]=[ON|OFF]`.
For example, double precision can be enabled by calling `cmake -DBUILD_DOUBLE_PRECISION=ON ..`.
See [CMakeLists.txt](https://bitbucket.org/jpekkila/astaroth/src/master/CMakeLists.txt) for an up-to-date list of options.
> **Note:** CMake will inform you if there are missing dependencies.
## CMake Options
| Option | Description | Default |
|--------|-------------|---------|
| BUILD_DEBUG | Builds Astaroth with extensive error checking | OFF |
| BUILD_STANDALONE | Builds a standalone library for testing, benchmarking and simulation | ON |
| BUILD_UTILS | Builds a generic utility library (WIP replacement for BUILD_STANDALONE) | ON |
| BUILD_RT_VISUALIZATION | Builds the real-time visualization module | OFF |
| BUILD_SAMPLES | Builds projects in samples subdirectory | OFF |
| DOUBLE_PRECISION | Generates double precision code | OFF |
| MULTIGPU_ENABLED | Enables Astaroth to use multiple GPUs on a single node | ON |
| MPI_ENABLED | Enables additional functions for MPI communciation | OFF |
| DSL_MODULE_DIR | Defines the directory to be scanned when looking for DSL files | `astaroth/acc/mhd_solver` |
### New approach
## Standalone Module
1. `mkdir whatever && cd whatever # Sourcing not required anymore`
1. `cmake -DDSL_MODULE_DIR=acc/mhd_solver .. && make -j`
1. `./ac_run -t ../config/astaroth.conf`
### Method I: In the code directory (DEPRECATED. REVISE.)
1. `cd build/`
1. `cmake -DDOUBLE_PRECISION=OFF -DBUILD_DEBUG=OFF ..` (Use `cmake -D CMAKE_C_COMPILER=icc -D CMAKE_CXX_COMPILER=icpc -DDOUBLE_PRECISION=OFF -DBUILD_DEBUG=OFF ..` if compiling on TIARA)
1. `../scripts/compile_acc.sh && make -j`
1. `./ac_run <options>`
Edit `config/astaroth.conf` to change the numerical setup.
### Method II: With a script in a custom build directory (DEPRECATED. REVISE.)
1. `source sourceme.sh` to add relevant directories to the `PATH`
1. `ac_mkbuilddir.sh -b my_build_dir/` to set up a custom build directory. There are also other options available. See `ac_mkbuilddir.sh -h` for more.
1. `compile_acc.sh` to generate kernels from the Domain Specific Language
1. `cd my_build_dir/`
1. `make -j`
1. `./ac_run <options>`
Edit `my_build_dir/astaroth.conf` to change the numerical setup.
### Available options
- `-s` simulation
- `-b` benchmark
- `-t` automated test
By default, the program does a real-time visualization of the simulation domain. The camera and the initial conditions can be controller by `arrow keys`, `pgup`, `pgdown` and `spacebar`.
## Visualization
```Bash
Usage: ./ac_run [options]
--help | -h: Prints this help.
--test | -t: Runs autotests.
--benchmark | -b: Runs benchmarks.
--simulate | -s: Runs the simulation.
--render | -r: Runs the real-time renderer.
--config | -c: Uses the config file given after this flag instead of the default.
```
See `analysis/python/` directory of existing data visualization and analysis scripts.
## Generating documentation
## Interface
Run `doxygen doxyfile` in astaroth_2.0 directory. The generated files can be found in `doc/doxygen`. The main page of the documentation will be at `dox/doxygen/astaroth_doc_html/index.html`.
* `astaroth/include/astaroth.h`: Legacy interface for backwards compatibility and quick testing.
* `astaroth/include/astaroth_node.h`: Multi-GPU interface (single node).
* `astaroth/include/astaroth_device.h`: Single-GPU interface.
* `astaroth/src/utils/`: Utility library for host-side memory allocations, verification and other tasks.
## Formatting
## FAQ
If you have clang-format, you may run `scripts/fix_style.sh`. This script will recursively fix style of all the source files down from the current working directory. The script will ask for a confirmation before making any changes.
Can I use the code even if I don't make my changes public?
## Directory structure
TODO
> [GPL](LICENCE.md) requires only that if you release a binary based on Astaroth to the public, then you should also release the source code for it. In private you can do whatever you want (secret forks, secret collaborations, etc).
## Contributing
How do I compile with MPI support?
0. **Do not break existing functionality.** Do not modify the interface functions declared in astaroth.h and device.cuh in any way. Bug fixes are exceptions. If you need new functionality, create a new function.
0. **Do not rename or redefine variables or constants declared in astaroth.h** without consulting everyone involved with the project.
0. **Ensure that the code compiles and the automated tests pass** by running `./ac_run -t` before pushing changes to master. If you want to implement a feature that consists of multiple commits, see Managing feature branches below.
### Managing feature branches
0. Ensure that you're on the latest version of master. `git checkout master && git pull`
0. Create a feature branch with `git checkout -b <feature_name_year-month-date>`, f.ex. `git checkout -b forcingtests_2019-01-01`
0. Do your commits in that branch until your new feature works
0. Merge master with your feature branch `git merge master`
0. Resolve the conflicts and test that the code compiles and still works by running `./ac_run -t`
0. If everything is OK, commit your final changes to the feature branch and merge it to master `git commit && git checkout master && git merge <your feature branch> && git push`
0. Unless you really have to keep your feature branch around for historical/other reasons, remove it from remote by calling `git push origin --delete <your feature branch>`
A flowchart is available at [doc/commitflowchart.png](https://bitbucket.org/jpekkila/astaroth/src/2d91df19dcb3/doc/commitflowchart.png?at=master).
### About branches in general
* Unused branches should not kept around after merging them into master in order to avoid cluttering the repository.
* `git branch -a --merged` shows a list of branches that have been merged to master and are likely not needed any more.
* `git push origin --delete <feature branch>` deletes a remote branch while `git branch -d <feature branch>` deletes a local branch
* If you think that you have messed up and lost work, run `git reflog` which lists the latests commits. All work that has been committed should be accessible with the hashes listed by this command with `git checkout <reflog hash>`.
## Coding style.
### In a nutshell
- Use [K&R indentation style](https://en.wikipedia.org/wiki/Indentation_style#K&R_style) and 4 space tabs.
- Line width is 100 characters
- Start function names after a linebreak in source files.
- [Be generous with `const` type qualifiers](https://isocpp.org/wiki/faq/const-correctness).
- When in doubt, see [Google C++ Style Guide](https://google.github.io/styleguide/cppguide.html).
### Header example:
```cpp
// Licence notice and doxygen description here
#pragma once
#include "avoid_including_headers_here.h"
/** Doxygen comments */
void globalFunction(void);
```
### Source example:
```cpp
#include "parent_header.h"
#include <standard_library_headers.h>
#include "other_headers.h"
#include "more_headers.h"
typedef struct {
int data;
} SomeStruct;
static inline int small_function(const SomeStruct& stuff) { return stuff.data; }
// Pass constant structs always by reference (&) and use const type qualifier.
// Modified structs are always passed as pointers (*), never as references.
// Constant parameters should be on the left-hand side, while non-consts go to the right.
static void
local_function(const SomeStruct& constant_struct, SomeStruct* modified_struct)
{
modified_struct->data = constant_struct.data;
}
void
globalFunction(void)
{
return;
}
```
## TIARA cluster compilation notes
Modules used when compiling the code on TIARA cluster.
* cmake/3.9.5
* gcc/8.3.0
* cuda/10.1
> MPI implementation for Astaroth is still work in progress, these commands are for testing only. Invoke CMake with `cmake -DMPI_ENABLED=ON -DBUILD_MPI_TEST=ON -DCMAKE_CXX_COMPILER=$(which mpicxx) ..`. Otherwise the build steps are the same. Run with `mpirun -np 4 ./mpitest`.
How do I contribute?
> See [Contributing](CONTRIBUTING.md).

56
acc/README.md
View File

@@ -1,42 +1,36 @@
# Dependencies
## Debian/Ubuntu
`apt install flex bison build-essential`
# ACC - Astaroth Code Compiler
# Usage
* `./build_acc.sh # Builds the ASPL compiler (acc)`
* `./compile.sh <.sps or .sas source> # Compiles the given stage into CUDA`
* `./test.sh # Tries to compile the sample stages`
* `./clean.sh # Removed directories generated by build_acc.sh and test.sh`
ACC is a source-to-source compiler for generating CUDA kernels from programs written in Astaroth Code (AC). This document focuses on how to build and run the compiler. For detailed description of code generation and compilation phases, we refer the reader to [J. Pekkilä, Astaroth: A Library for Stencil Computations on Graphics Processing Units. 2019.](http://urn.fi/URN:NBN:fi:aalto-201906233993), Section 4.3. We refer the reader to [Specification](doc/Astaroth_API_specification_and_user_manual/API_specification_and_user_manual.md) for a detailed description of AC syntax.
## Example
ACC is automatically compiled and invoked when compiling the Astaroth Library, user intervention is not needed. The instructions presented in this file are only for developers looking to debug the AC compiler.
- `./compile.sh src/stencil_assembly.sas # Generates stencil_assembly.cuh`
- `./compile.sh src/stencil_process.sps # Generates stencil_process.cuh`
## Dependencies
# What happens under the hood
`gcc flex bison`
The compiler is made of a scanner (flex), parser (bison), implementation of the abstract syntax tree (AST) and a code generator.
The language is defined by tokens and grammars found in acc.l and acc.y. These files are given as input to flex and bison, which generate the scanning and parsing stages for the compiler. The resulting AST is defined in ast.h. Finally, we traverse the generated AST with our code generator, generating CUDA code.
## Building
## ACC compilation stages
1. `mkdir build`
2. `cd build`
3. `cmake ..`
4. `make -j`
### In short:
* Preprocess .ac
* Compile preprocessed .ac to .cuh
* Compile .cuh
## Usage
### More detailed:
0. A Parser is generated: bison --verbose -d acc.y
0. A Scanner is generated: flex acc.l
0. The compiler is built: gcc -std=gnu11 code_generator.c acc.tab.c lex.yy.c -lfl
0. Source files (.sps and .sas) are preprocessed using the GCC preprocessor and cleaned from any residual directives which would be useful when compiling the code further with GCC. We do not need those when compiling with ACC and are not recognized by our grammar.
0. Either the stencil processing stage (.sps) or the stencil assembly stage (.sas) are generated by passing the preprocessed file to acc. This emits the final CUDA code.
0. Compilation is continued with the NVIDIA CUDA compiler
Script `compile_acc_module.sh` executes all compilation stages from preprocessing to linking AC standard libraries. The resulting cuda headers are placed in the current working directory. The script should be invoked as follows.
### Even more detailed:
The NVIDIA CUDA compiler compiles .cuh to .fatbin, which is embedded into a C++ binary containig host code of the program. A fatbin contains .cubin files, which contain the configuration of the GPU and the kernels in a streaming assembly code (.sass). We could also compile for a virtual architecture (.ptx) instead of the actual hardware-specific machine code (.cubin) by passing -code=compute_XX flag to nvcc, which would compile cuda sources at runtime (just-in-time compilation, JIT) when creating the CUDA context. However, we alway know which architecture we want to run the code on and JIT compilation would just increase the time to takes to launch the program.
> `./compile_acc_module <a directory containing AC files>`
nvcc -DAC_DOUBLE_PRECISION=1 -ptx --relocatable-device-code true -O3 -std=c++11 --maxrregcount=255 -ftz=true -gencode arch=compute_60,code=sm_60 device.cu -I ../../include -I ../../
nvcc -DAC_DOUBLE_PRECISION=1 -cubin --relocatable-device-code true -O3 -std=c++11 --maxrregcount=255 -ftz=true -gencode arch=compute_60,code=sm_60 device.cu -I ../../include -I ../../
cuobjdump --dump-sass device.cubin > device.sass
For preprocessing only, see `preprocess.sh`. The first parameter is regarded as the AC source file, while rest of the parameters are passed to gcc. For example:
> `./preprocess.sh file.ac -I dir`
Preprocesses `file.ac` and searches `dir` for files to be included.
For invoking the code generator, pass preprocessed files that respect AC syntax to `acc`.
For example:
> `acc < file.ac.preprocessed`
See [Building](#markdown-header-building) on how to obtain `acc`.

25
acc/build_acc.sh
View File

@@ -1,25 +0,0 @@
#!/bin/bash
cd `dirname $0` # Only operate in the same directory with this script
COMPILER_NAME="acc"
SRC_DIR=${PWD}/src
BUILD_DIR=${PWD}/build
echo "-- Compiling acc:" ${BUILD_DIR}
mkdir -p ${BUILD_DIR}
cd ${BUILD_DIR}
#echo ${BASE_DIR}
#echo ${SRC_DIR}
#echo ${BUILD_DIR}
# Generate Bison headers
bison --verbose -d ${SRC_DIR}/${COMPILER_NAME}.y
## Generate Flex sources and headers
flex ${SRC_DIR}/${COMPILER_NAME}.l
## Compile the ASPL compiler
gcc -std=gnu11 ${SRC_DIR}/code_generator.c ${COMPILER_NAME}.tab.c lex.yy.c -lfl -I ${BUILD_DIR} -I ${SRC_DIR} -o ${COMPILER_NAME}

5
acc/clean.sh
View File

@@ -1,5 +0,0 @@
#!/bin/bash
cd `dirname $0` # Only operate in the same directory with this script
rm -rf build testbin

28
acc/compile.sh
View File

@@ -1,28 +0,0 @@
#!/bin/bash
# Usage ./compile <acc binary> <source file> <gcc preprocessor flags, f.ex. -I some/path>
ACC_DIR=`dirname $0`
ACC_BINARY=$1
FULL_NAME=$(basename -- $2)
FILENAME="${FULL_NAME%.*}"
EXTENSION="${FULL_NAME##*.}"
if [ "${EXTENSION}" = "sas" ]; then
COMPILE_FLAGS="-sas" # Generate stencil assembly stage
CUH_FILENAME="stencil_assembly.cuh"
echo "-- Generating stencil assembly stage: ${FILENAME}.sas -> ${CUH_FILENAME}"
elif [ "${EXTENSION}" = "sps" ]; then
COMPILE_FLAGS="-sps" # Generate stencil processing stage
CUH_FILENAME="stencil_process.cuh"
echo "-- Generating stencil processing stage: ${FILENAME}.sps -> ${CUH_FILENAME}"
elif [ "${EXTENSION}" = "sdh" ]; then
COMPILE_FLAGS="-sdh" # Generate stencil definition header
CUH_FILENAME="stencil_defines.h"
echo "-- Generating stencil definition header: ${FILENAME}.sdh -> ${CUH_FILENAME}"
else
echo "-- Error: unknown extension" ${EXTENSION} "of file" ${FULL_NAME}
echo "-- Extension should be either .sas, .sps or .sdh"
exit
fi
${ACC_DIR}/preprocess.sh ${@:2} | ${ACC_BINARY} ${COMPILE_FLAGS} > ${CUH_FILENAME}

