commit ce233eeda7857b166ff431ca03da43b24f577f59
Author: vaplv <vaplv@free.fr>
Date: Fri, 17 Oct 2014 14:12:42 +0200
Helper API on the 4-wide SIMD <int|float> vector data type
Diffstat:
| A | COPYING | | | 674 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | COPYING.LESSER | | | 165 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | cmake/CMakeLists.txt | | | 85 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | src/rsimd.h | | | 36 | ++++++++++++++++++++++++++++++++++++ |
| A | src/sse/CMakeLists.txt | | | 9 | +++++++++ |
| A | src/sse/sse.c | | | 124 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | src/sse/sse.h | | | 26 | ++++++++++++++++++++++++++ |
| A | src/sse/sse_swz.h | | | 62 | ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | src/sse/ssef.c | | | 150 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | src/sse/ssef.h | | | 568 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | src/sse/ssei.h | | | 163 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | src/test_v4f.c | | | 597 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | src/test_v4i.c | | | 155 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
13 files changed, 2814 insertions(+), 0 deletions(-)
diff --git a/COPYING b/COPYING
@@ -0,0 +1,674 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+ The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works. By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users. We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors. You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+ To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights. Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received. You must make sure that they, too, receive
+or can get the source code. And you must show them these terms so they
+know their rights.
+
+ Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+ For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software. For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+ Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so. This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software. The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable. Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products. If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+ Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary. To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ TERMS AND CONDITIONS
+
+ 0. Definitions.
+
+ "This License" refers to version 3 of the GNU General Public License.
+
+ "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+ "The Program" refers to any copyrightable work licensed under this
+License. Each licensee is addressed as "you". "Licensees" and
+"recipients" may be individuals or organizations.
+
+ To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy. The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+ A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+ To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy. Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+ To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies. Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+ An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License. If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+ 1. Source Code.
+
+ The "source code" for a work means the preferred form of the work
+for making modifications to it. "Object code" means any non-source
+form of a work.
+
+ A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+ The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form. A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+ The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities. However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work. For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+ The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+ The Corresponding Source for a work in source code form is that
+same work.
+
+ 2. Basic Permissions.
+
+ All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met. This License explicitly affirms your unlimited
+permission to run the unmodified Program. The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work. This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+ You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force. You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright. Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+ Conveying under any other circumstances is permitted solely under
+the conditions stated below. Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+ 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+ No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+ When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+ 4. Conveying Verbatim Copies.
+
+ You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+ You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+ 5. Conveying Modified Source Versions.
+
+ You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+ a) The work must carry prominent notices stating that you modified
+ it, and giving a relevant date.
+
+ b) The work must carry prominent notices stating that it is
+ released under this License and any conditions added under section
+ 7. This requirement modifies the requirement in section 4 to
+ "keep intact all notices".
+
+ c) You must license the entire work, as a whole, under this
+ License to anyone who comes into possession of a copy. This
+ License will therefore apply, along with any applicable section 7
+ additional terms, to the whole of the work, and all its parts,
+ regardless of how they are packaged. This License gives no
+ permission to license the work in any other way, but it does not
+ invalidate such permission if you have separately received it.
+
+ d) If the work has interactive user interfaces, each must display
+ Appropriate Legal Notices; however, if the Program has interactive
+ interfaces that do not display Appropriate Legal Notices, your
+ work need not make them do so.
+
+ A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit. Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+ 6. Conveying Non-Source Forms.
+
+ You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+ a) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by the
+ Corresponding Source fixed on a durable physical medium
+ customarily used for software interchange.
+
+ b) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by a
+ written offer, valid for at least three years and valid for as
+ long as you offer spare parts or customer support for that product
+ model, to give anyone who possesses the object code either (1) a
+ copy of the Corresponding Source for all the software in the
+ product that is covered by this License, on a durable physical
+ medium customarily used for software interchange, for a price no
+ more than your reasonable cost of physically performing this
+ conveying of source, or (2) access to copy the
+ Corresponding Source from a network server at no charge.
+
+ c) Convey individual copies of the object code with a copy of the
+ written offer to provide the Corresponding Source. This
+ alternative is allowed only occasionally and noncommercially, and
+ only if you received the object code with such an offer, in accord
+ with subsection 6b.
+
+ d) Convey the object code by offering access from a designated
+ place (gratis or for a charge), and offer equivalent access to the
+ Corresponding Source in the same way through the same place at no
+ further charge. You need not require recipients to copy the
+ Corresponding Source along with the object code. If the place to
+ copy the object code is a network server, the Corresponding Source
+ may be on a different server (operated by you or a third party)
+ that supports equivalent copying facilities, provided you maintain
+ clear directions next to the object code saying where to find the
+ Corresponding Source. Regardless of what server hosts the
+ Corresponding Source, you remain obligated to ensure that it is
+ available for as long as needed to satisfy these requirements.
+
+ e) Convey the object code using peer-to-peer transmission, provided
+ you inform other peers where the object code and Corresponding
+ Source of the work are being offered to the general public at no
+ charge under subsection 6d.
+
+ A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+ A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling. In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage. For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product. A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+ "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source. The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+ If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information. But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+ The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed. Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+ Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+ 7. Additional Terms.
+
+ "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law. If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+ When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it. (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.) You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+ Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+ a) Disclaiming warranty or limiting liability differently from the
+ terms of sections 15 and 16 of this License; or
+
+ b) Requiring preservation of specified reasonable legal notices or
+ author attributions in that material or in the Appropriate Legal
+ Notices displayed by works containing it; or
+
+ c) Prohibiting misrepresentation of the origin of that material, or
+ requiring that modified versions of such material be marked in
+ reasonable ways as different from the original version; or
+
+ d) Limiting the use for publicity purposes of names of licensors or
+ authors of the material; or
+
+ e) Declining to grant rights under trademark law for use of some
+ trade names, trademarks, or service marks; or
+
+ f) Requiring indemnification of licensors and authors of that
+ material by anyone who conveys the material (or modified versions of
+ it) with contractual assumptions of liability to the recipient, for
+ any liability that these contractual assumptions directly impose on
+ those licensors and authors.
+
+ All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10. If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term. If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+ If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+ Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+ 8. Termination.
+
+ You may not propagate or modify a covered work except as expressly
+provided under this License. Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+ However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+ Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+ Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License. If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+ 9. Acceptance Not Required for Having Copies.
+
+ You are not required to accept this License in order to receive or
+run a copy of the Program. Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance. However,
+nothing other than this License grants you permission to propagate or
+modify any covered work. These actions infringe copyright if you do
+not accept this License. Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+ 10. Automatic Licensing of Downstream Recipients.
+
+ Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License. You are not responsible
+for enforcing compliance by third parties with this License.
+
+ An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations. If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+ You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License. For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+ 11. Patents.
+
+ A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based. The
+work thus licensed is called the contributor's "contributor version".
+
+ A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version. For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+ Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+ In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement). To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+ If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients. "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+ If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+ A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License. You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+ Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+ 12. No Surrender of Others' Freedom.
+
+ If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all. For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+ 13. Use with the GNU Affero General Public License.
+
+ Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work. The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+ 14. Revised Versions of this License.
+
+ The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+ Each version is given a distinguishing version number. If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation. If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+ If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+ Later license versions may give you additional or different
+permissions. However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+ 15. Disclaimer of Warranty.
+
+ THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+ 16. Limitation of Liability.
+
+ IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+ 17. Interpretation of Sections 15 and 16.
