diff --git a/LICENSE b/LICENSE new file mode 100644 --- /dev/null +++ b/LICENSE @@ -0,0 +1,661 @@ + GNU AFFERO GENERAL PUBLIC LICENSE + Version 3, 19 November 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU Affero General Public License is a free, copyleft license for +software and other kinds of works, specifically designed to ensure +cooperation with the community in the case of network server software. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +our General Public Licenses are 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. + + 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. + + Developers that use our General Public Licenses protect your rights +with two steps: (1) assert copyright on the software, and (2) offer +you this License which gives you legal permission to copy, distribute +and/or modify the software. + + A secondary benefit of defending all users' freedom is that +improvements made in alternate versions of the program, if they +receive widespread use, become available for other developers to +incorporate. Many developers of free software are heartened and +encouraged by the resulting cooperation. However, in the case of +software used on network servers, this result may fail to come about. +The GNU General Public License permits making a modified version and +letting the public access it on a server without ever releasing its +source code to the public. + + The GNU Affero General Public License is designed specifically to +ensure that, in such cases, the modified source code becomes available +to the community. It requires the operator of a network server to +provide the source code of the modified version running there to the +users of that server. Therefore, public use of a modified version, on +a publicly accessible server, gives the public access to the source +code of the modified version. + + An older license, called the Affero General Public License and +published by Affero, was designed to accomplish similar goals. This is +a different license, not a version of the Affero GPL, but Affero has +released a new version of the Affero GPL which permits relicensing under +this license. + + 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 Affero 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. Remote Network Interaction; Use with the GNU General Public License. + + Notwithstanding any other provision of this License, if you modify the +Program, your modified version must prominently offer all users +interacting with it remotely through a computer network (if your version +supports such interaction) an opportunity to receive the Corresponding +Source of your version by providing access to the Corresponding Source +from a network server at no charge, through some standard or customary +means of facilitating copying of software. This Corresponding Source +shall include the Corresponding Source for any work covered by version 3 +of the GNU General Public License that is incorporated pursuant to the +following paragraph. + + 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 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 work with which it is combined will remain governed by version +3 of the GNU General Public License. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU Affero 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 Affero 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 Affero 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 Affero 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. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero 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 Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If your software can interact with users remotely through a computer +network, you should also make sure that it provides a way for users to +get its source. For example, if your program is a web application, its +interface could display a "Source" link that leads users to an archive +of the code. There are many ways you could offer source, and different +solutions will be better for different programs; see section 13 for the +specific requirements. + + 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 AGPL, see +. diff --git a/OpenCL.cabal b/OpenCL.cabal new file mode 100644 --- /dev/null +++ b/OpenCL.cabal @@ -0,0 +1,43 @@ +Name: OpenCL +Version: 1.0.1.3 +License: GPL +License-File: LICENSE +Author: Luis Cabellos +Copyright: (c) 2011 Luis Cabellos +Category: GPU, FFI, Graphics +Build-Type: Simple +Stability: Experimental +Maintainer: Luis Cabellos +Homepage: https://github.com/zhensydow/opencl +Synopsis: Haskell high-level wrapper for OpenCL +Description: Haskell FFI binding to OpenCL library. It includes high-level wrappers to help development. Based on OpenCLRaw package. +bug-reports: https://github.com/zhensydow/opencl/issues +Cabal-Version: >=1.8 +Tested-With: GHC + +source-repository this + type: git + location: https://zhensydow@github.com/zhensydow/opencl.git + tag: 1.0.1.3 + branch: master + +source-repository head + type: git + location: https://zhensydow@github.com/zhensydow/opencl.git + branch: develop + +Library + Build-tools: c2hs + hs-Source-Dirs: src + ghc-options: -Wall + Build-Depends: base >=4.0 && < 5, bytestring -any, mtl==2.0.* + Exposed-Modules: + System.GPU.OpenCL + System.GPU.OpenCL.Query + System.GPU.OpenCL.Context + System.GPU.OpenCL.CommandQueue + System.GPU.OpenCL.Memory + System.GPU.OpenCL.Event + System.GPU.OpenCL.Program + Other-Modules: + System.GPU.OpenCL.Types diff --git a/Setup.hs b/Setup.hs new file mode 100644 --- /dev/null +++ b/Setup.hs @@ -0,0 +1,2 @@ +import Distribution.Simple +main = defaultMain diff --git a/src/System/GPU/OpenCL.hs b/src/System/GPU/OpenCL.hs new file mode 100644 --- /dev/null +++ b/src/System/GPU/OpenCL.hs @@ -0,0 +1,39 @@ +-- ----------------------------------------------------------------------------- +-- This file is part of Haskell-Opencl. + +-- Haskell-Opencl 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. + +-- Haskell-Opencl 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 Haskell-Opencl. If not, see . +-- ----------------------------------------------------------------------------- +module System.GPU.OpenCL( + -- * Basic Types + CLError(..), CLint, CLuint, CLulong, + -- * Modules + module System.GPU.OpenCL.Query, + module System.GPU.OpenCL.Context, + module System.GPU.OpenCL.CommandQueue, + module System.GPU.OpenCL.Memory, + module System.GPU.OpenCL.Event, + module System.GPU.OpenCL.Program ) + where + +-- ----------------------------------------------------------------------------- +import System.GPU.OpenCL.Query +import System.GPU.OpenCL.Context +import System.GPU.OpenCL.CommandQueue +import System.GPU.OpenCL.Memory +import System.GPU.OpenCL.Event +import System.GPU.OpenCL.Program +import System.GPU.OpenCL.Types( + CLError(..), CLint, CLuint, CLulong ) + +-- ----------------------------------------------------------------------------- diff --git a/src/System/GPU/OpenCL/CommandQueue.chs b/src/System/GPU/OpenCL/CommandQueue.chs new file mode 100644 --- /dev/null +++ b/src/System/GPU/OpenCL/CommandQueue.chs @@ -0,0 +1,553 @@ +-- ----------------------------------------------------------------------------- +-- This file is part of Haskell-Opencl. + +-- Haskell-Opencl 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. + +-- Haskell-Opencl 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 Haskell-Opencl. If not, see . +-- ----------------------------------------------------------------------------- +{-# LANGUAGE ForeignFunctionInterface, ScopedTypeVariables #-} +module System.GPU.OpenCL.CommandQueue( + -- * Types + CLCommandQueue, CLCommandQueueProperty(..), + -- * Command Queue Functions + clCreateCommandQueue, clRetainCommandQueue, clReleaseCommandQueue, + clGetCommandQueueContext, clGetCommandQueueDevice, + clGetCommandQueueReferenceCount, clGetCommandQueueProperties, + clSetCommandQueueProperty, + -- * Memory Commands + clEnqueueReadBuffer, clEnqueueWriteBuffer, + -- * Executing Kernels + clEnqueueNDRangeKernel, clEnqueueTask, clEnqueueMarker, + clEnqueueWaitForEvents, clEnqueueBarrier, + -- * Flush and Finish + clFlush, clFinish + ) where + +-- ----------------------------------------------------------------------------- +import Foreign +import Foreign.C.Types +import System.GPU.OpenCL.Types( + CLint, CLbool, CLuint, CLCommandQueueProperty_, CLCommandQueueInfo_, + CLError(..), CLCommandQueue, CLDeviceID, CLContext, CLCommandQueueProperty(..), + CLEvent, CLMem, CLKernel, + wrapCheckSuccess, wrapPError, wrapGetInfo, getCLValue, getEnumCL, + bitmaskToCommandQueueProperties, bitmaskFromFlags ) + +#include + +-- ----------------------------------------------------------------------------- +foreign import ccall "clCreateCommandQueue" raw_clCreateCommandQueue :: + CLContext -> CLDeviceID -> CLCommandQueueProperty_ -> Ptr CLint -> IO CLCommandQueue +foreign import ccall "clRetainCommandQueue" raw_clRetainCommandQueue :: + CLCommandQueue -> IO CLint +foreign import ccall "clReleaseCommandQueue" raw_clReleaseCommandQueue :: + CLCommandQueue -> IO CLint +foreign import ccall "clGetCommandQueueInfo" raw_clGetCommandQueueInfo :: + CLCommandQueue -> CLCommandQueueInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint +foreign import ccall "clSetCommandQueueProperty" raw_clSetCommandQueueProperty :: + CLCommandQueue -> CLCommandQueueProperty_ -> CLbool -> Ptr CLCommandQueueProperty_ -> IO CLint +foreign import ccall "clEnqueueReadBuffer" raw_clEnqueueReadBuffer :: + CLCommandQueue -> CLMem -> CLbool -> CSize -> CSize -> Ptr () -> CLuint -> Ptr CLEvent -> Ptr CLEvent -> IO CLint +foreign import ccall "clEnqueueWriteBuffer" raw_clEnqueueWriteBuffer :: + CLCommandQueue -> CLMem -> CLbool -> CSize -> CSize -> Ptr () -> CLuint -> Ptr CLEvent -> Ptr CLEvent -> IO CLint +foreign import ccall "clEnqueueNDRangeKernel" raw_clEnqueueNDRangeKernel :: + CLCommandQueue -> CLKernel -> CLuint -> Ptr CSize -> Ptr CSize -> Ptr CSize -> CLuint -> Ptr CLEvent -> Ptr CLEvent -> IO CLint +foreign import ccall "clEnqueueTask" raw_clEnqueueTask :: + CLCommandQueue -> CLKernel -> CLuint -> Ptr CLEvent -> Ptr CLEvent -> IO CLint +foreign import ccall "clEnqueueMarker" raw_clEnqueueMarker :: + CLCommandQueue -> Ptr CLEvent -> IO CLint +foreign import ccall "clEnqueueWaitForEvents" raw_clEnqueueWaitForEvents :: + CLCommandQueue -> CLuint -> Ptr CLEvent -> IO CLint +foreign import ccall "clEnqueueBarrier" raw_clEnqueueBarrier :: + CLCommandQueue -> IO CLint +foreign import ccall "clFlush" raw_clFlush :: + CLCommandQueue -> IO CLint +foreign import ccall "clFinish" raw_clFinish :: + CLCommandQueue -> IO CLint + +-- ----------------------------------------------------------------------------- +{-| Create a command-queue on a specific device. + +The OpenCL functions that are submitted to a command-queue are enqueued in the +order the calls are made but can be configured to execute in-order or +out-of-order. The properties argument in clCreateCommandQueue can be used to +specify the execution order. + +If the 'CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE' property of a command-queue is +not set, the commands enqueued to a command-queue execute in order. For example, +if an application calls 'clEnqueueNDRangeKernel' to execute kernel A followed by +a 'clEnqueueNDRangeKernel' to execute kernel B, the application can assume that +kernel A finishes first and then kernel B is executed. If the memory objects +output by kernel A are inputs to kernel B then kernel B will see the correct +data in memory objects produced by execution of kernel A. If the +'CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE' property of a commandqueue is set, then +there is no guarantee that kernel A will finish before kernel B starts execution. + +Applications can configure the commands enqueued to a command-queue to execute +out-of-order by setting the 'CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE' property of +the command-queue. This can be specified when the command-queue is created or +can be changed dynamically using 'clCreateCommandQueue'. In out-of-order +execution mode there is no guarantee that the enqueued commands will finish +execution in the order they were queued. As there is no guarantee that kernels +will be executed in order, i.e. based on when the 'clEnqueueNDRangeKernel' calls +are made within a command-queue, it is therefore possible that an earlier +'clEnqueueNDRangeKernel' call to execute kernel A identified by event A may +execute and/or finish later than a 'clEnqueueNDRangeKernel' call to execute +kernel B which was called by the application at a later point in time. To +guarantee a specific order of execution of kernels, a wait on a particular event +(in this case event A) can be used. The wait for event A can be specified in the +event_wait_list argument to 'clEnqueueNDRangeKernel' for kernel B. + +In addition, a wait for events or a barrier command can be enqueued to the +command-queue. The wait for events command ensures that previously enqueued +commands identified by the list of events to wait for have finished before the +next batch of commands is executed. The barrier command ensures that all +previously enqueued commands in a command-queue have finished execution before +the next batch of commands is executed. + +Similarly, commands to read, write, copy or map memory objects that are enqueued +after 'clEnqueueNDRangeKernel', 'clEnqueueTask' or 'clEnqueueNativeKernel' +commands are not guaranteed to wait for kernels scheduled for execution to have +completed (if the 'CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE' property is set). To +ensure correct ordering of commands, the event object returned by +'clEnqueueNDRangeKernel', 'clEnqueueTask' or 'clEnqueueNativeKernel' can be +used to enqueue a wait for event or a barrier command can be enqueued that must +complete before reads or writes to the memory object(s) occur. +-} +clCreateCommandQueue :: CLContext -> CLDeviceID -> [CLCommandQueueProperty] + -> IO (Either CLError CLCommandQueue) +clCreateCommandQueue ctx did xs = wrapPError $ \perr -> do + raw_clCreateCommandQueue ctx did props perr + where + props = bitmaskFromFlags xs + +{-| Increments the command_queue reference count. 'clCreateCommandQueue' +performs an implicit retain. This is very helpful for 3rd party libraries, which +typically get a command-queue passed to them by the application. However, it is +possible that the application may delete the command-queue without informing the +library. Allowing functions to attach to (i.e. retain) and release a +command-queue solves the problem of a command-queue being used by a library no +longer being valid. Returns 'True' if the function is executed successfully. It +returns 'False' if command_queue is not a valid command-queue. +-} +clRetainCommandQueue :: CLCommandQueue -> IO Bool +clRetainCommandQueue = wrapCheckSuccess . raw_clRetainCommandQueue + +-- | Decrements the command_queue reference count. +-- After the command_queue reference count becomes zero and all commands queued +-- to command_queue have finished (e.g., kernel executions, memory object +-- updates, etc.), the command-queue is deleted. +-- Returns 'True' if the function is executed successfully. It returns 'False' +-- if command_queue is not a valid command-queue. +clReleaseCommandQueue :: CLCommandQueue -> IO Bool +clReleaseCommandQueue = wrapCheckSuccess . raw_clReleaseCommandQueue + +#c +enum CLCommandQueueInfo { + cL_QUEUE_CONTEXT=CL_QUEUE_CONTEXT, + cL_QUEUE_DEVICE=CL_QUEUE_DEVICE, + cL_QUEUE_REFERENCE_COUNT=CL_QUEUE_REFERENCE_COUNT, + cL_QUEUE_PROPERTIES=CL_QUEUE_PROPERTIES, + }; +#endc +{#enum CLCommandQueueInfo {upcaseFirstLetter} #} + +-- | Return the context specified when the command-queue is created. +clGetCommandQueueContext :: CLCommandQueue -> IO (Either CLError CLContext) +clGetCommandQueueContext cq = wrapGetInfo (\(dat :: Ptr CLContext) + -> raw_clGetCommandQueueInfo cq infoid size (castPtr dat)) id + where + infoid = getCLValue CL_QUEUE_CONTEXT + size = fromIntegral $ sizeOf (nullPtr::CLContext) + +-- | Return the device specified when the command-queue is created. +clGetCommandQueueDevice :: CLCommandQueue -> IO (Either CLError CLDeviceID) +clGetCommandQueueDevice cq = wrapGetInfo (\(dat :: Ptr CLDeviceID) + -> raw_clGetCommandQueueInfo cq infoid size (castPtr dat)) id + where + infoid = getCLValue CL_QUEUE_DEVICE + size = fromIntegral $ sizeOf (nullPtr::CLDeviceID) + +-- | Return the command-queue reference count. +-- The reference count returned should be considered immediately stale. It is +-- unsuitable for general use in applications. This feature is provided for +-- identifying memory leaks. +clGetCommandQueueReferenceCount :: CLCommandQueue -> IO (Either CLError CLuint) +clGetCommandQueueReferenceCount cq = wrapGetInfo (\(dat :: Ptr CLuint) + -> raw_clGetCommandQueueInfo cq infoid size (castPtr dat)) id + where + infoid = getCLValue CL_QUEUE_REFERENCE_COUNT + size = fromIntegral $ sizeOf (0::CLuint) + + +-- | Return the currently specified properties for the command-queue. These +-- properties are specified by the properties argument in 'clCreateCommandQueue' +-- , and can be changed by 'clSetCommandQueueProperty'. +clGetCommandQueueProperties :: CLCommandQueue -> IO (Either CLError [CLCommandQueueProperty]) +clGetCommandQueueProperties cq = wrapGetInfo (\(dat :: Ptr CLCommandQueueProperty_) + -> raw_clGetCommandQueueInfo cq infoid size (castPtr dat)) bitmaskToCommandQueueProperties + where + infoid = getCLValue CL_QUEUE_PROPERTIES + size = fromIntegral $ sizeOf (0::CLCommandQueueProperty_) + +{-| Enable or disable the properties of a command-queue. Returns the +command-queue properties before they were changed by +'clSetCommandQueueProperty'. As specified for 'clCreateCommandQueue', the +'CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE' command-queue property determines +whether the commands in a command-queue are executed in-order or +out-of-order. Changing this command-queue property will cause the OpenCL +implementation to block until all previously queued commands in command_queue +have completed. This can be an expensive operation and therefore changes to the +'CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE' property should be only done when +absolutely necessary. + + It is possible that a device(s) becomes unavailable after a context and +command-queues that use this device(s) have been created and commands have been +queued to command-queues. In this case the behavior of OpenCL API calls that use +this context (and command-queues) are considered to be +implementation-defined. The user callback function, if specified when the +context is created, can be used to record appropriate information when the +device becomes unavailable. +-} +clSetCommandQueueProperty :: CLCommandQueue -> [CLCommandQueueProperty] -> Bool + -> IO (Either CLError [CLCommandQueueProperty]) +clSetCommandQueueProperty cq xs val = alloca $ \(dat :: Ptr CLCommandQueueProperty_) -> do + errcode <- raw_clSetCommandQueueProperty cq props (fromBool val) dat + if errcode == getCLValue CL_SUCCESS + then fmap (Right . bitmaskToCommandQueueProperties) $ peek dat + else return . Left . getEnumCL $ errcode + where + props = bitmaskFromFlags xs + +-- ----------------------------------------------------------------------------- +clEnqueue :: (CLuint -> Ptr CLEvent -> Ptr CLEvent -> IO CLint) -> [CLEvent] + -> IO (Either CLError CLEvent) +clEnqueue f [] = alloca $ \event -> do + errcode <- f 0 nullPtr event + if errcode == getCLValue CL_SUCCESS + then fmap Right $ peek event + else return . Left . getEnumCL $ errcode +clEnqueue f events = allocaArray nevents $ \pevents -> do + pokeArray pevents events + alloca $ \event -> do + errcode <- f cnevents pevents event + if errcode == getCLValue CL_SUCCESS + then fmap Right $ peek event + else return . Left . getEnumCL $ errcode + where + nevents = length events + cnevents = fromIntegral nevents + +-- ----------------------------------------------------------------------------- +{-| Enqueue commands to read from a buffer object to host memory. Calling +clEnqueueReadBuffer to read a region of the buffer object with the ptr argument +value set to host_ptr + offset, where host_ptr is a pointer to the memory region +specified when the buffer object being read is created with +'CL_MEM_USE_HOST_PTR', must meet the following requirements in order to avoid +undefined behavior: + + * All commands that use this buffer object have finished execution before the +read command begins execution + + * The buffer object is not mapped + + * The buffer object is not used by any command-queue until the read command has +finished execution Errors + +'clEnqueueReadBuffer' returns the event if the function is executed +successfully. Otherwise, it returns one of the following errors: + + * 'CL_INVALID_COMMAND_QUEUE' if command_queue is not a valid command-queue. + + * 'CL_INVALID_CONTEXT' if the context associated with command_queue and buffer +are not the same or if the context associated with command_queue and events in +event_wait_list are not the same. + + * 'CL_INVALID_MEM_OBJECT' if buffer is not a valid buffer object. + + * 'CL_INVALID_VALUE' if the region being read specified by (offset, cb) is out +of bounds or if ptr is a NULL value. + + * 'CL_INVALID_EVENT_WAIT_LIST' if event_wait_list is NULL and +num_events_in_wait_list greater than 0, or event_wait_list is not NULL and +num_events_in_wait_list is 0, or if event objects in event_wait_list are not +valid events. + + * 'CL_MEM_OBJECT_ALLOCATION_FAILURE' if there is a failure to allocate memory +for data store associated with buffer. + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +by the OpenCL implementation on the host. +-} +clEnqueueReadBuffer :: Integral a => CLCommandQueue -> CLMem -> Bool -> a -> a + -> Ptr () -> [CLEvent] -> IO (Either CLError CLEvent) +clEnqueueReadBuffer cq mem check off size dat = clEnqueue (raw_clEnqueueReadBuffer cq mem (fromBool check) (fromIntegral off) (fromIntegral size) dat) + +{-| Enqueue commands to write to a buffer object from host memory.Calling +clEnqueueWriteBuffer to update the latest bits in a region of the buffer object +with the ptr argument value set to host_ptr + offset, where host_ptr is a +pointer to the memory region specified when the buffer object being written is +created with 'CL_MEM_USE_HOST_PTR', must meet the following requirements in +order to avoid undefined behavior: + + * The host memory region given by (host_ptr + offset, cb) contains the latest +bits when the enqueued write command begins execution. + + * The buffer object is not mapped. + + * The buffer object is not used by any command-queue until the write command +has finished execution. + +'clEnqueueWriteBuffer' returns the Event if the function is executed +successfully. Otherwise, it returns one of the following errors: + + * 'CL_INVALID_COMMAND_QUEUE' if command_queue is not a valid command-queue. + + * 'CL_INVALID_CONTEXT' if the context associated with command_queue and buffer +are not the same or if the context associated with command_queue and events in +event_wait_list are not the same. + + * 'CL_INVALID_MEM_OBJECT' if buffer is not a valid buffer object. + + * 'CL_INVALID_VALUE' if the region being written specified by (offset, cb) is +out of bounds or if ptr is a NULL value. + + * 'CL_INVALID_EVENT_WAIT_LIST' if event_wait_list is NULL and +num_events_in_wait_list greater than 0, or event_wait_list is not NULL and +num_events_in_wait_list is 0, or if event objects in event_wait_list are not +valid events. + + * 'CL_MEM_OBJECT_ALLOCATION_FAILURE' if there is a failure to allocate memory +for data store associated with buffer. + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +by the OpenCL implementation on the host. +-} +clEnqueueWriteBuffer :: Integral a => CLCommandQueue -> CLMem -> Bool -> a -> a + -> Ptr () -> [CLEvent] -> IO (Either CLError CLEvent) +clEnqueueWriteBuffer cq mem check off size dat = clEnqueue (raw_clEnqueueWriteBuffer cq mem (fromBool check) (fromIntegral off) (fromIntegral size) dat) + +-- ----------------------------------------------------------------------------- +{-| Enqueues a command to execute a kernel on a device. Each work-item is +uniquely identified by a global identifier. The global ID, which can be read +inside the kernel, is computed using the value given by global_work_size and +global_work_offset. In OpenCL 1.0, the starting global ID is always (0, 0, +... 0). In addition, a work-item is also identified within a work-group by a +unique local ID. The local ID, which can also be read by the kernel, is computed +using the value given by local_work_size. The starting local ID is always (0, 0, +... 0). + +Returns the event if the kernel execution was successfully queued. Otherwise, it +returns one of the following errors: + + * 'CL_INVALID_PROGRAM_EXECUTABLE' if there is no successfully built program +executable available for device associated with command_queue. + + * 'CL_INVALID_COMMAND_QUEUE' if command_queue is not a valid command-queue. + + * 'CL_INVALID_KERNEL' if kernel is not a valid kernel object. + + * 'CL_INVALID_CONTEXT' if context associated with command_queue and kernel is +not the same or if the context associated with command_queue and events in +event_wait_list are not the same. + + * 'CL_INVALID_KERNEL_ARGS' if the kernel argument values have not been +specified. + + * 'CL_INVALID_WORK_DIMENSION' if work_dim is not a valid value (i.e. a value +between 1 and 3). + + * 'CL_INVALID_WORK_GROUP_SIZE' if local_work_size is specified and number of +work-items specified by global_work_size is not evenly divisable by size of +work-group given by local_work_size or does not match the work-group size +specified for kernel using the __attribute__((reqd_work_group_size(X, Y, Z))) +qualifier in program source. + + * 'CL_INVALID_WORK_GROUP_SIZE' if local_work_size is specified and the total +number of work-items in the work-group computed as local_work_size[0] +*... local_work_size[work_dim - 1] is greater than the value specified by +'CL_DEVICE_MAX_WORK_GROUP_SIZE' in the table of OpenCL Device Queries for +clGetDeviceInfo. + + * 'CL_INVALID_WORK_GROUP_SIZE' if local_work_size is NULL and the +__attribute__((reqd_work_group_size(X, Y, Z))) qualifier is used to declare the +work-group size for kernel in the program source. + + * 'CL_INVALID_WORK_ITEM_SIZE' if the number of work-items specified in any of +local_work_size[0], ... local_work_size[work_dim - 1] is greater than the +corresponding values specified by 'CL_DEVICE_MAX_WORK_ITEM_SIZES'[0], +.... 'CL_DEVICE_MAX_WORK_ITEM_SIZES'[work_dim - 1]. + + * 'CL_OUT_OF_RESOURCES' if there is a failure to queue the execution instance +of kernel on the command-queue because of insufficient resources needed to +execute the kernel. For example, the explicitly specified local_work_size causes +a failure to execute the kernel because of insufficient resources such as +registers or local memory. Another example would be the number of read-only +image args used in kernel exceed the 'CL_DEVICE_MAX_READ_IMAGE_ARGS' value for +device or the number of write-only image args used in kernel exceed the +'CL_DEVICE_MAX_WRITE_IMAGE_ARGS' value for device or the number of samplers used +in kernel exceed 'CL_DEVICE_MAX_SAMPLERS' for device. + + * 'CL_MEM_OBJECT_ALLOCATION_FAILURE' if there is a failure to allocate memory for data store associated with image or buffer objects specified as arguments to kernel. + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required by +the OpenCL implementation on the host. +-} +clEnqueueNDRangeKernel :: Integral a => CLCommandQueue -> CLKernel -> [a] -> [a] -> [CLEvent] -> IO (Either CLError CLEvent) +clEnqueueNDRangeKernel cq krn gws lws events = withArray (map fromIntegral gws) $ \pgws -> withArray (map fromIntegral lws) $ \plws -> do + clEnqueue (raw_clEnqueueNDRangeKernel cq krn num nullPtr pgws plws) events + where + num = fromIntegral $ length gws + +{-| Enqueues a command to execute a kernel on a device. The kernel is executed +using a single work-item. + +'clEnqueueTask' is equivalent to calling 'clEnqueueNDRangeKernel' with work_dim += 1, global_work_offset = [], global_work_size[0] set to 1, and +local_work_size[0] set to 1. + +Returns the evens if the kernel execution was successfully queued, or one of the +errors below: + + * 'CL_INVALID_PROGRAM_EXECUTABLE' if there is no successfully built program +executable available for device associated with command_queue. + + * 'CL_INVALID_COMMAND_QUEUE if' command_queue is not a valid command-queue. + + * 'CL_INVALID_KERNEL' if kernel is not a valid kernel object. + + * 'CL_INVALID_CONTEXT' if context associated with command_queue and kernel is +not the same or if the context associated with command_queue and events in +event_wait_list are not the same. + + * 'CL_INVALID_KERNEL_ARGS' if the kernel argument values have not been specified. + + * 'CL_INVALID_WORK_GROUP_SIZE' if a work-group size is specified for kernel +using the __attribute__((reqd_work_group_size(X, Y, Z))) qualifier in program +source and is not (1, 1, 1). + + * 'CL_OUT_OF_RESOURCES' if there is a failure to queue the execution instance +of kernel on the command-queue because of insufficient resources needed to +execute the kernel. + + * 'CL_MEM_OBJECT_ALLOCATION_FAILURE' if there is a failure to allocate memory +for data store associated with image or buffer objects specified as arguments to +kernel. + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +by the OpenCL implementation on the host. +-} +clEnqueueTask :: CLCommandQueue -> CLKernel -> [CLEvent] + -> IO (Either CLError CLEvent) +clEnqueueTask cq krn = clEnqueue (raw_clEnqueueTask cq krn) + +-- ----------------------------------------------------------------------------- +-- | Enqueues a marker command to command_queue. The marker command returns an +-- event which can be used to queue a wait on this marker event i.e. wait for +-- all commands queued before the marker command to complete. Returns the event +-- if the function is successfully executed. It returns +-- 'CL_INVALID_COMMAND_QUEUE' if command_queue is not a valid command-queue and +-- returns 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources +-- required by the OpenCL implementation on the host. +clEnqueueMarker :: CLCommandQueue -> IO (Either CLError CLEvent) +clEnqueueMarker cq = alloca $ \event -> do + errcode <- raw_clEnqueueMarker cq event + if errcode == getCLValue CL_SUCCESS + then fmap Right $ peek event + else return . Left . getEnumCL $ errcode + +{-| Enqueues a wait for a specific event or a list of events to complete before +any future commands queued in the command-queue are executed. The context +associated with events in event_list and command_queue must be the same. + +Returns one of the errors below when fails: + + * 'CL_INVALID_COMMAND_QUEUE' if command_queue is not a valid command-queue. + + * 'CL_INVALID_CONTEXT' if the context associated with command_queue and events +in event_list are not the same. + + * 'CL_INVALID_VALUE' if num_events is zero. + + * 'CL_INVALID_EVENT' if event objects specified in event_list are not valid +events. + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +by the OpenCL implementation on the host. +-} +clEnqueueWaitForEvents :: CLCommandQueue -> [CLEvent] -> IO (Either CLError ()) +clEnqueueWaitForEvents cq [] = do + errcode <- raw_clEnqueueWaitForEvents cq 0 nullPtr + if errcode == getCLValue CL_SUCCESS + then return $ Right () + else return . Left . getEnumCL $ errcode +clEnqueueWaitForEvents cq events = allocaArray nevents $ \pevents -> do + pokeArray pevents events + errcode <- raw_clEnqueueWaitForEvents cq cnevents pevents + if errcode == getCLValue CL_SUCCESS + then return $ Right () + else return . Left . getEnumCL $ errcode + where + nevents = length events + cnevents = fromIntegral nevents + +-- | 'clEnqueueBarrier' is a synchronization point that ensures that all queued +-- commands in command_queue have finished execution before the next batch of +-- commands can begin execution. It returns 'CL_INVALID_COMMAND_QUEUE' if +-- command_queue is not a valid command-queue and returns +-- 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +-- by the OpenCL implementation on the host. +clEnqueueBarrier :: CLCommandQueue -> IO (Either CLError ()) +clEnqueueBarrier cq = do + errcode <- raw_clEnqueueBarrier cq + if errcode == getCLValue CL_SUCCESS + then return $ Right () + else return . Left . getEnumCL $ errcode + +-- ----------------------------------------------------------------------------- +{-| Issues all previously queued OpenCL commands in a command-queue to the +device associated with the command-queue. 'clFlush' only guarantees that all +queued commands to command_queue get issued to the appropriate device. There is +no guarantee that they will be complete after 'clFlush' returns. + + 'clFlush' returns 'True' if the function call was executed successfully. It +returns 'False' if command_queue is not a valid command-queue or if there is a +failure to allocate resources required by the OpenCL implementation on the host. + + Any blocking commands queued in a command-queue such as 'clEnqueueReadImage' or +'clEnqueueReadBuffer' with blocking_read set to 'True', 'clEnqueueWriteImage' or +'clEnqueueWriteBuffer' with blocking_write set to 'True', 'clEnqueueMapImage' or +'clEnqueueMapBuffer' with blocking_map set to 'True' or 'clWaitForEvents' +perform an implicit flush of the command-queue. + + To use event objects that refer to commands enqueued in a command-queue as +event objects to wait on by commands enqueued in a different command-queue, the +application must call a 'clFlush' or any blocking commands that perform an +implicit flush of the command-queue where the commands that refer to these event +objects are enqueued. +-} +clFlush :: CLCommandQueue -> IO Bool +clFlush = wrapCheckSuccess . raw_clFlush + +-- | Blocks until all previously queued OpenCL commands in a command-queue are +-- issued to the associated device and have completed. +-- 'clFinish' does not return until all queued commands in command_queue have +-- been processed and completed. 'clFinish' is also a synchronization point. +-- +-- 'clFinish' returns 'True' if the function call was executed successfully. It +-- returns 'False' if command_queue is not a valid command-queue or if there is +-- a failure to allocate resources required by the OpenCL implementation on the +-- host. +clFinish :: CLCommandQueue -> IO Bool +clFinish = wrapCheckSuccess . raw_clFinish + +-- ----------------------------------------------------------------------------- diff --git a/src/System/GPU/OpenCL/Context.chs b/src/System/GPU/OpenCL/Context.chs new file mode 100644 --- /dev/null +++ b/src/System/GPU/OpenCL/Context.chs @@ -0,0 +1,150 @@ +-- ----------------------------------------------------------------------------- +-- This file is part of Haskell-Opencl. + +-- Haskell-Opencl 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. + +-- Haskell-Opencl 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 Haskell-Opencl. If not, see . +-- ----------------------------------------------------------------------------- +{-# LANGUAGE ForeignFunctionInterface, ScopedTypeVariables #-} +module System.GPU.OpenCL.Context( + -- * Types + CLContext, + -- * Context Functions + clCreateContext, clCreateContextFromType, clRetainContext, clReleaseContext, + clGetContextReferenceCount, clGetContextDevices ) + where + +-- ----------------------------------------------------------------------------- +import Foreign( + Ptr, FunPtr, nullPtr, castPtr, alloca, allocaArray, peek, peekArray, + pokeArray ) +import Foreign.C.Types( CSize ) +import Foreign.C.String( CString, peekCString ) +import Foreign.Storable( sizeOf ) +import System.GPU.OpenCL.Types( + CLuint, CLint, CLDeviceType_, CLContextInfo_, CLContextProperty_, CLDeviceID, + CLContext, CLDeviceType, CLError(..), bitmaskFromFlags, getCLValue, getEnumCL, + wrapCheckSuccess, wrapPError, wrapGetInfo ) + +#include + +-- ----------------------------------------------------------------------------- +type ContextCallback = CString -> Ptr () -> CSize -> Ptr () -> IO () +foreign import ccall "wrapper" wrapContextCallback :: + ContextCallback -> IO (FunPtr ContextCallback) +foreign import ccall "clCreateContext" raw_clCreateContext :: + Ptr CLContextProperty_ -> CLuint -> Ptr CLDeviceID -> FunPtr ContextCallback -> + Ptr () -> Ptr CLint -> IO CLContext +foreign import ccall "clCreateContextFromType" raw_clCreateContextFromType :: + Ptr CLContextProperty_ -> CLDeviceType_ -> FunPtr ContextCallback -> + Ptr () -> Ptr CLint -> IO CLContext +foreign import ccall "clRetainContext" raw_clRetainContext :: + CLContext -> IO CLint +foreign import ccall "clReleaseContext" raw_clReleaseContext :: + CLContext -> IO CLint +foreign import ccall "clGetContextInfo" raw_clGetContextInfo :: + CLContext -> CLContextInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint + +-- ----------------------------------------------------------------------------- +mkContextCallback :: (String -> IO ()) -> ContextCallback +mkContextCallback f msg _ _ _ = peekCString msg >>= f + +-- | Creates an OpenCL context. +-- An OpenCL context is created with one or more devices. Contexts are used by +-- the OpenCL runtime for managing objects such as command-queues, memory, +-- program and kernel objects and for executing kernels on one or more devices +-- specified in the context. +clCreateContext :: [CLDeviceID] -> (String -> IO ()) + -> IO (Either CLError CLContext) +clCreateContext devs f = allocaArray ndevs $ \pdevs -> do + pokeArray pdevs devs + wrapPError $ \perr -> do + fptr <- wrapContextCallback $ mkContextCallback f + raw_clCreateContext nullPtr cndevs pdevs fptr nullPtr perr + where + ndevs = length devs + cndevs = fromIntegral ndevs + +-- | Create an OpenCL context from a device type that identifies the specific +-- device(s) to use. +clCreateContextFromType :: [CLDeviceType] -> (String -> IO ()) + -> IO (Either CLError CLContext) +clCreateContextFromType xs f = wrapPError $ \perr -> do + fptr <- wrapContextCallback $ mkContextCallback f + raw_clCreateContextFromType nullPtr types fptr nullPtr perr + where + types = bitmaskFromFlags xs + +-- | Increment the context reference count. +-- 'clCreateContext' and 'clCreateContextFromType' perform an implicit retain. +-- This is very helpful for 3rd party libraries, which typically get a context +-- passed to them by the application. However, it is possible that the +-- application may delete the context without informing the library. Allowing +-- functions to attach to (i.e. retain) and release a context solves the +-- problem of a context being used by a library no longer being valid. +-- Returns 'True' if the function is executed successfully, or 'False' if +-- context is not a valid OpenCL context. +clRetainContext :: CLContext -> IO Bool +clRetainContext ctx = wrapCheckSuccess $ raw_clRetainContext ctx + +-- | Decrement the context reference count. +-- After the context reference count becomes zero and all the