0
scripts/compile_acc_module.sh → acc/compile_acc_module.sh
View File

163
acc/hydro_solver/stencil_defines.h
View File

@@ -1,163 +0,0 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
This file is part of Astaroth.
Astaroth is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Astaroth is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with Astaroth. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
/*
* =============================================================================
* Logical switches
* =============================================================================
*/
#define STENCIL_ORDER (6)
#define NGHOST (STENCIL_ORDER / 2)
#define LDENSITY (1)
#define LHYDRO (1)
#define LMAGNETIC (0)
#define LENTROPY (0)
#define LTEMPERATURE (0)
#define LFORCING (0)
#define LUPWD (0)
#define AC_THERMAL_CONDUCTIVITY (AcReal(0.001)) // TODO: make an actual config parameter
/*
* =============================================================================
* User-defined parameters
* =============================================================================
*/
// clang-format off
#define AC_FOR_USER_INT_PARAM_TYPES(FUNC)\
/* Other */\
FUNC(AC_max_steps), \
FUNC(AC_save_steps), \
FUNC(AC_bin_steps), \
FUNC(AC_bc_type),
#define AC_FOR_USER_INT3_PARAM_TYPES(FUNC)
#define AC_FOR_USER_REAL_PARAM_TYPES(FUNC)\
/* cparams */\
FUNC(AC_dsx), \
FUNC(AC_dsy), \
FUNC(AC_dsz), \
FUNC(AC_dsmin), \
/* physical grid*/\
FUNC(AC_xlen), \
FUNC(AC_ylen), \
FUNC(AC_zlen), \
FUNC(AC_xorig), \
FUNC(AC_yorig), \
FUNC(AC_zorig), \
/*Physical units*/\
FUNC(AC_unit_density),\
FUNC(AC_unit_velocity),\
FUNC(AC_unit_length),\
/* properties of gravitating star*/\
FUNC(AC_star_pos_x),\
FUNC(AC_star_pos_y),\
FUNC(AC_star_pos_z),\
FUNC(AC_M_star),\
/* Run params */\
FUNC(AC_cdt), \
FUNC(AC_cdtv), \
FUNC(AC_cdts), \
FUNC(AC_nu_visc), \
FUNC(AC_cs_sound), \
FUNC(AC_eta), \
FUNC(AC_mu0), \
FUNC(AC_cp_sound), \
FUNC(AC_gamma), \
FUNC(AC_cv_sound), \
FUNC(AC_lnT0), \
FUNC(AC_lnrho0), \
FUNC(AC_zeta), \
FUNC(AC_trans),\
/* Other */\
FUNC(AC_bin_save_t), \
/* Initial condition params */\
FUNC(AC_ampl_lnrho), \
FUNC(AC_ampl_uu), \
FUNC(AC_angl_uu), \
FUNC(AC_lnrho_edge),\
FUNC(AC_lnrho_out),\
/* Forcing parameters. User configured. */\
FUNC(AC_forcing_magnitude),\
FUNC(AC_relhel), \
FUNC(AC_kmin), \
FUNC(AC_kmax), \
/* Forcing parameters. Set by the generator. */\
FUNC(AC_forcing_phase),\
FUNC(AC_k_forcex),\
FUNC(AC_k_forcey),\
FUNC(AC_k_forcez),\
FUNC(AC_kaver),\
FUNC(AC_ff_hel_rex),\
FUNC(AC_ff_hel_rey),\
FUNC(AC_ff_hel_rez),\
FUNC(AC_ff_hel_imx),\
FUNC(AC_ff_hel_imy),\
FUNC(AC_ff_hel_imz),\
/* Additional helper params */\
/* (deduced from other params do not set these directly!) */\
FUNC(AC_G_CONST),\
FUNC(AC_GM_star),\
FUNC(AC_sq2GM_star),\
FUNC(AC_cs2_sound), \
FUNC(AC_inv_dsx), \
FUNC(AC_inv_dsy), \
FUNC(AC_inv_dsz),
#define AC_FOR_USER_REAL3_PARAM_TYPES(FUNC)
// clang-format on
/*
* =============================================================================
* User-defined vertex buffers
* =============================================================================
*/
// clang-format off
#if LENTROPY
#define AC_FOR_VTXBUF_HANDLES(FUNC) \
FUNC(VTXBUF_LNRHO), \
FUNC(VTXBUF_UUX), \
FUNC(VTXBUF_UUY), \
FUNC(VTXBUF_UUZ), \
FUNC(VTXBUF_AX), \
FUNC(VTXBUF_AY), \
FUNC(VTXBUF_AZ), \
FUNC(VTXBUF_ENTROPY),
#elif LMAGNETIC
#define AC_FOR_VTXBUF_HANDLES(FUNC) \
FUNC(VTXBUF_LNRHO), \
FUNC(VTXBUF_UUX), \
FUNC(VTXBUF_UUY), \
FUNC(VTXBUF_UUZ), \
FUNC(VTXBUF_AX), \
FUNC(VTXBUF_AY), \
FUNC(VTXBUF_AZ),
#elif LHYDRO
#define AC_FOR_VTXBUF_HANDLES(FUNC) \
FUNC(VTXBUF_LNRHO), \
FUNC(VTXBUF_UUX), \
FUNC(VTXBUF_UUY), \
FUNC(VTXBUF_UUZ),
#else
#define AC_FOR_VTXBUF_HANDLES(FUNC) \
FUNC(VTXBUF_LNRHO),
#endif
// clang-format on

163
acc/magnetic_solver/stencil_defines.h
View File

@@ -1,163 +0,0 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
This file is part of Astaroth.
Astaroth is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Astaroth is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with Astaroth. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
/*
* =============================================================================
* Logical switches
* =============================================================================
*/
#define STENCIL_ORDER (6)
#define NGHOST (STENCIL_ORDER / 2)
#define LDENSITY (1)
#define LHYDRO (1)
#define LMAGNETIC (1)
#define LENTROPY (0)
#define LTEMPERATURE (0)
#define LFORCING (0)
#define LUPWD (0)
#define AC_THERMAL_CONDUCTIVITY (AcReal(0.001)) // TODO: make an actual config parameter
/*
* =============================================================================
* User-defined parameters
* =============================================================================
*/
// clang-format off
#define AC_FOR_USER_INT_PARAM_TYPES(FUNC)\
/* Other */\
FUNC(AC_max_steps), \
FUNC(AC_save_steps), \
FUNC(AC_bin_steps), \
FUNC(AC_bc_type),
#define AC_FOR_USER_INT3_PARAM_TYPES(FUNC)
#define AC_FOR_USER_REAL_PARAM_TYPES(FUNC)\
/* cparams */\
FUNC(AC_dsx), \
FUNC(AC_dsy), \
FUNC(AC_dsz), \
FUNC(AC_dsmin), \
/* physical grid*/\
FUNC(AC_xlen), \
FUNC(AC_ylen), \
FUNC(AC_zlen), \
FUNC(AC_xorig), \
FUNC(AC_yorig), \
FUNC(AC_zorig), \
/*Physical units*/\
FUNC(AC_unit_density),\
FUNC(AC_unit_velocity),\
FUNC(AC_unit_length),\
/* properties of gravitating star*/\
FUNC(AC_star_pos_x),\
FUNC(AC_star_pos_y),\
FUNC(AC_star_pos_z),\
FUNC(AC_M_star),\
/* Run params */\
FUNC(AC_cdt), \
FUNC(AC_cdtv), \
FUNC(AC_cdts), \
FUNC(AC_nu_visc), \
FUNC(AC_cs_sound), \
FUNC(AC_eta), \
FUNC(AC_mu0), \
FUNC(AC_cp_sound), \
FUNC(AC_gamma), \
FUNC(AC_cv_sound), \
FUNC(AC_lnT0), \
FUNC(AC_lnrho0), \
FUNC(AC_zeta), \
FUNC(AC_trans),\
/* Other */\
FUNC(AC_bin_save_t), \
/* Initial condition params */\
FUNC(AC_ampl_lnrho), \
FUNC(AC_ampl_uu), \
FUNC(AC_angl_uu), \
FUNC(AC_lnrho_edge),\
FUNC(AC_lnrho_out),\
/* Forcing parameters. User configured. */\
FUNC(AC_forcing_magnitude),\
FUNC(AC_relhel), \
FUNC(AC_kmin), \
FUNC(AC_kmax), \
/* Forcing parameters. Set by the generator. */\
FUNC(AC_forcing_phase),\
FUNC(AC_k_forcex),\
FUNC(AC_k_forcey),\
FUNC(AC_k_forcez),\
FUNC(AC_kaver),\
FUNC(AC_ff_hel_rex),\
FUNC(AC_ff_hel_rey),\
FUNC(AC_ff_hel_rez),\
FUNC(AC_ff_hel_imx),\
FUNC(AC_ff_hel_imy),\
FUNC(AC_ff_hel_imz),\
/* Additional helper params */\
/* (deduced from other params do not set these directly!) */\
FUNC(AC_G_CONST),\
FUNC(AC_GM_star),\
FUNC(AC_sq2GM_star),\
FUNC(AC_cs2_sound), \
FUNC(AC_inv_dsx), \
FUNC(AC_inv_dsy), \
FUNC(AC_inv_dsz),
#define AC_FOR_USER_REAL3_PARAM_TYPES(FUNC)
// clang-format on
/*
* =============================================================================
* User-defined vertex buffers
* =============================================================================
*/
// clang-format off
#if LENTROPY
#define AC_FOR_VTXBUF_HANDLES(FUNC) \
FUNC(VTXBUF_LNRHO), \
FUNC(VTXBUF_UUX), \
FUNC(VTXBUF_UUY), \
FUNC(VTXBUF_UUZ), \
FUNC(VTXBUF_AX), \
FUNC(VTXBUF_AY), \
FUNC(VTXBUF_AZ), \
FUNC(VTXBUF_ENTROPY),
#elif LMAGNETIC
#define AC_FOR_VTXBUF_HANDLES(FUNC) \
FUNC(VTXBUF_LNRHO), \
FUNC(VTXBUF_UUX), \
FUNC(VTXBUF_UUY), \
FUNC(VTXBUF_UUZ), \
FUNC(VTXBUF_AX), \
FUNC(VTXBUF_AY), \
FUNC(VTXBUF_AZ),
#elif LHYDRO
#define AC_FOR_VTXBUF_HANDLES(FUNC) \
FUNC(VTXBUF_LNRHO), \
FUNC(VTXBUF_UUX), \
FUNC(VTXBUF_UUY), \
FUNC(VTXBUF_UUZ),
#else
#define AC_FOR_VTXBUF_HANDLES(FUNC) \
FUNC(VTXBUF_LNRHO),
#endif
// clang-format on

2
acc/mhd_solver/stencil_kernel.ac
View File

@@ -607,7 +607,7 @@ forcing(int3 globalVertexIdx, Scalar dt)
Vector force = helical_forcing(magnitude, k_force, xx, ff_re, ff_im, phase);
// Scaling N = magnitude*cs*sqrt(k*cs/dt) * dt
const Scalar NN = cs * sqrt(AC_kaver * cs);
const Scalar NN = cs * magnitude * sqrt(AC_kaver * cs);
// MV: Like in the Pencil Code. I don't understandf the logic here.
force.x = sqrt(dt) * NN * force.x;
force.y = sqrt(dt) * NN * force.y;

75
acc/mhd_solver_DEPRECATED/stencil_assembly.sas
View File

@@ -1,75 +0,0 @@
#include "stencil_definition.sdh"
Preprocessed Scalar
value(in ScalarField vertex)
{
return vertex[vertexIdx];
}
Preprocessed Vector
gradient(in ScalarField vertex)
{
return (Vector){derx(vertexIdx, vertex), dery(vertexIdx, vertex), derz(vertexIdx, vertex)};
}
#if LUPWD
Preprocessed Scalar
der6x_upwd(in ScalarField vertex)
{
Scalar inv_ds = AC_inv_dsx;
return (Scalar){Scalar(1.0 / 60.0) * inv_ds *
(-Scalar(20.0) * vertex[vertexIdx.x, vertexIdx.y, vertexIdx.z] +
Scalar(15.0) * (vertex[vertexIdx.x + 1, vertexIdx.y, vertexIdx.z] +
vertex[vertexIdx.x - 1, vertexIdx.y, vertexIdx.z]) -
Scalar(6.0) * (vertex[vertexIdx.x + 2, vertexIdx.y, vertexIdx.z] +
vertex[vertexIdx.x - 2, vertexIdx.y, vertexIdx.z]) +
vertex[vertexIdx.x + 3, vertexIdx.y, vertexIdx.z] +
vertex[vertexIdx.x - 3, vertexIdx.y, vertexIdx.z])};
}
Preprocessed Scalar
der6y_upwd(in ScalarField vertex)
{
Scalar inv_ds = AC_inv_dsy;
return (Scalar){Scalar(1.0 / 60.0) * inv_ds *
(-Scalar(20.0) * vertex[vertexIdx.x, vertexIdx.y, vertexIdx.z] +
Scalar(15.0) * (vertex[vertexIdx.x, vertexIdx.y + 1, vertexIdx.z] +
vertex[vertexIdx.x, vertexIdx.y - 1, vertexIdx.z]) -
Scalar(6.0) * (vertex[vertexIdx.x, vertexIdx.y + 2, vertexIdx.z] +
vertex[vertexIdx.x, vertexIdx.y - 2, vertexIdx.z]) +
vertex[vertexIdx.x, vertexIdx.y + 3, vertexIdx.z] +
vertex[vertexIdx.x, vertexIdx.y - 3, vertexIdx.z])};
}
Preprocessed Scalar
der6z_upwd(in ScalarField vertex)
{
Scalar inv_ds = AC_inv_dsz;
return (Scalar){Scalar(1.0 / 60.0) * inv_ds *
(-Scalar(20.0) * vertex[vertexIdx.x, vertexIdx.y, vertexIdx.z] +
Scalar(15.0) * (vertex[vertexIdx.x, vertexIdx.y, vertexIdx.z + 1] +
vertex[vertexIdx.x, vertexIdx.y, vertexIdx.z - 1]) -
Scalar(6.0) * (vertex[vertexIdx.x, vertexIdx.y, vertexIdx.z + 2] +
vertex[vertexIdx.x, vertexIdx.y, vertexIdx.z - 2]) +
vertex[vertexIdx.x, vertexIdx.y, vertexIdx.z + 3] +
vertex[vertexIdx.x, vertexIdx.y, vertexIdx.z - 3])};
}
#endif
Preprocessed Matrix
hessian(in ScalarField vertex)
{
Matrix hessian;
hessian.row[0] = (Vector){derxx(vertexIdx, vertex), derxy(vertexIdx, vertex),
derxz(vertexIdx, vertex)};
hessian.row[1] = (Vector){hessian.row[0].y, deryy(vertexIdx, vertex), deryz(vertexIdx, vertex)};
hessian.row[2] = (Vector){hessian.row[0].z, hessian.row[1].z, derzz(vertexIdx, vertex)};
return hessian;
}

137
acc/mhd_solver_DEPRECATED/stencil_definition.sdh
View File

@@ -1,137 +0,0 @@
#define LDENSITY (1)
#define LHYDRO (1)
#define LMAGNETIC (1)
#define LENTROPY (1)
#define LTEMPERATURE (0)
#define LFORCING (1)
#define LUPWD (1)
#define LSINK (0)
#define AC_THERMAL_CONDUCTIVITY (AcReal(0.001)) // TODO: make an actual config parameter
// Int params
uniform int AC_max_steps;
uniform int AC_save_steps;
uniform int AC_bin_steps;
uniform int AC_bc_type;
uniform int AC_start_step;
// Real params
uniform Scalar AC_dt;
uniform Scalar AC_max_time;
// Spacing
uniform Scalar AC_dsx;
uniform Scalar AC_dsy;
uniform Scalar AC_dsz;
uniform Scalar AC_dsmin;
// physical grid
uniform Scalar AC_xlen;
uniform Scalar AC_ylen;
uniform Scalar AC_zlen;
uniform Scalar AC_xorig;
uniform Scalar AC_yorig;
uniform Scalar AC_zorig;
// Physical units
uniform Scalar AC_unit_density;
uniform Scalar AC_unit_velocity;
uniform Scalar AC_unit_length;
// properties of gravitating star
uniform Scalar AC_star_pos_x;
uniform Scalar AC_star_pos_y;
uniform Scalar AC_star_pos_z;
uniform Scalar AC_M_star;
// properties of sink particle
uniform Scalar AC_sink_pos_x;
uniform Scalar AC_sink_pos_y;
uniform Scalar AC_sink_pos_z;
uniform Scalar AC_M_sink;
uniform Scalar AC_M_sink_init;
uniform Scalar AC_M_sink_Msun;
uniform Scalar AC_soft;
uniform Scalar AC_accretion_range;
uniform Scalar AC_switch_accretion;
// Run params
uniform Scalar AC_cdt;
uniform Scalar AC_cdtv;
uniform Scalar AC_cdts;
uniform Scalar AC_nu_visc;
uniform Scalar AC_cs_sound;
uniform Scalar AC_eta;
uniform Scalar AC_mu0;
uniform Scalar AC_cp_sound;
uniform Scalar AC_gamma;
uniform Scalar AC_cv_sound;
uniform Scalar AC_lnT0;
uniform Scalar AC_lnrho0;
uniform Scalar AC_zeta;
uniform Scalar AC_trans;
// Other
uniform Scalar AC_bin_save_t;
// Initial condition params
uniform Scalar AC_ampl_lnrho;
uniform Scalar AC_ampl_uu;
uniform Scalar AC_angl_uu;
uniform Scalar AC_lnrho_edge;
uniform Scalar AC_lnrho_out;
// Forcing parameters. User configured.
uniform Scalar AC_forcing_magnitude;
uniform Scalar AC_relhel;
uniform Scalar AC_kmin;
uniform Scalar AC_kmax;
// Forcing parameters. Set by the generator.
uniform Scalar AC_forcing_phase;
uniform Scalar AC_k_forcex;
uniform Scalar AC_k_forcey;
uniform Scalar AC_k_forcez;
uniform Scalar AC_kaver;
uniform Scalar AC_ff_hel_rex;
uniform Scalar AC_ff_hel_rey;
uniform Scalar AC_ff_hel_rez;
uniform Scalar AC_ff_hel_imx;
uniform Scalar AC_ff_hel_imy;
uniform Scalar AC_ff_hel_imz;
// Additional helper params // (deduced from other params do not set these directly!)
uniform Scalar AC_G_const;
uniform Scalar AC_GM_star;
uniform Scalar AC_unit_mass;
uniform Scalar AC_sq2GM_star;
uniform Scalar AC_cs2_sound;
uniform Scalar AC_inv_dsx;
uniform Scalar AC_inv_dsy;
uniform Scalar AC_inv_dsz;
/*
* =============================================================================
* User-defined vertex buffers
* =============================================================================
*/
#if LENTROPY
uniform ScalarField VTXBUF_LNRHO;
uniform ScalarField VTXBUF_UUX;
uniform ScalarField VTXBUF_UUY;
uniform ScalarField VTXBUF_UUZ;
uniform ScalarField VTXBUF_AX;
uniform ScalarField VTXBUF_AY;
uniform ScalarField VTXBUF_AZ;
uniform ScalarField VTXBUF_ENTROPY;
#elif LMAGNETIC
uniform ScalarField VTXBUF_LNRHO;
uniform ScalarField VTXBUF_UUX;
uniform ScalarField VTXBUF_UUY;
uniform ScalarField VTXBUF_UUZ;
uniform ScalarField VTXBUF_AX;
uniform ScalarField VTXBUF_AY;
uniform ScalarField VTXBUF_AZ;
#elif LHYDRO
uniform ScalarField VTXBUF_LNRHO;
uniform ScalarField VTXBUF_UUX;
uniform ScalarField VTXBUF_UUY;
uniform ScalarField VTXBUF_UUZ;
#else
uniform ScalarField VTXBUF_LNRHO;
#endif
#if LSINK
uniform ScalarField VTXBUF_ACCRETION;
#endif