+
+ If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+ If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+ <program> Copyright (C) <year> <name of author>
+ This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+ You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+ The GNU General Public License does not permit incorporating your program
+into proprietary programs. If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library. If this is what you want to do, use the GNU Lesser General
+Public License instead of this License. But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.
diff --git a/COPYING.LESSER b/COPYING.LESSER
@@ -0,0 +1,165 @@
+ GNU LESSER GENERAL PUBLIC LICENSE
+ Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+
+ This version of the GNU Lesser General Public License incorporates
+the terms and conditions of version 3 of the GNU General Public
+License, supplemented by the additional permissions listed below.
+
+ 0. Additional Definitions.
+
+ As used herein, "this License" refers to version 3 of the GNU Lesser
+General Public License, and the "GNU GPL" refers to version 3 of the GNU
+General Public License.
+
+ "The Library" refers to a covered work governed by this License,
+other than an Application or a Combined Work as defined below.
+
+ An "Application" is any work that makes use of an interface provided
+by the Library, but which is not otherwise based on the Library.
+Defining a subclass of a class defined by the Library is deemed a mode
+of using an interface provided by the Library.
+
+ A "Combined Work" is a work produced by combining or linking an
+Application with the Library. The particular version of the Library
+with which the Combined Work was made is also called the "Linked
+Version".
+
+ The "Minimal Corresponding Source" for a Combined Work means the
+Corresponding Source for the Combined Work, excluding any source code
+for portions of the Combined Work that, considered in isolation, are
+based on the Application, and not on the Linked Version.
+
+ The "Corresponding Application Code" for a Combined Work means the
+object code and/or source code for the Application, including any data
+and utility programs needed for reproducing the Combined Work from the
+Application, but excluding the System Libraries of the Combined Work.
+
+ 1. Exception to Section 3 of the GNU GPL.
+
+ You may convey a covered work under sections 3 and 4 of this License
+without being bound by section 3 of the GNU GPL.
+
+ 2. Conveying Modified Versions.
+
+ If you modify a copy of the Library, and, in your modifications, a
+facility refers to a function or data to be supplied by an Application
+that uses the facility (other than as an argument passed when the
+facility is invoked), then you may convey a copy of the modified
+version:
+
+ a) under this License, provided that you make a good faith effort to
+ ensure that, in the event an Application does not supply the
+ function or data, the facility still operates, and performs
+ whatever part of its purpose remains meaningful, or
+
+ b) under the GNU GPL, with none of the additional permissions of
+ this License applicable to that copy.
+
+ 3. Object Code Incorporating Material from Library Header Files.
+
+ The object code form of an Application may incorporate material from
+a header file that is part of the Library. You may convey such object
+code under terms of your choice, provided that, if the incorporated
+material is not limited to numerical parameters, data structure
+layouts and accessors, or small macros, inline functions and templates
+(ten or fewer lines in length), you do both of the following:
+
+ a) Give prominent notice with each copy of the object code that the
+ Library is used in it and that the Library and its use are
+ covered by this License.
+
+ b) Accompany the object code with a copy of the GNU GPL and this license
+ document.
+
+ 4. Combined Works.
+
+ You may convey a Combined Work under terms of your choice that,
+taken together, effectively do not restrict modification of the
+portions of the Library contained in the Combined Work and reverse
+engineering for debugging such modifications, if you also do each of
+the following:
+
+ a) Give prominent notice with each copy of the Combined Work that
+ the Library is used in it and that the Library and its use are
+ covered by this License.
+
+ b) Accompany the Combined Work with a copy of the GNU GPL and this license
+ document.
+
+ c) For a Combined Work that displays copyright notices during
+ execution, include the copyright notice for the Library among
+ these notices, as well as a reference directing the user to the
+ copies of the GNU GPL and this license document.
+
+ d) Do one of the following:
+
+ 0) Convey the Minimal Corresponding Source under the terms of this
+ License, and the Corresponding Application Code in a form
+ suitable for, and under terms that permit, the user to
+ recombine or relink the Application with a modified version of
+ the Linked Version to produce a modified Combined Work, in the
+ manner specified by section 6 of the GNU GPL for conveying
+ Corresponding Source.
+
+ 1) Use a suitable shared library mechanism for linking with the
+ Library. A suitable mechanism is one that (a) uses at run time
+ a copy of the Library already present on the user's computer
+ system, and (b) will operate properly with a modified version
+ of the Library that is interface-compatible with the Linked
+ Version.
+
+ e) Provide Installation Information, but only if you would otherwise
+ be required to provide such information under section 6 of the
+ GNU GPL, and only to the extent that such information is
+ necessary to install and execute a modified version of the
+ Combined Work produced by recombining or relinking the
+ Application with a modified version of the Linked Version. (If
+ you use option 4d0, the Installation Information must accompany
+ the Minimal Corresponding Source and Corresponding Application
+ Code. If you use option 4d1, you must provide the Installation
+ Information in the manner specified by section 6 of the GNU GPL
+ for conveying Corresponding Source.)
+
+ 5. Combined Libraries.
+
+ You may place library facilities that are a work based on the
+Library side by side in a single library together with other library
+facilities that are not Applications and are not covered by this
+License, and convey such a combined library under terms of your
+choice, if you do both of the following:
+
+ a) Accompany the combined library with a copy of the same work based
+ on the Library, uncombined with any other library facilities,
+ conveyed under the terms of this License.
+
+ b) Give prominent notice with the combined library that part of it
+ is a work based on the Library, and explaining where to find the
+ accompanying uncombined form of the same work.
+
+ 6. Revised Versions of the GNU Lesser General Public License.
+
+ The Free Software Foundation may publish revised and/or new versions
+of the GNU Lesser 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
+Library as you received it specifies that a certain numbered version
+of the GNU Lesser General Public License "or any later version"
+applies to it, you have the option of following the terms and
+conditions either of that published version or of any later version
+published by the Free Software Foundation. If the Library as you
+received it does not specify a version number of the GNU Lesser
+General Public License, you may choose any version of the GNU Lesser
+General Public License ever published by the Free Software Foundation.
+
+ If the Library as you received it specifies that a proxy can decide
+whether future versions of the GNU Lesser General Public License shall
+apply, that proxy's public statement of acceptance of any version is
+permanent authorization for you to choose that version for the
+Library.
diff --git a/cmake/CMakeLists.txt b/cmake/CMakeLists.txt
@@ -0,0 +1,85 @@
+# Copyright (C) 2014 Vincent Forest (vaplv@free.fr)
+#
+# The RSIMD CMake 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.
+#
+# The RSIMD CMake 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 the RSIMD CMake. If not, see <http://www.gnu.org/licenses/>.