objects attached +-- to context (such as memory objects, command-queues) are released, the +-- context is deleted. +-- Returns 'True' if the function is executed successfully, or 'False' if +-- context is not a valid OpenCL context. +clReleaseContext :: CLContext -> IO Bool +clReleaseContext ctx = wrapCheckSuccess $ raw_clReleaseContext ctx + +getContextInfoSize :: CLContext -> CLContextInfo_ -> IO (Either CLError CSize) +getContextInfoSize ctx infoid = alloca $ \(value_size :: Ptr CSize) -> do + errcode <- raw_clGetContextInfo ctx infoid 0 nullPtr value_size + if errcode == getCLValue CL_SUCCESS + then fmap Right $ peek value_size + else return . Left . getEnumCL $ errcode + +#c +enum CLContextInfo { + cL_CONTEXT_REFERENCE_COUNT=CL_CONTEXT_REFERENCE_COUNT, + cL_CONTEXT_DEVICES=CL_CONTEXT_DEVICES, + cL_CONTEXT_PROPERTIES=CL_CONTEXT_PROPERTIES + }; +#endc +{#enum CLContextInfo {upcaseFirstLetter} #} + +-- | Return the context reference count. The reference count returned should be +-- considered immediately stale. It is unsuitable for general use in +-- applications. This feature is provided for identifying memory leaks. +clGetContextReferenceCount :: CLContext -> IO (Either CLError CLuint) +clGetContextReferenceCount ctx = wrapGetInfo (\(dat :: Ptr CLuint) + -> raw_clGetContextInfo ctx infoid size (castPtr dat)) id + where + infoid = getCLValue CL_CONTEXT_REFERENCE_COUNT + size = fromIntegral $ sizeOf (0::CLuint) + +-- | Return the list of devices in context. +clGetContextDevices :: CLContext -> IO (Either CLError [CLDeviceID]) +clGetContextDevices ctx = do + val <- getContextInfoSize ctx infoid + case val of + Left err -> return . Left $ err + Right size -> let n = (fromIntegral size) `div` elemSize + in allocaArray n $ \(buff :: Ptr CLDeviceID) -> do + errcode <- raw_clGetContextInfo ctx infoid size (castPtr buff) nullPtr + if errcode == getCLValue CL_SUCCESS + then fmap Right $ peekArray n buff + else return . Left . getEnumCL $ errcode + where + infoid = getCLValue CL_CONTEXT_DEVICES + elemSize = sizeOf (nullPtr :: CLDeviceID) + +-- ----------------------------------------------------------------------------- diff --git a/src/System/GPU/OpenCL/Event.chs b/src/System/GPU/OpenCL/Event.chs new file mode 100644 --- /dev/null +++ b/src/System/GPU/OpenCL/Event.chs @@ -0,0 +1,158 @@ +-- ----------------------------------------------------------------------------- +-- This file is part of Haskell-Opencl. + +-- Haskell-Opencl 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. + +-- Haskell-Opencl 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 Haskell-Opencl. If not, see . +-- ----------------------------------------------------------------------------- +{-# LANGUAGE ForeignFunctionInterface, ScopedTypeVariables #-} +module System.GPU.OpenCL.Event( + -- * Types + CLEvent, CLCommandType(..), CLProfilingInfo(..), CLCommandExecutionStatus(..), + -- * Functions + clWaitForEvents, clRetainEvent, clReleaseEvent, clGetEventCommandQueue, + clGetEventCommandType, clGetEventReferenceCount, + clGetEventCommandExecutionStatus, clGetEventProfilingInfo + ) where + +-- ----------------------------------------------------------------------------- +import Foreign +import Foreign.C.Types +import System.GPU.OpenCL.Types( + CLEvent, CLint, CLuint, CLulong, CLEventInfo_, CLProfilingInfo_, CLError(..), + CLCommandQueue, CLCommandType(..), CLCommandType_, + CLCommandExecutionStatus(..), CLProfilingInfo(..), getCommandExecutionStatus, + getCLValue, getEnumCL, wrapCheckSuccess, wrapGetInfo ) + +#include + +-- ----------------------------------------------------------------------------- +foreign import ccall "clWaitForEvents" raw_clWaitForEvents :: + CLuint -> Ptr CLEvent -> IO CLint +foreign import ccall "clGetEventInfo" raw_clGetEventInfo :: + CLEvent -> CLEventInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint +foreign import ccall "clRetainEvent" raw_clRetainEvent :: + CLEvent -> IO CLint +foreign import ccall "clReleaseEvent" raw_clReleaseEvent :: + CLEvent -> IO CLint +foreign import ccall "clGetEventProfilingInfo" raw_clGetEventProfilingInfo :: + CLEvent -> CLProfilingInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint + +-- ----------------------------------------------------------------------------- +-- | Waits on the host thread for commands identified by event objects in +-- event_list to complete. A command is considered complete if its execution +-- status is 'CL_COMPLETE' or a negative value. +-- Returns 'True' if the function was executed successfully. It returns 'False' +-- if the list of events is empty, or if events specified in event_list do not +-- belong to the same context, or if event objects specified in event_list are +-- not valid event objects. +clWaitForEvents :: [CLEvent] -> IO Bool +clWaitForEvents [] = return False +clWaitForEvents xs = allocaArray nevents $ \pevents -> do + pokeArray pevents xs + wrapCheckSuccess $ raw_clWaitForEvents (fromIntegral nevents) pevents + where + nevents = length xs + +-- | Increments the event reference count. +-- The OpenCL commands that return an event perform an implicit retain. +-- Returns 'True' if the function is executed successfully. It returns 'False' +-- if event is not a valid event object. +clRetainEvent :: CLEvent -> IO Bool +clRetainEvent ev = wrapCheckSuccess $ raw_clRetainEvent ev + +-- | Decrements the event reference count. +-- Decrements the event reference count. The event object is deleted once the +-- reference count becomes zero, the specific command identified by this event +-- has completed (or terminated) and there are no commands in the command-queues +-- of a context that require a wait for this event to complete. +-- Returns 'True' if the function is executed successfully. It returns 'False' +-- if event is not a valid event object. +clReleaseEvent :: CLEvent -> IO Bool +clReleaseEvent ev = wrapCheckSuccess $ raw_clReleaseEvent ev + +#c +enum CLEventInfo { + cL_EVENT_COMMAND_QUEUE=CL_EVENT_COMMAND_QUEUE, + cL_EVENT_COMMAND_TYPE=CL_EVENT_COMMAND_TYPE, + cL_EVENT_COMMAND_EXECUTION_STATUS=CL_EVENT_COMMAND_EXECUTION_STATUS, + cL_EVENT_REFERENCE_COUNT=CL_EVENT_REFERENCE_COUNT + }; +#endc +{#enum CLEventInfo {upcaseFirstLetter} #} + + +-- | Return the command-queue associated with event. +clGetEventCommandQueue :: CLEvent -> IO (Either CLError CLCommandQueue) +clGetEventCommandQueue ev = wrapGetInfo (\(dat :: Ptr CLCommandQueue) + -> raw_clGetEventInfo ev infoid size (castPtr dat)) id + where + infoid = getCLValue CL_EVENT_COMMAND_QUEUE + size = fromIntegral $ sizeOf (nullPtr::CLCommandQueue) + +-- | Return the command associated with event. +clGetEventCommandType :: CLEvent -> IO (Either CLError CLCommandType) +clGetEventCommandType ev = wrapGetInfo (\(dat :: Ptr CLCommandType_) + -> raw_clGetEventInfo ev infoid size (castPtr dat)) getEnumCL + where + infoid = getCLValue CL_EVENT_COMMAND_TYPE + size = fromIntegral $ sizeOf (0::CLCommandType_) + +-- | Return the event reference count. The reference count returned should be +-- considered immediately stale. It is unsuitable for general use in applications. +-- This feature is provided for identifying memory leaks. +clGetEventReferenceCount :: CLEvent -> IO (Either CLError CLint) +clGetEventReferenceCount ev = wrapGetInfo (\(dat :: Ptr CLint) + -> raw_clGetEventInfo ev infoid size (castPtr dat)) id + where + infoid = getCLValue CL_EVENT_REFERENCE_COUNT + size = fromIntegral $ sizeOf (0::CLint) + +-- | Return the execution status of the command identified by event. +clGetEventCommandExecutionStatus :: CLEvent -> IO (Either CLError CLCommandExecutionStatus) +clGetEventCommandExecutionStatus ev = wrapGetInfo (\(dat :: Ptr CLint) + -> raw_clGetEventInfo ev infoid size (castPtr dat)) getCommandExecutionStatus + where + infoid = getCLValue CL_EVENT_COMMAND_EXECUTION_STATUS + size = fromIntegral $ sizeOf (0::CLint) + +{-| Returns profiling information for the command associated with event if +profiling is enabled. The unsigned 64-bit values returned can be used to measure +the time in nano-seconds consumed by OpenCL commands. + +OpenCL devices are required to correctly track time across changes in device +frequency and power states. The 'CL_DEVICE_PROFILING_TIMER_RESOLUTION' specifies +the resolution of the timer i.e. the number of nanoseconds elapsed before the +timer is incremented. + +Event objects can be used to capture profiling information that measure +execution time of a command. Profiling of OpenCL commands can be enabled either +by using a command-queue created with 'CL_QUEUE_PROFILING_ENABLE' flag set in +properties argument to clCreateCommandQueue or by setting the +'CL_QUEUE_PROFILING_ENABLE' flag in properties argument to +'clSetCommandQueueProperty'. + +'clGetEventProfilingInfo' returns the valueif the function is executed +successfully and the profiling information has been recorded, and returns +'Nothing' if the 'CL_QUEUE_PROFILING_ENABLE' flag is not set for the +command-queue and if the profiling information is currently not available +(because the command identified by event has not completed), or if event is a +not a valid event object. +-} +clGetEventProfilingInfo :: CLEvent -> CLProfilingInfo -> IO (Either CLError CLulong) +clGetEventProfilingInfo ev prof = wrapGetInfo (\(dat :: Ptr CLulong) + -> raw_clGetEventProfilingInfo ev infoid size (castPtr dat)) id + where + infoid = getCLValue prof + size = fromIntegral $ sizeOf (0::CLulong) + +-- ----------------------------------------------------------------------------- diff --git a/src/System/GPU/OpenCL/Memory.chs b/src/System/GPU/OpenCL/Memory.chs new file mode 100644 --- /dev/null +++ b/src/System/GPU/OpenCL/Memory.chs @@ -0,0 +1,286 @@ +-- ----------------------------------------------------------------------------- +-- This file is part of Haskell-Opencl. + +-- Haskell-Opencl 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. + +-- Haskell-Opencl 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 Haskell-Opencl. If not, see . +-- ----------------------------------------------------------------------------- +{-# LANGUAGE ForeignFunctionInterface, ScopedTypeVariables #-} +module System.GPU.OpenCL.Memory( + -- * Types + CLMem, CLSampler, CLMemFlag(..), CLMemObjectType(..), CLAddressingMode(..), + CLFilterMode(..), + -- * Memory Functions + clCreateBuffer, clRetainMemObject, clReleaseMemObject, clGetMemType, + clGetMemFlags, clGetMemSize, clGetMemHostPtr, clGetMemMapCount, + clGetMemReferenceCount, clGetMemContext, + -- * Sampler Functions + clCreateSampler, clRetainSampler, clReleaseSampler, clGetSamplerReferenceCount, + clGetSamplerContext, clGetSamplerAddressingMode, clGetSamplerFilterMode, + clGetSamplerNormalizedCoords + ) where + +-- ----------------------------------------------------------------------------- +import Foreign +import Foreign.C.Types +import System.GPU.OpenCL.Types( + CLMem, CLContext, CLSampler, CLint, CLuint, CLbool, CLMemFlags_, CLError(..), + CLMemInfo_, CLAddressingMode_, CLFilterMode_, CLSamplerInfo_, + CLAddressingMode(..), CLFilterMode(..), CLMemFlag(..), CLMemObjectType_, + CLMemObjectType(..), + wrapPError, wrapCheckSuccess, wrapGetInfo, getEnumCL, bitmaskFromFlags, + bitmaskToMemFlags, getCLValue ) + +#include + +-- ----------------------------------------------------------------------------- +foreign import ccall "clCreateBuffer" raw_clCreateBuffer :: + CLContext -> CLMemFlags_ -> CSize -> Ptr () -> Ptr CLint -> IO CLMem +--foreign import ccall "clCreateImage2D" raw_clCreateImage2D :: +-- CLContext -> CLMemFlags_ -> CLImageFormat_p -> CSize -> CSize -> CSize +-- -> Ptr () -> Ptr CLint -> IO CLMem +--foreign import ccall "clCreateImage3D" raw_clCreateImage3D :: +-- CLContext -> CLMemFlags_-> CLImageFormat_p -> CSize -> CSize -> CSize -> CSize +-- -> CSize -> Ptr () -> Ptr CLint -> IO CLMem +foreign import ccall "clRetainMemObject" raw_clRetainMemObject :: + CLMem -> IO CLint +foreign import ccall "clReleaseMemObject" raw_clReleaseMemObject :: + CLMem -> IO CLint +--foreign import ccall "clGetSupportedImageFormats" raw_clGetSupportedImageFormats :: +-- CLContext -> CLMemFlags_ -> CLMemObjectType_ -> CLuint -> CLImageFormat_p +-- -> Ptr CLuint -> IO CLint +foreign import ccall "clGetMemObjectInfo" raw_clGetMemObjectInfo :: + CLMem -> CLMemInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint +--foreign import ccall "clGetImageInfo" raw_clGetImageInfo :: +-- CLMem -> CLImageInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint +foreign import ccall "clCreateSampler" raw_clCreateSampler :: + CLContext -> CLbool -> CLAddressingMode_ -> CLFilterMode_ -> Ptr CLint -> IO CLSampler +foreign import ccall "clRetainSampler" raw_clRetainSampler :: + CLSampler -> IO CLint +foreign import ccall "clReleaseSampler" raw_clReleaseSampler :: + CLSampler -> IO CLint +foreign import ccall "clGetSamplerInfo" raw_clGetSamplerInfo :: + CLSampler -> CLSamplerInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint + +-- ----------------------------------------------------------------------------- +{-| Creates a buffer object. Returns a valid non-zero buffer object if the +buffer object is created successfully. Otherwise, it returns: + + * 'CL_INVALID_CONTEXT' if context is not a valid context. + + * 'CL_INVALID_VALUE' if values specified in flags are not valid. + + * 'CL_INVALID_BUFFER_SIZE' if size is 0 or is greater than +'clDeviceMaxMemAllocSize' value for all devices in context. + + * 'CL_INVALID_HOST_PTR' if host_ptr is NULL and 'CL_MEM_USE_HOST_PTR' or +'CL_MEM_COPY_HOST_PTR' are set in flags or if host_ptr is not NULL but +'CL_MEM_COPY_HOST_PTR' or 'CL_MEM_USE_HOST_PTR' are not set in flags. + + * 'CL_MEM_OBJECT_ALLOCATION_FAILURE' if there is a failure to allocate memory +for buffer object. + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +by the OpenCL implementation on the host. +-} +clCreateBuffer :: Integral a => CLContext -> [CLMemFlag] -> (a, Ptr ()) -> IO (Either CLError CLMem) +clCreateBuffer ctx xs (sbuff,buff) = wrapPError $ \perr -> do + raw_clCreateBuffer ctx flags (fromIntegral sbuff) buff perr + where + flags = bitmaskFromFlags xs + +-- | Increments the memory object reference count. returns 'True' if the +-- function is executed successfully. After the memobj reference count becomes +-- zero and commands queued for execution on a command-queue(s) that use memobj +-- have finished, the memory object is deleted. It returns 'False' if memobj is +-- not a valid memory object. +clRetainMemObject :: CLMem -> IO Bool +clRetainMemObject mem = wrapCheckSuccess $ raw_clRetainMemObject mem + +-- | Decrements the memory object reference count. After the memobj reference +-- count becomes zero and commands queued for execution on a command-queue(s) +-- that use memobj have finished, the memory object is deleted. Returns 'True' +-- if the function is executed successfully. It returns 'False' if memobj is not +-- a valid memory object. +clReleaseMemObject :: CLMem -> IO Bool +clReleaseMemObject mem = wrapCheckSuccess $ raw_clReleaseMemObject mem + +#c +enum CLMemInfo { + cL_MEM_TYPE=CL_MEM_TYPE, + cL_MEM_FLAGS=CL_MEM_FLAGS, + cL_MEM_SIZE=CL_MEM_SIZE, + cL_MEM_HOST_PTR=CL_MEM_HOST_PTR, + cL_MEM_MAP_COUNT=CL_MEM_MAP_COUNT, + cL_MEM_REFERENCE_COUNT=CL_MEM_REFERENCE_COUNT, + cL_MEM_CONTEXT=CL_MEM_CONTEXT, + }; +#endc +{#enum CLMemInfo {upcaseFirstLetter} #} + +-- | Returns the mem object type. +clGetMemType :: CLMem -> IO (Either CLError CLMemObjectType) +clGetMemType mem = wrapGetInfo (\(dat :: Ptr CLMemObjectType_) + -> raw_clGetMemObjectInfo mem infoid size (castPtr dat)) getEnumCL + where + infoid = getCLValue CL_MEM_TYPE + size = fromIntegral $ sizeOf (0::CLMemObjectType_) + +-- | Return the flags argument value specified when memobj was created. +clGetMemFlags :: CLMem -> IO (Either CLError [CLMemFlag]) +clGetMemFlags mem = wrapGetInfo (\(dat :: Ptr CLMemFlags_) + -> raw_clGetMemObjectInfo mem infoid size (castPtr dat)) bitmaskToMemFlags + where + infoid = getCLValue CL_MEM_FLAGS + size = fromIntegral $ sizeOf (0::CLMemFlags_) + +-- | Return actual size of memobj in bytes. +clGetMemSize :: CLMem -> IO (Either CLError CSize) +clGetMemSize mem = wrapGetInfo (\(dat :: Ptr CSize) + -> raw_clGetMemObjectInfo mem infoid size (castPtr dat)) id + where + infoid = getCLValue CL_MEM_SIZE + size = fromIntegral $ sizeOf (0::CSize) + +-- | Return the host_ptr argument value specified when memobj is created. +clGetMemHostPtr :: CLMem -> IO (Either CLError (Ptr ())) +clGetMemHostPtr mem = wrapGetInfo (\(dat :: Ptr (Ptr ())) + -> raw_clGetMemObjectInfo mem infoid size (castPtr dat)) id + where + infoid = getCLValue CL_MEM_HOST_PTR + size = fromIntegral $ sizeOf (nullPtr::Ptr ()) + +-- | Map count. The map count returned should be considered immediately +-- stale. It is unsuitable for general use in applications. This feature is +-- provided for debugging. +clGetMemMapCount :: CLMem -> IO (Either CLError CLuint) +clGetMemMapCount mem = wrapGetInfo (\(dat :: Ptr CLuint) + -> raw_clGetMemObjectInfo mem infoid size (castPtr dat)) id + where + infoid = getCLValue CL_MEM_MAP_COUNT + size = fromIntegral $ sizeOf (0 :: CLuint) + +-- | Return memobj reference count. The reference count returned should be +-- considered immediately stale. It is unsuitable for general use in +-- applications. This feature is provided for identifying memory leaks. +clGetMemReferenceCount :: CLMem -> IO (Either CLError CLuint) +clGetMemReferenceCount mem = wrapGetInfo (\(dat :: Ptr CLuint) + -> raw_clGetMemObjectInfo mem infoid size (castPtr dat)) id + where + infoid = getCLValue CL_MEM_REFERENCE_COUNT + size = fromIntegral $ sizeOf (0 :: CLuint) + +-- | Return context specified when memory object is created. +clGetMemContext :: CLMem -> IO (Either CLError CLContext) +clGetMemContext mem = wrapGetInfo (\(dat :: Ptr CLContext) + -> raw_clGetMemObjectInfo mem infoid size (castPtr dat)) id + where + infoid = getCLValue CL_MEM_CONTEXT + size = fromIntegral $ sizeOf (0 :: CLuint) + +-- ----------------------------------------------------------------------------- +{-| Creates a sampler object. A sampler object describes how to sample an image +when the image is read in the kernel. The built-in functions to read from an +image in a kernel take a sampler as an argument. The sampler arguments to the +image read function can be sampler objects created using OpenCL functions and +passed as argument values to the kernel or can be samplers declared inside a +kernel. In this section we discuss how sampler objects are created using OpenCL +functions. + +Returns a valid non-zero sampler object if the sampler object is created +successfully. Otherwise, it returns one of the following error values: + + * 'CL_INVALID_CONTEXT' if context is not a valid context. + + * 'CL_INVALID_VALUE' if addressing_mode, filter_mode, or normalized_coords or a +combination of these argument values are not valid. + + * 'CL_INVALID_OPERATION' if images are not supported by any device associated +with context (i.e. 'CL_DEVICE_IMAGE_SUPPORT' specified in the table of OpenCL +Device Queries for clGetDeviceInfo is 'False'). + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +by the OpenCL implementation on the host. +-} +clCreateSampler :: CLContext -> Bool -> CLAddressingMode -> CLFilterMode -> IO (Either CLError CLSampler) +clCreateSampler ctx norm am fm = wrapPError $ \perr -> do + raw_clCreateSampler ctx (fromBool norm) (getCLValue am) (getCLValue fm) perr + +-- | Increments the sampler reference count. 