504
acc/mhd_solver_DEPRECATED/stencil_process.sps
View File

@@ -1,504 +0,0 @@
#include "stencil_definition.sdh"
Vector
value(in VectorField uu)
{
return (Vector){value(uu.x), value(uu.y), value(uu.z)};
}
#if LUPWD
Scalar
upwd_der6(in VectorField uu, in ScalarField lnrho)
{
Scalar uux = fabs(value(uu).x);
Scalar uuy = fabs(value(uu).y);
Scalar uuz = fabs(value(uu).z);
return (Scalar){uux * der6x_upwd(lnrho) + uuy * der6y_upwd(lnrho) + uuz * der6z_upwd(lnrho)};
}
#endif
Matrix
gradients(in VectorField uu)
{
return (Matrix){gradient(uu.x), gradient(uu.y), gradient(uu.z)};
}
#if LSINK
Vector
sink_gravity(int3 globalVertexIdx){
int accretion_switch = int(AC_switch_accretion);
if (accretion_switch == 1){
Vector force_gravity;
const Vector grid_pos = (Vector){(globalVertexIdx.x - DCONST(AC_nx_min)) * AC_dsx,
(globalVertexIdx.y - DCONST(AC_ny_min)) * AC_dsy,
(globalVertexIdx.z - DCONST(AC_nz_min)) * AC_dsz};
const Scalar sink_mass = AC_M_sink;
const Vector sink_pos = (Vector){AC_sink_pos_x,
AC_sink_pos_y,
AC_sink_pos_z};
const Scalar distance = length(grid_pos - sink_pos);
const Scalar soft = AC_soft;
//MV: The commit 083ff59 had AC_G_const defined wrong here in DSL making it exxessively strong.
//MV: Scalar gravity_magnitude = ... below is correct!
const Scalar gravity_magnitude = (AC_G_const * sink_mass) / pow(((distance * distance) + soft*soft), 1.5);
const Vector direction = (Vector){(sink_pos.x - grid_pos.x) / distance,
(sink_pos.y - grid_pos.y) / distance,
(sink_pos.z - grid_pos.z) / distance};
force_gravity = gravity_magnitude * direction;
return force_gravity;
} else {
return (Vector){0.0, 0.0, 0.0};
}
}
#endif
#if LSINK
// Give Truelove density
Scalar
truelove_density(in ScalarField lnrho){
const Scalar rho = exp(value(lnrho));
const Scalar Jeans_length_squared = (M_PI * AC_cs2_sound) / (AC_G_const * rho);
const Scalar TJ_rho = ((M_PI) * ((AC_dsx * AC_dsx) / Jeans_length_squared) * AC_cs2_sound) / (AC_G_const * AC_dsx * AC_dsx);
//TODO: AC_dsx will cancel out, deal with it later for optimization.
Scalar accretion_rho = TJ_rho;
return accretion_rho;
}
// This controls accretion of density/mass to the sink particle.
Scalar
sink_accretion(int3 globalVertexIdx, in ScalarField lnrho, Scalar dt){
const Vector grid_pos = (Vector){(globalVertexIdx.x - DCONST(AC_nx_min)) * AC_dsx,
(globalVertexIdx.y - DCONST(AC_ny_min)) * AC_dsy,
(globalVertexIdx.z - DCONST(AC_nz_min)) * AC_dsz};
const Vector sink_pos = (Vector){AC_sink_pos_x,
AC_sink_pos_y,
AC_sink_pos_z};
const Scalar profile_range = AC_accretion_range;
const Scalar accretion_distance = length(grid_pos - sink_pos);
int accretion_switch = AC_switch_accretion;
Scalar accretion_density;
Scalar weight;
if (accretion_switch == 1){
if ((accretion_distance) <= profile_range){
//weight = Scalar(1.0);
//Hann window function
Scalar window_ratio = accretion_distance/profile_range;
weight = Scalar(0.5)*(Scalar(1.0) - cos(Scalar(2.0)*M_PI*window_ratio));
} else {
weight = Scalar(0.0);
}
//Truelove criterion is used as a kind of arbitrary density floor.
const Scalar lnrho_min = log(truelove_density(lnrho));
Scalar rate;
if (value(lnrho) > lnrho_min) {
rate = (exp(value(lnrho)) - exp(lnrho_min)) / dt;
} else {
rate = Scalar(0.0);
}
accretion_density = weight * rate ;
} else {
accretion_density = Scalar(0.0);
}
return accretion_density;
}
// This controls accretion of velocity to the sink particle.
Vector
sink_accretion_velocity(int3 globalVertexIdx, in VectorField uu, Scalar dt) {
const Vector grid_pos = (Vector){(globalVertexIdx.x - DCONST(AC_nx_min)) * AC_dsx,
(globalVertexIdx.y - DCONST(AC_ny_min)) * AC_dsy,
(globalVertexIdx.z - DCONST(AC_nz_min)) * AC_dsz};
const Vector sink_pos = (Vector){AC_sink_pos_x,
AC_sink_pos_y,
AC_sink_pos_z};
const Scalar profile_range = AC_accretion_range;
const Scalar accretion_distance = length(grid_pos - sink_pos);
int accretion_switch = AC_switch_accretion;
Vector accretion_velocity;
if (accretion_switch == 1){
Scalar weight;
// Step function weighting
// Arch of a cosine function?
// Cubic spline x^3 - x in range [-0.5 , 0.5]
if ((accretion_distance) <= profile_range){
//weight = Scalar(1.0);
//Hann window function
Scalar window_ratio = accretion_distance/profile_range;
weight = Scalar(0.5)*(Scalar(1.0) - cos(Scalar(2.0)*M_PI*window_ratio));
} else {
weight = Scalar(0.0);
}
Vector rate;
// MV: Could we use divergence here ephasize velocitie which are compressive and
// MV: not absorbins stuff that would not be accreted anyway?
if (length(value(uu)) > Scalar(0.0)) {
rate = (Scalar(1.0)/dt) * value(uu);
} else {
rate = (Vector){0.0, 0.0, 0.0};
}
accretion_velocity = weight * rate ;
} else {
accretion_velocity = (Vector){0.0, 0.0, 0.0};
}
return accretion_velocity;
}
#endif
Scalar
continuity(int3 globalVertexIdx, in VectorField uu, in ScalarField lnrho, Scalar dt)
{
return -dot(value(uu), gradient(lnrho))
#if LUPWD
// This is a corrective hyperdiffusion term for upwinding.
+ upwd_der6(uu, lnrho)
#endif
#if LSINK
- sink_accretion(globalVertexIdx, lnrho, dt) / exp(value(lnrho))
#endif
- divergence(uu);
}
#if LENTROPY
Vector
momentum(int3 globalVertexIdx, in VectorField uu, in ScalarField lnrho, in ScalarField ss, in VectorField aa, Scalar dt)
{
const Matrix S = stress_tensor(uu);
const Scalar cs2 = AC_cs2_sound * exp(AC_gamma * value(ss) / AC_cp_sound +
(AC_gamma - 1) * (value(lnrho) - AC_lnrho0));
const Vector j = (Scalar(1.0) / AC_mu0) *
(gradient_of_divergence(aa) - laplace_vec(aa)); // Current density
const Vector B = curl(aa);
// TODO: DOES INTHERMAL VERSTION INCLUDE THE MAGNETIC FIELD?
const Scalar inv_rho = Scalar(1.0) / exp(value(lnrho));
// Regex replace CPU constants with get\(AC_([a-zA-Z_0-9]*)\)
// \1
const Vector mom = -mul(gradients(uu), value(uu)) -
cs2 * ((Scalar(1.0) / AC_cp_sound) * gradient(ss) + gradient(lnrho)) +
inv_rho * cross(j, B) +
AC_nu_visc *
(laplace_vec(uu) + Scalar(1.0 / 3.0) * gradient_of_divergence(uu) +
Scalar(2.0) * mul(S, gradient(lnrho))) +
AC_zeta * gradient_of_divergence(uu)
#if LSINK
//Gravity term
+ sink_gravity(globalVertexIdx)
//Corresponding loss of momentum
- //(Scalar(1.0) / Scalar( (AC_dsx*AC_dsy*AC_dsz) * exp(value(lnrho)))) * // Correction factor by unit mass
sink_accretion_velocity(globalVertexIdx, uu, dt) // As in Lee et al.(2014)
;
#else
;
#endif
return mom;
}
#elif LTEMPERATURE
Vector
momentum(int3 globalVertexIdx, in VectorField uu, in ScalarField lnrho, in ScalarField tt)
{
Vector mom;
const Matrix S = stress_tensor(uu);
const Vector pressure_term = (AC_cp_sound - AC_cv_sound) *
(gradient(tt) + value(tt) * gradient(lnrho));
mom = -mul(gradients(uu), value(uu)) - pressure_term +
AC_nu_visc * (laplace_vec(uu) + Scalar(1.0 / 3.0) * gradient_of_divergence(uu) +
Scalar(2.0) * mul(S, gradient(lnrho))) +
AC_zeta * gradient_of_divergence(uu)
#if LSINK
+ sink_gravity(globalVertexIdx);
#else
;
#endif
#if LGRAVITY
mom = mom - (Vector){0, 0, -10.0};
#endif
return mom;
}
#else
Vector
momentum(int3 globalVertexIdx, in VectorField uu, in ScalarField lnrho, Scalar dt)
{
Vector mom;
const Matrix S = stress_tensor(uu);
// Isothermal: we have constant speed of sound
mom = -mul(gradients(uu), value(uu)) - AC_cs2_sound * gradient(lnrho) +
AC_nu_visc * (laplace_vec(uu) + Scalar(1.0 / 3.0) * gradient_of_divergence(uu) +
Scalar(2.0) * mul(S, gradient(lnrho))) +
AC_zeta * gradient_of_divergence(uu)
#if LSINK
+ sink_gravity(globalVertexIdx)
//Corresponding loss of momentum
- //(Scalar(1.0) / Scalar( (AC_dsx*AC_dsy*AC_dsz) * exp(value(lnrho)))) * // Correction factor by unit mass
sink_accretion_velocity(globalVertexIdx, uu, dt) // As in Lee et al.(2014)
;
#else
;
#endif
#if LGRAVITY
mom = mom - (Vector){0, 0, -10.0};
#endif
return mom;
}
#endif
Vector
induction(in VectorField uu, in VectorField aa)
{
// Note: We do (-nabla^2 A + nabla(nabla dot A)) instead of (nabla x (nabla
// x A)) in order to avoid taking the first derivative twice (did the math,
// yes this actually works. See pg.28 in arXiv:astro-ph/0109497)
// u cross B - AC_eta * AC_mu0 * (AC_mu0^-1 * [- laplace A + grad div A ])
const Vector B = curl(aa);
const Vector grad_div = gradient_of_divergence(aa);
const Vector lap = laplace_vec(aa);
// Note, AC_mu0 is cancelled out
const Vector ind = cross(value(uu), B) - AC_eta * (grad_div - lap);
return ind;
}
#if LENTROPY
Scalar
lnT(in ScalarField ss, in ScalarField lnrho)
{
const Scalar lnT = AC_lnT0 + AC_gamma * value(ss) / AC_cp_sound +
(AC_gamma - Scalar(1.0)) * (value(lnrho) - AC_lnrho0);
return lnT;
}
// Nabla dot (K nabla T) / (rho T)
Scalar
heat_conduction(in ScalarField ss, in ScalarField lnrho)
{
const Scalar inv_AC_cp_sound = AcReal(1.0) / AC_cp_sound;
const Vector grad_ln_chi = -gradient(lnrho);
const Scalar first_term = AC_gamma * inv_AC_cp_sound * laplace(ss) +
(AC_gamma - AcReal(1.0)) * laplace(lnrho);
const Vector second_term = AC_gamma * inv_AC_cp_sound * gradient(ss) +
(AC_gamma - AcReal(1.0)) * gradient(lnrho);
const Vector third_term = AC_gamma * (inv_AC_cp_sound * gradient(ss) + gradient(lnrho)) +
grad_ln_chi;
const Scalar chi = AC_THERMAL_CONDUCTIVITY / (exp(value(lnrho)) * AC_cp_sound);
return AC_cp_sound * chi * (first_term + dot(second_term, third_term));
}
Scalar
heating(const int i, const int j, const int k)
{
return 1;
}
Scalar
entropy(in ScalarField ss, in VectorField uu, in ScalarField lnrho, in VectorField aa)
{
const Matrix S = stress_tensor(uu);
const Scalar inv_pT = Scalar(1.0) / (exp(value(lnrho)) * exp(lnT(ss, lnrho)));
const Vector j = (Scalar(1.0) / AC_mu0) *
(gradient_of_divergence(aa) - laplace_vec(aa)); // Current density
const Scalar RHS = H_CONST - C_CONST + AC_eta * (AC_mu0)*dot(j, j) +
Scalar(2.0) * exp(value(lnrho)) * AC_nu_visc * contract(S) +
AC_zeta * exp(value(lnrho)) * divergence(uu) * divergence(uu);
return -dot(value(uu), gradient(ss)) + inv_pT * RHS + heat_conduction(ss, lnrho);
}
#endif
#if LTEMPERATURE
Scalar
heat_transfer(in VectorField uu, in ScalarField lnrho, in ScalarField tt)
{
const Matrix S = stress_tensor(uu);
const Scalar heat_diffusivity_k = 0.0008; // 8e-4;
return -dot(value(uu), gradient(tt)) + heat_diffusivity_k * laplace(tt) +
heat_diffusivity_k * dot(gradient(lnrho), gradient(tt)) +
AC_nu_visc * contract(S) * (Scalar(1.0) / AC_cv_sound) -
(AC_gamma - 1) * value(tt) * divergence(uu);
}
#endif
#if LFORCING
Vector
simple_vortex_forcing(Vector a, Vector b, Scalar magnitude){
int accretion_switch = AC_switch_accretion;
if (accretion_switch == 0){
return magnitude * cross(normalized(b - a), (Vector){ 0, 0, 1}); // Vortex
} else {
return (Vector){0,0,0};
}
}
Vector
simple_outward_flow_forcing(Vector a, Vector b, Scalar magnitude){
int accretion_switch = AC_switch_accretion;
if (accretion_switch == 0){
return magnitude * (1 / length(b - a)) * normalized(b - a); // Outward flow
} else {
return (Vector){0,0,0};
}
}
// The Pencil Code forcing_hel_noshear(), manual Eq. 222, inspired forcing function with adjustable
// helicity
Vector
helical_forcing(Scalar magnitude, Vector k_force, Vector xx, Vector ff_re, Vector ff_im, Scalar phi)
{
// JP: This looks wrong:
// 1) Should it be AC_dsx * AC_nx instead of AC_dsx * AC_ny?
// 2) Should you also use globalGrid.n instead of the local n?
// MV: You are rigth. Made a quickfix. I did not see the error because multigpu is split
// in z direction not y direction.
// 3) Also final point: can we do this with vectors/quaternions instead?
// Tringonometric functions are much more expensive and inaccurate/
// MV: Good idea. No an immediate priority.
// Fun related article:
// https://randomascii.wordpress.com/2014/10/09/intel-underestimates-error-bounds-by-1-3-quintillion/
xx.x = xx.x * (2.0 * M_PI / (AC_dsx * globalGridN.x));
xx.y = xx.y * (2.0 * M_PI / (AC_dsy * globalGridN.y));
xx.z = xx.z * (2.0 * M_PI / (AC_dsz * globalGridN.z));
Scalar cos_phi = cos(phi);
Scalar sin_phi = sin(phi);
Scalar cos_k_dot_x = cos(dot(k_force, xx));
Scalar sin_k_dot_x = sin(dot(k_force, xx));
// Phase affect only the x-component
// Scalar real_comp = cos_k_dot_x;
// Scalar imag_comp = sin_k_dot_x;
Scalar real_comp_phase = cos_k_dot_x * cos_phi - sin_k_dot_x * sin_phi;
Scalar imag_comp_phase = cos_k_dot_x * sin_phi + sin_k_dot_x * cos_phi;
Vector force = (Vector){ff_re.x * real_comp_phase - ff_im.x * imag_comp_phase,
ff_re.y * real_comp_phase - ff_im.y * imag_comp_phase,
ff_re.z * real_comp_phase - ff_im.z * imag_comp_phase};
return force;
}
Vector
forcing(int3 globalVertexIdx, Scalar dt)
{
int accretion_switch = AC_switch_accretion;
if (accretion_switch == 0){
Vector a = Scalar(0.5) * (Vector){globalGridN.x * AC_dsx,
globalGridN.y * AC_dsy,
globalGridN.z * AC_dsz}; // source (origin)
Vector xx = (Vector){(globalVertexIdx.x - DCONST(AC_nx_min)) * AC_dsx,
(globalVertexIdx.y - DCONST(AC_ny_min)) * AC_dsy,
(globalVertexIdx.z - DCONST(AC_nz_min)) * AC_dsz}; // sink (current index)
const Scalar cs2 = AC_cs2_sound;
const Scalar cs = sqrt(cs2);
//Placeholders until determined properly
Scalar magnitude = AC_forcing_magnitude;
Scalar phase = AC_forcing_phase;
Vector k_force = (Vector){AC_k_forcex, AC_k_forcey, AC_k_forcez};
Vector ff_re = (Vector){AC_ff_hel_rex, AC_ff_hel_rey, AC_ff_hel_rez};
Vector ff_im = (Vector){AC_ff_hel_imx, AC_ff_hel_imy, AC_ff_hel_imz};
//Determine that forcing funtion type at this point.
//Vector force = simple_vortex_forcing(a, xx, magnitude);
//Vector force = simple_outward_flow_forcing(a, xx, magnitude);
Vector force = helical_forcing(magnitude, k_force, xx, ff_re,ff_im, phase);
//Scaling N = magnitude*cs*sqrt(k*cs/dt) * dt
const Scalar NN = cs*sqrt(AC_kaver*cs);
//MV: Like in the Pencil Code. I don't understandf the logic here.
force.x = sqrt(dt)*NN*force.x;
force.y = sqrt(dt)*NN*force.y;
force.z = sqrt(dt)*NN*force.z;
if (is_valid(force)) { return force; }
else { return (Vector){0, 0, 0}; }
} else {
return (Vector){0,0,0};
}
}
#endif // LFORCING
// Declare input and output arrays using locations specified in the
// array enum in astaroth.h
in ScalarField lnrho(VTXBUF_LNRHO);
out ScalarField out_lnrho(VTXBUF_LNRHO);
in VectorField uu(VTXBUF_UUX, VTXBUF_UUY, VTXBUF_UUZ);
out VectorField out_uu(VTXBUF_UUX, VTXBUF_UUY, VTXBUF_UUZ);
#if LMAGNETIC
in VectorField aa(VTXBUF_AX, VTXBUF_AY, VTXBUF_AZ);
out VectorField out_aa(VTXBUF_AX, VTXBUF_AY, VTXBUF_AZ);
#endif
#if LENTROPY
in ScalarField ss(VTXBUF_ENTROPY);
out ScalarField out_ss(VTXBUF_ENTROPY);
#endif
#if LTEMPERATURE
in ScalarField tt(VTXBUF_TEMPERATURE);
out ScalarField out_tt(VTXBUF_TEMPERATURE);
#endif
#if LSINK
in ScalarField accretion(VTXBUF_ACCRETION);
out ScalarField out_accretion(VTXBUF_ACCRETION);
#endif
Kernel void
solve()
{
Scalar dt = AC_dt;
out_lnrho = rk3(out_lnrho, lnrho, continuity(globalVertexIdx, uu, lnrho, dt), dt);
#if LMAGNETIC
out_aa = rk3(out_aa, aa, induction(uu, aa), dt);
#endif
#if LENTROPY
out_uu = rk3(out_uu, uu, momentum(globalVertexIdx, uu, lnrho, ss, aa, dt), dt);
out_ss = rk3(out_ss, ss, entropy(ss, uu, lnrho, aa), dt);
#elif LTEMPERATURE
out_uu = rk3(out_uu, uu, momentum(globalVertexIdx, uu, lnrho, tt, dt), dt);
out_tt = rk3(out_tt, tt, heat_transfer(uu, lnrho, tt), dt);
#else
out_uu = rk3(out_uu, uu, momentum(globalVertexIdx, uu, lnrho, dt), dt);
#endif
#if LFORCING
if (step_number == 2) {
out_uu = out_uu + forcing(globalVertexIdx, dt);
}
#endif
#if LSINK
out_accretion = rk3(out_accretion, accretion, sink_accretion(globalVertexIdx, lnrho, dt), dt);// unit now is rho!
if (step_number == 2) {
out_accretion = out_accretion * AC_dsx * AC_dsy * AC_dsz;// unit is now mass!
}
#endif
}