+
+cmake_minimum_required(VERSION 2.6)
+project(rsimd C)
+cmake_policy(SET CMP0011 NEW)
+enable_testing()
+
+option(BUILD_STATIC "Build RSIMD as a static library" ON)
+set(RSIMD_SOURCE_DIR ${PROJECT_SOURCE_DIR}/../src)
+
+################################################################################
+# Check dependencies
+################################################################################
+find_package(RCMake REQUIRED)
+find_package(RSys REQUIRED)
+
+include_directories(${RSys_INCLUDE_DIR})
+set(CMAKE_MODULE_PATH ${RCMAKE_SOURCE_DIR})
+include(rcmake)
+
+################################################################################
+# Configure and define targets
+################################################################################
+set(VERSION_MAJOR 0)
+set(VERSION_MINOR 0)
+set(VERSION_PATCH 0)
+set(VERSION ${VERSION_MAJOR}.${VERSION_MINOR}.${VERSION_PATCH})
+
+set(RSIMD_FILES_INC
+ rsimd.h
+ sse/sse.h
+ sse/ssef.h
+ sse/ssei.h
+ sse/sse_swz.h)
+set(RSIMD_FILES_SRC sse/ssef.c)
+rcmake_prepend_path(RSIMD_FILES_INC ${RSIMD_SOURCE_DIR})
+rcmake_prepend_path(RSIMD_FILES_SRC ${RSIMD_SOURCE_DIR})
+
+if(BUILD_STATIC)
+ add_library(rsimd STATIC ${RSIMD_FILES_INC} ${RSIMD_FILES_SRC})
+ set_target_properties(rsimd PROPERTIES DEFINE_SYMBOL RSIMD_STATIC)
+else(BUILD_STATIC)
+ add_library(rsimd SHARED ${RSIMD_FILES_INC} ${RSIMD_FILES_SRC})
+ set_target_properties(rsimd PROPERTIES
+ DEFINE_SYMBOL RSIMD_SHARED_BUILD
+ VERSION ${VERSION}
+ SOVERSION ${VERSION_MAJOR})
+endif(BUILD_STATIC)
+
+rcmake_setup_devel(rsimd RSIMD ${VERSION} rsimd_version.h)
+
+################################################################################
+# Add tests
+################################################################################
+macro(new_test _name)
+ add_executable(${_name} ${RSIMD_SOURCE_DIR}/${_name}.c)
+ target_link_libraries(${_name} rsimd m)
+ add_test(${_name} ${_name})
+endmacro(new_test)
+
+new_test(test_v4f)
+new_test(test_v4i)
+
+################################################################################
+# Install directives
+################################################################################
+install(TARGETS rsimd
+ ARCHIVE DESTINATION lib
+ LIBRARY DESTINATION lib
+ RUNTIME DESTINATION bin)
+install(FILES ${RSIMD_FILES_INC} DESTINATION include/rsimd)
+
diff --git a/src/rsimd.h b/src/rsimd.h
@@ -0,0 +1,36 @@
+/* Copyright (C) 2014 Vincent Forest (vaplv@free.fr)
+ *
+ * The RSIMD library is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * The RSIMD library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with the RSIMD library. If not, see <http://www.gnu.org/licenses/>. */
+
+#ifndef RSIMD_H
+#define RSIMD_H
+
+#include <rsys/rsys.h>
+
+#if defined(RSIMD_SHARED_BUILD)
+ #define RSIMD_API extern EXPORT_SYM
+#elif defined(RSIMD_STATIC)
+ #define RSIMD_API extern LOCAL_SYM
+#else
+ #define RSIMD_API extern IMPORT_SYM
+#endif
+
+#ifdef SIMD_SSE
+ #include "sse/sse.h"
+#else
+ #error Unsupported_Platform
+#endif
+
+#endif /* RSIMD_H */
+
diff --git a/src/sse/CMakeLists.txt b/src/sse/CMakeLists.txt
@@ -0,0 +1,9 @@
+cmake_minimum_required(VERSION 2.6)
+
+set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -msse3")
+
+
+file(GLOB MATHS_FILES *.c ../regular/*.c)
+add_library(mathssse SHARED ${MATHS_FILES})
+set_target_properties(mathssse PROPERTIES DEFINE_SYMBOL BUILD_SIMD)
+
diff --git a/src/sse/sse.c b/src/sse/sse.c
@@ -0,0 +1,124 @@
+#include "maths/simd/simd.h"
+#include "sys/sys.h"
+
+vf4_t
+vf4_sin(vf4_t v)
+{
+ const vi4_t zeroi = vi4_zero();
+ const vi4_t onei = vi4_set1(1);
+ const vi4_t twoi = vi4_set1(2);
+ const vi4_t threei = vi4_set1(3);
+
+ const vf4_t x = vf4_mul(v, KC0);
+ const vi4_t q = vf4_to_vi4(x);
+ const vi4_t off = vi4_and(q, threei);
+ const vf4_t qf = vi4_to_vf4(q);
+
+ const vf4_t tmp = vf4_sub(v, vf4_mul(qf, KC1));
+ const vf4_t xl = vf4_sub(tmp, vf4_mul(qf, KC2));
+ const vf4_t xl2 = vf4_mul(xl, xl);
+ const vf4_t xl3 = vf4_mul(xl2, xl);
+
+ const vf4_t cx =
+ vf4_madd(vf4_madd(vf4_madd(CC0, xl2, CC1), xl2, CC2), xl2, ONE);
+ const vf4_t sx =
+ vf4_madd(vf4_madd(vf4_madd(SC0, xl2, SC1), xl2, SC2), xl3, xl);
+
+ const vf4_t mask0 = (vf4_t) vi4_eq(vi4_and(off, onei), zeroi);
+ const vf4_t mask1 = (vf4_t) vi4_eq(vi4_and(off, twoi), zeroi);
+ const vf4_t res = vf4_sel(cx, sx, mask0);
+ return vf4_sel(vf4_minus(res), res, mask1);
+}
+
+vf4_t
+vf4_cos(vf4_t v)
+{
+ const vi4_t zeroi = vi4_zero();
+ const vi4_t onei = vi4_set1(1);
+ const vi4_t twoi = vi4_set1(2);
+ const vi4_t threei = vi4_set1(3);
+
+ const vf4_t x = vf4_mul(v, KC0);
+ const vi4_t q = vf4_to_vi4(x);
+ const vi4_t off = vi4_add(vi4_and(q, threei), onei);
+ const vf4_t qf = vi4_to_vf4(q);
+
+ const vf4_t tmp = vf4_sub(v, vf4_mul(qf, KC1));
+ const vf4_t xl = vf4_sub(tmp, vf4_mul(qf, KC2));
+ const vf4_t xl2 = vf4_mul(xl, xl);
+ const vf4_t xl3 = vf4_mul(xl2, xl);
+
+ const vf4_t cx =
+ vf4_madd(vf4_madd(vf4_madd(CC0, xl2, CC1), xl2, CC2), xl2, ONE);
+ const vf4_t sx =
+ vf4_madd(vf4_madd(vf4_madd(SC0, xl2, SC1), xl2, SC2), xl3, xl);
+
+ const vf4_t mask0 = (vf4_t) vi4_eq(vi4_and(off, onei), zeroi);
+ const vf4_t mask1 = (vf4_t) vi4_eq(vi4_and(off, twoi), zeroi);
+ const vf4_t res = vf4_sel(cx, sx, mask0);
+ return vf4_sel(vf4_minus(res), res, mask1);
+}
+
+void
+vf4_sincos(vf4_t v, vf4_t* restrict s, vf4_t* restrict c)
+{
+ const vi4_t zeroi = vi4_zero();
+ const vi4_t onei = vi4_set1(1);
+ const vi4_t twoi = vi4_set1(2);
+ const vi4_t threei = vi4_set1(3);
+
+ const vf4_t x = vf4_mul(v, KC0);
+ const vi4_t q = vf4_to_vi4(x);
+ const vi4_t soff = vi4_and(q, threei);