'clCreateSampler' does an implicit +-- retain. Returns 'True' if the function is executed successfully. It returns +-- 'False' if sampler is not a valid sampler object. +clRetainSampler :: CLSampler -> IO Bool +clRetainSampler mem = wrapCheckSuccess $ raw_clRetainSampler mem + +-- | Decrements the sampler reference count. The sampler object is deleted after +-- the reference count becomes zero and commands queued for execution on a +-- command-queue(s) that use sampler have finished. 'clReleaseSampler' returns +-- 'True' if the function is executed successfully. It returns 'False' if +-- sampler is not a valid sampler object. +clReleaseSampler :: CLSampler -> IO Bool +clReleaseSampler mem = wrapCheckSuccess $ raw_clReleaseSampler mem + +#c +enum CLSamplerInfo { + cL_SAMPLER_REFERENCE_COUNT=CL_SAMPLER_REFERENCE_COUNT, + cL_SAMPLER_CONTEXT=CL_SAMPLER_CONTEXT, + cL_SAMPLER_ADDRESSING_MODE=CL_SAMPLER_ADDRESSING_MODE, + cL_SAMPLER_FILTER_MODE=CL_SAMPLER_FILTER_MODE, + cL_SAMPLER_NORMALIZED_COORDS=CL_SAMPLER_NORMALIZED_COORDS + }; +#endc +{#enum CLSamplerInfo {upcaseFirstLetter} #} + +-- | Return the sampler reference count. The reference count returned should be +-- considered immediately stale. It is unsuitable for general use in +-- applications. This feature is provided for identifying memory leaks. +clGetSamplerReferenceCount :: CLSampler -> IO (Either CLError CLuint) +clGetSamplerReferenceCount sam = wrapGetInfo (\(dat :: Ptr CLuint) + -> raw_clGetSamplerInfo sam infoid size (castPtr dat)) id + where + infoid = getCLValue CL_SAMPLER_REFERENCE_COUNT + size = fromIntegral $ sizeOf (0 :: CLuint) + +-- | Return the context specified when the sampler is created. +clGetSamplerContext :: CLSampler -> IO (Either CLError CLContext) +clGetSamplerContext sam = wrapGetInfo (\(dat :: Ptr CLContext) + -> raw_clGetSamplerInfo sam infoid size (castPtr dat)) id + where + infoid = getCLValue CL_SAMPLER_CONTEXT + size = fromIntegral $ sizeOf (nullPtr :: CLContext) + +-- | Return the value specified by addressing_mode argument to clCreateSampler. +clGetSamplerAddressingMode :: CLSampler -> IO (Either CLError CLAddressingMode) +clGetSamplerAddressingMode sam = wrapGetInfo (\(dat :: Ptr CLAddressingMode_) + -> raw_clGetSamplerInfo sam infoid size (castPtr dat)) getEnumCL + where + infoid = getCLValue CL_SAMPLER_ADDRESSING_MODE + size = fromIntegral $ sizeOf (0 :: CLAddressingMode_) + +-- | Return the value specified by filter_mode argument to clCreateSampler. +clGetSamplerFilterMode :: CLSampler -> IO (Either CLError CLFilterMode) +clGetSamplerFilterMode sam = wrapGetInfo (\(dat :: Ptr CLFilterMode_) + -> raw_clGetSamplerInfo sam infoid size (castPtr dat)) getEnumCL + where + infoid = getCLValue CL_SAMPLER_FILTER_MODE + size = fromIntegral $ sizeOf (0 :: CLFilterMode_) + +-- | Return the value specified by normalized_coords argument to +-- clCreateSampler. +clGetSamplerNormalizedCoords :: CLSampler -> IO (Either CLError Bool) +clGetSamplerNormalizedCoords sam = wrapGetInfo (\(dat :: Ptr CLbool) + -> raw_clGetSamplerInfo sam infoid size (castPtr dat)) (/=0) + where + infoid = getCLValue CL_SAMPLER_NORMALIZED_COORDS + size = fromIntegral $ sizeOf (0 :: CLbool) + +-- ----------------------------------------------------------------------------- diff --git a/src/System/GPU/OpenCL/Program.chs b/src/System/GPU/OpenCL/Program.chs new file mode 100644 --- /dev/null +++ b/src/System/GPU/OpenCL/Program.chs @@ -0,0 +1,745 @@ +-- ----------------------------------------------------------------------------- +-- This file is part of Haskell-Opencl. + +-- Haskell-Opencl 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. + +-- Haskell-Opencl 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 Haskell-Opencl. If not, see . +-- ----------------------------------------------------------------------------- +{-# LANGUAGE ForeignFunctionInterface, ScopedTypeVariables #-} +module System.GPU.OpenCL.Program( + -- * Types + CLProgram, CLBuildStatus(..), CLKernel, + -- * Program Functions + clCreateProgramWithSource, clRetainProgram, clReleaseProgram, + clUnloadCompiler, clBuildProgram, clGetProgramReferenceCount, + clGetProgramContext, clGetProgramNumDevices, clGetProgramDevices, + clGetProgramSource, clGetProgramBinarySizes, clGetProgramBinaries, + clGetProgramBuildStatus, clGetProgramBuildOptions, clGetProgramBuildLog, + -- * Kernel Functions + clCreateKernel, clCreateKernelsInProgram, clRetainKernel, clReleaseKernel, + clSetKernelArg, clGetKernelFunctionName, clGetKernelNumArgs, + clGetKernelReferenceCount, clGetKernelContext, clGetKernelProgram, + clGetKernelWorkGroupSize, clGetKernelCompileWorkGroupSize, + clGetKernelLocalMemSize + ) where + +-- ----------------------------------------------------------------------------- +import Control.Monad( zipWithM ) +import Foreign +import Foreign.C.Types +import Foreign.C.String( CString, withCString, newCString, peekCString ) +import System.GPU.OpenCL.Types( + CLint, CLuint, CLulong, CLProgram, CLContext, CLKernel, CLDeviceID, + CLError(..), CLProgramInfo_, CLBuildStatus(..), CLBuildStatus_, + CLProgramBuildInfo_, CLKernelInfo_, CLKernelWorkGroupInfo_, wrapCheckSuccess, + wrapPError, wrapGetInfo, getCLValue, getEnumCL ) + +#include + +-- ----------------------------------------------------------------------------- +type BuildCallback = CLProgram -> Ptr () -> IO () +foreign import ccall "clCreateProgramWithSource" raw_clCreateProgramWithSource :: + CLContext -> CLuint -> Ptr CString -> Ptr CSize -> Ptr CLint -> IO CLProgram +--foreign import ccall "clCreateProgramWithBinary" raw_clCreateProgramWithBinary :: +-- CLContext -> CLuint -> Ptr CLDeviceID -> Ptr CSize -> Ptr (Ptr Word8) -> Ptr CLint -> Ptr CLint -> IO CLProgram +foreign import ccall "clRetainProgram" raw_clRetainProgram :: + CLProgram -> IO CLint +foreign import ccall "clReleaseProgram" raw_clReleaseProgram :: + CLProgram -> IO CLint +foreign import ccall "clBuildProgram" raw_clBuildProgram :: + CLProgram -> CLuint -> Ptr CLDeviceID -> CString -> FunPtr BuildCallback -> Ptr () -> IO CLint +foreign import ccall "clUnloadCompiler" raw_clUnloadCompiler :: + IO CLint +foreign import ccall "clGetProgramInfo" raw_clGetProgramInfo :: + CLProgram -> CLProgramInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint +foreign import ccall "clGetProgramBuildInfo" raw_clGetProgramBuildInfo :: + CLProgram -> CLDeviceID -> CLProgramBuildInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint +foreign import ccall "clCreateKernel" raw_clCreateKernel :: + CLProgram -> CString -> Ptr CLint -> IO CLKernel +foreign import ccall "clCreateKernelsInProgram" raw_clCreateKernelsInProgram :: + CLProgram -> CLuint -> Ptr CLKernel -> Ptr CLuint -> IO CLint +foreign import ccall "clRetainKernel" raw_clRetainKernel :: + CLKernel -> IO CLint +foreign import ccall "clReleaseKernel" raw_clReleaseKernel :: + CLKernel -> IO CLint +foreign import ccall "clSetKernelArg" raw_clSetKernelArg :: + CLKernel -> CLuint -> CSize -> Ptr () -> IO CLint +foreign import ccall "clGetKernelInfo" raw_clGetKernelInfo :: + CLKernel -> CLKernelInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint +foreign import ccall "clGetKernelWorkGroupInfo" raw_clGetKernelWorkGroupInfo :: + CLKernel -> CLDeviceID -> CLKernelWorkGroupInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint + +-- ----------------------------------------------------------------------------- +{-| Creates a program object for a context, and loads the source code specified +by the text strings in the strings array into the program object. The devices +associated with the program object are the devices associated with context. + +OpenCL allows applications to create a program object using the program source +or binary and build appropriate program executables. This allows applications to +determine whether they want to use the pre-built offline binary or load and +compile the program source and use the executable compiled/linked online as the +program executable. This can be very useful as it allows applications to load +and build program executables online on its first instance for appropriate +OpenCL devices in the system. These executables can now be queried and cached by +the application. Future instances of the application launching will no longer +need to compile and build the program executables. The cached executables can be +read and loaded by the application, which can help significantly reduce the +application initialization time. + +An OpenCL program consists of a set of kernels that are identified as functions +declared with the __kernel qualifier in the program source. OpenCL programs may +also contain auxiliary functions and constant data that can be used by __kernel +functions. The program executable can be generated online or offline by the +OpenCL compiler for the appropriate target device(s). + +'clCreateProgramWithSource' returns a valid non-zero program object if the +program object is created successfully. Otherwise, it returns one of the +following error values: + + * 'CL_INVALID_CONTEXT' if context is not a valid context. + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +by the OpenCL implementation on the host. +-} +clCreateProgramWithSource :: CLContext -> String -> IO (Either CLError CLProgram) +clCreateProgramWithSource ctx source = wrapPError $ \perr -> do + let strings = lines source + count = fromIntegral $ length strings + cstrings <- mapM newCString strings + prog <- withArray cstrings $ \srcArray -> do + raw_clCreateProgramWithSource ctx count srcArray nullPtr perr + mapM_ free cstrings + return prog + +-- | Increments the program reference count. 'clRetainProgram' returns 'True' if +-- the function is executed successfully. It returns 'False' if program is not a +-- valid program object. +clRetainProgram :: CLProgram -> IO Bool +clRetainProgram prg = wrapCheckSuccess $ raw_clRetainProgram prg + +-- | Decrements the program reference count. The program object is deleted after +-- all kernel objects associated with program have been deleted and the program +-- reference count becomes zero. 'clReleseProgram' returns 'True' if +-- the function is executed successfully. It returns 'False' if program is not a +-- valid program object. +clReleaseProgram :: CLProgram -> IO Bool +clReleaseProgram prg = wrapCheckSuccess $ raw_clReleaseProgram prg + +-- | Allows the implementation to release the resources allocated by the OpenCL +-- compiler. This is a hint from the application and does not guarantee that the +-- compiler will not be used in the future or that the compiler will actually be +-- unloaded by the implementation. Calls to 'clBuildProgram' after +-- 'clUnloadCompiler' will reload the compiler, if necessary, to build the +-- appropriate program executable. +clUnloadCompiler :: IO () +clUnloadCompiler = raw_clUnloadCompiler >> return () + +{-| Builds (compiles and links) a program executable from the program source or +binary. OpenCL allows program executables to be built using the source or the +binary. The build options are categorized as pre-processor options, options for +math intrinsics, options that control optimization and miscellaneous +options. This specification defines a standard set of options that must be +supported by an OpenCL compiler when building program executables online or +offline. These may be extended by a set of vendor- or platform-specific options. + + * Preprocessor Options + +These options control the OpenCL preprocessor which is run on each program +source before actual compilation. -D options are processed in the order they are +given in the options argument to clBuildProgram. + + [-D name] Predefine name as a macro, with definition 1. + + [-D name=definition] The contents of definition are tokenized and processed as +if they appeared during translation phase three in a `#define' directive. In +particular, the definition will be truncated by embedded newline characters. + + [-I dir] Add the directory dir to the list of directories to be searched for +header files. + + * Math Intrinsics Options + +These options control compiler behavior regarding floating-point +arithmetic. These options trade off between speed and correctness. + + [-cl-single-precision-constant] Treat double precision floating-point constant +as single precision constant. + + [-cl-denorms-are-zero] This option controls how single precision and double +precision denormalized numbers are handled. If specified as a build option, the +single precision denormalized numbers may be flushed to zero and if the optional +extension for double precision is supported, double precision denormalized +numbers may also be flushed to zero. This is intended to be a performance hint +and the OpenCL compiler can choose not to flush denorms to zero if the device +supports single precision (or double precision) denormalized numbers. + +This option is ignored for single precision numbers if the device does not +support single precision denormalized numbers i.e. 'CL_FP_DENORM' bit is not set +in 'clGetDeviceSingleFPConfig'. + +This option is ignored for double precision numbers if the device does not +support double precision or if it does support double precison but +'CL_FP_DENORM' bit is not set in 'clGetDeviceDoubleFPConfig'. + +This flag only applies for scalar and vector single precision floating-point +variables and computations on these floating-point variables inside a +program. It does not apply to reading from or writing to image objects. + + * Optimization Options + +These options control various sorts of optimizations. Turning on optimization +flags makes the compiler attempt to improve the performance and/or code size at +the expense of compilation time and possibly the ability to debug the program. + + [-cl-opt-disable] This option disables all optimizations. The default is +optimizations are enabled. + + [-cl-strict-aliasing] This option allows the compiler to assume the strictest +aliasing rules. + +The following options control compiler behavior regarding floating-point +arithmetic. These options trade off between performance and correctness and must +be specifically enabled. These options are not turned on by default since it can +result in incorrect output for programs which depend on an exact implementation +of IEEE 754 rules/specifications for math functions. + + [-cl-mad-enable] Allow a * b + c to be replaced by a mad. The mad computes a * +b + c with reduced accuracy. For example, some OpenCL devices implement mad as +truncate the result of a * b before adding it to c. + + [-cl-no-signed-zeros] Allow optimizations for floating-point arithmetic that +ignore the signedness of zero. IEEE 754 arithmetic specifies the behavior of +distinct +0.0 and -0.0 values, which then prohibits simplification of +expressions such as x+0.0 or 0.0*x (even with -clfinite-math only). This option +implies that the sign of a zero result isn't significant. + + [-cl-unsafe-math-optimizations] Allow optimizations for floating-point +arithmetic that (a) assume that arguments and results are valid, (b) may violate +IEEE 754 standard and (c) may violate the OpenCL numerical compliance +requirements as defined in section 7.4 for single-precision floating-point, +section 9.3.9 for double-precision floating-point, and edge case behavior in +section 7.5. This option includes the -cl-no-signed-zeros and -cl-mad-enable +options. + + [-cl-finite-math-only] Allow optimizations for floating-point arithmetic that +assume that arguments and results are not NaNs or ±∞. This option may violate +the OpenCL numerical compliance requirements defined in in section 7.4 for +single-precision floating-point, section 9.3.9 for double-precision +floating-point, and edge case behavior in section 7.5. + + [-cl-fast-relaxed-math] Sets the optimization options -cl-finite-math-only and +-cl-unsafe-math-optimizations. This allows optimizations for floating-point +arithmetic that may violate the IEEE 754 standard and the OpenCL numerical +compliance requirements defined in the specification in section 7.4 for +single-precision floating-point, section 9.3.9 for double-precision +floating-point, and edge case behavior in section 7.5. This option causes the +preprocessor macro __FAST_RELAXED_MATH__ to be defined in the OpenCL program. + + * Options to Request or Suppress Warnings + +Warnings are diagnostic messages that report constructions which are not +inherently erroneous but which are risky or suggest there may have been an +error. The following languageindependent options do not enable specific warnings +but control the kinds of diagnostics produced by the OpenCL compiler. + + [-w] Inhibit all warning messages. + + [-Werror] Make all warnings into errors. + +clBuildProgram returns the following errors when fails: + + * 'CL_INVALID_PROGRAM' if program is not a valid program object. + + * 'CL_INVALID_DEVICE' if OpenCL devices listed in device_list are not in the +list of devices associated with program. + + * 'CL_INVALID_BINARY' if program is created with +'clCreateWithProgramWithBinary' and devices listed in device_list do not have a +valid program binary loaded. + + * 'CL_INVALID_BUILD_OPTIONS' if the build options specified by options are +invalid. + + * 'CL_INVALID_OPERATION' if the build of a program executable for any of the +devices listed in device_list by a previous call to 'clBuildProgram' for program +has not completed. + + * 'CL_COMPILER_NOT_AVAILABLE' if program is created with +'clCreateProgramWithSource' and a compiler is not available +i.e. 