2
acc/src/code_generator.c
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

705
acc/src/code_generator0.c
View File

@@ -1,705 +0,0 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
This file is part of Astaroth.
Astaroth is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Astaroth is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with Astaroth. If not, see <http://www.gnu.org/licenses/>.
*/
/**
* @file
* \brief Brief info.
*
* Detailed info.
*
*/
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "acc.tab.h"
#include "ast.h"
ASTNode* root = NULL;
static const char inout_name_prefix[] = "handle_";
typedef enum { STENCIL_ASSEMBLY, STENCIL_PROCESS, STENCIL_HEADER } CompilationType;
static CompilationType compilation_type;
/*
* =============================================================================
* Translation
* =============================================================================
*/
#define TRANSLATION_TABLE_SIZE (1024)
static const char* translation_table[TRANSLATION_TABLE_SIZE] = {
[0] = NULL,
// Control flow
[IF] = "if",
[ELSE] = "else",
[ELIF] = "else if",
[WHILE] = "while",
[FOR] = "for",
// Type specifiers
[VOID] = "void",
[INT] = "int",
[INT3] = "int3",
[SCALAR] = "AcReal",
[VECTOR] = "AcReal3",
[MATRIX] = "AcMatrix",
[SCALARFIELD] = "AcReal",
[SCALARARRAY] = "const AcReal* __restrict__",
[COMPLEX] = "acComplex",
// Type qualifiers
[KERNEL] = "template <int step_number> static __global__",
//__launch_bounds__(RK_THREADBLOCK_SIZE,
// RK_LAUNCH_BOUND_MIN_BLOCKS),
[PREPROCESSED] = "static __device__ "
"__forceinline__",
[CONSTANT] = "const",
[IN] = "in",
[OUT] = "out",
[UNIFORM] = "uniform",
// ETC
[INPLACE_INC] = "++",
[INPLACE_DEC] = "--",
// Unary
[','] = ",",
[';'] = ";\n",
['('] = "(",
[')'] = ")",
['['] = "[",
[']'] = "]",
['{'] = "{\n",
['}'] = "}\n",
['='] = "=",
['+'] = "+",
['-'] = "-",
['/'] = "/",
['*'] = "*",
['<'] = "<",
['>'] = ">",
['!'] = "!",
['.'] = "."};
static const char*
translate(const int token)
{
assert(token >= 0);
assert(token < TRANSLATION_TABLE_SIZE);
if (token > 0) {
if (!translation_table[token])
printf("ERROR: unidentified token %d\n", token);
assert(translation_table[token]);
}
return translation_table[token];
}
/*
* =============================================================================
* Symbols
* =============================================================================
*/
typedef enum {
SYMBOLTYPE_FUNCTION,
SYMBOLTYPE_FUNCTION_PARAMETER,
SYMBOLTYPE_OTHER,
NUM_SYMBOLTYPES
} SymbolType;
#define MAX_ID_LEN (128)
typedef struct {
SymbolType type;
int type_qualifier;
int type_specifier;
char identifier[MAX_ID_LEN];
} Symbol;
#define SYMBOL_TABLE_SIZE (4096)
static Symbol symbol_table[SYMBOL_TABLE_SIZE] = {};
static int num_symbols = 0;
static int
symboltable_lookup(const char* identifier)
{
if (!identifier)
return -1;
for (int i = 0; i < num_symbols; ++i)
if (strcmp(identifier, symbol_table[i].identifier) == 0)
return i;
return -1;
}
static void
add_symbol(const SymbolType type, const int tqualifier, const int tspecifier, const char* id)
{
assert(num_symbols < SYMBOL_TABLE_SIZE);
symbol_table[num_symbols].type = type;
symbol_table[num_symbols].type_qualifier = tqualifier;
symbol_table[num_symbols].type_specifier = tspecifier;
strcpy(symbol_table[num_symbols].identifier, id);
++num_symbols;
}
static void
rm_symbol(const int handle)
{
assert(handle >= 0 && handle < num_symbols);
assert(num_symbols > 0);
if (&symbol_table[handle] != &symbol_table[num_symbols - 1])
memcpy(&symbol_table[handle], &symbol_table[num_symbols - 1], sizeof(Symbol));
--num_symbols;
}
static void
print_symbol(const int handle)
{
assert(handle < SYMBOL_TABLE_SIZE);
const char* fields[] = {translate(symbol_table[handle].type_qualifier),
translate(symbol_table[handle].type_specifier),
symbol_table[handle].identifier};
const size_t num_fields = sizeof(fields) / sizeof(fields[0]);
for (size_t i = 0; i < num_fields; ++i)
if (fields[i])
printf("%s ", fields[i]);
}
static void
translate_latest_symbol(void)
{
const int handle = num_symbols - 1;
assert(handle < SYMBOL_TABLE_SIZE);
Symbol* symbol = &symbol_table[handle];
// FUNCTION
if (symbol->type == SYMBOLTYPE_FUNCTION) {
// KERNEL FUNCTION
if (symbol->type_qualifier == KERNEL) {
printf("%s %s\n%s", translate(symbol->type_qualifier),
translate(symbol->type_specifier), symbol->identifier);
}
// PREPROCESSED FUNCTION
else if (symbol->type_qualifier == PREPROCESSED) {
printf("%s %s\npreprocessed_%s", translate(symbol->type_qualifier),
translate(symbol->type_specifier), symbol->identifier);
}
// OTHER FUNCTION
else {
const char* regular_function_decorator = "static __device__ "
"__forceinline__";
printf("%s %s %s\n%s", regular_function_decorator,
translate(symbol->type_qualifier) ? translate(symbol->type_qualifier) : "",
translate(symbol->type_specifier), symbol->identifier);
}
}
// FUNCTION PARAMETER
else if (symbol->type == SYMBOLTYPE_FUNCTION_PARAMETER) {
if (symbol->type_qualifier == IN || symbol->type_qualifier == OUT) {
if (compilation_type == STENCIL_ASSEMBLY)
printf("const __restrict__ %s* %s", translate(symbol->type_specifier),
symbol->identifier);
else if (compilation_type == STENCIL_PROCESS)
printf("const %sData& %s", translate(symbol->type_specifier), symbol->identifier);
else
printf("Invalid compilation type %d, IN and OUT qualifiers not supported\n",
compilation_type);
}
else {
print_symbol(handle);
}
}
// UNIFORM
else if (symbol->type_qualifier == UNIFORM) {
// if (compilation_type != STENCIL_HEADER) {
// printf("ERROR: %s can only be used in stencil headers\n", translation_table[UNIFORM]);
//}
/* Do nothing */
}
// IN / OUT
else if (symbol->type != SYMBOLTYPE_FUNCTION_PARAMETER &&
(symbol->type_qualifier == IN || symbol->type_qualifier == OUT)) {
printf("static __device__ const %s %s%s",
symbol->type_specifier == SCALARFIELD ? "int" : "int3", inout_name_prefix,
symbol_table[handle].identifier);
if (symbol->type_specifier == VECTOR)
printf(" = make_int3");
}
// OTHER
else {
print_symbol(handle);
}
}
static inline void
print_symbol_table(void)
{
for (int i = 0; i < num_symbols; ++i) {
printf("%d: ", i);
const char* fields[] = {translate(symbol_table[i].type_qualifier),
translate(symbol_table[i].type_specifier),
symbol_table[i].identifier};
const size_t num_fields = sizeof(fields) / sizeof(fields[0]);
for (size_t j = 0; j < num_fields; ++j)
if (fields[j])
printf("%s ", fields[j]);
if (symbol_table[i].type == SYMBOLTYPE_FUNCTION)
printf("(function)");
else if (symbol_table[i].type == SYMBOLTYPE_FUNCTION_PARAMETER)
printf("(function parameter)");
else
printf("(other)");
printf("\n");
}
}
/*
* =============================================================================
* State
* =============================================================================
*/
static bool inside_declaration = false;
static bool inside_function_declaration = false;
static bool inside_function_parameter_declaration = false;
static bool inside_kernel = false;
static bool inside_preprocessed = false;
static int scope_start = 0;
/*
* =============================================================================
* AST traversal
* =============================================================================
*/
static int compound_statement_nests = 0;
static void
traverse(const ASTNode* node)
{
// Prefix logic %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
if (node->type == NODE_FUNCTION_DECLARATION)
inside_function_declaration = true;
if (node->type == NODE_FUNCTION_PARAMETER_DECLARATION)
inside_function_parameter_declaration = true;
if (node->type == NODE_DECLARATION)
inside_declaration = true;
if (!inside_declaration && translate(node->prefix))
printf("%s", translate(node->prefix));
if (node->type == NODE_COMPOUND_STATEMENT)
++compound_statement_nests;
// BOILERPLATE START////////////////////////////////////////////////////////
if (node->type == NODE_TYPE_QUALIFIER && node->token == KERNEL)
inside_kernel = true;
// Kernel parameter boilerplate
const char* kernel_parameter_boilerplate = "GEN_KERNEL_PARAM_BOILERPLATE";
if (inside_kernel && node->type == NODE_FUNCTION_PARAMETER_DECLARATION) {
printf("%s", kernel_parameter_boilerplate);
if (node->lhs != NULL) {
printf("Compilation error: function parameters for Kernel functions not allowed!\n");
exit(EXIT_FAILURE);
}
}
// Kernel builtin variables boilerplate (read input/output arrays and setup
// indices)
const char* kernel_builtin_variables_boilerplate = "GEN_KERNEL_BUILTIN_VARIABLES_"
"BOILERPLATE();";
if (inside_kernel && node->type == NODE_COMPOUND_STATEMENT && compound_statement_nests == 1) {
printf("%s ", kernel_builtin_variables_boilerplate);
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_qualifier == IN) {
printf("const %sData %s = READ(%s%s);\n", translate(symbol_table[i].type_specifier),
symbol_table[i].identifier, inout_name_prefix, symbol_table[i].identifier);
}
else if (symbol_table[i].type_qualifier == OUT) {
printf("%s %s = READ_OUT(%s%s);", translate(symbol_table[i].type_specifier),
symbol_table[i].identifier, inout_name_prefix, symbol_table[i].identifier);
// printf("%s %s = buffer.out[%s%s][IDX(vertexIdx.x, vertexIdx.y, vertexIdx.z)];\n",
// translate(symbol_table[i].type_specifier), symbol_table[i].identifier,
// inout_name_prefix, symbol_table[i].identifier);
}
}
}
// Preprocessed parameter boilerplate
if (node->type == NODE_TYPE_QUALIFIER && node->token == PREPROCESSED)
inside_preprocessed = true;
static const char preprocessed_parameter_boilerplate
[] = "const int3& vertexIdx, const int3& globalVertexIdx, ";
if (inside_preprocessed && node->type == NODE_FUNCTION_PARAMETER_DECLARATION)
printf("%s ", preprocessed_parameter_boilerplate);
// BOILERPLATE END////////////////////////////////////////////////////////
// Enter LHS
if (node->lhs)
traverse(node->lhs);
// Infix logic %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
if (!inside_declaration && translate(node->infix))
printf("%s ", translate(node->infix));
if (node->type == NODE_FUNCTION_DECLARATION)
inside_function_declaration = false;
// If the node is a subscript expression and the expression list inside it is not empty
if (node->type == NODE_MULTIDIM_SUBSCRIPT_EXPRESSION && node->rhs)
printf("IDX(");
// Do a regular translation
if (!inside_declaration) {
const int handle = symboltable_lookup(node->buffer);
if (handle >= 0) { // The variable exists in the symbol table
const Symbol* symbol = &symbol_table[handle];
if (symbol->type_qualifier == UNIFORM) {
if (inside_kernel && symbol->type_specifier == SCALARARRAY) {
printf("buffer.profiles[%s] ", symbol->identifier);
}
else {
printf("DCONST(%s) ", symbol->identifier);
}
}
else {
// Do a regular translation
if (translate(node->token))
printf("%s ", translate(node->token));
if (node->buffer) {
if (node->type == NODE_REAL_NUMBER) {
printf("%s(%s) ", translate(SCALAR),
node->buffer); // Cast to correct precision
}
else {
printf("%s ", node->buffer);
}
}
}
}
else {
// Do a regular translation
if (translate(node->token))
printf("%s ", translate(node->token));
if (node->buffer) {
if (node->type == NODE_REAL_NUMBER) {
printf("%s(%s) ", translate(SCALAR), node->buffer); // Cast to correct precision
}
else {
printf("%s ", node->buffer);
}
}
}
}
if (node->type == NODE_FUNCTION_DECLARATION) {
scope_start = num_symbols;
}
// Enter RHS
if (node->rhs)
traverse(node->rhs);
// Postfix logic %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
// If the node is a subscript expression and the expression list inside it is not empty
if (node->type == NODE_MULTIDIM_SUBSCRIPT_EXPRESSION && node->rhs)
printf(")"); // Closing bracket of IDX()
// Generate writeback boilerplate for OUT fields
if (inside_kernel && node->type == NODE_COMPOUND_STATEMENT && compound_statement_nests == 1) {
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_qualifier == OUT) {
printf("WRITE_OUT(%s%s, %s);\n", inout_name_prefix, symbol_table[i].identifier,
symbol_table[i].identifier);
// printf("buffer.out[%s%s][IDX(vertexIdx.x, vertexIdx.y, vertexIdx.z)] = %s;\n",
// inout_name_prefix, symbol_table[i].identifier, symbol_table[i].identifier);
}
}
}
if (!inside_declaration && translate(node->postfix))
printf("%s", translate(node->postfix));
if (node->type == NODE_DECLARATION) {
inside_declaration = false;
int tqual = 0;
int tspec = 0;
if (node->lhs && node->lhs->lhs) {
if (node->lhs->lhs->type == NODE_TYPE_QUALIFIER)
tqual = node->lhs->lhs->token;
else if (node->lhs->lhs->type == NODE_TYPE_SPECIFIER)
tspec = node->lhs->lhs->token;
}
if (node->lhs && node->lhs->rhs) {
if (node->lhs->rhs->type == NODE_TYPE_SPECIFIER)
tspec = node->lhs->rhs->token;
}
// Determine symbol type
SymbolType symboltype = SYMBOLTYPE_OTHER;
if (inside_function_declaration)
symboltype = SYMBOLTYPE_FUNCTION;
else if (inside_function_parameter_declaration)
symboltype = SYMBOLTYPE_FUNCTION_PARAMETER;
// Determine identifier
if (node->rhs->type == NODE_IDENTIFIER) {
add_symbol(symboltype, tqual, tspec, node->rhs->buffer); // Ordinary
translate_latest_symbol();
}
else {
add_symbol(symboltype, tqual, tspec,
node->rhs->lhs->buffer); // Array
translate_latest_symbol();
// Traverse the expression once again, this time with
// "inside_declaration" flag off
printf("%s ", translate(node->rhs->infix));
if (node->rhs->rhs)
traverse(node->rhs->rhs);
printf("%s ", translate(node->rhs->postfix));
}
}
if (node->type == NODE_COMPOUND_STATEMENT)
--compound_statement_nests;
if (node->type == NODE_FUNCTION_PARAMETER_DECLARATION)
inside_function_parameter_declaration = false;
if (node->type == NODE_FUNCTION_DEFINITION) {
while (num_symbols > scope_start)
rm_symbol(num_symbols - 1);
inside_kernel = false;
inside_preprocessed = false;
}
}
// TODO: these should use the generic type names SCALAR and VECTOR
static void
generate_preprocessed_structures(void)
{
// PREPROCESSED DATA STRUCT
printf("\n");
printf("typedef struct {\n");
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_qualifier == PREPROCESSED)
printf("%s %s;\n", translate(symbol_table[i].type_specifier),
symbol_table[i].identifier);
}
printf("} %sData;\n", translate(SCALAR));
// FILLING THE DATA STRUCT
printf("static __device__ __forceinline__ AcRealData\
read_data(const int3& vertexIdx,\
const int3& globalVertexIdx,\
AcReal* __restrict__ buf[], const int handle)\
{\n\
%sData data;\n",
translate(SCALAR));
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_qualifier == PREPROCESSED)
printf("data.%s = preprocessed_%s(vertexIdx, globalVertexIdx, buf[handle]);\n",
symbol_table[i].identifier, symbol_table[i].identifier);
}
printf("return data;\n");
printf("}\n");
// FUNCTIONS FOR ACCESSING MEMBERS OF THE PREPROCESSED STRUCT
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_qualifier == PREPROCESSED)
printf("static __device__ __forceinline__ %s\
%s(const AcRealData& data)\
{\n\
return data.%s;\
}\n",
translate(symbol_table[i].type_specifier), symbol_table[i].identifier,
symbol_table[i].identifier);
}
// Syntactic sugar: generate also a Vector data struct
printf("\
typedef struct {\
AcRealData x;\
AcRealData y;\
AcRealData z;\
} AcReal3Data;\
\
static __device__ __forceinline__ AcReal3Data\
read_data(const int3& vertexIdx,\
const int3& globalVertexIdx,\
AcReal* __restrict__ buf[], const int3& handle)\
{\
AcReal3Data data;\
\
data.x = read_data(vertexIdx, globalVertexIdx, buf, handle.x);\
data.y = read_data(vertexIdx, globalVertexIdx, buf, handle.y);\
data.z = read_data(vertexIdx, globalVertexIdx, buf, handle.z);\
\
return data;\
}\
");
}
static void
generate_header(void)
{
printf("\n#pragma once\n");
// Int params
printf("#define AC_FOR_USER_INT_PARAM_TYPES(FUNC)");
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_specifier == INT) {
printf("\\\nFUNC(%s),", symbol_table[i].identifier);
}
}
printf("\n\n");
// Int3 params
printf("#define AC_FOR_USER_INT3_PARAM_TYPES(FUNC)");
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_specifier == INT3) {
printf("\\\nFUNC(%s),", symbol_table[i].identifier);
}
}
printf("\n\n");
// Scalar params
printf("#define AC_FOR_USER_REAL_PARAM_TYPES(FUNC)");
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_specifier == SCALAR) {
printf("\\\nFUNC(%s),", symbol_table[i].identifier);
}
}
printf("\n\n");
// Vector params
printf("#define AC_FOR_USER_REAL3_PARAM_TYPES(FUNC)");
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_specifier == VECTOR) {
printf("\\\nFUNC(%s),", symbol_table[i].identifier);
}
}
printf("\n\n");
// Scalar fields
printf("#define AC_FOR_VTXBUF_HANDLES(FUNC)");
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_specifier == SCALARFIELD) {
printf("\\\nFUNC(%s),", symbol_table[i].identifier);
}
}
printf("\n\n");
// Scalar arrays
printf("#define AC_FOR_SCALARARRAY_HANDLES(FUNC)");
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_specifier == SCALARARRAY) {
printf("\\\nFUNC(%s),", symbol_table[i].identifier);
}
}
printf("\n\n");
/*
printf("\n");
printf("typedef struct {\n");
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_qualifier == PREPROCESSED)
printf("%s %s;\n", translate(symbol_table[i].type_specifier),
symbol_table[i].identifier);
}
printf("} %sData;\n", translate(SCALAR));
*/
}
static void
generate_library_hooks(void)
{
for (int i = 0; i < num_symbols; ++i) {
if (symbol_table[i].type_qualifier == KERNEL) {
printf("GEN_DEVICE_FUNC_HOOK(%s)\n", symbol_table[i].identifier);
// printf("GEN_NODE_FUNC_HOOK(%s)\n", symbol_table[i].identifier);
}
}
}
int
main(int argc, char** argv)
{
if (argc == 2) {
if (!strcmp(argv[1], "-sas"))
compilation_type = STENCIL_ASSEMBLY;
else if (!strcmp(argv[1], "-sps"))
compilation_type = STENCIL_PROCESS;
else if (!strcmp(argv[1], "-sdh"))
compilation_type = STENCIL_HEADER;
else {
printf("Unknown flag %s. Generating stencil assembly.\n", argv[1]);
return EXIT_FAILURE;
}
}
else {
printf("Usage: ./acc [flags]\n"
"Flags:\n"
"\t-sas - Generates code for the stencil assembly stage\n"
"\t-sps - Generates code for the stencil processing stage\n"
"\t-hh - Generates stencil definitions from a header file\n");
printf("\n");
return EXIT_FAILURE;
}
root = astnode_create(NODE_UNKNOWN, NULL, NULL);
const int retval = yyparse();
if (retval) {
printf("COMPILATION FAILED\n");
return EXIT_FAILURE;
}
// Traverse
traverse(root);
if (compilation_type == STENCIL_ASSEMBLY)
generate_preprocessed_structures();
else if (compilation_type == STENCIL_HEADER)
generate_header();
else if (compilation_type == STENCIL_PROCESS)
generate_library_hooks();
// print_symbol_table();
// Cleanup
astnode_destroy(root);
// printf("COMPILATION SUCCESS\n");
return EXIT_SUCCESS;
}