+ const vi4_t coff = vi4_add(vi4_and(q, threei), onei);
+ const vf4_t qf = vi4_to_vf4(q);
+
+ const vf4_t tmp = vf4_sub(v, vf4_mul(qf, KC1));
+ const vf4_t xl = vf4_sub(tmp, vf4_mul(qf, KC2));
+ const vf4_t xl2 = vf4_mul(xl, xl);
+ const vf4_t xl3 = vf4_mul(xl2, xl);
+
+ const vf4_t cx =
+ vf4_madd(vf4_madd(vf4_madd(CC0, xl2, CC1), xl2, CC2), xl2, ONE);
+ const vf4_t sx =
+ vf4_madd(vf4_madd(vf4_madd(SC0, xl2, SC1), xl2, SC2), xl3, xl);
+
+ const vf4_t smask0 = (vf4_t) vi4_eq(vi4_and(soff, onei), zeroi);
+ const vf4_t smask1 = (vf4_t) vi4_eq(vi4_and(soff, twoi), zeroi);
+ const vf4_t sres = vf4_sel(cx, sx, smask0);
+ *s = vf4_sel(vf4_minus(sres), sres, smask1);
+
+ const vf4_t cmask0 = (vf4_t) vi4_eq(vi4_and(coff, onei), zeroi);
+ const vf4_t cmask1 = (vf4_t) vi4_eq(vi4_and(coff, twoi), zeroi);
+ const vf4_t cres = vf4_sel(cx, sx, cmask0);
+ *c = vf4_sel(vf4_minus(cres), cres, cmask1);
+}
+
+vf4_t
+vf4_acos(vf4_t v)
+{
+ const vf4_t absv = vf4_abs(v);
+ const vf4_t t0 = vf4_sqrt(vf4_sub(vf4_set1(1.f), absv));
+ const vf4_t absv2 =vf4_mul(absv, absv);
+ const vf4_t absv4 = vf4_mul(absv2, absv2);
+
+ const vf4_t h0 = vf4_set1(-0.0012624911f);
+ const vf4_t h1 = vf4_set1(0.0066700901f);
+ const vf4_t h2 = vf4_set1(-0.0170881256f);
+ const vf4_t h3 = vf4_set1(0.0308918810f);
+ const vf4_t hi =
+ vf4_madd(vf4_madd(vf4_madd(h0, absv, h1), absv, h2), absv, h3);
+
+ const vf4_t l0 = vf4_set1(-0.0501743046f);
+ const vf4_t l1 = vf4_set1(0.0889789874f);
+ const vf4_t l2 = vf4_set1(-0.2145988016f);
+ const vf4_t l3 = vf4_set1(1.5707963050f);
+ const vf4_t lo =
+ vf4_madd(vf4_madd(vf4_madd(l0, absv, l1), absv, l2), absv, l3);
+
+ const vf4_t res = vf4_mul(vf4_madd(hi, absv4, lo), t0);
+ const vf4_t mask = vf4_lt(v, vf4_zero());
+
+ return vf4_sel(res, vf4_set1(3.14159265358979323846) - res, mask);
+}
+
diff --git a/src/sse/sse.h b/src/sse/sse.h
@@ -0,0 +1,26 @@
+/* Copyright (C) 2014 Vincent Forest (vaplv@free.fr)
+ *
+ * The RSIMD library is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * The RSIMD library 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with the RSIMD library. If not, see <http://www.gnu.org/licenses/>. */
+
+#ifndef RSIMD_SSE_H
+#define RSIMD_SSE_H
+
+#include "ssef.h"
+#include "ssei.h"
+
+static FINLINE v4i_T v4f_to_v4i(const v4f_T v) { return _mm_cvtps_epi32(v); }
+static FINLINE v4f_T v4i_to_v4f(const v4i_T v) { return _mm_cvtepi32_ps(v); }
+
+#endif /* SIMD_SSE_H */
+
diff --git a/src/sse/sse_swz.h b/src/sse/sse_swz.h
@@ -0,0 +1,62 @@
+/* Copyright (C) 2014 Vincent Forest (vaplv@free.fr)
+ *
+ * The RSIMD library is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * The RSIMD library 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with the RSIMD library. If not, see <http://www.gnu.org/licenses/>. */
+
+#ifndef RSIMD_SSE_SWZ_H
+#define RSIMD_SSE_SWZ_H
+
+/*
+ * Helper macro for the generation of swizzling function
+ */
+
+/* Swizzle operands */
+#define SWZ_X__ 0
+#define SWZ_Y__ 1
+#define SWZ_Z__ 2
+#define SWZ_W__ 3
+
+#define V4_SWZ_0__(Prefix, Func, Append, Op0, Op1, Op2, Op3) \
+ static FINLINE Prefix##_T \
+ Prefix ##_ ## Func ## Append(Prefix##_T vec) \
+ { \
+ return Prefix ## _SWZ__(vec, Op0, Op1, Op2, Op3); \
+ }
+
+#define V4_SWZ_1__(Prefix, Func, Append, Op0, Op1, Op2) \
+ V4_SWZ_0__(Prefix, Func ## Append, x, Op0, Op1, Op2, SWZ_X__) \
+ V4_SWZ_0__(Prefix, Func ## Append, y, Op0, Op1, Op2, SWZ_Y__) \
+ V4_SWZ_0__(Prefix, Func ## Append, z, Op0, Op1, Op2, SWZ_Z__) \
+ V4_SWZ_0__(Prefix, Func ## Append, w, Op0, Op1, Op2, SWZ_W__)
+
+#define V4_SWZ_2__(Prefix, Func, Append, Op0, Op1) \
+ V4_SWZ_1__(Prefix, Func ## Append, x, Op0, Op1, SWZ_X__) \
+ V4_SWZ_1__(Prefix, Func ## Append, y, Op0, Op1, SWZ_Y__) \
+ V4_SWZ_1__(Prefix, Func ## Append, z, Op0, Op1, SWZ_Z__) \
+ V4_SWZ_1__(Prefix, Func ## Append, w, Op0, Op1, SWZ_W__)
+
+#define V4_SWZ_3__(Prefix, Func, Op0) \
+ V4_SWZ_2__(Prefix, Func, x, Op0, SWZ_X__) \
+ V4_SWZ_2__(Prefix, Func, y, Op0, SWZ_Y__) \
+ V4_SWZ_2__(Prefix, Func, z, Op0, SWZ_Z__) \
+ V4_SWZ_2__(Prefix, Func, w, Op0, SWZ_W__)
+
+#define GENERATE_V4_SWZ_FUNCS__(Prefix) \
+ V4_SWZ_3__(Prefix, x, SWZ_X__) \
+ V4_SWZ_3__(Prefix, y, SWZ_Y__) \
+ V4_SWZ_3__(Prefix, z, SWZ_Z__) \
+ V4_SWZ_3__(Prefix, w, SWZ_W__)
+
+#endif /* RSIMD_SSE_SWZ_H */
+
+
diff --git a/src/sse/ssef.c b/src/sse/ssef.c
@@ -0,0 +1,150 @@
+/* Copyright (C) 2014 Vincent Forest (vaplv@free.fr)
+ *
+ * The RSIMD library is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * The RSIMD library 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with the RSIMD library. If not, see <http://www.gnu.org/licenses/>. */
+
+#include "../rsimd.h"
+
+#define KC0 v4f_set1(0.63661977236f)
+#define KC1 v4f_set1(1.57079625129f)
+#define KC2 v4f_set1(7.54978995489e-8f)
+#define CC0 v4f_set1(-0.0013602249f)
+#define CC1 v4f_set1(0.0416566950f)
+#define CC2 v4f_set1(-0.4999990225f)
+#define SC0 v4f_set1(-0.0001950727f)
+#define SC1 v4f_set1(0.0083320758f)
+#define SC2 v4f_set1(-0.1666665247f)
+#define ONE v4f_set1(1.f)
+
+v4f_T
+v4f_sin(const v4f_T v)
+{
+ const v4i_T zeroi = v4i_zero();
+ const v4i_T onei = v4i_set1(1);
+ const v4i_T twoi = v4i_set1(2);
+ const v4i_T threei = v4i_set1(3);
+
+ const v4f_T x = v4f_mul(v, KC0);
+ const v4i_T q = v4f_to_v4i(x);
+ const v4i_T off = v4i_and(q, threei);
+ const v4f_T qf = v4i_to_v4f(q);
+
+ const v4f_T tmp = v4f_sub(v, v4f_mul(qf, KC1));
+ const v4f_T xl = v4f_sub(tmp, v4f_mul(qf, KC2));
+ const v4f_T xl2 = v4f_mul(xl, xl);
+ const v4f_T xl3 = v4f_mul(xl2, xl);
+
+ const v4f_T cx =
+ v4f_madd(v4f_madd(v4f_madd(CC0, xl2, CC1), xl2, CC2), xl2, ONE);