'clGetDeviceCompilerAvailable' is set to 'False'. + + * 'CL_BUILD_PROGRAM_FAILURE' if there is a failure to build the program +executable. This error will be returned if 'clBuildProgram' does not return +until the build has completed. + + * 'CL_INVALID_OPERATION' if there are kernel objects attached to program. + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +by the OpenCL implementation on the host. +-} +clBuildProgram :: CLProgram -> [CLDeviceID] -> String -> IO (Either CLError ()) +clBuildProgram prg devs opts = allocaArray ndevs $ \pdevs -> do + pokeArray pdevs devs + withCString opts $ \copts -> do + errcode <- raw_clBuildProgram prg cndevs pdevs copts nullFunPtr nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then return $ Right () + else return . Left . toEnum . fromIntegral $ errcode + where + ndevs = length devs + cndevs = fromIntegral ndevs + +#c +enum CLProgramInfo { + cL_PROGRAM_REFERENCE_COUNT=CL_PROGRAM_REFERENCE_COUNT, + cL_PROGRAM_CONTEXT=CL_PROGRAM_CONTEXT, + cL_PROGRAM_NUM_DEVICES=CL_PROGRAM_NUM_DEVICES, + cL_PROGRAM_DEVICES=CL_PROGRAM_DEVICES, + cL_PROGRAM_SOURCE=CL_PROGRAM_SOURCE, + cL_PROGRAM_BINARY_SIZES=CL_PROGRAM_BINARY_SIZES, + cL_PROGRAM_BINARIES=CL_PROGRAM_BINARIES, + }; +#endc +{#enum CLProgramInfo {upcaseFirstLetter} #} + +getProgramInfoSize :: CLProgram -> CLProgramInfo_ -> IO (Either CLError CSize) +getProgramInfoSize prg infoid = alloca $ \(value_size :: Ptr CSize) -> do + errcode <- raw_clGetProgramInfo prg infoid 0 nullPtr value_size + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peek value_size + else return . Left . toEnum . fromIntegral $ errcode + +-- | Return the program reference count. The reference count returned should be +-- considered immediately stale. It is unsuitable for general use in +-- applications. This feature is provided for identifying memory leaks. +clGetProgramReferenceCount :: CLProgram -> IO (Either CLError CLuint) +clGetProgramReferenceCount prg = wrapGetInfo (\(dat :: Ptr CLuint) + -> raw_clGetProgramInfo prg infoid size (castPtr dat)) id + where + infoid = getCLValue CL_PROGRAM_REFERENCE_COUNT + size = fromIntegral $ sizeOf (0::CLuint) + +-- | Return the context specified when the program object is created. +clGetProgramContext :: CLProgram -> IO (Either CLError CLContext) +clGetProgramContext prg = wrapGetInfo (\(dat :: Ptr CLContext) + -> raw_clGetProgramInfo prg infoid size (castPtr dat)) id + where + infoid = getCLValue CL_PROGRAM_CONTEXT + size = fromIntegral $ sizeOf (nullPtr::CLContext) + +-- | Return the number of devices associated with program. +clGetProgramNumDevices :: CLProgram -> IO (Either CLError CLuint) +clGetProgramNumDevices prg = wrapGetInfo (\(dat :: Ptr CLuint) + -> raw_clGetProgramInfo prg infoid size (castPtr dat)) id + where + infoid = getCLValue CL_PROGRAM_NUM_DEVICES + size = fromIntegral $ sizeOf (0::CLuint) + +-- | Return the list of devices associated with the program object. This can be +-- the devices associated with context on which the program object has been +-- created or can be a subset of devices that are specified when a progam object +-- is created using 'clCreateProgramWithBinary'. +clGetProgramDevices :: CLProgram -> IO (Either CLError [CLDeviceID]) +clGetProgramDevices prg = do + sval <- getProgramInfoSize prg infoid + case sval of + Left err -> return . Left $ err + Right size -> allocaArray (numElems size) $ \(buff :: Ptr CLDeviceID) -> do + errcode <- raw_clGetProgramInfo prg infoid size (castPtr buff) nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peekArray (numElems size) buff + else return . Left . toEnum . fromIntegral $ errcode + where + infoid = getCLValue CL_PROGRAM_DEVICES + numElems s = (fromIntegral s) `div` elemSize + elemSize = sizeOf (nullPtr::CLDeviceID) + +-- | Return the program source code specified by +-- 'clCreateProgramWithSource'. The source string returned is a concatenation of +-- all source strings specified to 'clCreateProgramWithSource' with a null +-- terminator. The concatenation strips any nulls in the original source +-- strings. The actual number of characters that represents the program source +-- code including the null terminator is returned in param_value_size_ret. +clGetProgramSource :: CLProgram -> IO (Either CLError String) +clGetProgramSource prg = do + sval <- getProgramInfoSize prg infoid + case sval of + Left err -> return . Left $ err + Right n -> allocaArray (fromIntegral n) $ \(buff :: CString) -> do + errcode <- raw_clGetProgramInfo prg infoid n (castPtr buff) nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peekCString buff + else return . Left . toEnum . fromIntegral $ errcode + where + infoid = getCLValue CL_PROGRAM_SOURCE + +-- | Returns an array that contains the size in bytes of the program binary for +-- each device associated with program. The size of the array is the number of +-- devices associated with program. If a binary is not available for a +-- device(s), a size of zero is returned. +clGetProgramBinarySizes :: CLProgram -> IO (Either CLError [CSize]) +clGetProgramBinarySizes prg = do + sval <- getProgramInfoSize prg infoid + case sval of + Left err -> return . Left $ err + Right size -> allocaArray (numElems size) $ \(buff :: Ptr CSize) -> do + errcode <- raw_clGetProgramInfo prg infoid size (castPtr buff) nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peekArray (numElems size) buff + else return . Left . toEnum . fromIntegral $ errcode + where + infoid = getCLValue CL_PROGRAM_BINARY_SIZES + numElems s = (fromIntegral s) `div` elemSize + elemSize = sizeOf (0::CSize) + +{-| Return the program binaries for all devices associated with program. For +each device in program, the binary returned can be the binary specified for the +device when program is created with 'clCreateProgramWithBinary' or it can be the +executable binary generated by 'clBuildProgram'. If program is created with +'clCreateProgramWithSource', the binary returned is the binary generated by +'clBuildProgram'. The bits returned can be an implementation-specific +intermediate representation (a.k.a. IR) or device specific executable bits or +both. The decision on which information is returned in the binary is up to the +OpenCL implementation. + +To find out which device the program binary in the array refers to, use the +'clGetProgramDevices' query to get the list of devices. There is a one-to-one +correspondence between the array of data returned by 'clGetProgramBinaries' and +array of devices returned by 'clGetProgramDevices'. +-} +clGetProgramBinaries :: CLProgram -> IO (Either CLError [[Word8]]) +clGetProgramBinaries prg = do + sval <- clGetProgramBinarySizes prg + case sval of + Left err -> return . Left $ err + Right sizes -> do + let numElems = length sizes + size = fromIntegral $ numElems * elemSize + buffers <- (mapM (mallocArray.fromIntegral) sizes) :: IO [Ptr Word8] + ret <- withArray buffers $ \(parray :: Ptr (Ptr Word8)) -> do + errcode <- raw_clGetProgramInfo prg infoid size (castPtr parray) nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then do + vals <- zipWithM peekArray (map fromIntegral sizes) buffers + return . Right $ vals + else return . Left . toEnum . fromIntegral $ errcode + mapM_ free buffers + return ret + where + infoid = getCLValue CL_PROGRAM_BINARIES + elemSize = sizeOf (nullPtr::Ptr Word8) + +-- ----------------------------------------------------------------------------- +#c +enum CLProgramBuildInfo { + cL_PROGRAM_BUILD_STATUS=CL_PROGRAM_BUILD_STATUS, + cL_PROGRAM_BUILD_OPTIONS=CL_PROGRAM_BUILD_OPTIONS, + cL_PROGRAM_BUILD_LOG=CL_PROGRAM_BUILD_LOG, + }; +#endc +{#enum CLProgramBuildInfo {upcaseFirstLetter} #} + +getProgramBuildInfoSize :: CLProgram -> CLDeviceID -> CLProgramInfo_ -> IO (Either CLError CSize) +getProgramBuildInfoSize prg device infoid = alloca $ \(value_size :: Ptr CSize) -> do + errcode <- raw_clGetProgramBuildInfo prg device infoid 0 nullPtr value_size + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peek value_size + else return . Left . toEnum . fromIntegral $ errcode + +-- | Returns the build status of program for a specific device as given by +-- device. +clGetProgramBuildStatus :: CLProgram -> CLDeviceID -> IO (Either CLError CLBuildStatus) +clGetProgramBuildStatus prg device = wrapGetInfo (\(dat :: Ptr CLBuildStatus_) + -> raw_clGetProgramBuildInfo prg device infoid size (castPtr dat)) getEnumCL + where + infoid = getCLValue CL_PROGRAM_BUILD_STATUS + size = fromIntegral $ sizeOf (0::CLBuildStatus_) + +-- | Return the build options specified by the options argument in +-- clBuildProgram for device. If build status of program for device is +-- 'CL_BUILD_NONE', an empty string is returned. +clGetProgramBuildOptions :: CLProgram -> CLDeviceID -> IO (Either CLError String) +clGetProgramBuildOptions prg device = do + sval <- getProgramBuildInfoSize prg device infoid + case sval of + Left err -> return . Left $ err + Right n -> allocaArray (fromIntegral n) $ \(buff :: CString) -> do + errcode <- raw_clGetProgramBuildInfo prg device infoid n (castPtr buff) nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peekCString buff + else return . Left . toEnum . fromIntegral $ errcode + where + infoid = getCLValue CL_PROGRAM_BUILD_OPTIONS + +-- | Return the build log when 'clBuildProgram' was called for device. If build +-- status of program for device is 'CL_BUILD_NONE', an empty string is returned. +clGetProgramBuildLog :: CLProgram -> CLDeviceID -> IO (Either CLError String) +clGetProgramBuildLog prg device = do + sval <- getProgramBuildInfoSize prg device infoid + case sval of + Left err -> return . Left $ err + Right n -> allocaArray (fromIntegral n) $ \(buff :: CString) -> do + errcode <- raw_clGetProgramBuildInfo prg device infoid n (castPtr buff) nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peekCString buff + else return . Left . toEnum . fromIntegral $ errcode + where + infoid = getCLValue CL_PROGRAM_BUILD_LOG + +-- ----------------------------------------------------------------------------- +{-| Creates a kernal object. A kernel is a function declared in a program. A +kernel is identified by the __kernel qualifier applied to any function in a +program. A kernel object encapsulates the specific __kernel function declared in +a program and the argument values to be used when executing this __kernel +function. + +'clCreateKernel' returns a valid non-zero kernel object if the kernel object is +created successfully. Otherwise, it returns one of the following error values: + + * 'CL_INVALID_PROGRAM' if program is not a valid program object. + + * 'CL_INVALID_PROGRAM_EXECUTABLE' if there is no successfully built executable + for program. + + * 'CL_INVALID_KERNEL_NAME' if kernel_name is not found in program. + + * 'CL_INVALID_KERNEL_DEFINITION' if the function definition for __kernel +function given by kernel_name such as the number of arguments, the argument +types are not the same for all devices for which the program executable has been +built. + + * 'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required +by the OpenCL implementation on the host. +-} +clCreateKernel :: CLProgram -> String -> IO (Either CLError CLKernel) +clCreateKernel prg name = withCString name $ \cname -> wrapPError $ \perr -> do + raw_clCreateKernel prg cname perr + +{-| Creates kernel objects for all kernel functions in a program object. Kernel +objects are not created for any __kernel functions in program that do not have +the same function definition across all devices for which a program executable +has been successfully built. + +Kernel objects can only be created once you have a program object with a valid +program source or binary loaded into the program object and the program +executable has been successfully built for one or more devices associated with +program. No changes to the program executable are allowed while there are kernel +objects associated with a program object. This means that calls to +'clBuildProgram' return 'CL_INVALID_OPERATION' if there are kernel objects +attached to a program object. The OpenCL context associated with program will be +the context associated with kernel. The list of devices associated with program +are the devices associated with kernel. Devices associated with a program object +for which a valid program executable has been built can be used to execute +kernels declared in the program object. + +'clCreateKernelsInProgram' will return the kernel objects if the kernel objects +were successfully allocated, returns 'CL_INVALID_PROGRAM' if program is not a +valid program object, returns 'CL_INVALID_PROGRAM_EXECUTABLE' if there is no +successfully built executable for any device in program and returns +'CL_OUT_OF_HOST_MEMORY' if there is a failure to allocate resources required by +the OpenCL implementation on the host. +-} +clCreateKernelsInProgram :: CLProgram -> IO (Either CLError [CLKernel]) +clCreateKernelsInProgram prg = do + nks <- alloca $ \pn -> do + errcode <- raw_clCreateKernelsInProgram prg 0 nullPtr pn + if errcode == (getCLValue CL_SUCCESS) + then peek pn >>= (return . Right) + else return $ Left errcode + + case nks of + Left err -> return . Left . getEnumCL $ err + Right n -> allocaArray (fromIntegral n) $ \pks -> do + errcode <- raw_clCreateKernelsInProgram prg n pks nullPtr + if errcode == (getCLValue CL_SUCCESS) + then peekArray (fromIntegral n) pks >>= (return . Right) + else return . Left .getEnumCL $ errcode + +-- | Increments the program program reference count. 'clRetainKernel' returns +-- 'True' if the function is executed successfully. 'clCreateKernel' or +-- 'clCreateKernelsInProgram' do an implicit retain. +clRetainKernel :: CLKernel -> IO Bool +clRetainKernel krn = wrapCheckSuccess $ raw_clRetainKernel krn + +-- | Decrements the kernel reference count. The kernel object is deleted once +-- the number of instances that are retained to kernel become zero and the +-- kernel object is no longer needed by any enqueued commands that use +-- kernel. 'clReleaseKernel' returns 'True' if the function is executed +-- successfully. +clReleaseKernel :: CLKernel -> IO Bool +clReleaseKernel krn = wrapCheckSuccess $ raw_clReleaseKernel krn + +{-| Used to set the argument value for a specific argument of a kernel. + +A kernel object does not update the reference count for objects such as memory, +sampler objects specified as argument values by 'clSetKernelArg', Users may not +rely on a kernel object to retain objects specified as argument values to the +kernel. + +Implementations shall not allow 'CLKernel' objects to hold reference counts to +'CLKernel' arguments, because no mechanism is provided for the user to tell the +kernel to release that ownership right. If the kernel holds ownership rights on +kernel args, that would make it impossible for the user to tell with certainty +when he may safely release user allocated resources associated with OpenCL +objects such as the CLMem backing store used with 'CL_MEM_USE_HOST_PTR'. + +'clSetKernelArg' returns returns one of the following errors when fails: + + * 'CL_INVALID_KERNEL' if kernel is not a valid kernel object. + + * 'CL_INVALID_ARG_INDEX' if arg_index is not a valid argument index. + + * 'CL_INVALID_ARG_VALUE' if arg_value specified is NULL for an argument that is +not declared with the __local qualifier or vice-versa. + + * 'CL_INVALID_MEM_OBJECT' for an argument declared to be a memory object when +the specified arg_value is not a valid memory object. + + * 'CL_INVALID_SAMPLER' for an argument declared to be of type sampler_t when +the specified arg_value is not a valid sampler object. + + * 'CL_INVALID_ARG_SIZE' if arg_size does not match the size of the data type +for an argument that is not a memory object or if the argument is a memory +object and arg_size != sizeof(cl_mem) or if arg_size is zero and the argument is +declared with the __local qualifier or if the argument is a sampler and arg_size +!= sizeof(cl_sampler). +-} +clSetKernelArg :: Storable a => CLKernel -> CLuint -> a -> IO (Either CLError ()) +clSetKernelArg krn idx val = with val $ \pval -> do + errcode <- raw_clSetKernelArg krn idx (fromIntegral . sizeOf $ val) (castPtr pval) + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then return $ Right () + else return . Left . toEnum . fromIntegral $ errcode + +#c +enum CLKernelInfo { + cL_KERNEL_FUNCTION_NAME=CL_KERNEL_FUNCTION_NAME, + cL_KERNEL_NUM_ARGS=CL_KERNEL_NUM_ARGS, + cL_KERNEL_REFERENCE_COUNT=CL_KERNEL_REFERENCE_COUNT, + cL_KERNEL_CONTEXT=CL_KERNEL_CONTEXT, + cL_KERNEL_PROGRAM=CL_KERNEL_PROGRAM + }; +#endc +{#enum CLKernelInfo {upcaseFirstLetter} #} + +getKernelInfoSize :: CLKernel -> CLKernelInfo_ -> IO (Either CLError CSize) +getKernelInfoSize krn infoid = alloca $ \(value_size :: Ptr CSize) -> do + errcode <- raw_clGetKernelInfo krn infoid 0 nullPtr value_size + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peek value_size + else return . Left . toEnum . fromIntegral $ errcode + +-- | Return the kernel function name. +clGetKernelFunctionName :: CLKernel -> IO (Either CLError String) +clGetKernelFunctionName krn = do + sval <- getKernelInfoSize krn infoid + case sval of + Left err -> return . Left $ err + Right n -> allocaArray (fromIntegral n) $ \(buff :: CString) -> do + errcode <- raw_clGetKernelInfo krn infoid n (castPtr buff) nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peekCString buff + else return . Left . toEnum . fromIntegral $ errcode + where + infoid = getCLValue CL_KERNEL_FUNCTION_NAME + +-- | Return the number of arguments to kernel. +clGetKernelNumArgs :: CLKernel -> IO (Either CLError CLuint) +clGetKernelNumArgs krn = wrapGetInfo (\(dat :: Ptr CLuint) + -> raw_clGetKernelInfo krn infoid size (castPtr dat)) id + where + infoid = getCLValue CL_KERNEL_NUM_ARGS + size = fromIntegral $ sizeOf (0::CLuint) + +-- | Return the kernel reference count. The reference count returned should be +-- considered immediately stale. It is unsuitable for general use in +-- applications. This feature is provided for identifying memory leaks. +clGetKernelReferenceCount :: CLKernel -> IO (Either CLError CLuint) +clGetKernelReferenceCount krn = wrapGetInfo (\(dat :: Ptr CLuint) + -> raw_clGetKernelInfo krn infoid size (castPtr dat)) id + where + infoid = getCLValue CL_KERNEL_REFERENCE_COUNT + size = fromIntegral $ sizeOf (0::CLuint) + +-- | Return the context associated with kernel. +clGetKernelContext :: CLKernel -> IO (Either CLError CLContext) +clGetKernelContext krn = wrapGetInfo (\(dat :: Ptr CLContext) + -> raw_clGetKernelInfo krn infoid size (castPtr dat)) id + where + infoid = getCLValue CL_KERNEL_CONTEXT + size = fromIntegral $ sizeOf (nullPtr::CLContext) + +-- | Return the program object associated with kernel. +clGetKernelProgram :: CLKernel -> IO (Either CLError CLProgram) +clGetKernelProgram krn = wrapGetInfo (\(dat :: Ptr CLProgram) + -> raw_clGetKernelInfo krn infoid size (castPtr dat)) id + where + infoid = getCLValue CL_KERNEL_PROGRAM + size = fromIntegral $ sizeOf (nullPtr::CLProgram) + + +#c +enum CLKernelGroupInfo { + cL_KERNEL_WORK_GROUP_SIZE=CL_KERNEL_WORK_GROUP_SIZE, + cL_KERNEL_COMPILE_WORK_GROUP_SIZE=CL_KERNEL_COMPILE_WORK_GROUP_SIZE, + cL_KERNEL_LOCAL_MEM_SIZE=CL_KERNEL_LOCAL_MEM_SIZE, + }; +#endc +{#enum CLKernelGroupInfo {upcaseFirstLetter} #} + +-- | This provides a mechanism for the application to query the work-group size +-- that can be used to execute a kernel on a specific device given by +-- device. The OpenCL implementation uses the resource requirements of the +-- kernel (register usage etc.) to determine what this work-group size should +-- be. +clGetKernelWorkGroupSize :: CLKernel -> CLDeviceID -> IO (Either CLError CSize) +clGetKernelWorkGroupSize krn device = wrapGetInfo (\(dat :: Ptr CSize) + -> raw_clGetKernelWorkGroupInfo krn device infoid size (castPtr dat)) id + where + infoid = getCLValue CL_KERNEL_WORK_GROUP_SIZE + size = fromIntegral $ sizeOf (0::CSize) + +-- | Returns the work-group size specified by the __attribute__((reqd_work_gr +-- oup_size(X, Y, Z))) qualifier. See Function Qualifiers. If the work-group +-- size is not specified using the above attribute qualifier (0, 0, 0) is +-- returned. +clGetKernelCompileWorkGroupSize :: CLKernel -> CLDeviceID -> IO (Either CLError [CSize]) +clGetKernelCompileWorkGroupSize krn device = do + allocaArray num $ \(buff :: Ptr CSize) -> do + errcode <- raw_clGetKernelWorkGroupInfo krn device infoid size (castPtr buff) nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS) + then fmap Right $ peekArray num buff + else return . Left . toEnum . fromIntegral $ errcode + where + infoid = getCLValue CL_KERNEL_COMPILE_WORK_GROUP_SIZE + num = 3 + elemSize = fromIntegral $ sizeOf (0::CSize) + size = fromIntegral $ num * elemSize + + +-- | Returns the amount of local memory in bytes being used by a kernel. This +-- includes local memory that may be needed by an implementation to execute the +-- kernel, variables declared inside the kernel with the __local address +-- qualifier and local memory to be allocated for arguments to the kernel +-- declared as pointers with the __local address qualifier and whose size is +-- specified with 'clSetKernelArg'. +-- +-- If the local memory size, for any pointer argument to the kernel declared +-- with the __local address qualifier, is not specified, its size is assumed to +-- be 0. +clGetKernelLocalMemSize :: CLKernel -> CLDeviceID -> IO (Either CLError CLulong) +clGetKernelLocalMemSize krn device = wrapGetInfo (\(dat :: Ptr CLulong) + -> raw_clGetKernelWorkGroupInfo krn device infoid size (castPtr dat)) id + where + infoid = getCLValue CL_KERNEL_LOCAL_MEM_SIZE + size = fromIntegral $ sizeOf (0::CLulong) +-- ----------------------------------------------------------------------------- diff --git a/src/System/GPU/OpenCL/Query.chs b/src/System/GPU/OpenCL/Query.chs new file mode 100644 --- /dev/null +++ b/src/System/GPU/OpenCL/Query.chs @@ -0,0 +1,590 @@ +-- ----------------------------------------------------------------------------- +-- This file is part of Haskell-Opencl. + +-- Haskell-Opencl 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. + +-- Haskell-Opencl 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 Haskell-Opencl. If not, see . +-- ----------------------------------------------------------------------------- +{-# LANGUAGE ForeignFunctionInterface, ScopedTypeVariables #-} +module System.GPU.OpenCL.Query( + -- * Types + CLPlatformInfo(..), CLPlatformID, CLDeviceID, CLDeviceType(..), + CLDeviceFPConfig(..), CLDeviceExecCapability(..), CLDeviceLocalMemType(..), + CLDeviceMemCacheType(..), + -- * Platform Query Functions + clGetPlatformIDs, clGetPlatformInfo, + -- * Device Query Functions + clGetDeviceIDs, clGetDeviceExecutionCapabilities, + clGetDeviceAddressBits, clGetDeviceAvailable, clGetDeviceCompilerAvailable, + clGetDeviceEndianLittle, clGetDeviceErrorCorrectionSupport, + clGetDeviceExtensions, clGetDeviceGlobalMemCacheSize, + clGetDeviceGlobalMemCachelineSize, clGetDeviceGlobalMemSize, + clGetDeviceImageSupport, clGetDeviceImage2DMaxHeight, + clGetDeviceImage2DMaxWidth, clGetDeviceImage3DMaxDepth, + clGetDeviceImage3DMaxHeight, clGetDeviceImage3DMaxWidth, + clGetDeviceLocalMemSize, clGetDeviceMaxClockFrequency, + clGetDeviceMaxComputeUnits, clGetDeviceMaxConstantArgs, + clGetDeviceMaxConstantBufferSize, clGetDeviceMaxMemAllocSize, + clGetDeviceMaxParameterSize, clGetDeviceMaxReadImageArgs, + clGetDeviceMaxSamplers, clGetDeviceMaxWorkGroupSize, + clGetDeviceMaxWorkItemDimensions, clGetDeviceMaxWorkItemSizes, + clGetDeviceMaxWriteImageArgs, clGetDeviceMemBaseAddrAlign, + clGetDeviceMinDataTypeAlignSize, clGetDeviceName, clGetDevicePlatform, + clGetDevicePreferredVectorWidthChar, clGetDevicePreferredVectorWidthShort, + clGetDevicePreferredVectorWidthInt, clGetDevicePreferredVectorWidthLong, + clGetDevicePreferredVectorWidthFloat, clGetDevicePreferredVectorWidthDouble, + clGetDeviceProfile, clGetDeviceProfilingTimerResolution, clGetDeviceVendor, + clGetDeviceVendorID, clGetDeviceVersion, clGetDeviceDriverVersion, + clGetDeviceSingleFPConfig, clGetDeviceDoubleFPConfig, + clGetDeviceHalfFPConfig, clGetDeviceLocalMemType, + clGetDeviceGlobalMemCacheType, clGetDeviceQueueProperties, clGetDeviceType ) + where + +-- ----------------------------------------------------------------------------- +import Foreign( Ptr, nullPtr, castPtr, alloca, allocaArray, peek, peekArray ) +import Foreign.C.String( CString, peekCString ) +import Foreign.C.Types( CSize ) +import Foreign.Storable( sizeOf ) +import System.GPU.OpenCL.Types( + CLbool, CLint, CLuint, CLulong, CLPlatformInfo_, CLDeviceType_, CLError(..), + CLDeviceInfo_, CLDeviceFPConfig(..), CLDeviceExecCapability(..), + CLDeviceLocalMemType(..), CLDeviceMemCacheType(..), CLPlatformInfo(..), + CLPlatformID, CLDeviceID, CLDeviceType(..), CLCommandQueueProperty, + getCLValue, getEnumCL, bitmaskToDeviceTypes, bitmaskToCommandQueueProperties, + whenSuccess, bitmaskToFPConfig, bitmaskToExecCapability ) + +-- ----------------------------------------------------------------------------- +foreign import ccall "clGetPlatformIDs" raw_clGetPlatformIDs :: + CLuint -> Ptr CLPlatformID -> Ptr CLuint -> IO CLint +foreign import ccall "clGetPlatformInfo" raw_clGetPlatformInfo :: + CLPlatformID -> CLPlatformInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint +foreign import ccall "clGetDeviceIDs" raw_clGetDeviceIDs :: + CLPlatformID -> CLDeviceType_ -> CLuint -> Ptr CLDeviceID -> Ptr CLuint -> IO CLint +foreign import ccall "clGetDeviceInfo" raw_clGetDeviceInfo :: + CLDeviceID -> CLDeviceInfo_ -> CSize -> Ptr () -> Ptr CSize -> IO CLint + +#include + +-- ----------------------------------------------------------------------------- +getNumPlatforms :: IO (Either CLError CLuint) +getNumPlatforms = alloca $ \(num_platforms :: Ptr CLuint) -> do + whenSuccess (raw_clGetPlatformIDs 0 nullPtr num_platforms) + $ peek num_platforms + +-- | Obtain the list of platforms available. Returns the list if the function +-- is executed successfully. Otherwise it returns the empty list. +clGetPlatformIDs :: IO (Either CLError [CLPlatformID]) +clGetPlatformIDs = do + nplats <- getNumPlatforms + case nplats of + Left err -> return . Left $ err + Right n -> allocaArray (fromIntegral n) $ \(plats :: Ptr CLPlatformID) -> do + whenSuccess (raw_clGetPlatformIDs n plats nullPtr) + $ peekArray (fromIntegral n) plats + +getPlatformInfoSize :: CLPlatformID -> CLuint -> IO (Either CLError CSize) +getPlatformInfoSize platform infoid = alloca $ \(value_size :: Ptr CSize) -> do + whenSuccess (raw_clGetPlatformInfo platform infoid 0 nullPtr value_size) + $ peek value_size + +-- | Get specific information about the OpenCL platform. It returns Nothing if +-- platform is not a valid platform. +clGetPlatformInfo :: CLPlatformID -> CLPlatformInfo -> IO (Either CLError String) +clGetPlatformInfo platform infoid = do + sval <- getPlatformInfoSize platform infocl + case sval of + Left err -> return . Left $ err + Right n -> allocaArray (fromIntegral n) $ \(buff :: CString) -> do + whenSuccess (raw_clGetPlatformInfo platform infocl n (castPtr buff) nullPtr) + $ peekCString buff + where + infocl = getCLValue infoid + +-- ----------------------------------------------------------------------------- +getNumDevices :: CLPlatformID -> CLDeviceType_ -> IO (Either CLError CLuint) +getNumDevices platform dtype = alloca $ \(num_devices :: Ptr CLuint) -> do + whenSuccess (raw_clGetDeviceIDs platform dtype 0 nullPtr num_devices) + $ peek num_devices + +-- | Obtain the list of devices available on a platform. Returns the list if +-- the function is executed successfully. Otherwise it returns the empty list +-- if platform is not a valid platform or no OpenCL devices that matched +-- device_type were found. +clGetDeviceIDs :: CLPlatformID -> CLDeviceType -> IO (Either CLError [CLDeviceID]) +clGetDeviceIDs platform dtype = do + ndevs <- getNumDevices platform dval + case ndevs of + Left err -> return . Left $ err + Right n -> allocaArray (fromIntegral n) $ \(devs :: Ptr CLDeviceID) -> do + whenSuccess (raw_clGetDeviceIDs platform dval n devs nullPtr) + $ peekArray (fromIntegral n) devs + where + dval = getCLValue dtype + +getDeviceInfoSize :: CLDeviceID -> CLDeviceInfo_ -> IO (Either CLError CSize) +getDeviceInfoSize device infoid = alloca $ \(value_size :: Ptr CSize) -> do + whenSuccess (raw_clGetDeviceInfo device infoid 0 nullPtr value_size) + $ peek value_size + +getDeviceInfoString :: CLDeviceInfo_ -> CLDeviceID -> IO (Either CLError String) +getDeviceInfoString infoid device = do + sval <- getDeviceInfoSize device infoid + case sval of + Left err -> return . Left $ err + Right n -> allocaArray (fromIntegral n) $ \(buff :: CString) -> do + whenSuccess (raw_clGetDeviceInfo device infoid n (castPtr buff) nullPtr) + $ peekCString buff + +getDeviceInfoUint :: CLDeviceInfo_ -> CLDeviceID -> IO (Either CLError CLuint) +getDeviceInfoUint infoid device = alloca $ \(dat :: Ptr CLuint) -> do + whenSuccess (raw_clGetDeviceInfo device infoid size (castPtr dat) nullPtr) + $ peek dat + where + size = fromIntegral $ sizeOf (0::CLuint) + +getDeviceInfoUlong :: CLDeviceInfo_ -> CLDeviceID -> IO (Either CLError CLulong) +getDeviceInfoUlong infoid device = alloca $ \(dat :: Ptr CLulong) -> do + whenSuccess (raw_clGetDeviceInfo device infoid size (castPtr dat) nullPtr) + $ peek dat + where + size = fromIntegral $ sizeOf (0::CLulong) + +getDeviceInfoSizet :: CLDeviceInfo_ -> CLDeviceID -> IO (Either CLError CSize) +getDeviceInfoSizet infoid device = alloca $ \(dat :: Ptr CSize) -> do + whenSuccess (raw_clGetDeviceInfo device infoid size (castPtr dat) nullPtr) + $ peek dat + where + size = fromIntegral $ sizeOf (0::CSize) + +getDeviceInfoBool :: CLDeviceInfo_ -> CLDeviceID -> IO (Either CLError Bool) +getDeviceInfoBool infoid device = alloca $ \(dat :: Ptr CLbool) -> do + whenSuccess (raw_clGetDeviceInfo device infoid size (castPtr dat) nullPtr) + $ peek dat >>= return . (/=0) + where + size = fromIntegral $ sizeOf (0::CLbool) + +getDeviceInfoFP :: CLDeviceInfo_ -> CLDeviceID -> IO (Either CLError [CLDeviceFPConfig]) +getDeviceInfoFP infoid device = do + val <- getDeviceInfoUlong infoid device + case val of + Left err -> return . Left $ err + Right flags -> return . Right . bitmaskToFPConfig $ flags + +#c +enum CLDeviceInfo { + cL_DEVICE_ADDRESS_BITS=CL_DEVICE_ADDRESS_BITS, + cL_DEVICE_AVAILABLE=CL_DEVICE_AVAILABLE, + cL_DEVICE_COMPILER_AVAILABLE=CL_DEVICE_COMPILER_AVAILABLE, +#ifdef CL_DEVICE_DOUBLE_FP_CONFIG + cL_DEVICE_DOUBLE_FP_CONFIG=CL_DEVICE_DOUBLE_FP_CONFIG, +#else + cL_DEVICE_DOUBLE_FP_CONFIG=0x1032, +#endif + cL_DEVICE_ENDIAN_LITTLE=CL_DEVICE_ENDIAN_LITTLE, + cL_DEVICE_ERROR_CORRECTION_SUPPORT=CL_DEVICE_ERROR_CORRECTION_SUPPORT, + cL_DEVICE_EXECUTION_CAPABILITIES=CL_DEVICE_EXECUTION_CAPABILITIES, + cL_DEVICE_EXTENSIONS=CL_DEVICE_EXTENSIONS, + cL_DEVICE_GLOBAL_MEM_CACHE_SIZE=CL_DEVICE_GLOBAL_MEM_CACHE_SIZE, + cL_DEVICE_GLOBAL_MEM_CACHE_TYPE=CL_DEVICE_GLOBAL_MEM_CACHE_TYPE, + cL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE=CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE, + cL_DEVICE_GLOBAL_MEM_SIZE=CL_DEVICE_GLOBAL_MEM_SIZE, +#ifdef CL_DEVICE_HALF_FP_CONFIG + cL_DEVICE_HALF_FP_CONFIG=CL_DEVICE_HALF_FP_CONFIG, +#else + cL_DEVICE_HALF_FP_CONFIG=0x1033, +#endif + cL_DEVICE_IMAGE_SUPPORT=CL_DEVICE_IMAGE_SUPPORT, + cL_DEVICE_IMAGE2D_MAX_HEIGHT=CL_DEVICE_IMAGE2D_MAX_HEIGHT, + cL_DEVICE_IMAGE2D_MAX_WIDTH=CL_DEVICE_IMAGE2D_MAX_WIDTH, + cL_DEVICE_IMAGE3D_MAX_DEPTH=CL_DEVICE_IMAGE3D_MAX_DEPTH, + cL_DEVICE_IMAGE3D_MAX_HEIGHT=CL_DEVICE_IMAGE3D_MAX_HEIGHT, + cL_DEVICE_IMAGE3D_MAX_WIDTH=CL_DEVICE_IMAGE3D_MAX_WIDTH, + cL_DEVICE_LOCAL_MEM_SIZE=CL_DEVICE_LOCAL_MEM_SIZE, + cL_DEVICE_LOCAL_MEM_TYPE=CL_DEVICE_LOCAL_MEM_TYPE, + cL_DEVICE_MAX_CLOCK_FREQUENCY=CL_DEVICE_MAX_CLOCK_FREQUENCY, + cL_DEVICE_MAX_COMPUTE_UNITS=CL_DEVICE_MAX_COMPUTE_UNITS, + cL_DEVICE_MAX_CONSTANT_ARGS=CL_DEVICE_MAX_CONSTANT_ARGS, + cL_DEVICE_MAX_CONSTANT_BUFFER_SIZE=CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE, + cL_DEVICE_MAX_MEM_ALLOC_SIZE=CL_DEVICE_MAX_MEM_ALLOC_SIZE, + cL_DEVICE_MAX_PARAMETER_SIZE=CL_DEVICE_MAX_PARAMETER_SIZE, + cL_DEVICE_MAX_READ_IMAGE_ARGS=CL_DEVICE_MAX_READ_IMAGE_ARGS, + cL_DEVICE_MAX_SAMPLERS=CL_DEVICE_MAX_SAMPLERS, + cL_DEVICE_MAX_WORK_GROUP_SIZE=CL_DEVICE_MAX_WORK_GROUP_SIZE, + cL_DEVICE_MAX_WORK_ITEM_DIMENSIONS=CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS, + cL_DEVICE_MAX_WORK_ITEM_SIZES=CL_DEVICE_MAX_WORK_ITEM_SIZES, + cL_DEVICE_MAX_WRITE_IMAGE_ARGS=CL_DEVICE_MAX_WRITE_IMAGE_ARGS, + cL_DEVICE_MEM_BASE_ADDR_ALIGN=CL_DEVICE_MEM_BASE_ADDR_ALIGN, + cL_DEVICE_MIN_DATA_TYPE_ALIGN_SIZE=CL_DEVICE_MIN_DATA_TYPE_ALIGN_SIZE, + cL_DEVICE_NAME=CL_DEVICE_NAME, + cL_DEVICE_PLATFORM=CL_DEVICE_PLATFORM, + cL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR=CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR, + cL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT=CL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT, + cL_DEVICE_PREFERRED_VECTOR_WIDTH_INT=CL_DEVICE_PREFERRED_VECTOR_WIDTH_INT, + cL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG=CL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG, + cL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT=CL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT, + cL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE=CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE, + cL_DEVICE_PROFILE=CL_DEVICE_PROFILE, + cL_DEVICE_PROFILING_TIMER_RESOLUTION=CL_DEVICE_PROFILING_TIMER_RESOLUTION, + cL_DEVICE_QUEUE_PROPERTIES=CL_DEVICE_QUEUE_PROPERTIES, + cL_DEVICE_SINGLE_FP_CONFIG=CL_DEVICE_SINGLE_FP_CONFIG, + cL_DEVICE_TYPE=CL_DEVICE_TYPE, + cL_DEVICE_VENDOR=CL_DEVICE_VENDOR, + cL_DEVICE_VENDOR_ID=CL_DEVICE_VENDOR_ID, + cL_DEVICE_VERSION=CL_DEVICE_VERSION, + cL_DRIVER_VERSION=CL_DRIVER_VERSION, + }; +#endc +{#enum CLDeviceInfo {upcaseFirstLetter} #} + +-- | The default compute device address space size specified as an unsigned +-- integer value in bits. Currently supported values are 32 or 64 bits. +clGetDeviceAddressBits :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceAddressBits = getDeviceInfoUint . getCLValue $ CL_DEVICE_ADDRESS_BITS + +-- | Is 'True' if the device is available and 'False' if the device is not +-- available. +clGetDeviceAvailable :: CLDeviceID -> IO (Either CLError Bool) +clGetDeviceAvailable = getDeviceInfoBool . getCLValue $ CL_DEVICE_AVAILABLE + +-- | Is 'False' if the implementation does not have a compiler available to +-- compile the program source. Is 'True' if the compiler is available. This can +-- be 'False' for the embededed platform profile only. +clGetDeviceCompilerAvailable :: CLDeviceID -> IO (Either CLError Bool) +clGetDeviceCompilerAvailable = getDeviceInfoBool . getCLValue $ CL_DEVICE_COMPILER_AVAILABLE + +-- | Describes the OPTIONAL double precision floating-point capability of the +-- OpenCL device. This is a bit-field that describes one or more of the +-- 'CLDeviceFPConfig' values. +-- The mandated minimum double precision floating-point capability is +-- 'CL_FP_FMA' | 'CL_FP_ROUND_TO_NEAREST' | 'CL_FP_ROUND_TO_ZERO' | +-- 'CL_FP_ROUND_TO_INF' | 'CL_FP_INF_NAN' | 'CL_FP_DENORM'. +clGetDeviceDoubleFPConfig :: CLDeviceID -> IO (Either CLError [CLDeviceFPConfig]) +clGetDeviceDoubleFPConfig = getDeviceInfoFP . getCLValue $ CL_DEVICE_DOUBLE_FP_CONFIG + +-- | Is 'True' if the OpenCL device is a little endian device and 'False' +-- otherwise. +clGetDeviceEndianLittle :: CLDeviceID -> IO (Either CLError Bool) +clGetDeviceEndianLittle = getDeviceInfoBool . getCLValue $ CL_DEVICE_ENDIAN_LITTLE + +-- | Is 'True' if the device implements error correction for the memories, +-- caches, registers etc. in the device. Is 'False' if the device does not +-- implement error correction. This can be a requirement for certain clients of +-- OpenCL. +clGetDeviceErrorCorrectionSupport :: CLDeviceID -> IO (Either CLError Bool) +clGetDeviceErrorCorrectionSupport = getDeviceInfoBool . getCLValue $ CL_DEVICE_ERROR_CORRECTION_SUPPORT + +-- | Describes the execution capabilities of the device. This is a list that +-- describes one or more of the 'CLDeviceExecCapability' values. +-- The mandated minimum capability is 'CL_EXEC_KERNEL'. +clGetDeviceExecutionCapabilities :: CLDeviceID -> IO (Either CLError [CLDeviceExecCapability]) +clGetDeviceExecutionCapabilities device = do + val <- getDeviceInfoUlong (getCLValue CL_DEVICE_EXECUTION_CAPABILITIES) device + case val of + Left err -> return . Left $ err + Right flags -> return . Right . bitmaskToExecCapability $ flags + +-- | Returns a space separated list of extension names (the extension names +-- themselves do not contain any spaces). The list of extension names returned +-- currently can include one or more of the following approved extension names: +-- +-- * cl_khr_fp64 +-- +-- * cl_khr_select_fprounding_mode +-- +-- * cl_khr_global_int32_base_atomics +-- +-- * cl_khr_global_int32_extended_atomics +-- +-- * cl_khr_local_int32_base_atomics +-- +-- * cl_khr_local_int32_extended_atomics +-- +-- * cl_khr_int64_base_atomics +-- +-- * cl_khr_int64_extended_atomics +-- +-- * cl_khr_3d_image_writes +-- +-- * cl_khr_byte_addressable_store +-- +-- * cl_khr_fp16 +clGetDeviceExtensions :: CLDeviceID -> IO (Either CLError String) +clGetDeviceExtensions = getDeviceInfoString . getCLValue $ CL_DEVICE_EXTENSIONS + +-- | Size of global memory cache in bytes. +clGetDeviceGlobalMemCacheSize :: CLDeviceID -> IO (Either CLError CLulong) +clGetDeviceGlobalMemCacheSize = getDeviceInfoUlong . getCLValue $ CL_DEVICE_GLOBAL_MEM_CACHE_SIZE + +-- | Type of global memory cache supported. Valid values are: 'CL_NONE', +-- 'CL_READ_ONLY_CACHE', and 'CL_READ_WRITE_CACHE'. +clGetDeviceGlobalMemCacheType :: CLDeviceID -> IO (Either CLError CLDeviceMemCacheType) +clGetDeviceGlobalMemCacheType device = do + val <- getDeviceInfoUint (getCLValue CL_DEVICE_GLOBAL_MEM_CACHE_TYPE) device + case val of + Left err -> return . Left $ err + Right typ -> return . Right . getEnumCL $ typ + +-- | Size of global memory cache line in bytes. +clGetDeviceGlobalMemCachelineSize :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceGlobalMemCachelineSize = getDeviceInfoUint . getCLValue $ CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE + +-- | Size of global device memory in bytes. +clGetDeviceGlobalMemSize :: CLDeviceID -> IO (Either CLError CLulong) +clGetDeviceGlobalMemSize = getDeviceInfoUlong . getCLValue $ CL_DEVICE_GLOBAL_MEM_SIZE + +-- | Describes the OPTIONAL half precision floating-point capability of the +-- OpenCL device. This is a bit-field that describes one or more of the +-- 'CLDeviceFPConfig' values. +-- The required minimum half precision floating-point capability as implemented +-- by this extension is 'CL_FP_ROUND_TO_ZERO' | 'CL_FP_ROUND_TO_INF' | +-- 'CL_FP_INF_NAN'. +clGetDeviceHalfFPConfig :: CLDeviceID -> IO (Either CLError [CLDeviceFPConfig]) +clGetDeviceHalfFPConfig = getDeviceInfoFP . getCLValue $ CL_DEVICE_HALF_FP_CONFIG + +-- | Is 'True' if images are supported by the OpenCL device and 'False' otherwise. +clGetDeviceImageSupport :: CLDeviceID -> IO (Either CLError Bool) +clGetDeviceImageSupport = getDeviceInfoBool . getCLValue $ CL_DEVICE_IMAGE_SUPPORT + +-- | Max height of 2D image in pixels. The minimum value is 8192 if +-- 'clGetDeviceImageSupport' is 'True'. +clGetDeviceImage2DMaxHeight :: CLDeviceID -> IO (Either CLError CSize) +clGetDeviceImage2DMaxHeight = getDeviceInfoSizet . getCLValue $ CL_DEVICE_IMAGE2D_MAX_HEIGHT + +-- | Max width of 2D image in pixels. The minimum value is 8192 if +-- 'clGetDeviceImageSupport' is 'True'. +clGetDeviceImage2DMaxWidth :: CLDeviceID -> IO (Either CLError CSize) +clGetDeviceImage2DMaxWidth = getDeviceInfoSizet . getCLValue $ CL_DEVICE_IMAGE2D_MAX_WIDTH + +-- | Max depth of 3D image in pixels. The minimum value is 2048 if +-- 'clGetDeviceImageSupport' is 'True'. +clGetDeviceImage3DMaxDepth :: CLDeviceID -> IO (Either CLError CSize) +clGetDeviceImage3DMaxDepth = getDeviceInfoSizet . getCLValue $ CL_DEVICE_IMAGE3D_MAX_DEPTH + +-- | Max height of 3D image in pixels. The minimum value is 2048 if +-- 'clGetDeviceImageSupport' is 'True'. +clGetDeviceImage3DMaxHeight :: CLDeviceID -> IO (Either CLError CSize) +clGetDeviceImage3DMaxHeight = getDeviceInfoSizet . getCLValue $ CL_DEVICE_IMAGE3D_MAX_HEIGHT + +-- | Max width of 3D image in pixels. The minimum value is 2048 if +-- 'clGetDeviceImageSupport' is 'True'. +clGetDeviceImage3DMaxWidth :: CLDeviceID -> IO (Either CLError CSize) +clGetDeviceImage3DMaxWidth = getDeviceInfoSizet . getCLValue $ CL_DEVICE_IMAGE3D_MAX_WIDTH + +-- | Size of local memory arena in bytes. The minimum value is 16 KB. +clGetDeviceLocalMemSize :: CLDeviceID -> IO (Either CLError CLulong) +clGetDeviceLocalMemSize = getDeviceInfoUlong . getCLValue $ CL_DEVICE_LOCAL_MEM_SIZE + +-- | Type of local memory supported. This can be set to 'CL_LOCAL' implying +-- dedicated local memory storage such as SRAM, or 'CL_GLOBAL'. +clGetDeviceLocalMemType :: CLDeviceID -> IO (Either CLError CLDeviceLocalMemType) +clGetDeviceLocalMemType device = do + val <- getDeviceInfoUint (getCLValue CL_DEVICE_LOCAL_MEM_TYPE) device + case val of + Left err -> return . Left $ err + Right typ -> return . Right . getEnumCL $ typ + +-- | Maximum configured clock frequency of the device in MHz. +clGetDeviceMaxClockFrequency :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceMaxClockFrequency = getDeviceInfoUint . getCLValue $ CL_DEVICE_MAX_CLOCK_FREQUENCY + +-- | The number of parallel