48
acc/test_grammar.sh
View File

@@ -1,48 +0,0 @@
#!/bin/bash
cd `dirname $0` # Only operate in the same directory with this script
./build_acc.sh
mkdir -p testbin
./compile.sh samples/sample_stencil_process.sps
./compile.sh samples/sample_stencil_assembly.sas
mv stencil_process.cuh testbin/
mv stencil_assembly.cuh testbin/
printf "
#include <stdio.h>
#include <stdlib.h>
#include \"%s\" // i.e. astaroth.h
__constant__ AcMeshInfo d_mesh_info;
#define DCONST(X) (d_mesh_info.int_params[X])
#define DCONST_REAL(X) (d_mesh_info.real_params[X])
#define DEVICE_VTXBUF_IDX(i, j, k) ((i) + (j)*DCONST(AC_mx) + (k)*DCONST(AC_mxy))
static __device__ __forceinline__ int
IDX(const int i)
{
return i;
}
static __device__ __forceinline__ int
IDX(const int i, const int j, const int k)
{
return DEVICE_VTXBUF_IDX(i, j, k);
}
static __device__ __forceinline__ int
IDX(const int3 idx)
{
return DEVICE_VTXBUF_IDX(idx.x, idx.y, idx.z);
}
#include \"%s\"
#include \"%s\"
int main(void) { printf(\"Grammar check complete.\\\nAll tests passed.\\\n\"); return EXIT_SUCCESS; }
" common_header.h stencil_assembly.cuh stencil_process.cuh >testbin/test.cu
cd testbin
nvcc -std=c++11 test.cu -I ../samples -o test && ./test

36
acc/test_solver/stencil_assembly.sas
View File

@@ -1,36 +0,0 @@
#include "stencil_definition.sdh"
//JP NOTE IMPORTANT/////////////////////////////////////////////////////////////////////////////////
// These functions are defined here temporarily.
//
// Currently the built-in functions (derx, derxx etc) are defined in CUDA in integrate.cuh.
// This is bad. Instead the built-in functions should be defined in the DSL, and be "includable"
// as a standard DSL library, analogous to f.ex. stdlib.h in C.
////////////////////////////////////////////////////////////////////////////////////////////////////
Preprocessed Scalar
value(in ScalarField vertex)
{
return vertex[vertexIdx];
}
Preprocessed Vector
gradient(in ScalarField vertex)
{
return (Vector){derx(vertexIdx, vertex), dery(vertexIdx, vertex), derz(vertexIdx, vertex)};
}
Preprocessed Matrix
hessian(in ScalarField vertex)
{
Matrix hessian;
hessian.row[0] = (Vector){derxx(vertexIdx, vertex), derxy(vertexIdx, vertex),
derxz(vertexIdx, vertex)};
hessian.row[1] = (Vector){hessian.row[0].y, deryy(vertexIdx, vertex), deryz(vertexIdx, vertex)};
hessian.row[2] = (Vector){hessian.row[0].z, hessian.row[1].z, derzz(vertexIdx, vertex)};
return hessian;
}

18
acc/test_solver/stencil_definition.sdh
View File

@@ -1,18 +0,0 @@
//JP NOTE IMPORTANT/////////////////////////////////////////////////////////////////////////////////
// AC_dsx etc are defined here temporarily (otherwise does not compile).
//
// These should ultimately be defined in the standard DSL libraries.
// See test_solver/stencil_assembly.sas for more info.
////////////////////////////////////////////////////////////////////////////////////////////////////
uniform Scalar AC_dsx;// TODO include these from the std lib
uniform Scalar AC_dsy;
uniform Scalar AC_dsz;
uniform Scalar AC_inv_dsx;
uniform Scalar AC_inv_dsy;
uniform Scalar AC_inv_dsz;
uniform Scalar AC_dt;
uniform ScalarField VTXBUF_A;
uniform ScalarField VTXBUF_B;
uniform ScalarField VTXBUF_C;

18
acc/test_solver/stencil_process.sps
View File

@@ -1,18 +0,0 @@
#include "stencil_definition.sdh"
Vector
value(in VectorField uu)
{
return (Vector){value(uu.x), value(uu.y), value(uu.z)};
}
in VectorField uu(VTXBUF_A, VTXBUF_B, VTXBUF_C);
out VectorField out_uu(VTXBUF_A, VTXBUF_B, VTXBUF_C);
Kernel void
solve()
{
Scalar dt = AC_dt;
Vector rate_of_change = (Vector){1, 2, 3};
out_uu = rk3(out_uu, uu, rate_of_change, dt);
}

2
analysis/python/astar/__init__.py
View File

@@ -1,5 +1,5 @@
'''
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
analysis/python/astar/data/__init__.py
View File

@@ -1,5 +1,5 @@
'''
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

117
analysis/python/astar/data/read.py
View File

@@ -1,5 +1,5 @@
'''
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -21,6 +21,12 @@
import numpy as np
#Optional YT interface
try:
import yt
yt_present = True
except ImportError:
yt_present = False
def set_dtype(endian, AcRealSize):
if endian == 0:
@@ -55,7 +61,8 @@ def read_bin(fname, fdir, fnum, minfo, numtype=np.longdouble):
return array, timestamp, read_ok
def read_meshtxt(fdir, fname):
def read_meshtxt(fdir, fname, dbg_output):
with open(fdir+fname) as f:
filetext = f.read().splitlines()
@@ -65,30 +72,33 @@ def read_meshtxt(fdir, fname):
line = line.split()
if line[0] == 'int':
contents[line[1]] = np.int(line[2])
print(line[1], contents[line[1]])
if dbg_output:
print(line[1], contents[line[1]])
elif line[0] == 'size_t':
contents[line[1]] = np.int(line[2])
print(line[1], contents[line[1]])
if dbg_output:
print(line[1], contents[line[1]])
elif line[0] == 'int3':
contents[line[1]] = [np.int(line[2]), np.int(line[3]), np.int(line[4])]
print(line[1], contents[line[1]])
if dbg_output:
print(line[1], contents[line[1]])
elif line[0] == 'real':
contents[line[1]] = np.float(line[2])
print(line[1], contents[line[1]])
if dbg_output:
print(line[1], contents[line[1]])
elif line[0] == 'real3':
contents[line[1]] = [np.float(line[2]), np.float(line[3]), np.float(line[4])]
print(line[1], contents[line[1]])
if dbg_output:
print(line[1], contents[line[1]])
else:
print(line)
print('ERROR: ' + line[0] +' not recognized!')
return contents
#Now just 2nd order
def DERX(array, dx):
output = np.zeros_like(array)
for i in range(3, array.shape[0]-3): #Keep boundary poits as 0
#output[i,:,:] = (- array[i-1,:,:] + array[i+1,:,:])/(2.0*dx)
output[i,:,:] =( -45.0*array[i-1,:,:] + 45.0*array[i+1,:,:]
+ 9.0*array[i-2,:,:] - 9.0*array[i+2,:,:]
- array[i-3,:,:] + array[i+3,:,:] )/(60.0*dx)
@@ -97,7 +107,6 @@ def DERX(array, dx):
def DERY(array, dy):
output = np.zeros_like(array)
for i in range(3,array.shape[1]-3):
#output[:,i,:] = (- array[:,i-1,:] + array[:,i+1,:])/(2.0*dy)
output[:,i,:] =( -45.0*array[:,i-1,:] + 45.0*array[:,i+1,:]
+ 9.0*array[:,i-2,:] - 9.0*array[:,i+2,:]
- array[:,i-3,:] + array[:,i+3,:] )/(60.0*dy)
@@ -106,7 +115,6 @@ def DERY(array, dy):
def DERZ(array, dz):
output = np.zeros_like(array)
for i in range(3, array.shape[2]-3):
#output[:,:,i] = (- array[:,:,i-1] + array[:,:,i+1])/(2.0*dz)
output[:,:,i] =( -45.0*array[:,:,i-1] + 45.0*array[:,:,i+1]
+ 9.0*array[:,:,i-2] - 9.0*array[:,:,i+2]
- array[:,:,i-3] + array[:,:,i+3] )/(60.0*dz)
@@ -124,8 +132,8 @@ def curl(aa, minfo):
class MeshInfo():
'''Object that contains all mesh info'''
def __init__(self, fdir):
self.contents = read_meshtxt(fdir, 'mesh_info.list')
def __init__(self, fdir, dbg_output=False):
self.contents = read_meshtxt(fdir, 'mesh_info.list', dbg_output)
class Mesh:
'''Class tha contains all 3d mesh data'''
@@ -176,9 +184,88 @@ class Mesh:
self.xmid = int(self.minfo.contents['AC_mx']/2)
self.ymid = int(self.minfo.contents['AC_my']/2)
self.zmid = int(self.minfo.contents['AC_mz']/2)
def Bfield(self):
def Bfield(self, get_jj = False):
self.bb = curl(self.aa, self.minfo)
print(self.bb[2])
if get_jj:
self.jj = curl(self.bb, self.minfo)
def yt_conversion(self):
if yt_present:
self.ytdict = dict(density = (np.exp(self.lnrho)*self.minfo.contents['AC_unit_density'], "g/cm**3"),
uux = (self.uu[0]*self.minfo.contents['AC_unit_velocity'], "cm/s"),
uuy = (self.uu[1]*self.minfo.contents['AC_unit_velocity'], "cm/s"),
uuz = (self.uu[2]*self.minfo.contents['AC_unit_velocity'], "cm/s"),
bbx = (self.bb[0]*self.minfo.contents['AC_unit_magnetic'], "gauss"),
bby = (self.bb[1]*self.minfo.contents['AC_unit_magnetic'], "gauss"),
bbz = (self.bb[2]*self.minfo.contents['AC_unit_magnetic'], "gauss"),
)
bbox = self.minfo.contents['AC_unit_length'] \
*np.array([[self.xx.min(), self.xx.max()], [self.yy.min(), self.yy.max()], [self.zz.min(), self.zz.max()]])
self.ytdata = yt.load_uniform_grid(self.ytdict, self.lnrho.shape, length_unit="cm", bbox=bbox)
else:
print("ERROR. No YT support found!")
def export_csv(self):
csvfile = open("grid.csv.%s" % self.framenum, "w")
csvfile.write("xx, yy, zz, rho, uux, uuy, uuz, bbx, bby, bbz\n")
ul = self.minfo.contents['AC_unit_length']
uv = self.minfo.contents['AC_unit_velocity']
ud = self.minfo.contents['AC_unit_density']
um = self.minfo.contents['AC_unit_magnetic']
for kk in np.arange(3, self.zz.size-3):
for jj in np.arange(3, self.yy.size-3):
for ii in np.arange(3, self.xx.size-3):
#print(self.xx.size, self.yy.size, self.zz.size)
linestring = "%e, %e, %e, %e, %e, %e, %e, %e, %e, %e\n"% (self.xx[ii]*ul, self.yy[jj]*ul, self.zz[kk]*ul,
np.exp(self.lnrho[ii, jj, kk])*ud,
self.uu[0][ii, jj, kk]*uv, self.uu[1][ii, jj, kk]*uv,
self.uu[2][ii, jj, kk]*uv,
self.bb[0][ii, jj, kk]*um, self.bb[1][ii, jj, kk]*um,
self.bb[2][ii, jj, kk]*um)
csvfile.write(linestring)
csvfile.close()
def export_raw(self):
uv = self.minfo.contents['AC_unit_velocity']
ud = self.minfo.contents['AC_unit_density']
um = self.minfo.contents['AC_unit_magnetic']
print(self.lnrho.shape, set_dtype(self.minfo.contents['endian'], self.minfo.contents['AcRealSize']))
f = open("rho%s.raw" % self.framenum, 'w+b')
binary_format =(np.exp(self.lnrho)*ud).tobytes()
f.write(binary_format)
f.close()
f = open("uux%s.raw" % self.framenum, 'w+b')
binary_format =(self.uu[0]*uv).tobytes()
f.write(binary_format)
f.close()
f = open("uuy%s.raw" % self.framenum, 'w+b')
binary_format =(self.uu[1]*uv).tobytes()
f.write(binary_format)
f.close()
f = open("uuz%s.raw" % self.framenum, 'w+b')
binary_format =(self.uu[2]*uv).tobytes()
f.write(binary_format)
f.close()
f = open("bbx%s.raw" % self.framenum, 'w+b')
binary_format =(self.bb[0]*um).tobytes()
f.write(binary_format)
f.close()
f = open("bby%s.raw" % self.framenum, 'w+b')
binary_format =(self.bb[1]*um).tobytes()
f.write(binary_format)
f.close()
f = open("bbz%s.raw" % self.framenum, 'w+b')
binary_format =(self.bb[2]*um).tobytes()
f.write(binary_format)
f.close()
def parse_ts(fdir, fname):