+ const v4f_T sx =
+ v4f_madd(v4f_madd(v4f_madd(SC0, xl2, SC1), xl2, SC2), xl3, xl);
+
+ const v4f_T mask0 = (v4f_T) v4i_eq(v4i_and(off, onei), zeroi);
+ const v4f_T mask1 = (v4f_T) v4i_eq(v4i_and(off, twoi), zeroi);
+ const v4f_T res = v4f_sel(cx, sx, mask0);
+ return v4f_sel(v4f_minus(res), res, mask1);
+}
+
+v4f_T
+v4f_cos(const v4f_T v)
+{
+ const v4i_T zeroi = v4i_zero();
+ const v4i_T onei = v4i_set1(1);
+ const v4i_T twoi = v4i_set1(2);
+ const v4i_T threei = v4i_set1(3);
+
+ const v4f_T x = v4f_mul(v, KC0);
+ const v4i_T q = v4f_to_v4i(x);
+ const v4i_T off = v4i_add(v4i_and(q, threei), onei);
+ const v4f_T qf = v4i_to_v4f(q);
+
+ const v4f_T tmp = v4f_sub(v, v4f_mul(qf, KC1));
+ const v4f_T xl = v4f_sub(tmp, v4f_mul(qf, KC2));
+ const v4f_T xl2 = v4f_mul(xl, xl);
+ const v4f_T xl3 = v4f_mul(xl2, xl);
+
+ const v4f_T cx =
+ v4f_madd(v4f_madd(v4f_madd(CC0, xl2, CC1), xl2, CC2), xl2, ONE);
+ const v4f_T sx =
+ v4f_madd(v4f_madd(v4f_madd(SC0, xl2, SC1), xl2, SC2), xl3, xl);
+
+ const v4f_T mask0 = (v4f_T) v4i_eq(v4i_and(off, onei), zeroi);
+ const v4f_T mask1 = (v4f_T) v4i_eq(v4i_and(off, twoi), zeroi);
+ const v4f_T res = v4f_sel(cx, sx, mask0);
+ return v4f_sel(v4f_minus(res), res, mask1);
+}
+
+void
+v4f_sincos(const v4f_T v, v4f_T* RESTRICT s, v4f_T* RESTRICT c)
+{
+ const v4i_T zeroi = v4i_zero();
+ const v4i_T onei = v4i_set1(1);
+ const v4i_T twoi = v4i_set1(2);
+ const v4i_T threei = v4i_set1(3);
+
+ const v4f_T x = v4f_mul(v, KC0);
+ const v4i_T q = v4f_to_v4i(x);
+ const v4i_T soff = v4i_and(q, threei);
+ const v4i_T coff = v4i_add(v4i_and(q, threei), onei);
+ const v4f_T qf = v4i_to_v4f(q);
+
+ const v4f_T tmp = v4f_sub(v, v4f_mul(qf, KC1));
+ const v4f_T xl = v4f_sub(tmp, v4f_mul(qf, KC2));
+ const v4f_T xl2 = v4f_mul(xl, xl);
+ const v4f_T xl3 = v4f_mul(xl2, xl);
+
+ const v4f_T cx =
+ v4f_madd(v4f_madd(v4f_madd(CC0, xl2, CC1), xl2, CC2), xl2, ONE);
+ const v4f_T sx =
+ v4f_madd(v4f_madd(v4f_madd(SC0, xl2, SC1), xl2, SC2), xl3, xl);
+
+ const v4f_T smask0 = (v4f_T) v4i_eq(v4i_and(soff, onei), zeroi);
+ const v4f_T smask1 = (v4f_T) v4i_eq(v4i_and(soff, twoi), zeroi);
+ const v4f_T sres = v4f_sel(cx, sx, smask0);
+
+ const v4f_T cmask0 = (v4f_T) v4i_eq(v4i_and(coff, onei), zeroi);
+ const v4f_T cmask1 = (v4f_T) v4i_eq(v4i_and(coff, twoi), zeroi);
+ const v4f_T cres = v4f_sel(cx, sx, cmask0);
+
+ *s = v4f_sel(v4f_minus(sres), sres, smask1);
+ *c = v4f_sel(v4f_minus(cres), cres, cmask1);
+}
+
+v4f_T
+v4f_acos(const v4f_T v)
+{
+ const v4f_T absv = v4f_abs(v);
+ const v4f_T t0 = v4f_sqrt(v4f_sub(v4f_set1(1.f), absv));
+ const v4f_T absv2 =v4f_mul(absv, absv);
+ const v4f_T absv4 = v4f_mul(absv2, absv2);
+
+ const v4f_T h0 = v4f_set1(-0.0012624911f);
+ const v4f_T h1 = v4f_set1(0.0066700901f);
+ const v4f_T h2 = v4f_set1(-0.0170881256f);
+ const v4f_T h3 = v4f_set1(0.0308918810f);
+ const v4f_T hi =
+ v4f_madd(v4f_madd(v4f_madd(h0, absv, h1), absv, h2), absv, h3);
+
+ const v4f_T l0 = v4f_set1(-0.0501743046f);
+ const v4f_T l1 = v4f_set1(0.0889789874f);
+ const v4f_T l2 = v4f_set1(-0.2145988016f);
+ const v4f_T l3 = v4f_set1((float)(PI*0.5));
+ const v4f_T lo =
+ v4f_madd(v4f_madd(v4f_madd(l0, absv, l1), absv, l2), absv, l3);
+
+ const v4f_T res = v4f_mul(v4f_madd(hi, absv4, lo), t0);
+ const v4f_T mask = v4f_lt(v, v4f_zero());
+
+ return v4f_sel(res, v4f_set1((float)PI) - res, mask);
+}
+
diff --git a/src/sse/ssef.h b/src/sse/ssef.h
@@ -0,0 +1,568 @@
+/* Copyright (C) 2014 Vincent Forest (vaplv@free.fr)
+ *
+ * The RSIMD library is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * The RSIMD library 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with the RSIMD library. If not, see <http://www.gnu.org/licenses/>. */
+
+#ifndef RSIMD_SSEF_H
+#define RSIMD_SSEF_H
+
+/*
+ * 4 packed single precision floating-point values
+ */
+
+#include "sse_swz.h"
+
+#include <rsys/math.h>
+#ifdef SIMD_SSE
+ #include <xmmintrin.h>
+#endif
+#ifdef SIMD_SSE2
+ #include <emmintrin.h>
+#endif
+
+typedef __m128 v4f_T;
+#define V4F_AT__(Vec, Id) __builtin_ia32_vec_ext_v4sf(Vec, Id)
+
+#define v4f_SWZ__(Vec, Op0, Op1, Op2, Op3) \
+ _mm_shuffle_ps(vec, vec, _MM_SHUFFLE(Op3, Op2, Op1, Op0))
+GENERATE_V4_SWZ_FUNCS__(v4f) /* Swizzle operations */
+
+/*******************************************************************************
+ * Set operations
+ ******************************************************************************/
+static FINLINE float*
+v4f_store(float dst[4], v4f_T v)
+{
+ ASSERT(dst && IS_ALIGNED(dst, 16));
+ _mm_store_ps(dst, v);
+ return dst;
+}
+
+static FINLINE v4f_T
+v4f_load(const float dst[4])
+{
+ ASSERT(dst && IS_ALIGNED(dst, 16));
+ return _mm_load_ps(dst);
+}
+
+static FINLINE v4f_T
+v4f_set1(float x)
+{
+ return _mm_set1_ps(x);
+}
+
+static FINLINE v4f_T
+v4f_set(const float x, const float y, const float z, const float w)
+{
+ return _mm_set_ps(w, z, y, x);
+}
+
+static FINLINE v4f_T
+v4f_zero(void)
+{
+ return _mm_setzero_ps();
+}
+
+static FINLINE v4f_T
+v4f_mask(const int32_t x, const int32_t y, const int32_t z, const int32_t w)
+{
+ union { int32_t i[4]; float f[4]; } mask;
+ mask.i[0] = x;
+ mask.i[1] = y;
+ mask.i[2] = z;
+ mask.i[3] = w;
+ return v4f_set(mask.f[0], mask.f[1], mask.f[2], mask.f[3]);
+}
+
+static FINLINE v4f_T
+v4f_true(void)
+{
+ const union { int32_t i; float f; } mask = { ~0 };
+ return v4f_set1(mask.f);
+}
+
+static FINLINE v4f_T
+v4f_false(void)
+{
+ return v4f_zero();
+}
+
+static FINLINE v4f_T
+v4f_xmask(void)
+{
+ const union { int32_t i; float f; } mask = { ~0 };
+ return v4f_set(mask.f, 0.f, 0.f, 0.f);
+}
+
+static FINLINE v4f_T
+v4f_ymask(void)
+{