compute cores on the OpenCL device. The minimum +-- value is 1. +clGetDeviceMaxComputeUnits :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceMaxComputeUnits = getDeviceInfoUint . getCLValue $ CL_DEVICE_MAX_COMPUTE_UNITS + +-- | Max number of arguments declared with the __constant qualifier in a kernel. +-- The minimum value is 8. +clGetDeviceMaxConstantArgs :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceMaxConstantArgs = getDeviceInfoUint . getCLValue $ CL_DEVICE_MAX_CONSTANT_ARGS + +-- | Max size in bytes of a constant buffer allocation. The minimum value is +-- 64 KB. +clGetDeviceMaxConstantBufferSize :: CLDeviceID -> IO (Either CLError CLulong) +clGetDeviceMaxConstantBufferSize = getDeviceInfoUlong . getCLValue $ CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE + +-- | Max size of memory object allocation in bytes. The minimum value is max +-- (1/4th of 'clGetDeviceGlobalMemSize', 128*1024*1024) +clGetDeviceMaxMemAllocSize :: CLDeviceID -> IO (Either CLError CLulong) +clGetDeviceMaxMemAllocSize = getDeviceInfoUlong . getCLValue $ CL_DEVICE_MAX_MEM_ALLOC_SIZE + +-- | Max size in bytes of the arguments that can be passed to a kernel. The +-- minimum value is 256. +clGetDeviceMaxParameterSize :: CLDeviceID -> IO (Either CLError CSize) +clGetDeviceMaxParameterSize = getDeviceInfoSizet . getCLValue $ CL_DEVICE_MAX_PARAMETER_SIZE + +-- | Max number of simultaneous image objects that can be read by a kernel. The +-- minimum value is 128 if 'clGetDeviceImageSupport' is 'True'. +clGetDeviceMaxReadImageArgs :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceMaxReadImageArgs = getDeviceInfoUint . getCLValue $ CL_DEVICE_MAX_READ_IMAGE_ARGS + +-- | Maximum number of samplers that can be used in a kernel. The minimum value +-- is 16 if 'clGetDeviceImageSupport' is 'True'. (Also see sampler type.) +clGetDeviceMaxSamplers :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceMaxSamplers = getDeviceInfoUint . getCLValue $ CL_DEVICE_MAX_SAMPLERS + +-- | Maximum number of work-items in a work-group executing a kernel using the +-- data parallel execution model. (Refer to 'clEnqueueNDRangeKernel'). The +-- minimum value is 1. +clGetDeviceMaxWorkGroupSize :: CLDeviceID -> IO (Either CLError CSize) +clGetDeviceMaxWorkGroupSize = getDeviceInfoSizet . getCLValue $ CL_DEVICE_MAX_WORK_GROUP_SIZE + +-- | Maximum dimensions that specify the global and local work-item IDs used by +-- the data parallel execution model. (Refer to 'clEnqueueNDRangeKernel'). +-- The minimum value is 3. +clGetDeviceMaxWorkItemDimensions :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceMaxWorkItemDimensions = getDeviceInfoUint . getCLValue $ CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS + +-- | Maximum number of work-items that can be specified in each dimension of the +-- work-group to 'clEnqueueNDRangeKernel'. +-- Returns n entries, where n is the value returned by the query for +-- clDeviceMaxWorkItemDimensions. The minimum value is (1, 1, 1). +clGetDeviceMaxWorkItemSizes :: CLDeviceID -> IO (Either CLError [CSize]) +clGetDeviceMaxWorkItemSizes device = do + val <- clGetDeviceMaxWorkItemDimensions device + case val of + Left err -> return . Left $ err + Right n -> allocaArray (fromIntegral n) $ \(buff :: Ptr CSize) -> do + whenSuccess (raw_clGetDeviceInfo device infoid (size n) (castPtr buff) nullPtr) + $ peekArray (fromIntegral n) buff + where + infoid = getCLValue CL_DEVICE_MAX_WORK_ITEM_SIZES + size n = fromIntegral $ (fromIntegral n) * (sizeOf (0::CSize)) + +-- | Max number of simultaneous image objects that can be written to by a +-- kernel. The minimum value is 8 if 'clGetDeviceImageSupport' is 'True'. +clGetDeviceMaxWriteImageArgs :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceMaxWriteImageArgs = getDeviceInfoUint . getCLValue $ CL_DEVICE_MAX_WRITE_IMAGE_ARGS + +-- | Describes the alignment in bits of the base address of any allocated +-- memory object. +clGetDeviceMemBaseAddrAlign :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceMemBaseAddrAlign = getDeviceInfoUint . getCLValue $ CL_DEVICE_MEM_BASE_ADDR_ALIGN + +-- | The smallest alignment in bytes which can be used for any data type. +clGetDeviceMinDataTypeAlignSize :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceMinDataTypeAlignSize = getDeviceInfoUint . getCLValue $ CL_DEVICE_MIN_DATA_TYPE_ALIGN_SIZE + +-- | Device name string. +clGetDeviceName :: CLDeviceID -> IO (Either CLError String) +clGetDeviceName = getDeviceInfoString . getCLValue $ CL_DEVICE_NAME + +-- | The platform associated with this device. +clGetDevicePlatform :: CLDeviceID -> IO (Either CLError CLPlatformID) +clGetDevicePlatform device = alloca $ \(dat :: Ptr CLPlatformID) -> do + whenSuccess (raw_clGetDeviceInfo device infoid size (castPtr dat) nullPtr) + $ peek dat + where + infoid = getCLValue CL_DEVICE_PLATFORM + size = fromIntegral $ sizeOf (nullPtr :: CLPlatformID) + +-- | Preferred native vector width size for built-in char types that can be put +-- into vectors. The vector width is defined as the number of scalar elements +-- that can be stored in the vector. +clGetDevicePreferredVectorWidthChar :: CLDeviceID -> IO (Either CLError CLuint) +clGetDevicePreferredVectorWidthChar = getDeviceInfoUint . getCLValue $ CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR + +-- | Preferred native vector width size for built-in short types that can be put +-- into vectors. The vector width is defined as the number of scalar elements +-- that can be stored in the vector. +clGetDevicePreferredVectorWidthShort :: CLDeviceID -> IO (Either CLError CLuint) +clGetDevicePreferredVectorWidthShort = getDeviceInfoUint . getCLValue $ CL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT + +-- | Preferred native vector width size for built-in int types that can be put +-- into vectors. The vector width is defined as the number of scalar elements +-- that can be stored in the vector. +clGetDevicePreferredVectorWidthInt :: CLDeviceID -> IO (Either CLError CLuint) +clGetDevicePreferredVectorWidthInt = getDeviceInfoUint . getCLValue $ CL_DEVICE_PREFERRED_VECTOR_WIDTH_INT + +-- | Preferred native vector width size for built-in long types that can be put +-- into vectors. The vector width is defined as the number of scalar elements +-- that can be stored in the vector. +clGetDevicePreferredVectorWidthLong :: CLDeviceID -> IO (Either CLError CLuint) +clGetDevicePreferredVectorWidthLong = getDeviceInfoUint . getCLValue $ CL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG + +-- | Preferred native vector width size for built-in float types that can be put +-- into vectors. The vector width is defined as the number of scalar elements +-- that can be stored in the vector. +clGetDevicePreferredVectorWidthFloat :: CLDeviceID -> IO (Either CLError CLuint) +clGetDevicePreferredVectorWidthFloat = getDeviceInfoUint . getCLValue $ CL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT + +-- | Preferred native vector width size for built-in double types that can be put +-- into vectors. The vector width is defined as the number of scalar elements +-- that can be stored in the vector. +-- | If the cl_khr_fp64 extension is not supported, +-- 'clGetDevicePreferredVectorWidthDouble' must return 0. +clGetDevicePreferredVectorWidthDouble :: CLDeviceID -> IO (Either CLError CLuint) +clGetDevicePreferredVectorWidthDouble = getDeviceInfoUint . getCLValue $ CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE + +-- | OpenCL profile string. Returns the profile name supported by the device +-- (see note). The profile name returned can be one of the following strings: +-- +-- * FULL_PROFILE - if the device supports the OpenCL specification +-- (functionality defined as part of the core specification and does not require +-- any extensions to be supported). +-- +-- * EMBEDDED_PROFILE - if the device supports the OpenCL embedded profile. +clGetDeviceProfile :: CLDeviceID -> IO (Either CLError String) +clGetDeviceProfile = getDeviceInfoString . getCLValue $ CL_DEVICE_PROFILE + +-- | Describes the resolution of device timer. This is measured in nanoseconds. +clGetDeviceProfilingTimerResolution :: CLDeviceID -> IO (Either CLError CSize) +clGetDeviceProfilingTimerResolution = getDeviceInfoSizet . getCLValue $ CL_DEVICE_PROFILING_TIMER_RESOLUTION + +-- | Describes the command-queue properties supported by the device. This is a +-- list that describes one or more of the CLCommandQueueProperty values. +-- These properties are described in the table for 'clCreateCommandQueue'. +-- The mandated minimum capability is 'CL_QUEUE_PROFILING_ENABLE'. +clGetDeviceQueueProperties :: CLDeviceID -> IO (Either CLError [CLCommandQueueProperty]) +clGetDeviceQueueProperties device = do + val <- getDeviceInfoUlong (getCLValue CL_DEVICE_QUEUE_PROPERTIES) device + case val of + Left err -> return . Left $ err + Right flags -> return . Right . bitmaskToCommandQueueProperties $ flags + +-- | Describes single precision floating-point capability of the device. This is +-- a bit-field that describes one or more of the 'CLDeviceFPConfig' values. +-- The mandated minimum floating-point capability is 'CL_FP_ROUND_TO_NEAREST' | +-- 'CL_FP_INF_NAN'. +clGetDeviceSingleFPConfig :: CLDeviceID -> IO (Either CLError [CLDeviceFPConfig]) +clGetDeviceSingleFPConfig = getDeviceInfoFP . getCLValue $ CL_DEVICE_SINGLE_FP_CONFIG + +-- | The OpenCL device type. Currently supported values are one of or a +-- combination of: 'CL_DEVICE_TYPE_CPU', 'CL_DEVICE_TYPE_GPU', +-- 'CL_DEVICE_TYPE_ACCELERATOR', or 'CL_DEVICE_TYPE_DEFAULT'. +clGetDeviceType :: CLDeviceID -> IO (Either CLError [CLDeviceType]) +clGetDeviceType device = do + val <- getDeviceInfoUlong (getCLValue CL_DEVICE_TYPE) device + case val of + Left err -> return . Left $ err + Right flags -> return . Right . bitmaskToDeviceTypes $ flags + +-- | Vendor name string. +clGetDeviceVendor :: CLDeviceID -> IO (Either CLError String) +clGetDeviceVendor = getDeviceInfoString . getCLValue $ CL_DEVICE_VENDOR + +-- | A unique device vendor identifier. An example of a unique device identifier +-- could be the PCIe ID. +clGetDeviceVendorID :: CLDeviceID -> IO (Either CLError CLuint) +clGetDeviceVendorID = getDeviceInfoUint . getCLValue $ CL_DEVICE_VENDOR_ID + +-- | OpenCL version string. Returns the OpenCL version supported by the device. +-- This version string has the following format: +-- /OpenCL major_version.minor_version vendor-specific information/ +-- The major_version.minor_version value returned will be 1.0. +clGetDeviceVersion :: CLDeviceID -> IO (Either CLError String) +clGetDeviceVersion = getDeviceInfoString . getCLValue $ CL_DEVICE_VERSION + +-- | OpenCL software driver version string in the form major_number.minor_number. +clGetDeviceDriverVersion :: CLDeviceID -> IO (Either CLError String) +clGetDeviceDriverVersion = getDeviceInfoString . getCLValue $ CL_DRIVER_VERSION + +-- ----------------------------------------------------------------------------- diff --git a/src/System/GPU/OpenCL/Types.chs b/src/System/GPU/OpenCL/Types.chs new file mode 100644 --- /dev/null +++ b/src/System/GPU/OpenCL/Types.chs @@ -0,0 +1,692 @@ +-- ----------------------------------------------------------------------------- +-- This file is part of Haskell-Opencl. + +-- Haskell-Opencl 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. + +-- Haskell-Opencl 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 Haskell-Opencl. If not, see . +-- ----------------------------------------------------------------------------- +module System.GPU.OpenCL.Types( + -- * Symple CL Types + CLbool, CLint, CLuint, CLulong, CLProgram, CLEvent, CLMem, CLPlatformID, + CLDeviceID, CLContext, CLCommandQueue, CLPlatformInfo_, CLDeviceType_, + CLDeviceInfo_, CLContextInfo_, CLContextProperty_, CLCommandQueueInfo_, + CLEventInfo_, CLProfilingInfo_, CLCommandType_, CLCommandQueueProperty_, + CLMemFlags_, CLImageFormat_p, CLMemObjectType_, CLMemInfo_, CLImageInfo_, + CLProgramInfo_, CLBuildStatus_,CLKernel, CLProgramBuildInfo_, CLKernelInfo_, + CLKernelWorkGroupInfo_, CLDeviceLocalMemType_, CLDeviceMemCacheType_, + CLSampler, CLFilterMode_, CLSamplerInfo_, CLAddressingMode_, + -- * High Level Types + CLError(..), CLDeviceFPConfig(..), CLDeviceMemCacheType(..), + CLDeviceExecCapability(..), CLDeviceLocalMemType(..), CLDeviceType(..), + CLCommandQueueProperty(..), CLCommandType(..), CLCommandExecutionStatus(..), + CLProfilingInfo(..), CLPlatformInfo(..), CLMemFlag(..), CLMemObjectType(..), + CLBuildStatus(..), CLAddressingMode(..), CLFilterMode(..), + -- * Functions + wrapPError, wrapCheckSuccess, wrapGetInfo, whenSuccess, getCLValue, + getEnumCL, bitmaskToFlags, getCommandExecutionStatus, bitmaskToDeviceTypes, + bitmaskFromFlags, bitmaskToCommandQueueProperties, bitmaskToFPConfig, + bitmaskToExecCapability, bitmaskToMemFlags ) + where + +-- ----------------------------------------------------------------------------- +import Foreign +import Foreign.C.Types +import Data.List( foldl' ) + +#include + +-- ----------------------------------------------------------------------------- + +type CLPlatformID = {#type cl_platform_id#} +type CLDeviceID = {#type cl_device_id#} +type CLContext = {#type cl_context#} +type CLCommandQueue = {#type cl_command_queue#} +type CLMem = {#type cl_mem#} +type CLEvent = {#type cl_event#} +type CLProgram = {#type cl_program#} +type CLKernel = {#type cl_kernel#} +type CLSampler = {#type cl_sampler#} + +type CLint = {#type cl_int#} +type CLuint = {#type cl_uint#} +type CLulong = {#type cl_ulong#} +type CLbool = {#type cl_bool#} + +type CLPlatformInfo_ = {#type cl_platform_info#} +type CLDeviceType_ = {#type cl_device_type#} +type CLDeviceInfo_ = {#type cl_device_info#} +type CLDeviceFPConfig_ = {#type cl_device_fp_config#} +type CLDeviceMemCacheType_ = {#type cl_device_mem_cache_type#} +type CLDeviceLocalMemType_ = {#type cl_device_local_mem_type#} +type CLDeviceExecCapability_ = {#type cl_device_exec_capabilities#} +type CLContextInfo_ = {#type cl_context_info#} +type CLContextProperty_ = {#type cl_context_properties#} +type CLCommandQueueInfo_ = {#type cl_command_queue_info#} +type CLCommandQueueProperty_ = {#type cl_command_queue_properties#} +type CLEventInfo_ = {#type cl_event_info#} +type CLProfilingInfo_ = {#type cl_profiling_info#} +type CLCommandType_ = {#type cl_command_type#} +type CLMemFlags_ = {#type cl_mem_flags#} +type CLMemObjectType_ = {#type cl_mem_object_type#} +type CLMemInfo_ = {#type cl_mem_info#} +type CLImageInfo_ = {#type cl_image_info#} +type CLProgramInfo_ = {#type cl_program_info#} +type CLProgramBuildInfo_ = {#type cl_program_build_info#} +type CLBuildStatus_ = {#type cl_build_status#} +type CLKernelInfo_ = {#type cl_kernel_info#} +type CLKernelWorkGroupInfo_ = {#type cl_kernel_work_group_info#} +type CLFilterMode_ = {#type cl_filter_mode#} +type CLSamplerInfo_ = {#type cl_sampler_info#} +type CLAddressingMode_ = {#type cl_addressing_mode#} + +{#pointer *cl_image_format as CLImageFormat_p#} + +--type CLImageChannelOrder_ = {#type cl_channel_order#} +--type CLImageChannelDataType_ = {#type cl_channel_type#} + +-- ----------------------------------------------------------------------------- +#c +enum CLError { + cL_BUILD_PROGRAM_FAILURE=CL_BUILD_PROGRAM_FAILURE, + cL_COMPILER_NOT_AVAILABLE=CL_COMPILER_NOT_AVAILABLE, + cL_DEVICE_NOT_AVAILABLE=CL_DEVICE_NOT_AVAILABLE, + cL_DEVICE_NOT_FOUND=CL_DEVICE_NOT_FOUND, + cL_IMAGE_FORMAT_MISMATCH=CL_IMAGE_FORMAT_MISMATCH, + cL_IMAGE_FORMAT_NOT_SUPPORTED=CL_IMAGE_FORMAT_NOT_SUPPORTED, + cL_INVALID_ARG_INDEX=CL_INVALID_ARG_INDEX, + cL_INVALID_ARG_SIZE=CL_INVALID_ARG_SIZE, + cL_INVALID_ARG_VALUE=CL_INVALID_ARG_VALUE, + cL_INVALID_BINARY=CL_INVALID_BINARY, + cL_INVALID_BUFFER_SIZE=CL_INVALID_BUFFER_SIZE, + cL_INVALID_BUILD_OPTIONS=CL_INVALID_BUILD_OPTIONS, + cL_INVALID_COMMAND_QUEUE=CL_INVALID_COMMAND_QUEUE, + cL_INVALID_CONTEXT=CL_INVALID_CONTEXT, + cL_INVALID_DEVICE=CL_INVALID_DEVICE, + cL_INVALID_DEVICE_TYPE=CL_INVALID_DEVICE_TYPE, + cL_INVALID_EVENT=CL_INVALID_EVENT, + cL_INVALID_EVENT_WAIT_LIST=CL_INVALID_EVENT_WAIT_LIST, + cL_INVALID_GL_OBJECT=CL_INVALID_GL_OBJECT, + cL_INVALID_GLOBAL_OFFSET=CL_INVALID_GLOBAL_OFFSET, + cL_INVALID_HOST_PTR=CL_INVALID_HOST_PTR, + cL_INVALID_IMAGE_FORMAT_DESCRIPTOR=CL_INVALID_IMAGE_FORMAT_DESCRIPTOR, + cL_INVALID_IMAGE_SIZE=CL_INVALID_IMAGE_SIZE, + cL_INVALID_KERNEL_NAME=CL_INVALID_KERNEL_NAME, + cL_INVALID_KERNEL=CL_INVALID_KERNEL, + cL_INVALID_KERNEL_ARGS=CL_INVALID_KERNEL_ARGS, + cL_INVALID_KERNEL_DEFINITION=CL_INVALID_KERNEL_DEFINITION, + cL_INVALID_MEM_OBJECT=CL_INVALID_MEM_OBJECT, + cL_INVALID_OPERATION=CL_INVALID_OPERATION, + cL_INVALID_PLATFORM=CL_INVALID_PLATFORM, + cL_INVALID_PROGRAM=CL_INVALID_PROGRAM, + cL_INVALID_PROGRAM_EXECUTABLE=CL_INVALID_PROGRAM_EXECUTABLE, + cL_INVALID_QUEUE_PROPERTIES=CL_INVALID_QUEUE_PROPERTIES, + cL_INVALID_SAMPLER=CL_INVALID_SAMPLER, + cL_INVALID_VALUE=CL_INVALID_VALUE, + cL_INVALID_WORK_DIMENSION=CL_INVALID_WORK_DIMENSION, + cL_INVALID_WORK_GROUP_SIZE=CL_INVALID_WORK_GROUP_SIZE, + cL_INVALID_WORK_ITEM_SIZE=CL_INVALID_WORK_ITEM_SIZE, + cL_MAP_FAILURE=CL_MAP_FAILURE, + cL_MEM_OBJECT_ALLOCATION_FAILURE=CL_MEM_OBJECT_ALLOCATION_FAILURE, + cL_MEM_COPY_OVERLAP=CL_MEM_COPY_OVERLAP, + cL_OUT_OF_HOST_MEMORY=CL_OUT_OF_HOST_MEMORY, + cL_OUT_OF_RESOURCES=CL_OUT_OF_RESOURCES, + cL_PROFILING_INFO_NOT_AVAILABLE=CL_PROFILING_INFO_NOT_AVAILABLE, + cL_SUCCESS=CL_SUCCESS + }; +#endc + +{-| + * 'CL_BUILD_PROGRAM_FAILURE', Returned if there is a failure to build the +program executable. + + * 'CL_COMPILER_NOT_AVAILABLE', Returned if the parameter program is created with +'clCreateProgramWithSource' and a compiler is not available. For example +'clDeviceCompilerAvalaible' is set to 'False'. + + * 'CL_DEVICE_NOT_AVAILABLE', Returned if the specified device is not currently +available. + + * 'CL_DEVICE_NOT_FOUND', Returned if no OpenCL devices that match the specified +devices were found. + + * 'CL_IMAGE_FORMAT_MISMATCH', Returned if the specified source and destination +images are not valid image objects. + + * 'CL_IMAGE_FORMAT_NOT_SUPPORTED', Returned if the specified image format is not +supported. + + * 'CL_INVALID_ARG_INDEX', Returned if an invalid argument index is specified. + + * 'CL_INVALID_ARG_SIZE', Returned if argument size specified (arg_size) does not +match the size of the data type for an argument that is not a memory object, or +if the argument is a memory object and arg_size != sizeof(cl_mem) or if arg_size +is zero and the argument is declared with the __local qualifier or if the +argument is a sampler and arg_size != sizeof(cl_sampler). + + * 'CL_INVALID_ARG_VALUE', Returned if the argument value specified is NULL for +an argument that is not declared with the __local qualifier or vice-versa. + + * 'CL_INVALID_BINARY', Returned if the program binary is not a valid binary for +the specified device. + + * 'CL_INVALID_BUFFER_SIZE', Returned if the value of the parameter size is 0 or +is greater than 'clDeviceMaxMemAllocSize' for all devices specified in the +parameter context. + + * 'CL_INVALID_BUILD_OPTIONS', Returned if the specified build options are +invalid. + + * 'CL_INVALID_COMMAND_QUEUE', Returned if the specified command-queue is not a +valid command-queue. + + * 'CL_INVALID_CONTEXT', Returned if the specified context is not a valid OpenCL +context, or the context associated with certain parameters are not the same. + + * 'CL_INVALID_DEVICE', Returned if the device or devices specified are not +valid. + + * 'CL_INVALID_DEVICE_TYPE', Returned if device type specified is not valid. + + * 'CL_INVALID_EVENT', Returned if the event objects specified are