2
analysis/python/astar/visual/__init__.py
View File

@@ -1,5 +1,5 @@
'''
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

30
analysis/python/astar/visual/lineplot.py
View File

@@ -1,5 +1,5 @@
'''
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -37,7 +37,9 @@ def plot_min_man_rms(ts, xaxis, yaxis1, yaxis2, yaxis3):
plt.close()
def plot_ts(ts, isotherm=False, show_all=False, lnrho=False, uutot=False,
uux=False, uuy=False, uuz=False, ss=False, acc=False, sink=False):
uux=False, uuy=False, uuz=False,
aax=False, aay=False, aaz=False,
ss=False, acc=False, sink=False, rho=False):
if show_all:
lnrho=True
@@ -109,6 +111,30 @@ def plot_ts(ts, isotherm=False, show_all=False, lnrho=False, uutot=False,
yaxis3 = 'uuz_max'
plot_min_man_rms(ts, xaxis, yaxis1, yaxis2, yaxis3)
if aax:
plt.figure()
xaxis = 't_step'
yaxis1 = 'aax_rms'
yaxis2 = 'aax_min'
yaxis3 = 'aax_max'
plot_min_man_rms(ts, xaxis, yaxis1, yaxis2, yaxis3)
if aay:
plt.figure()
xaxis = 't_step'
yaxis1 = 'aay_rms'
yaxis2 = 'aay_min'
yaxis3 = 'aay_max'
plot_min_man_rms(ts, xaxis, yaxis1, yaxis2, yaxis3)
if aaz:
plt.figure()
xaxis = 't_step'
yaxis1 = 'aaz_rms'
yaxis2 = 'aaz_min'
yaxis3 = 'aaz_max'
plot_min_man_rms(ts, xaxis, yaxis1, yaxis2, yaxis3)
if ss:
plt.figure()
xaxis = 't_step'

55
analysis/python/astar/visual/slices.py
View File

@@ -1,6 +1,6 @@
'''
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -26,7 +26,8 @@ CM_INFERNO = plt.get_cmap('inferno')
def plot_3(mesh, input_grid, title = '', fname = 'default', bitmap=False,
slicetype = 'middle', colrange=None, colormap=CM_INFERNO ,
contourplot=False, points_from_centre = -1, bfieldlines=False, velfieldlines=False):
contourplot=False, points_from_centre = -1, bfieldlines=False, velfieldlines=False, trimghost = 0):
fig = plt.figure(figsize=(8, 8))
grid = gridspec.GridSpec(2, 3, wspace=0.4, hspace=0.4, width_ratios=[1,1, 0.15])
ax00 = fig.add_subplot( grid[0,0] )
@@ -40,20 +41,29 @@ def plot_3(mesh, input_grid, title = '', fname = 'default', bitmap=False,
yz_slice = input_grid[mesh.xmid, :, :]
xz_slice = input_grid[:, mesh.ymid, :]
xy_slice = input_grid[:, :, mesh.zmid]
if colrange==None:
plotnorm = colors.Normalize(vmin=input_grid.min(),vmax=input_grid.max())
else:
plotnorm = colors.Normalize(vmin=colrange[0],vmax=colrange[1])
elif slicetype == 'sum':
yz_slice = np.sum(input_grid, axis=0)
xz_slice = np.sum(input_grid, axis=1)
xy_slice = np.sum(input_grid, axis=2)
cmin = np.amin([yz_slice.min(), xz_slice.min(), xy_slice.min()])
cmax = np.amax([yz_slice.max(), xz_slice.max(), xy_slice.max()])
if colrange==None:
plotnorm = colors.Normalize(vmin=cmin,vmax=cmax)
else:
plotnorm = colors.Normalize(vmin=colrange[0],vmax=colrange[1])
yz_slice = yz_slice[trimghost : yz_slice.shape[0]-trimghost,
trimghost : yz_slice.shape[1]-trimghost]
xz_slice = xz_slice[trimghost : xz_slice.shape[0]-trimghost,
trimghost : xz_slice.shape[1]-trimghost]
xy_slice = xy_slice[trimghost : xy_slice.shape[0]-trimghost,
trimghost : xy_slice.shape[1]-trimghost]
mesh_xx_tmp = mesh.xx[trimghost : mesh.xx.shape[0]-trimghost]
mesh_yy_tmp = mesh.yy[trimghost : mesh.yy.shape[0]-trimghost]
mesh_zz_tmp = mesh.zz[trimghost : mesh.zz.shape[0]-trimghost]
#Set the coulourscale
cmin = np.amin([yz_slice.min(), xz_slice.min(), xy_slice.min()])
cmax = np.amax([yz_slice.max(), xz_slice.max(), xy_slice.max()])
if colrange==None:
plotnorm = colors.Normalize(vmin=cmin,vmax=cmax)
else:
plotnorm = colors.Normalize(vmin=colrange[0],vmax=colrange[1])
if points_from_centre > 0:
yz_slice = yz_slice[int(yz_slice.shape[0]/2)-points_from_centre : int(yz_slice.shape[0]/2)+points_from_centre,
@@ -62,11 +72,11 @@ def plot_3(mesh, input_grid, title = '', fname = 'default', bitmap=False,
int(xz_slice.shape[1]/2)-points_from_centre : int(xz_slice.shape[1]/2)+points_from_centre]
xy_slice = xy_slice[int(xy_slice.shape[0]/2)-points_from_centre : int(xy_slice.shape[0]/2)+points_from_centre,
int(xy_slice.shape[1]/2)-points_from_centre : int(xy_slice.shape[1]/2)+points_from_centre]
mesh.xx = mesh.xx[int(mesh.xx.shape[0]/2)-points_from_centre : int(mesh.xx.shape[0]/2)+points_from_centre]
mesh.yy = mesh.yy[int(mesh.yy.shape[0]/2)-points_from_centre : int(mesh.yy.shape[0]/2)+points_from_centre]
mesh.zz = mesh.zz[int(mesh.zz.shape[0]/2)-points_from_centre : int(mesh.zz.shape[0]/2)+points_from_centre]
mesh_xx_tmp = mesh.xx[int(mesh.xx.shape[0]/2)-points_from_centre : int(mesh.xx.shape[0]/2)+points_from_centre]
mesh_yy_tmp = mesh.yy[int(mesh.yy.shape[0]/2)-points_from_centre : int(mesh.yy.shape[0]/2)+points_from_centre]
mesh_zz_tmp = mesh.zz[int(mesh.zz.shape[0]/2)-points_from_centre : int(mesh.zz.shape[0]/2)+points_from_centre]
yy, zz = np.meshgrid(mesh.yy, mesh.zz, indexing='ij')
yy, zz = np.meshgrid(mesh_xx_tmp, mesh_xx_tmp, indexing='ij')
if contourplot:
map1 = ax00.contourf(yy, zz, yz_slice, norm=plotnorm, cmap=colormap, nlev=10)
else:
@@ -76,9 +86,10 @@ def plot_3(mesh, input_grid, title = '', fname = 'default', bitmap=False,
ax00.set_title('%s t = %.4e' % (title, mesh.timestamp) )
ax00.set_aspect('equal')
ax00.contour(yy, zz, np.sqrt((yy-yy.max()/2.0)**2.0 + (zz-zz.max()/2.0)**2.0), [mesh.minfo.contents["AC_accretion_range"]])
if mesh.minfo.contents["AC_accretion_range"] > 0.0:
ax00.contour(yy, zz, np.sqrt((yy-yy.max()/2.0)**2.0 + (zz-zz.max()/2.0)**2.0), [mesh.minfo.contents["AC_accretion_range"]])
xx, zz = np.meshgrid(mesh.xx, mesh.zz, indexing='ij')
xx, zz = np.meshgrid(mesh_xx_tmp, mesh_zz_tmp, indexing='ij')
if contourplot:
ax10.contourf(xx, zz, xz_slice, norm=plotnorm, cmap=colormap, nlev=10)
else:
@@ -87,9 +98,10 @@ def plot_3(mesh, input_grid, title = '', fname = 'default', bitmap=False,
ax10.set_ylabel('z')
ax10.set_aspect('equal')
ax10.contour(xx, zz, np.sqrt((xx-xx.max()/2.0)**2.0 + (zz-zz.max()/2.0)**2.0), [mesh.minfo.contents["AC_accretion_range"]])
if mesh.minfo.contents["AC_accretion_range"] > 0.0:
ax10.contour(xx, zz, np.sqrt((xx-xx.max()/2.0)**2.0 + (zz-zz.max()/2.0)**2.0), [mesh.minfo.contents["AC_accretion_range"]])
xx, yy = np.meshgrid(mesh.xx, mesh.yy, indexing='ij')
xx, yy = np.meshgrid(mesh_xx_tmp, mesh_yy_tmp, indexing='ij')
if contourplot:
ax11.contourf(xx, yy, xy_slice, norm=plotnorm, cmap=colormap, nlev=10)
else:
@@ -98,7 +110,8 @@ def plot_3(mesh, input_grid, title = '', fname = 'default', bitmap=False,
ax11.set_ylabel('y')
ax11.set_aspect('equal')
ax11.contour(xx, yy, np.sqrt((xx-xx.max()/2.0)**2.0 + (yy-yy.max()/2.0)**2.0), [mesh.minfo.contents["AC_accretion_range"]])
if mesh.minfo.contents["AC_accretion_range"] > 0.0:
ax11.contour(xx, yy, np.sqrt((xx-xx.max()/2.0)**2.0 + (yy-yy.max()/2.0)**2.0), [mesh.minfo.contents["AC_accretion_range"]])
if bfieldlines:
ax00.streamplot(mesh.yy, mesh.zz, np.mean(mesh.bb[1], axis=0), np.mean(mesh.bb[2], axis=0))

2
analysis/python/samples/readtest.py
View File

@@ -1,5 +1,5 @@
'''
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

5
bitbucket-pipelines.yml
View File

@@ -21,6 +21,9 @@ pipelines:
- mkdir -p build && cd build
- apt-get update
- apt-get install -y cmake flex bison
- cmake -DDSL_MODULE_DIR="acc/mhd_solver" ..
- cmake -DDSL_MODULE_DIR="acc/mhd_solver" -DBUILD_STANDALONE=ON -DBUILD_UTILS=ON -DBUILD_RT_VISUALIZATION=OFF -DBUILD_SAMPLES=ON -DDOUBLE_PRECISION=OFF -DMULTIGPU_ENABLED=ON -DMPI_ENABLED=OFF .. # Single precision
- make -j
- rm -rf *
- cmake -DDSL_MODULE_DIR="acc/mhd_solver" -DBUILD_STANDALONE=ON -DBUILD_UTILS=ON -DBUILD_RT_VISUALIZATION=OFF -DBUILD_SAMPLES=ON -DDOUBLE_PRECISION=ON -DMULTIGPU_ENABLED=ON -DMPI_ENABLED=OFF .. # Double precision
- make -j
# - ./ac_run -t

3
config/astaroth.conf
View File

@@ -48,7 +48,8 @@ AC_relhel = 0.0
AC_forcing_magnitude = 1e-5
AC_kmin = 0.8
AC_kmax = 1.2
// Switches forcing off and accretion on
AC_switch_accretion = 0
// Entropy
AC_cp_sound = 1.0

298
doc/Astaroth_API_specification_and_user_manual/API_specification_and_user_manual.md
View File