+ const union { int32_t i; float f; } mask = { ~0 };
+ return v4f_set(0.f, mask.f, 0.f, 0.f);
+}
+
+static FINLINE v4f_T
+v4f_zmask(void)
+{
+ const union { int32_t i; float f; } mask = { ~0 };
+ return v4f_set(0.f, 0.f, mask.f, 0.f);
+}
+
+static FINLINE v4f_T
+v4f_wmask(void)
+{
+ const union { int32_t i; float f; } mask = { ~0 };
+ return v4f_set(0.f, 0.f, 0.f, mask.f);
+}
+
+/*******************************************************************************
+ * Extract components
+ ******************************************************************************/
+static FINLINE float v4f_x(const v4f_T v) { return V4F_AT__(v, 0); }
+static FINLINE float v4f_y(const v4f_T v) { return V4F_AT__(v, 1); }
+static FINLINE float v4f_z(const v4f_T v) { return V4F_AT__(v, 2); }
+static FINLINE float v4f_w(const v4f_T v) { return V4F_AT__(v, 3); }
+
+static FINLINE int32_t
+v4f_mask_x(const v4f_T v)
+{
+ union { float f; int32_t i; } ucast;
+ ucast.f = v4f_x(v);
+ return ucast.i;
+}
+
+static FINLINE int32_t
+v4f_mask_y(const v4f_T v)
+{
+ union { float f; int32_t i; } ucast;
+ ucast.f = v4f_y(v);
+ return ucast.i;
+}
+
+static FINLINE int32_t
+v4f_mask_z(const v4f_T v)
+{
+ union { float f; int32_t i; } ucast;
+ ucast.f = v4f_z(v);
+ return ucast.i;
+}
+
+static FINLINE int32_t
+v4f_mask_w(const v4f_T v)
+{
+ union { float f; int32_t i; } ucast;
+ ucast.f = v4f_w(v);
+ return ucast.i;
+}
+
+/*******************************************************************************
+ * Merge operations
+ ******************************************************************************/
+static FINLINE v4f_T
+v4f_xayb(const v4f_T xyzw, const v4f_T abcd)
+{
+ return _mm_unpacklo_ps(xyzw, abcd);
+}
+
+static FINLINE v4f_T
+v4f_xyab(const v4f_T xyzw, const v4f_T abcd)
+{
+ return _mm_movelh_ps(xyzw, abcd);
+}
+
+static FINLINE v4f_T
+v4f_zcwd(const v4f_T xyzw, const v4f_T abcd)
+{
+ return _mm_unpackhi_ps(xyzw, abcd);
+}
+
+static FINLINE v4f_T
+v4f_zwcd(const v4f_T xyzw, const v4f_T abcd)
+{
+ return _mm_movehl_ps(abcd, xyzw);
+}
+
+static FINLINE v4f_T
+v4f_ayzw(const v4f_T xyzw, const v4f_T abcd)
+{
+ return _mm_move_ss(xyzw, abcd);
+}
+
+static FINLINE v4f_T
+v4f_xbzw(const v4f_T xyzw, const v4f_T abcd)
+{
+ const v4f_T zwzw = _mm_movehl_ps(xyzw, xyzw);
+ const v4f_T abzw = _mm_movelh_ps(abcd, zwzw);
+ return _mm_move_ss(abzw, xyzw);
+}
+
+static FINLINE v4f_T
+v4f_xycw(const v4f_T xyzw, const v4f_T abcd)
+{
+#if 0 /* SSE3 */
+ const v4f_T yyww = _mm_movehdup_ps(xyzw);
+#else
+ const v4f_T yyww = v4f_yyww(xyzw);
+#endif
+ const v4f_T cwdw = _mm_unpackhi_ps(abcd, yyww);
+ return _mm_movelh_ps(xyzw, cwdw);
+}
+
+static FINLINE v4f_T
+v4f_xyzd(const v4f_T xyzw, const v4f_T abcd)
+{
+#if 0 /* SSE3 */
+ const v4f_T bbdd = _mm_movehdup_ps(abcd);
+#else
+ const v4f_T bbdd = v4f_yyww(abcd);
+#endif
+ const v4f_T zdwd = _mm_unpackhi_ps(xyzw, bbdd);
+ return _mm_movelh_ps(xyzw, zdwd);
+}
+
+static FINLINE v4f_T
+v4f_048C
+ (const v4f_T v0123, const v4f_T v4567, const v4f_T v89AB, const v4f_T vCDEF)
+{
+ const v4f_T v0415 = v4f_xayb(v0123, v4567);
+ const v4f_T v8C9D = v4f_xayb(v89AB, vCDEF);
+ return v4f_xyab(v0415, v8C9D);
+}
+
+/*******************************************************************************
+ * Bitwise operations
+ ******************************************************************************/
+static FINLINE v4f_T
+v4f_or(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_or_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_and(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_and_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_xor(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_xor_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_sel(const v4f_T vfalse, const v4f_T vtrue, const v4f_T vcond)
+{
+ return v4f_xor(vfalse, v4f_and(vcond, v4f_xor(vfalse, vtrue)));
+}
+
+/*******************************************************************************
+ * Arithmetic operations
+ ******************************************************************************/
+static FINLINE v4f_T
+v4f_minus(const v4f_T v)
+{
+ return v4f_xor(v4f_set1(-0.f), v);
+}
+
+static FINLINE v4f_T
+v4f_add(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_add_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_sub(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_sub_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_mul(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_mul_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_div(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_div_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_madd(const v4f_T v0, const v4f_T v1, const v4f_T v2)
+{
+ return _mm_add_ps(_mm_mul_ps(v0, v1), v2);
+}
+
+static FINLINE v4f_T
+v4f_abs(const v4f_T v)
+{
+ const union { int32_t i; float f; } mask = { 0x7fffffff };
+ return v4f_and(v, v4f_set1(mask.f));
+}
+
+static FINLINE v4f_T
+v4f_sqrt(const v4f_T v)
+{
+ return _mm_sqrt_ps(v);
+}
+
+static FINLINE v4f_T
+v4f_rsqrte(const v4f_T v)
+{
+ return _mm_rsqrt_ps(v);
+}
+
+static FINLINE v4f_T
+v4f_rsqrt(const v4f_T v)
+{
+ const v4f_T y = v4f_rsqrte(v);
+ const v4f_T yyv = v4f_mul(v4f_mul(y, y), v);
+ const v4f_T tmp = v4f_sub(v4f_set1(1.5f), v4f_mul(yyv, v4f_set1(0.5f)));
+ return v4f_mul(tmp, y);
+}
+
+static FINLINE v4f_T
+v4f_rcpe(const v4f_T v)
+{
+ return _mm_rcp_ps(v);
+}
+
+static FINLINE v4f_T
+v4f_rcp(const v4f_T v)
+{
+ const v4f_T y = v4f_rcpe(v);
+ const v4f_T tmp = v4f_sub(v4f_set1(2.f), v4f_mul(y, v));
+ return v4f_mul(tmp, y);
+}
+
+static FINLINE v4f_T
+v4f_lerp(const v4f_T from, const v4f_T to, const v4f_T param)