not valid. + + * 'CL_INVALID_EVENT_WAIT_LIST', Returned if event_wait_list is NULL and +num_events_in_wait_list > 0, or event_wait_list_list is not NULL and +num_events_in_wait_list is 0, or specified event objects are not valid events. + + * 'CL_INVALID_GL_OBJECT', Returned if obj is not a vaild GL object or is a GL +object but does not have an existing data store. + + * 'CL_INVALID_GLOBAL_OFFSET', Returned if global_work_offset is not NULL. + + * 'CL_INVALID_HOST_PTR', Returned if host_ptr is NULL and 'CL_MEM_USE_HOST_PTR' +or 'CL_MEM_COPY_HOST_PTR' are set in flags or if host_ptr is not NULL but +'CL_MEM_COPY_HOST_PTR' or 'CL_MEM_USE_HOST_PTR' are not set in flags. + + * 'CL_INVALID_IMAGE_FORMAT_DESCRIPTOR', Returned if the image format specified +is not valid or is NULL or does not map to a supported OpenCL image format. + + * 'CL_INVALID_IMAGE_SIZE', Returned if the specified image width or height are +invalid or if the image row pitch and image slice pitch do not follow the rules. + + * 'CL_INVALID_KERNEL_NAME', Returned if the specified kernel name is not found +in program. + + * 'CL_INVALID_KERNEL', Returned if the specified kernel is not a valid kernel +object. + + * 'CL_INVALID_KERNEL_ARGS', Returned if the kernel argument values have not been +specified. + + * 'CL_INVALID_KERNEL_DEFINITION', Returned if the function definition for +__kernel function given by kernel_name such as the number of arguments, the +argument types are not the same for all devices for which the program executable +has been built. + + * 'CL_INVALID_MEM_OBJECT', Returned if a parameter is not a valid memory, image, +or buffer object. + + * 'CL_INVALID_OPERATION', Returned if there are no devices in context that +support images. Returned if the build of a program executable for any of the +devices specified by a previous call to 'clBuildProgram' for program has not +completed, or if there are kernel objects attached to program. Returned by +'clEnqueueNativeKernel' if the specified device cannot execute the native +kernel. + + * 'CL_INVALID_PLATFORM', Returned if the specified platform is not a valid +platform, or no platform could be selected, or if platform value specified in +properties is not a valid platform. + + * 'CL_INVALID_PROGRAM', Returned if the specified program is not a valid program +object. + + * 'CL_INVALID_PROGRAM_EXECUTABLE', Returned if there is no successfully built +executable for program, or if there is no device in program. Returned if there +is no successfully built program executable available for device associated with +command_queue. + + * 'CL_INVALID_QUEUE_PROPERTIES', Returned if specified properties are valid but +are not supported by the device. + + * 'CL_INVALID_SAMPLER', Returned if the specified sampler is not a valid sampler +object, or for an argument declared to be of type sampler_t when the specified +arg_value is not a valid sampler object. + + * 'CL_INVALID_VALUE', Returned if a parameter is not an expected value. + + * 'CL_INVALID_WORK_DIMENSION', Returned if work_dim is not a valid value. + + * 'CL_INVALID_WORK_GROUP_SIZE', Returned if local_work_size is specified and +number of workitems specified by global_work_size is not evenly divisible by +size of work-group given by local_work_size or does not match the work-group +size specified for kernel using the __attribute__((reqd_work_group_size(X, Y, +Z))) qualifier in program source. + + * 'CL_INVALID_WORK_ITEM_SIZE', Returned if the number of work-items specified in +any of local_work_size... [0]... local_work_size[work_dim - 1] is greater than +the corresponding values specified by 'clDeviceMaxWorkItemSizes'. + + * 'CL_MAP_FAILURE', Returned by if there is a failure to map the requested +region into the host address space. This error cannot occur for buffer objects +created with 'CLMEM_USE_HOST_PTR' or 'CLMEM_ALLOC_HOST_PTR'. + + * 'CL_MEM_OBJECT_ALLOCATION_FAILURE', Returned if there is a failure to allocate +memory for data store associated with image or buffer objects specified as +arguments to kernel. + + * 'CL_MEM_COPY_OVERLAP', Returned if the source and destination images are the +same image (or the source and destination buffers are the same buffer), and the +source and destination regions overlap. + + * 'CL_OUT_OF_HOST_MEMORY', Returned in the event of a failure to allocate +resources required by the OpenCL implementation on the host. + + * 'CL_OUT_OF_RESOURCES', Returned in the event of a failure to queue the +execution instance of kernel on the command-queue because of insufficient +resources needed to execute the kernel. + + * 'CL_PROFILING_INFO_NOT_AVAILABLE', Returned if the 'CL_QUEUE_PROFILING_ENABLE' +flag is not set for the command-queue and the profiling information is currently +not available (because the command identified by event has not completed). + + * 'CL_SUCCESS', Indicates that the function executed successfully. +-} +{#enum CLError {upcaseFirstLetter} deriving( Show, Eq ) #} + +wrapPError :: (Ptr CLint -> IO a) -> IO (Either CLError a) +wrapPError f = alloca $ \perr -> do + v <- f perr + errcode <- peek perr >>= return . toEnum . fromIntegral + if errcode == CL_SUCCESS + then return $ Right v + else return $ Left errcode + +wrapCheckSuccess :: IO CLint -> IO Bool +wrapCheckSuccess f = f >>= return . (==CL_SUCCESS) . toEnum . fromIntegral + +wrapGetInfo :: Storable a => (Ptr a -> Ptr CSize -> IO CLint) -> (a -> b) + -> IO (Either CLError b) +wrapGetInfo fget fconvert= alloca $ \dat -> do + errcode <- fget dat nullPtr + if errcode == (fromIntegral . fromEnum $ CL_SUCCESS ) + then fmap (Right . fconvert) $ peek dat + else return . Left . toEnum . fromIntegral $ errcode + +whenSuccess :: IO CLint -> IO a -> IO (Either CLError a) +whenSuccess fcheck fval = do + errcode <- fcheck + if errcode == getCLValue CL_SUCCESS + then fval >>= return . Right + else return . Left . getEnumCL $ errcode + +-- ----------------------------------------------------------------------------- +#c +enum CLPlatformInfo { + cL_PLATFORM_PROFILE=CL_PLATFORM_PROFILE, + cL_PLATFORM_VERSION=CL_PLATFORM_VERSION, + cL_PLATFORM_NAME=CL_PLATFORM_NAME, + cL_PLATFORM_VENDOR=CL_PLATFORM_VENDOR, + cL_PLATFORM_EXTENSIONS=CL_PLATFORM_EXTENSIONS + }; +#endc + +{-| + * 'CL_PLATFORM_PROFILE', OpenCL profile string. Returns the profile name +supported by the implementation. The profile name returned can be one of the +following strings: + + [@FULL_PROFILE@] If the implementation supports the OpenCL specification +(functionality defined as part of the core specification and does not require +any extensions to be supported). + + [@EMBEDDED_PROFILE@] If the implementation supports the OpenCL embedded +profile. The embedded profile is defined to be a subset for each version of +OpenCL. + + * 'CL_PLATFORM_VERSION', OpenCL version string. Returns the OpenCL version +supported by the implementation. This version string has the following format: +/OpenCL major_version.minor_version platform-specific information/ The +/major_version.minor_version/ value returned will be 1.0. + + * 'CL_PLATFORM_NAME', Platform name string. + + * 'CL_PLATFORM_VENDOR', Platform vendor string. + + * 'CL_PLATFORM_EXTENSIONS', Returns a space-separated list of extension names +(the extension names themselves do not contain any spaces) supported by the +platform. Extensions defined here must be supported by all devices associated +with this platform. +-} +{#enum CLPlatformInfo {upcaseFirstLetter} deriving( Show ) #} + +-- ----------------------------------------------------------------------------- +#c +enum CLDeviceType { + cL_DEVICE_TYPE_CPU=CL_DEVICE_TYPE_CPU, + cL_DEVICE_TYPE_GPU=CL_DEVICE_TYPE_GPU, + cL_DEVICE_TYPE_ACCELERATOR=CL_DEVICE_TYPE_ACCELERATOR, + cL_DEVICE_TYPE_DEFAULT=CL_DEVICE_TYPE_DEFAULT, + cL_DEVICE_TYPE_ALL=CL_DEVICE_TYPE_ALL + }; +#endc + +{-| + * 'CL_DEVICE_TYPE_CPU', An OpenCL device that is the host processor. The host +processor runs the OpenCL implementations and is a single or multi-core CPU. + + * 'CL_DEVICE_TYPE_GPU', An OpenCL device that is a GPU. By this we mean that the +device can also be used to accelerate a 3D API such as OpenGL or DirectX. + + * 'CL_DEVICE_TYPE_ACCELERATOR', Dedicated OpenCL accelerators (for example the +IBM CELL Blade). These devices communicate with the host processor using a +peripheral interconnect such as PCIe. + + * 'CL_DEVICE_TYPE_DEFAULT', The default OpenCL device in the system. + + * 'CL_DEVICE_TYPE_ALL', All OpenCL devices available in the system. +-} +{#enum CLDeviceType {upcaseFirstLetter} deriving( Show ) #} + +#c +enum CLCommandQueueProperty { + cL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE=CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE, + cL_QUEUE_PROFILING_ENABLE=CL_QUEUE_PROFILING_ENABLE + }; +#endc + +{-| + * 'CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE', Determines whether the commands +queued in the command-queue are executed in-order or out-of-order. If set, the +commands in the command-queue are executed out-of-order. Otherwise, commands are +executed in-order. + + * 'CL_QUEUE_PROFILING_ENABLE', Enable or disable profiling of commands in the +command-queue. If set, the profiling of commands is enabled. Otherwise profiling +of commands is disabled. See 'clGetEventProfilingInfo' for more information. +-} +{#enum CLCommandQueueProperty {upcaseFirstLetter} deriving( Show, Bounded, Eq, Ord ) #} + +#c +enum CLDeviceFPConfig { + cL_FP_DENORM=CL_FP_DENORM, cL_FP_INF_NAN=CL_FP_INF_NAN, + cL_FP_ROUND_TO_NEAREST=CL_FP_ROUND_TO_NEAREST, + cL_FP_ROUND_TO_ZERO=CL_FP_ROUND_TO_ZERO, + cL_FP_ROUND_TO_INF=CL_FP_ROUND_TO_INF, cL_FP_FMA=CL_FP_FMA, + }; +#endc + +{-| + * 'CL_FP_DENORM', denorms are supported. + + * 'CL_FP_INF_NAN', INF and NaNs are supported. + + * 'CL_FP_ROUND_TO_NEAREST', round to nearest even rounding mode supported. + + * 'CL_FP_ROUND_TO_ZERO', round to zero rounding mode supported. + + * 'CL_FP_ROUND_TO_INF', round to +ve and -ve infinity rounding modes supported. + + * 'CL_FP_FMA', IEEE754-2008 fused multiply-add is supported. +-} +{#enum CLDeviceFPConfig {upcaseFirstLetter} deriving( Show, Bounded, Eq, Ord ) #} + +#c +enum CLDeviceExecCapability { + cL_EXEC_KERNEL=CL_EXEC_KERNEL, + cL_EXEC_NATIVE_KERNEL=CL_EXEC_NATIVE_KERNEL + }; +#endc + +{-| + * 'CL_EXEC_KERNEL', The OpenCL device can execute OpenCL kernels. + + * 'CL_EXEC_NATIVE_KERNEL', The OpenCL device can execute native kernels. +-} +{#enum CLDeviceExecCapability {upcaseFirstLetter} deriving( Show, Bounded, Eq, Ord ) #} + +#c +enum CLDeviceMemCacheType { + cL_NONE=CL_NONE, cL_READ_ONLY_CACHE=CL_READ_ONLY_CACHE, + cL_READ_WRITE_CACHE=CL_READ_WRITE_CACHE + }; +#endc + +{#enum CLDeviceMemCacheType {upcaseFirstLetter} deriving( Show ) #} + +#c +enum CLDeviceLocalMemType { + cL_LOCAL=CL_LOCAL, cL_GLOBAL=CL_GLOBAL + }; +#endc + +{#enum CLDeviceLocalMemType {upcaseFirstLetter} deriving( Show ) #} + +-- ----------------------------------------------------------------------------- +#c +enum CLCommandType { + cL_COMMAND_NDRANGE_KERNEL=CL_COMMAND_NDRANGE_KERNEL, + cL_COMMAND_TASK=CL_COMMAND_TASK , + cL_COMMAND_NATIVE_KERNEL=CL_COMMAND_NATIVE_KERNEL, + cL_COMMAND_READ_BUFFER=CL_COMMAND_READ_BUFFER, + cL_COMMAND_WRITE_BUFFER=CL_COMMAND_WRITE_BUFFER, + cL_COMMAND_COPY_BUFFER=CL_COMMAND_COPY_BUFFER, + cL_COMMAND_READ_IMAGE=CL_COMMAND_READ_IMAGE, + cL_COMMAND_WRITE_IMAGE=CL_COMMAND_WRITE_IMAGE, + cL_COMMAND_COPY_IMAGE=CL_COMMAND_COPY_IMAGE, + cL_COMMAND_COPY_BUFFER_TO_IMAGE=CL_COMMAND_COPY_BUFFER_TO_IMAGE, + cL_COMMAND_COPY_IMAGE_TO_BUFFER=CL_COMMAND_COPY_IMAGE_TO_BUFFER, + cL_COMMAND_MAP_BUFFER=CL_COMMAND_MAP_BUFFER, + cL_COMMAND_MAP_IMAGE=CL_COMMAND_MAP_IMAGE, + cL_COMMAND_UNMAP_MEM_OBJECT=CL_COMMAND_UNMAP_MEM_OBJECT, + cL_COMMAND_MARKER=CL_COMMAND_MARKER, + cL_COMMAND_ACQUIRE_GL_OBJECTS=CL_COMMAND_ACQUIRE_GL_OBJECTS, + cL_COMMAND_RELEASE_GL_OBJECTS=CL_COMMAND_RELEASE_GL_OBJECTS + }; +#endc + +-- | Command associated with an event. +{#enum CLCommandType {upcaseFirstLetter} deriving( Show ) #} + +#c +enum CLCommandExecutionStatus { + cL_QUEUED=CL_QUEUED, cL_SUBMITTED=CL_SUBMITTED, cL_RUNNING=CL_RUNNING, + cL_COMPLETE=CL_COMPLETE, cL_EXEC_ERROR= -1 + }; +#endc + +{-| + * 'CL_QUEUED', command has been enqueued in the command-queue. + + * 'CL_SUBMITTED', enqueued command has been submitted by the host to the +device associated with the command-queue. + + * 'CL_RUNNING', device is currently executing this command. + + * 'CL_COMPLETE', the command has completed. + + * 'CL_EXEC_ERROR', command was abnormally terminated. +-} +{#enum CLCommandExecutionStatus {upcaseFirstLetter} deriving( Show ) #} + +#c +enum CLProfilingInfo { + cL_PROFILING_COMMAND_QUEUED=CL_PROFILING_COMMAND_QUEUED, + cL_PROFILING_COMMAND_SUBMIT=CL_PROFILING_COMMAND_SUBMIT, + cL_PROFILING_COMMAND_START=CL_PROFILING_COMMAND_START, + cL_PROFILING_COMMAND_END=CL_PROFILING_COMMAND_END + }; +#endc + +{-| Specifies the profiling data. + + * 'CL_PROFILING_COMMAND_QUEUED', A 64-bit value that describes the current +device time counter in nanoseconds when the command identified by event is +enqueued in a command-queue by the host. + + * 'CL_PROFILING_COMMAND_SUBMIT', A 64-bit value that describes the current +device time counter in nanoseconds when the command identified by event that has +been enqueued is submitted by the host to the device associated with the +commandqueue. + + * 'CL_PROFILING_COMMAND_START', A 64-bit value that describes the current +device time counter in nanoseconds when the command identified by event starts +execution on the device. + + * 'CL_PROFILING_COMMAND_END', A 64-bit value that describes the current device +time counter in nanoseconds when the command identified by event has finished +execution on the device. +-} +{#enum CLProfilingInfo {upcaseFirstLetter} deriving( Show ) #} + +-- ----------------------------------------------------------------------------- +#c +enum CLMemFlag { + cL_MEM_READ_WRITE=CL_MEM_READ_WRITE, + cL_MEM_WRITE_ONLY=CL_MEM_WRITE_ONLY, + cL_MEM_READ_ONLY=CL_MEM_READ_ONLY, + cL_MEM_USE_HOST_PTR=CL_MEM_USE_HOST_PTR, + cL_MEM_ALLOC_HOST_PTR=CL_MEM_ALLOC_HOST_PTR, + cL_MEM_COPY_HOST_PTR=CL_MEM_COPY_HOST_PTR + }; +#endc +{-| + * 'CL_MEM_READ_WRITE', This flag specifies that the memory object will be +read and written by a kernel. This is the default. + + * 'CL_MEM_WRITE_ONLY', This flags specifies that the memory object will be +written but not read by a kernel. Reading from a buffer or image object created +with 'CLMEM_WRITE_ONLY' inside a kernel is undefined. + + * 'CL_MEM_READ_ONLY', This flag specifies that the memory object is a read-only +memory object when used inside a kernel. Writing to a buffer or image object +created with 'CLMEM_READ_ONLY' inside a kernel is undefined. + + * 'CL_MEM_USE_HOST_PTR', This flag is valid only if host_ptr is not NULL. If +specified, it indicates that the application wants the OpenCL implementation to +use memory referenced by host_ptr as the storage bits for the memory +object. OpenCL implementations are allowed to cache the buffer contents pointed +to by host_ptr in device memory. This cached copy can be used when kernels are +executed on a device. The result of OpenCL commands that operate on multiple +buffer objects created with the same host_ptr or overlapping host regions is +considered to be undefined. + + * 'CL_MEM_ALLOC_HOST_PTR', This flag specifies that the application wants the +OpenCL implementation to allocate memory from host accessible +memory. 'CL_MEM_ALLOC_HOST_PTR' and 'CL_MEM_USE_HOST_PTR' are mutually exclusive. + + * 'CL_MEM_COPY_HOST_PTR', This flag is valid only if host_ptr is not NULL. If +specified, it indicates that the application wants the OpenCL implementation to +allocate memory for the memory object and copy the data from memory referenced +by host_ptr. 'CL_MEM_COPY_HOST_PTR' and 'CL_MEM_USE_HOST_PTR' are mutually +exclusive. 'CL_MEM_COPY_HOST_PTR' can be used with 'CL_MEM_ALLOC_HOST_PTR' to +initialize the contents of the cl_mem object allocated using host-accessible +(e.g. PCIe) memory. +-} +{#enum CLMemFlag {upcaseFirstLetter} deriving( Show, Bounded, Eq, Ord ) #} + +#c +enum CLMemObjectType { + cL_MEM_OBJECT_BUFFER=CL_MEM_OBJECT_BUFFER, + cL_MEM_OBJECT_IMAGE2D=CL_MEM_OBJECT_IMAGE2D, + cL_MEM_OBJECT_IMAGE3D=CL_MEM_OBJECT_IMAGE3D + }; +#endc + +{-| * 'CL_MEM_OBJECT_BUFFER' if memobj is created with 'clCreateBuffer'. + + * 'CL_MEM_OBJECT_IMAGE2D' if memobj is created with 'clCreateImage2D' + + * 'CL_MEM_OBJECT_IMAGE3D' if memobj is created with 'clCreateImage3D'. +-} +{#enum CLMemObjectType {upcaseFirstLetter} deriving( Show ) #} + +#c +enum CLBuildStatus { + cL_BUILD_NONE=CL_BUILD_NONE, + cL_BUILD_ERROR=CL_BUILD_ERROR, + cL_BUILD_SUCCESS=CL_BUILD_SUCCESS, + cL_BUILD_IN_PROGRESS=CL_BUILD_IN_PROGRESS, + }; +#endc + +{-| * 'CL_BUILD_NONE'. The build status returned if no build has been performed +on the specified program object for device. + + * 'CL_BUILD_ERROR'. The build status returned if the last call to +'clBuildProgram' on the specified program object for device generated an error. + + * 'CL_BUILD_SUCCESS'. The build status retrned if the last call to +'clBuildProgram' on the specified program object for device was successful. + + * 'CL_BUILD_IN_PROGRESS'. The build status returned if the last call to +'clBuildProgram' on the specified program object for device has not finished. +-} +{#enum CLBuildStatus {upcaseFirstLetter} deriving( Show ) #} + +#c +enum CLAddressingMode { + cL_ADDRESS_REPEAT=CL_ADDRESS_REPEAT, + cL_ADDRESS_CLAMP_TO_EDGE =CL_ADDRESS_CLAMP_TO_EDGE , + cL_ADDRESS_CLAMP=CL_ADDRESS_CLAMP, + cL_ADDRESS_NONE=CL_ADDRESS_NONE + }; +#endc +{#enum CLAddressingMode {upcaseFirstLetter} deriving( Show ) #} + +#c +enum CLFilterMode { + cL_FILTER_NEAREST=CL_FILTER_NEAREST, + cL_FILTER_LINEAR=CL_FILTER_LINEAR, + }; +#endc +{#enum CLFilterMode {upcaseFirstLetter} deriving( Show ) #} + +-- ----------------------------------------------------------------------------- +getCLValue :: (Enum a, Integral b) => a -> b +getCLValue = fromIntegral . fromEnum + +getEnumCL :: (Integral a, Enum b) => a -> b +getEnumCL = toEnum . fromIntegral + +getCommandExecutionStatus :: CLint -> CLCommandExecutionStatus +getCommandExecutionStatus n + | n < 0 = CL_EXEC_ERROR + | otherwise = getEnumCL $ n + +-- ----------------------------------------------------------------------------- +binaryFlags :: (Ord b, Enum b, Bounded b) => b -> [b] +binaryFlags m = map toEnum . takeWhile (<= (fromEnum m)) $ [1 `shiftL` n | n <- [0..]] + +testMask :: Bits b => b -> b -> Bool +testMask mask v = (v .&. mask) == v + +bitmaskFromFlags :: (Enum a, Bits b) => [a] -> b +bitmaskFromFlags = foldl' (.|.) 0 . map (fromIntegral . fromEnum) + +bitmaskToFlags :: (Enum a, Bits b) => [a] -> b -> [a] +bitmaskToFlags xs mask = filter (testMask mask . fromIntegral . fromEnum) xs + +bitmaskToDeviceTypes :: CLDeviceType_ -> [CLDeviceType] +bitmaskToDeviceTypes = bitmaskToFlags [CL_DEVICE_TYPE_CPU,CL_DEVICE_TYPE_GPU,CL_DEVICE_TYPE_ACCELERATOR,CL_DEVICE_TYPE_DEFAULT,CL_DEVICE_TYPE_ALL] + +bitmaskToCommandQueueProperties :: CLCommandQueueProperty_ -> [CLCommandQueueProperty] +bitmaskToCommandQueueProperties = bitmaskToFlags (binaryFlags maxBound) + +bitmaskToFPConfig :: CLDeviceFPConfig_ -> [CLDeviceFPConfig] +bitmaskToFPConfig = bitmaskToFlags (binaryFlags maxBound) + +bitmaskToExecCapability :: CLDeviceExecCapability_ -> [CLDeviceExecCapability] +bitmaskToExecCapability = bitmaskToFlags (binaryFlags maxBound) + +bitmaskToMemFlags :: CLMemFlags_ -> [CLMemFlag] +bitmaskToMemFlags = bitmaskToFlags (binaryFlags maxBound) + +-- -----------------------------------------------------------------------------