@@ -1,6 +1,6 @@
# Astaroth specification and user manual
# Astaroth Specification and User Manual
Copyright (C) 2014-2019, Johannes Pekkila, Miikka Vaisala.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
Astaroth is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -20,7 +20,7 @@ Copyright (C) 2014-2019, Johannes Pekkila, Miikka Vaisala.
along with Astaroth. If not, see <http://www.gnu.org/licenses/>.
# Introduction and background
# Introduction and Background
Astaroth is a collection of tools for utilizing multiple graphics processing units (GPUs)
efficiently in three-dimensional stencil computations. This document specifies the Astaroth
@@ -49,17 +49,17 @@ usable via the Astaroth API. While the Astaroth library is written in C++/CUDA,
the C99 standard.
# Publications
## Publications
The foundational work was done in (Väisälä, Pekkilä, 2017) and the library, API and DSL described
in this document were introduced in (Pekkilä, 2019). We kindly wish the users of Astaroth to cite
to these publications in their work.
> J. Pekkilä, Astaroth: A Library for Stencil Computations on Graphics Processing Units. Master's thesis, Aalto University School of Science, Espoo, Finland, 2019.
> [J. Pekkilä, Astaroth: A Library for Stencil Computations on Graphics Processing Units. Master's thesis, Aalto University School of Science, Espoo, Finland, 2019.](http://urn.fi/URN:NBN:fi:aalto-201906233993)
> M. S. Väisälä, Magnetic Phenomena of the Interstellar Medium in Theory and Observation. PhD thesis, University of Helsinki, Finland, 2017.
> [M. S. Väisälä, Magnetic Phenomena of the Interstellar Medium in Theory and Observation. PhD thesis, University of Helsinki, Finland, 2017.](http://urn.fi/URN:ISBN:978-951-51-2778-5)
> J. Pekkilä, M. S. Väisälä, M. Käpylä, P. J. Käpylä, and O. Anjum, “Methods for compressible fluid simulation on GPUs using high-order finite differences, ”Computer Physics Communications, vol. 217, pp. 11–22, Aug. 2017.
> [J. Pekkilä, M. S. Väisälä, M. Käpylä, P. J. Käpylä, and O. Anjum, “Methods for compressible fluid simulation on GPUs using high-order finite differences, ”Computer Physics Communications, vol. 217, pp. 11–22, Aug. 2017.](https://doi.org/10.1016/j.cpc.2017.03.011)
@@ -67,8 +67,8 @@ to these publications in their work.
The Astroth application-programming interface (API) provides the means for controlling execution of
user-defined and built-in functions on multiple graphics processing units. Functions in the API are
prefixed with lower case ```ac```, while structures and data types are prefixed with capitalized
```Ac```. Compile-time constants, such as definitions and enumerations, have the prefix ```AC_```.
prefixed with lower case `ac`, while structures and data types are prefixed with capitalized
`Ac`. Compile-time constants, such as definitions and enumerations, have the prefix `AC_`.
All of the API functions return an AcResult value indicating either success or failure. The return
codes are
```C
@@ -103,13 +103,13 @@ Finally, a third layer is provided for convenience and backwards compatibility.
There are also several helper functions defined in `include/astaroth_defines.h`, which can be used for, say, determining the size or performing index calculations within the simulation domain.
## List of Astaroth API functions
## List of Astaroth API Functions
Here's a non-exhaustive list of astaroth API functions. For more info and an up-to-date list, see
the corresponding header files in `include/astaroth_defines.h`, `include/astaroth.h`, `include/
astaroth_node.h`, `include/astaroth_device.h`.
### Initialization, quitting and helper functions
### Initialization, Quitting and Helper Functions
Device layer.
```C
@@ -137,7 +137,7 @@ size_t acVertexBufferCompdomainSizeBytes(const AcMeshInfo info);
size_t acVertexBufferIdx(const int i, const int j, const int k, const AcMeshInfo info);
```
### Loading and storing
### Loading and Storing
Loading meshes and vertex buffers to device memory.
```C
@@ -215,9 +215,10 @@ AcResult acDeviceLoadMeshInfo(const Device device, const Stream stream,
const AcMeshInfo device_config);
```
### Integration, Reductions and Boundary Conditions
### Computation
The library provides the following functions for integration, reductions and computing periodic
boundary conditions.
```C
AcResult acDeviceIntegrateSubstep(const Device device, const Stream stream, const int step_number,
const int3 start, const int3 end, const AcReal dt);
@@ -245,7 +246,16 @@ AcResult acNodeReduceVec(const Node node, const Stream stream_type, const Reduct
const VertexBufferHandle vtxbuf2, AcReal* result);
```
### Stream synchronization
Finally, there's a library function that is automatically generated for all user-specified `Kernel`
functions written with the Astaroth DSL,
```C
AcResult acDeviceKernel_##identifier(const Device device, const Stream stream,
const int3 start, const int3 end);
```
Where `##identifier` is replaced with the name of the user-specified kernel. For example, a device
function `Kernel solve()` can be called with `acDeviceKernel_solve()` via the API.
## Stream Synchronization
All library functions that take a `Stream` as a parameter are asynchronous. When calling these
functions, control returns immediately back to the host even if the called device function has not
@@ -267,13 +277,20 @@ synchronized at once by passing the alias `STREAM_ALL` to the synchronization fu
Usage of streams is demonstrated with the following example.
```C
funcA(STREAM_0);
funcB(STREAM_0); // Blocks until funcA has completed
funcC(STREAM_1); // May execute in parallel with funcB
funcB(STREAM_0); // Blocks until funcA has completed
funcC(STREAM_1); // May execute in parallel with funcB
barrierSynchronizeStream(STREAM_ALL); // Blocks until functions in all streams have completed
funcD(STREAM_2); // Is started when command returns from synchronizeStream()
funcD(STREAM_2); // Is started when command returns from synchronizeStream()
```
### Data synchronization
Astaroth API provides the following functions for barrier synchronization.
```C
AcResult acSynchronize(void);
AcResult acNodeSynchronizeStream(const Node node, const Stream stream);
AcResult acDeviceSynchronizeStream(const Device device, const Stream stream);
```
## Data Synchronization
Stream synchronization works in the same fashion on node and device layers. However on the node
layer, one has to take in account that a portion of the mesh is shared between devices and that the
@@ -291,14 +308,9 @@ AcResult acNodeSynchronizeVertexBuffer(const Node node, const Stream stream,
```
> **NOTE**: Local halos must be up to date before synchronizing the data. Local halos are the grid
points outside the computational domain which are used only by a single device. The mesh is
distributed to multiple devices by blocking along the z axis. If there are *n* devices and the z-
dimension of the computational domain is *nz*, then each device is assigned *nz / n* two-
dimensional planes. For example with two devices, the data block that has to be up to date ranges
from *(0, 0, nz)* to *(mx, my, nz + 2 * NGHOST)*
> **NOTE**: Local halos must be up to date before synchronizing the data. Local halos are the grid points outside the computational domain which are used only by a single device. The mesh is distributed to multiple devices by blocking along the z axis. If there are *n* devices and the z-dimension of the computational domain is *nz*, then each device is assigned *nz / n* two-dimensional planes. For example with two devices, the data block that has to be up to date ranges from *(0, 0, nz)* to *(mx, my, nz + 2 * NGHOST)*.
### Input and output buffers
## Input and Output Buffers
The mesh is duplicated to input and output buffers for performance reasons. The input buffers are
read-only in user-specified compute kernels, which allows us to read them via the texture cache
@@ -313,10 +325,7 @@ is done via the API calls
AcResult acDeviceSwapBuffers(const Device device);
AcResult acNodeSwapBuffers(const Node node);
```
> **NOTE**: All functions provided with the API operate on input buffers and ensure that the
complete result is available in the input buffer when the function has completed. User-specified
kernels are exceptions and write the result to output buffers. Therefore buffers have to be swapped
only after calling user-specified kernels.
> **NOTE**: All functions provided with the API operate on input buffers and ensure that the complete result is available in the input buffer when the function has completed. User-specified kernels are exceptions and write the result to output buffers. Therefore buffers have to be swapped only after calling user-specified kernels.
## Devices
@@ -362,14 +371,14 @@ Meshes are the primary structures for passing information to the library and ker
of a `Mesh` is declared as
```C
typedef struct {
int int_params[NUM_INT_PARAMS];
int3 int3_params[NUM_INT3_PARAMS];
AcReal real_params[NUM_REAL_PARAMS];
int int_params[NUM_INT_PARAMS];
int3 int3_params[NUM_INT3_PARAMS];
AcReal real_params[NUM_REAL_PARAMS];
AcReal3 real3_params[NUM_REAL3_PARAMS];
} AcMeshInfo;
typedef struct {
AcReal* vertex_buffer[NUM_VTXBUF_HANDLES];
AcReal* vertex_buffer[NUM_VTXBUF_HANDLES];
AcMeshInfo info;
} AcMesh;
```
@@ -420,45 +429,7 @@ Let *i* be the device id. The portion of the halos shared by neighboring devices
`acNodeSynchronizeVertexBuffer` and `acNodeSynchronizeMesh` communicate these shared areas among
the devices in the node.
## Integration, reductions and boundary conditions
The library provides the following functions for integration, reductions and computing periodic
boundary conditions.
```C
AcResult acDeviceIntegrateSubstep(const Device device, const Stream stream, const int step_number,
const int3 start, const int3 end, const AcReal dt);
AcResult acDevicePeriodicBoundcondStep(const Device device, const Stream stream,
const VertexBufferHandle vtxbuf_handle, const int3 start,
const int3 end);
AcResult acDevicePeriodicBoundconds(const Device device, const Stream stream, const int3 start,
const int3 end);
AcResult acDeviceReduceScal(const Device device, const Stream stream, const ReductionType rtype,
const VertexBufferHandle vtxbuf_handle, AcReal* result);
AcResult acDeviceReduceVec(const Device device, const Stream stream_type, const ReductionType rtype,
const VertexBufferHandle vtxbuf0, const VertexBufferHandle vtxbuf1,
const VertexBufferHandle vtxbuf2, AcReal* result);
AcResult acNodeIntegrateSubstep(const Node node, const Stream stream, const int step_number,
const int3 start, const int3 end, const AcReal dt);
AcResult acNodeIntegrate(const Node node, const AcReal dt);
AcResult acNodePeriodicBoundcondStep(const Node node, const Stream stream,
const VertexBufferHandle vtxbuf_handle);
AcResult acNodePeriodicBoundconds(const Node node, const Stream stream);
AcResult acNodeReduceScal(const Node node, const Stream stream, const ReductionType rtype,
const VertexBufferHandle vtxbuf_handle, AcReal* result);
AcResult acNodeReduceVec(const Node node, const Stream stream_type, const ReductionType rtype,
const VertexBufferHandle vtxbuf0, const VertexBufferHandle vtxbuf1,
const VertexBufferHandle vtxbuf2, AcReal* result);
```
Finally, there's a library function that is automatically generated for all user-specified `Kernel`
functions written with the Astaroth DSL,
```C
AcResult acDeviceKernel_##identifier(const Device device, const Stream stream,
const int3 start, const int3 end);
```
Where `##identifier` is replaced with the name of the user-specified kernel. For example, a device
function `Kernel solve()` can be called with `acDeviceKernel_solve()` via the API.
> **NOTE:** The decomposition scheme is subject to change.
# Astaroth Domain-Specific Language
@@ -487,18 +458,18 @@ pipeline shown in the following figure.
| Stage | File ending | Description |
|--------------------|-------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Stencil assembly | .sas | Defines the shape of the stencils and functions to be preprocessed before entering the stencil processing stage. Reading from input arrays is only possible during this stage. |
| Stencil process | .sps | The functions executed on streams of data are defined here. Contains kernels, which are essentially main functions of GPU programs. |
| Stencil definition | .sdh | All field identifiers and constant memory symbols are defined in this file. |
| Any | .h | Optional header files which can be included in any other file.
| Stencil assembly | .ac | Defines the shape of the stencils and functions to be preprocessed before entering the stencil processing stage. Reading from input arrays is only possible during this stage. |
| Stencil process | .ac | The functions executed on streams of data are defined here. Contains kernels, which are essentially main functions of GPU programs. |
| Stencil definition | .ac | All field identifiers and constant memory symbols are defined in this file. |
| Any | .h | Optional header files which can be included in any file.
Compilation of the DSL files is integrated into `CMakelists.txt` provided with the library and
dependencies are recompiled if needed when calling `make`. All DSL files should reside in the same
directory and there should be only one `.sas`, `.sps` and `.sdh` file. There may be any number of
directory and there should be only one `.ac` file. There may be any number of
optional `.h` files. When configuring the project, the user should pass the path to the DSL
directory as a cmake option like so: ```cmake -DDSL_MODULE_DIR="some/user/dir" ..```.
## Data types
## Data Types
In addition to basic datatypes in C/C++/CUDA, such as int and int3, we provide the following datatypes with the DSL.
@@ -517,13 +488,13 @@ In addition to basic datatypes in C/C++/CUDA, such as int and int3, we provide t
`Scalars` are 32-bit floating-point numbers by default. Double precision can be turned on by setting cmake option `DOUBLE_PRECISION=ON`.
All real number literals are converted automatically to the correct precision. In cases where , the precision can be declared explicitly by appending `f` or `d` postfix to the real number. For example,
```C
1.0 // The same precision as Scalar/AcReal
1.0f // Explicit float
1.0d // Explicit double
1.0 // The same precision as Scalar/AcReal
1.0f // Explicit float
1.0d // Explicit double
(1.0f * 1.0d) // 1.0f is implicitly cast to double and the multiplication is done in double precision.
```
## Control flow
## Control Flow
Conditional statements are expressed with the `if-else` construct. Unlike in C and C++, we require
that the scope of the `if-else` statement is explicitly declared using braces `{` and `}` in order
@@ -566,7 +537,7 @@ The following built-in variables are available in `Kernel`s.
| globalVertexIdx | Holds the global index of the currently processed vertex. If there is only single device, then vertexIdx is the same as globalVertexIdx. Otherwise globalVertexIdx is offset accordingly. |
| globalGridN | Holds the dimensions of the computational domain. |
## Preprocessed functions
## Preprocessed Functions
The type qualifier `Preprocessed` indicates which functions should be evaluated immediately when
entering a `Kernel` function. The return values of `Preprocessed` functions are cached and calling
@@ -574,11 +545,13 @@ these functions during the stencil processing stage is essentially free. As main
significantly slower than on-chip memories and registers, declaring reading-heavy functions as
`Preprocessed` is critical for obtaining good performance in stencil codes.
`Preprocessed` functions may only be defined in stencil assembly files.
The built-in variables `vertexIdx`, `globalVertexidx` and `globalGridN` are available in all
`Preprocessed` functions.
## Device Functions
The type qualifier `Device` indicates which functions can be called from `Kernel` functions or other `Device` functions.
## Uniforms
`Uniform`s are global device variables which stay constant for the duration of a kernel launch.
@@ -590,150 +563,27 @@ which use those uniforms.
`Uniform`s can be of type `Scalar`, `Vector`, `int`, `int3`, `ScalarField` and `ScalarArray`.
> Note: As of 2019-10-01, the types `ScalarField` (DSL) and `VertexBuffer` (CUDA) are aliases of the
same type. This naming may be changed in the future.
> Note: As of 2019-10-01, the types `ScalarField` (DSL) and `VertexBuffer` (CUDA) are aliases of the same type. This naming may be changed in the future.
> Note: As of 2019-10-01, ScalarFields cannot be declared as uniforms. Instead, one should declare
each component as a `ScalarField` and use them to construct a `VectorField` during the stencil
processing stage. For example, `in VectorField(A, B, C);`, where `A`, `B` and `C` are
`uniform ScalarField`s.
> Note: As of 2019-10-01, `VectorField`s cannot be declared as uniforms. Instead, one should declare each component as a `ScalarField` and use them to construct a `VectorField` during the stencil processing stage. For example, `in VectorField(A, B, C);`, where `A`, `B` and `C` are `uniform ScalarField`s.
> Note: As of 2019-10-01, `uniform`s cannot be assigned values in the stencil definition headers.
Instead, one should load the appropriate values during runtime using the `acLoadScalarUniform` and
related functions.
> Note: As of 2019-10-01, `uniform`s cannot be assigned values in the stencil definition headers. Instead, one should load the appropriate values during runtime using the `acLoadScalarUniform` and related functions.
## Standard libraries
## Standard Libraries
> Not implemented
The following table lists the standard libraries currently available.
## Performance considerations
| Built-in variable | Description |
|-------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| stdderiv.h | Contains functions for computing 2nd, 4th, 6th and 8th order derivatives (configured by defining the STENCIL_ORDER before including stdderiv.h) |
Astaroth DSL libraries can be included in the same way as C/C++ headers. For example, `#include <stdderiv.h>`.
## Performance Considerations
Uniforms are as fast as compile-time constants as long as
0. The halting condition of a tight loop does not depend on an uniform or a variable, as this would prevent unrolling of the loop during compile-time.
0. Uniforms are not multiplied with each other. The result should be stored in an auxiliary uniform instead. For example, the result of `nx * ny` should be stored in a new `uniform nxy`
0. At least 32 neighboring streams in the x-axis access the same `uniform`. That is, the vertices at vertexIdx.x = i... i + 32 should access the same `uniform` where i is a multiple of 32.
1. The halting condition of a tight loop does not depend on an uniform or a variable, as this would prevent unrolling of the loop during compile-time.
2. Uniforms are not multiplied with each other. The result should be stored in an auxiliary uniform instead. For example, the result of `nx * ny` should be stored in a new `uniform nxy`
3. At least 32 neighboring streams in the x-axis access the same `uniform`. That is, the vertices at vertexIdx.x = i... i + 32 should access the same `uniform` where i is a multiple of 32.

BIN
doc/astaroth_logo_small.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.5 KiB

18
doxyfile
View File

@@ -38,7 +38,7 @@ PROJECT_NAME = "Astaroth"
# could be handy for archiving the generated documentation or if some version
# control system is used.
PROJECT_NUMBER =
PROJECT_NUMBER = 2.1
# Using the PROJECT_BRIEF tag one can provide an optional one line description
# for a project that appears at the top of each page and should give viewer a
@@ -51,7 +51,7 @@ PROJECT_BRIEF =
# pixels and the maximum width should not exceed 200 pixels. Doxygen will copy
# the logo to the output directory.
PROJECT_LOGO =
PROJECT_LOGO = doc/astaroth_logo_small.png
# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path
# into which the generated documentation will be written. If a relative path is
@@ -242,7 +242,7 @@ TCL_SUBST =
# members will be omitted, etc.
# The default value is: NO.
OPTIMIZE_OUTPUT_FOR_C = NO
OPTIMIZE_OUTPUT_FOR_C = YES
# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or
# Python sources only. Doxygen will then generate output that is more tailored
@@ -771,7 +771,7 @@ WARN_LOGFILE = doc/doxygen/doxygen_warnings.log
# spaces. See also FILE_PATTERNS and EXTENSION_MAPPING
# Note: If this tag is empty the current directory is searched.
INPUT = src include
INPUT =
# This tag can be used to specify the character encoding of the source files
# that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
@@ -796,7 +796,7 @@ INPUT_ENCODING = UTF-8
# *.m, *.markdown, *.md, *.mm, *.dox, *.py, *.pyw, *.f90, *.f, *.for, *.tcl,
# *.vhd, *.vhdl, *.ucf, *.qsf, *.as and *.js.
FILE_PATTERNS = *.cc *.h *.cu *.cuh
FILE_PATTERNS = *.c *.cc *.h *.cu *.cuh *.md
# The RECURSIVE tag can be used to specify whether or not subdirectories should
# be searched for input files as well.
@@ -1187,7 +1187,7 @@ HTML_TIMESTAMP = NO
# The default value is: NO.
# This tag requires that the tag GENERATE_HTML is set to YES.
HTML_DYNAMIC_SECTIONS = NO
HTML_DYNAMIC_SECTIONS = YES
# With HTML_INDEX_NUM_ENTRIES one can control the preferred number of entries
# shown in the various tree structured indices initially; the user can expand
@@ -1416,7 +1416,7 @@ DISABLE_INDEX = NO
# The default value is: NO.
# This tag requires that the tag GENERATE_HTML is set to YES.
GENERATE_TREEVIEW = NO
GENERATE_TREEVIEW = YES
# The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that
# doxygen will group on one line in the generated HTML documentation.
@@ -2314,7 +2314,7 @@ DIRECTORY_GRAPH = YES
# The default value is: png.
# This tag requires that the tag HAVE_DOT is set to YES.
DOT_IMAGE_FORMAT = png
DOT_IMAGE_FORMAT = svg
# If DOT_IMAGE_FORMAT is set to svg, then this option can be set to YES to
# enable generation of interactive SVG images that allow zooming and panning.
@@ -2326,7 +2326,7 @@ DOT_IMAGE_FORMAT = png
# The default value is: NO.
# This tag requires that the tag HAVE_DOT is set to YES.
INTERACTIVE_SVG = NO
INTERACTIVE_SVG = YES
# The DOT_PATH tag can be used to specify the path where the dot tool can be
# found. If left blank, it is assumed the dot tool can be found in the path.