+{
+ return v4f_madd(v4f_sub(to, from), param, from);
+}
+
+static FINLINE v4f_T
+v4f_sum(const v4f_T v)
+{
+#if 0 /* SSE3 */
+ const v4f_T r0 = _mm_hadd_ps(v, v);
+ return _mm_hadd_ps(r0, r0);
+#else
+ const v4f_T yxwz = v4f_yxwz(v);
+ const v4f_T tmp0 = v4f_add(v, yxwz); /* x+y, y+x, z+w, w+z */
+ const v4f_T tmp1 = v4f_wzyx(tmp0); /* w+z, z+w, y+x, x+y */
+ return v4f_add(tmp0, tmp1);
+#endif
+}
+
+static FINLINE v4f_T
+v4f_dot(const v4f_T v0, const v4f_T v1)
+{
+ return v4f_sum(v4f_mul(v0, v1));
+}
+
+static FINLINE v4f_T
+v4f_len(const v4f_T v)
+{
+ return v4f_sqrt(v4f_dot(v, v));
+}
+
+static FINLINE v4f_T
+v4f_normalize(const v4f_T v)
+{
+ return v4f_mul(v, v4f_rsqrt(v4f_dot(v, v)));
+}
+
+static FINLINE v4f_T
+v4f_sum2(const v4f_T v)
+{
+#if 0 /* SSE3 */
+ return v4f_xxxx(_mm_hadd_ps(v, v));
+#else
+ return v4f_add(v4f_xxyy(v), v4f_yyxx(v));
+#endif
+}
+
+static FINLINE v4f_T
+v4f_dot2(const v4f_T v0, const v4f_T v1)
+{
+ return v4f_sum2(v4f_mul(v0, v1));
+}
+
+static FINLINE v4f_T
+v4f_len2(const v4f_T v)
+{
+ return v4f_sqrt(v4f_dot2(v, v));
+}
+
+static FINLINE v4f_T
+v4f_cross2(const v4f_T v0, const v4f_T v1)
+{
+ const v4f_T v = v4f_mul(v0, v4f_yxyx(v1));
+ return v4f_sub(v4f_xxxx(v), v4f_yyyy(v));
+}
+
+static FINLINE v4f_T
+v4f_normalize2(const v4f_T v)
+{
+ return v4f_mul(v, v4f_rsqrt(v4f_dot2(v, v)));
+}
+
+static FINLINE v4f_T
+v4f_sum3(const v4f_T v)
+{
+ const union { int32_t i; float f; } m = { ~0 };
+ const v4f_T r0 = v4f_and(v4f_set(m.f, m.f, m.f, 0.f), v);
+#if 0 /* SSE3 */
+ const v4f_T r1 = _mm_hadd_ps(r0, r0);
+ return _mm_hadd_ps(r1, r1);
+#else
+ return v4f_sum(r0);
+#endif
+}
+
+static FINLINE v4f_T
+v4f_dot3(const v4f_T v0, const v4f_T v1)
+{
+ return v4f_sum3(v4f_mul(v0, v1));
+}
+
+static FINLINE v4f_T
+v4f_len3(const v4f_T v)
+{
+ return v4f_sqrt(v4f_dot3(v, v));
+}
+
+static FINLINE v4f_T
+v4f_cross3(const v4f_T v0, const v4f_T v1)
+{
+ const v4f_T r0 = v4f_mul(v0, v4f_yzxw(v1));
+ const v4f_T r1 = v4f_mul(v1, v4f_yzxw(v0));
+ return v4f_yzxw(v4f_sub(r0, r1));
+}
+
+static FINLINE v4f_T
+v4f_normalize3(const v4f_T v)
+{
+ return v4f_mul(v, v4f_rsqrt(v4f_dot3(v, v)));
+}
+
+/*******************************************************************************
+ * Trigonometric operations
+ ******************************************************************************/
+RSIMD_API v4f_T v4f_sin(const v4f_T v);
+RSIMD_API v4f_T v4f_cos(const v4f_T v);
+RSIMD_API v4f_T v4f_acos(const v4f_T v);
+RSIMD_API void v4f_sincos(const v4f_T v, v4f_T* RESTRICT s, v4f_T* RESTRICT c);
+
+static FINLINE v4f_T
+v4f_tan(const v4f_T v)
+{
+ v4f_T s, c;
+ v4f_sincos(v, &s, &c);
+ return v4f_div(s, c);
+}
+
+static FINLINE v4f_T
+v4f_asin(const v4f_T v)
+{
+ return v4f_sub(v4f_set1((float)(PI*0.5)), v4f_acos(v));
+}
+
+static FINLINE v4f_T
+v4f_atan(v4f_T v)
+{
+ const v4f_T tmp = v4f_rsqrt(v4f_madd(v, v, v4f_set1(1.f)));
+ return v4f_asin(v4f_mul(v, tmp));
+}
+
+/*******************************************************************************
+ * Comparators
+ ******************************************************************************/
+static FINLINE v4f_T
+v4f_eq(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_cmpeq_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_neq(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_cmpneq_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_ge(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_cmpge_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_le(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_cmple_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_gt(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_cmpgt_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_lt(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_cmplt_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_eq_eps(const v4f_T v0, const v4f_T v1, const v4f_T eps)
+{
+ return v4f_lt(v4f_abs(v4f_sub(v0, v1)), eps);
+}
+
+static FINLINE v4f_T
+v4f_min(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_min_ps(v0, v1);
+}
+
+static FINLINE v4f_T
+v4f_max(const v4f_T v0, const v4f_T v1)
+{
+ return _mm_max_ps(v0, v1);
+}
+
+/*******************************************************************************
+ * Miscellaneous
+ ******************************************************************************/
+static FINLINE v4f_T /* Cartesian (xyz) to spherical (r, theta, phi)*/
+v4f_xyz_to_rthetaphi(const v4f_T v)
+{
+ const v4f_T zero = v4f_zero();
+ const v4f_T len2 = v4f_len2(v);
+ const v4f_T len3 = v4f_len3(v);
+ const v4f_T theta = v4f_sel
+ (v4f_acos(v4f_div(v4f_zzzz(v), len3)), zero, v4f_eq(len3, zero));
+ const v4f_T tmp_phi = v4f_sel
+ (v4f_asin(v4f_div(v4f_yyyy(v), len2)), zero, v4f_eq(len2, zero));
+ const v4f_T phi = v4f_sel
+ (v4f_sub(v4f_set1((float)PI), tmp_phi), tmp_phi, v4f_ge(v4f_xxxx(v), zero));
+
+ return v4f_xyab(v4f_xayb(len3, theta), phi);
+}
+
+#endif /* RSIMD_SSEF_H */
+
diff --git a/src/sse/ssei.h b/src/sse/ssei.h
@@ -0,0 +1,163 @@
+/* Copyright (C) 2014 Vincent Forest (vaplv@free.fr)
+ *
+ * The RSIMD library is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * The RSIMD library 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with the RSIMD library. If not, see <http://www.gnu.org/licenses/>. */
+
+#ifndef RSIMD_SSEI_H
+#define RSIMD_SSEI_H
+
+/*
+ * 4 packed signed integers
+ */
+
+#include "sse_swz.h"
+
+#include <rsys/math.h>
+#ifdef SIMD_SSE
+ #include <xmmintrin.h>
+#endif
+#ifdef SIMD_SSE2
+ #include <emmintrin.h>
+#endif
+
+typedef __m128i v4i_T;
+#define V4I_AT__(Vec, Id) __builtin_ia32_vec_ext_v4si((__v4si)Vec, Id)