4
include/astaroth.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -99,6 +99,8 @@ AcResult acLoadWithOffset(const AcMesh host_mesh, const int3 src, const int num_
/** */
int acGetNumDevicesPerNode(void);
Node acGetNode(void);
#ifdef __cplusplus
} // extern "C"
#endif

2
include/astaroth_defines.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

9
include/astaroth_device.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -16,6 +16,13 @@
You should have received a copy of the GNU General Public License
along with Astaroth. If not, see <http://www.gnu.org/licenses/>.
*/
/**
* @file Single-Device Interface
* \brief Provides functions for controlling a single device.
*
* Detailed info.
*
*/
#pragma once
#ifdef __cplusplus

2
include/astaroth_grid.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

42
include/astaroth_node.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -41,16 +41,48 @@ typedef struct {
Grid subgrid;
} DeviceConfiguration;
/** */
/**
Initializes all devices on the current node.
Devices on the node are configured based on the contents of AcMesh.
@return Exit status. Places the newly created handle in the output parameter.
@see AcMeshInfo
Usage example:
@code
AcMeshInfo info;
acLoadConfig(AC_DEFAULT_CONFIG, &info);
Node node;
acNodeCreate(0, info, &node);
acNodeDestroy(node);
@endcode
*/
AcResult acNodeCreate(const int id, const AcMeshInfo node_config, Node* node);
/** */
/**
Resets all devices on the current node.
@see acNodeCreate()
*/
AcResult acNodeDestroy(Node node);
/** */
/**
Prints information about the devices available on the current node.
Requires that Node has been initialized with
@See acNodeCreate().
*/
AcResult acNodePrintInfo(const Node node);
/** */
/**
@see DeviceConfiguration
*/
AcResult acNodeQueryDeviceConfiguration(const Node node, DeviceConfiguration* config);
/** */

3
samples/CMakeLists.txt Normal file
View File

@@ -0,0 +1,3 @@
add_subdirectory(ctest)
add_subdirectory(cpptest)
add_subdirectory(mpitest)

5
src/exampleproject/CMakeLists.txt → samples/cpptest/CMakeLists.txt
View File

@@ -6,6 +6,5 @@ set(CMAKE_CXX_STANDARD_REQUIRED ON)
add_compile_options(-Wall -Wextra -Werror -Wdouble-promotion -Wfloat-conversion -Wshadow)
## Compile and link
add_executable(ac_simulate simulation.cc)
target_link_libraries(ac_simulate PRIVATE astaroth_core astaroth_utils)
add_definitions(-DAC_DEFAULT_CONFIG="${CMAKE_SOURCE_DIR}/config/astaroth.conf")
add_executable(cpptest main.cc)
target_link_libraries(cpptest PRIVATE astaroth_core astaroth_utils)

58
samples/cpptest/main.cc Normal file
View File

@@ -0,0 +1,58 @@
/*
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
Astaroth is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Astaroth is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with Astaroth. If not, see <http://www.gnu.org/licenses/>.
*/
#include <assert.h>
#include <stdio.h>
#include <string.h>
#include "astaroth.h"
// From Astaroth Utils
#include "src/utils/config_loader.h"
#include "src/utils/memory.h"
#include "src/utils/verification.h"
int
main(void)
{
AcMeshInfo info;
acLoadConfig(AC_DEFAULT_CONFIG, &info);
// Alloc
AcMesh model, candidate;
acMeshCreate(info, &model);
acMeshCreate(info, &candidate);
// Init
acMeshRandomize(&model);
acMeshApplyPeriodicBounds(&model);
////////////////////////////////////////////////////////////////////////////////////////////////
acInit(info);
acLoad(model);
acStore(&candidate);
acQuit();
////////////////////////////////////////////////////////////////////////////////////////////////
// Verify and destroy
acVerifyMesh(model, candidate);
acMeshDestroy(&model);
acMeshDestroy(&candidate);
return EXIT_SUCCESS;
}

0
src/ctest/CMakeLists.txt → samples/ctest/CMakeLists.txt
View File

0
src/ctest/README.txt → samples/ctest/README.txt
View File

3
src/ctest/main.c → samples/ctest/main.c
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -41,7 +41,6 @@ main(void)
acMeshRandomize(&model);
acMeshApplyPeriodicBounds(&model);
// TODO load to candidate
////////////////////////////////////////////////////////////////////////////////////////////////
acInit(info);
acLoad(model);

2
src/mpitest/CMakeLists.txt → samples/mpitest/CMakeLists.txt
View File

@@ -6,4 +6,4 @@ set(CMAKE_CXX_STANDARD 11)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
add_executable(mpitest main.cc)
target_link_libraries(mpitest astaroth_core)
target_link_libraries(mpitest astaroth_core astaroth_utils)

11
samples/mpitest/README.txt Normal file
View File

@@ -0,0 +1,11 @@
This directory is used to test MPI with Astaroth.
Building (in the base astaroth directory):
cmake -DBUILD_SAMPLES=ON -DMPI_ENABLED=ON -DCMAKE_CXX_COMPILER=$(which mpicxx) .. && make -j
Running:
mpirun -np <nprocs> ./mpitest
or
srun <options> ./mpitest # With slurm
or
a batch script of your choice

2
src/mpitest/main.cc → samples/mpitest/main.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/mpitest/main0.c → samples/mpitest/main0.c
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/mpitest/main1.c → samples/mpitest/main1.c
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

82
scripts/compile_acc.sh
View File

@@ -1,82 +0,0 @@
#!/bin/bash
#!/bin/bash
if [ -z $AC_HOME ]
then
echo "ASTAROTH_HOME environment variable not set, run \"source ./sourceme.sh\" in Astaroth home directory"
exit 1
fi
OUTPUT_DIR=${PWD}
KERNEL_DIR=${AC_HOME}"/src/core/kernels"
ACC_DIR=${AC_HOME}"/acc"
ACC_DEFAULT_SAS="mhd_solver/stencil_assembly.sas"
ACC_DEFAULT_SPS="mhd_solver/stencil_process.sps"
ACC_DEFAULT_HEADER="mhd_solver/stencil_definition.sdh"
ACC_DEFAULT_INCLUDE_DIR="mhd_solver"
${ACC_DIR}/clean.sh
${ACC_DIR}/build_acc.sh
ACC_SAS=${ACC_DEFAULT_SAS}
ACC_SPS=${ACC_DEFAULT_SPS}
ACC_HEADER=${ACC_DEFAULT_HEADER}
ACC_INCLUDE_DIR=${ACC_DEFAULT_INCLUDE_DIR}
while [ "$#" -gt 0 ]
do
case $1 in
-h|--help)
echo "This script will help to compile DSL to CUDA code."
echo "The resulting kernels will be stored to $OUTPUT_DIR."
echo "You can set a custom files for DSL under the path $AC_DIR/"
echo "Example:"
echo "compile_acc.sh -a custom_setup/custom_assembly.sas -p custom_setup/custom_process.sps --header custom_setup/custom_header.h"
exit 0
;;
-I|--include)
shift
ACC_INCLUDE_DIR=${1}
shift
echo "CUSTOM include dir!"
;;
--header)
shift
ACC_HEADER=${1}
shift
echo "CUSTOM Header file!"
;;
-a|--assembly)
shift
ACC_SAS=${1}
shift
echo "CUSTOM Assembly file!"
;;
-p|--process)
shift
ACC_SPS=${1}
shift
echo "CUSTOM Process file!"
;;
*)
break
esac
done
echo "Header file:" ${ACC_DIR}/${ACC_HEADER}
echo "Assembly file: ${ACC_DIR}/${ACC_SAS}"
echo "Process file: ${ACC_DIR}/${ACC_SPS}"
cd ${ACC_DIR}/${ACC_INCLUDE_DIR}
echo ${PWD}
${ACC_DIR}/compile.sh ${ACC_DIR}/${ACC_SAS}
${ACC_DIR}/compile.sh ${ACC_DIR}/${ACC_SPS}
${ACC_DIR}/compile.sh ${ACC_DIR}/${ACC_HEADER}
echo "Moving stencil_assembly.cuh -> ${OUTPUT_DIR}"
mv stencil_assembly.cuh ${OUTPUT_DIR}
echo "Moving stencil_process.cuh -> ${OUTPUT_DIR}"
mv stencil_process.cuh ${OUTPUT_DIR}
echo "Moving stencil_defines.cuh -> ${OUTPUT_DIR}"
mv stencil_defines.h ${OUTPUT_DIR}

9
scripts/fix_style.sh Executable file
View File

@@ -0,0 +1,9 @@
#!/bin/bash
if [[ $1 == "DO" && $2 == "IT!" ]]; then
find -name \*.h -o -name \*.cc -o -name \*.c | xargs clang-format -i -style=file
echo "It is done."
else
find -name \*.h -o -name \*.cc -o -name \*.c
echo "I'm going to try to fix the style of these files."
echo "If you're absolutely sure, give \"DO IT!\" as a parameter."
fi

1
scripts/preprocess_device_files.sh
View File

@@ -1 +0,0 @@
nvcc -E ../src/core/device.cu -I ../include -I ../ > preprocessed_device_files.pp

17
src/core/astaroth.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -34,8 +34,10 @@ const char* scalararray_names[] = {AC_FOR_SCALARARRAY_HANDLES(AC_GEN_STR)};
const char* vtxbuf_names[] = {AC_FOR_VTXBUF_HANDLES(AC_GEN_STR)};
#undef AC_GEN_STR
static const int num_nodes = 1;
static Node nodes[num_nodes];
static const int max_num_nodes = 1;
static Node nodes[max_num_nodes] = {0};
static int num_nodes = 0;
void
acPrintMeshInfo(const AcMeshInfo config)
@@ -55,12 +57,14 @@ acPrintMeshInfo(const AcMeshInfo config)
AcResult
acInit(const AcMeshInfo mesh_info)
{
num_nodes = 1;
return acNodeCreate(0, mesh_info, &nodes[0]);
}
AcResult
acQuit(void)
{
num_nodes = 0;
return acNodeDestroy(nodes[0]);
}
@@ -176,3 +180,10 @@ acGetNumDevicesPerNode(void)
ERRCHK_CUDA_ALWAYS(cudaGetDeviceCount(&num_devices));
return num_devices;
}
Node
acGetNode(void)
{
ERRCHK_ALWAYS(num_nodes > 0);
return nodes[0];
}

2
src/core/device.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/errchk.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/grid.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/boundconds.cu
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/boundconds.cuh
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/common.cuh
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/deprecated/boundconds_PLACEHOLDER.cuh
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/deprecated/reduce_PLACEHOLDER.cuh
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/deprecated/rk3_PLACEHOLDER.cuh
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/integration.cu
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/integration.cuh
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/reductions.cu
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/kernels/reductions.cuh
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/math_utils.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/core/node.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

77
src/exampleproject/simulation.cc
View File

@@ -1,77 +0,0 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
This file is part of Astaroth.
Astaroth is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Astaroth is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with Astaroth. If not, see <http://www.gnu.org/licenses/>.
*/
#include "src/utils/config_loader.h"
#include "src/utils/memory.h"
#include <assert.h>
#include <stdio.h>
#include <string.h>
int
run_simulation(const char* config_path)
{
AcMeshInfo info;
acLoadConfig(config_path, &info);
AcMesh mesh;
acMeshCreate(info, &mesh);
acMeshClear(&mesh);
acInit(info);
acLoad(mesh);
const size_t num_steps = 10;
for (size_t i = 0; i < num_steps; ++i) {
const AcReal dt = 1; // JP: TODO! Set timestep here!
// JP: TODO! Make sure that AcMeshInfo parameters are properly initialized before calling
// acIntegrate()
// NANs indicate that either dt is too large or something was uninitalized
acIntegrate(dt);
}
for (int i = 0; i < NUM_VTXBUF_HANDLES; ++i) {
printf("%s:\n", vtxbuf_names[i]);
printf("\tmax: %g\n", (double)acReduceScal(RTYPE_MAX, VertexBufferHandle(i)));
printf("\tmin: %g\n", (double)acReduceScal(RTYPE_MIN, VertexBufferHandle(i)));
printf("\trms: %g\n", (double)acReduceScal(RTYPE_RMS, VertexBufferHandle(i)));
printf("\texp rms: %g\n", (double)acReduceScal(RTYPE_RMS_EXP, VertexBufferHandle(i)));
}
acStore(&mesh);
acQuit();
acMeshDestroy(&mesh);
return EXIT_SUCCESS;
}
int
main(int argc, char* argv[])
{
printf("Args: \n");
for (int i = 0; i < argc; ++i)
printf("%d: %s\n", i, argv[i]);
char* config_path;
(argc == 3) ? config_path = strdup(argv[2]) : config_path = strdup(AC_DEFAULT_CONFIG);
printf("Config path: %s\n", config_path);
assert(config_path);
run_simulation(config_path);
free(config_path);
return EXIT_SUCCESS;
}

1
src/mpitest/README.txt
View File

@@ -1 +0,0 @@
This directory is used to test MPI with Astaroth.

2
src/standalone/autotest.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/benchmark.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/config_loader.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/config_loader.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

167
src/standalone/main.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -61,6 +61,79 @@ errorlog_quit(void)
}
}
typedef struct {
char* key[2];
char* description;
} Option;
static Option
createOption(const char* key, const char* key_short, const char* description)
{
Option option;
option.key[0] = strdup(key);
option.key[1] = strdup(key_short);
option.description = strdup(description);
return option;
}
static void
destroyOption(Option* option)
{
free(option->key[0]);
free(option->key[1]);
free(option->description);
}
typedef enum {
HELP,
TEST,
BENCHMARK,
SIMULATE,
RENDER,
CONFIG,
NUM_OPTIONS,
} OptionType;
static int
findOption(const char* str, const Option options[NUM_OPTIONS])
{
for (int i = 0; i < NUM_OPTIONS; ++i)
if (!strcmp(options[i].key[0], str) || !strcmp(options[i].key[1], str))
return i;
return -1;
}
static void
print_options(const Option options[NUM_OPTIONS])
{
// Formatting
int keylen[2] = {0};
for (int i = 0; i < NUM_OPTIONS; ++i) {
int len0 = strlen(options[i].key[0]);
int len1 = strlen(options[i].key[1]);
if (keylen[0] < len0)
keylen[0] = len0;
if (keylen[1] < len1)
keylen[1] = len1;
}
for (int i = 0; i < NUM_OPTIONS; ++i)
printf("\t%*s | %*s: %s\n", keylen[0], options[i].key[0], keylen[1], options[i].key[1],
options[i].description);
}
static void
print_help(const Option options[NUM_OPTIONS])
{
puts("Usage: ./ac_run [options]");
print_options(options);
printf("\n");
puts("For bug reporting, see README.md");
}
int
main(int argc, char* argv[])
{
@@ -69,36 +142,76 @@ main(int argc, char* argv[])
atexit(errorlog_quit);
}
printf("Args: \n");
for (int i = 0; i < argc; ++i)
printf("%d: %s\n", i, argv[i]);
char* config_path;
(argc == 3) ? config_path = strdup(argv[2])
: config_path = strdup(AC_DEFAULT_CONFIG);
printf("Config path: %s\n", config_path);
ERRCHK(config_path);
// Create options
// clang-format off
Option options[NUM_OPTIONS];
options[HELP] = createOption("--help", "-h", "Prints this help.");
options[TEST] = createOption("--test", "-t", "Runs autotests.");
options[BENCHMARK] = createOption("--benchmark", "-b", "Runs benchmarks.");
options[SIMULATE] = createOption("--simulate", "-s", "Runs the simulation.");
options[RENDER] = createOption("--render", "-r", "Runs the real-time renderer.");
options[CONFIG] = createOption("--config", "-c", "Uses the config file given after this flag instead of the default.");
// clang-format on
if (argc == 1) {
return run_renderer(config_path);
}
else if (argc == 2 || argc == 3) {
if (strcmp(argv[1], "-t") == 0)
return run_autotest(config_path);
else if (strcmp(argv[1], "-b") == 0)
return run_benchmark(config_path);
else if (strcmp(argv[1], "-s") == 0)
return run_simulation(config_path);
else if (strcmp(argv[1], "-r") == 0)
return run_renderer(config_path);
else
WARNING("Unrecognized option");
print_help(options);
}
else {
WARNING("Too many options given");
char* config_path = NULL;
for (int i = 1; i < argc; ++i) {
const int option = findOption(argv[i], options);
switch (option) {
case CONFIG:
if (i + 1 < argc) {
config_path = strdup(argv[i + 1]);
}
else {
printf("Syntax error. Usage: --config <config path>.\n");
return EXIT_FAILURE;
}
break;
default:
break; // Do nothing
}
}
if (!config_path)
config_path = strdup(AC_DEFAULT_CONFIG);
printf("Config path: %s\n", config_path);
ERRCHK_ALWAYS(config_path);
for (int i = 1; i < argc; ++i) {
const int option = findOption(argv[i], options);
switch (option) {
case HELP:
print_help(options);
break;
case TEST:
run_autotest(config_path);
break;
case BENCHMARK:
run_benchmark(config_path);
break;
case SIMULATE:
run_simulation(config_path);
break;
case RENDER:
run_renderer(config_path);
break;
case CONFIG:
++i;
break;
default:
printf("Invalid option %s\n", argv[i]);
break; // Do nothing
}
}
free(config_path);
}
free(config_path);
return EXIT_FAILURE;
for (int i = 0; i < NUM_OPTIONS; ++i)
destroyOption(&options[i]);
return EXIT_SUCCESS;
}

13
src/standalone/model/host_forcing.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.
@@ -171,11 +171,14 @@ helical_forcing_special_vector(AcReal3* ff_hel_re, AcReal3* ff_hel_im, const AcR
// k_cross_k_cross_e.z/denominator};
// See PC forcing.f90 forcing_hel_both()
*ff_hel_re = (AcReal3){kabs * k_cross_e.x / denominator, kabs * k_cross_e.y,
kabs * k_cross_e.z};
*ff_hel_im = (AcReal3){kabs * k_cross_e.x / denominator,
kabs * k_cross_e.y / denominator,
kabs * k_cross_e.z / denominator};
*ff_hel_re = (AcReal3){relhel * k_cross_k_cross_e.x / denominator,
relhel * k_cross_k_cross_e.y / denominator,
relhel * k_cross_k_cross_e.z / denominator};
*ff_hel_im = (AcReal3){relhel * k_cross_k_cross_e.x / denominator, relhel * k_cross_k_cross_e.y,
relhel * k_cross_k_cross_e.z};
}
// Tool for loading forcing vector information into the device memory

2
src/standalone/model/host_forcing.h
View File

@@ -1,6 +1,6 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/host_memory.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/host_memory.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/host_timestep.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/host_timestep.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/model_boundconds.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/model_boundconds.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/model_diff.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/model_reduce.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/model_reduce.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/model_rk3.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/model_rk3.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/model/modelmesh.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/renderer.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/run.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/simulation.cc
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/standalone/timer_hires.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/utils/config_loader.c
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/utils/config_loader.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/utils/memory.c
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/utils/memory.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/utils/modelsolver.c
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

2
src/utils/modelsolver.h
View File

@@ -1,5 +1,5 @@
/*
Copyright (C) 2014-2019, Johannes Pekkilae, Miikka Vaeisalae.
Copyright (C) 2014-2020, Johannes Pekkila, Miikka Vaisala.
This file is part of Astaroth.

Some files were not shown because too many files have changed in this diff Show More