+
+#define v4i_SWZ__(Vec, Op0, Op1, Op2, Op3) \
+ _mm_shuffle_epi32(Vec, _MM_SHUFFLE(Op3, Op2, Op1, Op0))
+GENERATE_V4_SWZ_FUNCS__(v4i) /* Swizzle operations */
+
+/*******************************************************************************
+ * Set operations
+ ******************************************************************************/
+static FINLINE v4i_T
+v4i_set1(const int32_t i)
+{
+ return _mm_set1_epi32(i);
+}
+
+static FINLINE v4i_T
+v4i_set(const int32_t x, const int32_t y, const int32_t z, const int32_t w)
+{
+ return _mm_set_epi32(w, z, y, x);
+}
+
+static FINLINE v4i_T
+v4i_zero(void)
+{
+ return _mm_setzero_si128();
+}
+
+/*******************************************************************************
+ * Extract int32 from SIMD packed representation
+ ******************************************************************************/
+static FINLINE int32_t v4i_x(const v4i_T v) { return V4I_AT__(v, 0); }
+static FINLINE int32_t v4i_y(const v4i_T v) { return V4I_AT__(v, 1); }
+static FINLINE int32_t v4i_z(const v4i_T v) { return V4I_AT__(v, 2); }
+static FINLINE int32_t v4i_w(const v4i_T v) { return V4I_AT__(v, 3); }
+
+/*******************************************************************************
+ * Bitwise operators
+ ******************************************************************************/
+static FINLINE v4i_T
+v4i_or(const v4i_T v0, const v4i_T v1)
+{
+ return _mm_or_si128(v0, v1);
+}
+
+static FINLINE v4i_T
+v4i_and(const v4i_T v0, const v4i_T v1)
+{
+ return _mm_and_si128(v0, v1);
+}
+
+static FINLINE v4i_T
+v4i_andnot(const v4i_T v0, const v4i_T v1)
+{
+ return _mm_andnot_si128(v0, v1);
+}
+
+static FINLINE v4i_T
+v4i_xor(const v4i_T v0, const v4i_T v1)
+{
+ return _mm_xor_si128(v0, v1);
+}
+
+static FINLINE v4i_T
+v4i_not(const v4i_T v)
+{
+ return _mm_xor_si128(v, _mm_set1_epi32(-1));
+}
+
+/*******************************************************************************
+ * Arithmetic operators
+ ******************************************************************************/
+static FINLINE v4i_T
+v4i_add(const v4i_T v0, const v4i_T v1)
+{
+ return _mm_add_epi32(v0, v1);
+}
+
+static FINLINE v4i_T
+v4i_sub(const v4i_T v0, const v4i_T v1)
+{
+ return _mm_sub_epi32(v0, v1);
+}
+
+/*******************************************************************************
+ * Comparators
+ ******************************************************************************/
+static FINLINE v4i_T
+v4i_eq(const v4i_T v0, const v4i_T v1)
+{
+ return _mm_cmpeq_epi32(v0, v1);
+}
+
+static FINLINE v4i_T
+v4i_neq(const v4i_T v0, const v4i_T v1)
+{
+ return v4i_xor(v4i_eq(v0, v1), v4i_set1(-1));
+}
+
+static FINLINE v4i_T
+v4i_gt(const v4i_T v0, const v4i_T v1)
+{
+ return _mm_cmpgt_epi32(v0, v1);
+}
+
+static FINLINE v4i_T
+v4i_lt(const v4i_T v0, const v4i_T v1)
+{
+ return _mm_cmplt_epi32(v0, v1);
+}
+
+static FINLINE v4i_T
+v4i_ge(const v4i_T v0, const v4i_T v1)
+{
+ return v4i_xor(v4i_lt(v0, v1), v4i_set1(-1));
+}
+
+static FINLINE v4i_T
+v4i_le(const v4i_T v0, const v4i_T v1)
+{
+ return v4i_xor(v4i_gt(v0, v1), v4i_set1(-1));
+}
+
+static FINLINE v4i_T
+v4i_sel(const v4i_T vfalse, const v4i_T vtrue, const v4i_T vcond)
+{
+ return v4i_xor(vfalse, v4i_and(vcond, v4i_xor(vfalse, vtrue)));
+}
+
+#endif /* RSIMD_SSEI_H */
+
diff --git a/src/test_v4f.c b/src/test_v4f.c
@@ -0,0 +1,597 @@
+/* Copyright (C) 2014 Vincent Forest (vaplv@free.fr)
+ *
+ * The RSIMD library is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * The RSIMD library 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with the RSIMD library. If not, see <http://www.gnu.org/licenses/>. */
+
+#include "rsimd.h"
+
+int
+main(int argc, char** argv)
+{
+ union { int32_t i; float f; } cast;
+ v4f_T i, j, k;
+ v4i_T l;
+ ALIGN(16) float tmp[4] = { 0.f, 1.f, 2.f, 3.f };
+ float* ptr;
+ (void)argc, (void)argv;
+
+ i = v4f_load(tmp);
+ CHECK(v4f_x(i), 0.f);
+ CHECK(v4f_y(i), 1.f);
+ CHECK(v4f_z(i), 2.f);
+ CHECK(v4f_w(i), 3.f);
+
+ tmp[0] = tmp[1] = tmp[2] = tmp[3] = 0.f;
+ ptr = v4f_store(tmp, i);
+ CHECK(ptr, tmp);
+ CHECK(tmp[0], 0.f);
+ CHECK(tmp[1], 1.f);
+ CHECK(tmp[2], 2.f);
+ CHECK(tmp[3], 3.f);
+
+ i = v4f_set(1.f, 2.f, 3.f, 4.f);
+ CHECK(v4f_x(i), 1.f);
+ CHECK(v4f_y(i), 2.f);
+ CHECK(v4f_z(i), 3.f);
+ CHECK(v4f_w(i), 4.f);
+
+ i = v4f_set1(-2.f);
+ CHECK(v4f_x(i), -2.f);
+ CHECK(v4f_y(i), -2.f);
+ CHECK(v4f_z(i), -2.f);
+ CHECK(v4f_w(i), -2.f);
+
+ i = v4f_zero();
+ CHECK(v4f_x(i), 0.f);
+ CHECK(v4f_y(i), 0.f);
+ CHECK(v4f_z(i), 0.f);
+ CHECK(v4f_w(i), 0.f);
+
+ i = v4f_mask(~0, 0, ~0, ~0);
+ cast.f = v4f_x(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_y(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_w(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+
+ i = v4f_true();
+ cast.f = v4f_x(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_y(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_z(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_w(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+
+ i = v4f_false();
+ cast.f = v4f_x(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_y(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_w(i); CHECK(cast.i, (int32_t)0x00000000);
+
+ i = v4f_xmask();
+ cast.f = v4f_x(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_y(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_w(i); CHECK(cast.i, (int32_t)0x00000000);
+
+ i = v4f_ymask();
+ cast.f = v4f_x(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_y(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_z(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_w(i); CHECK(cast.i, (int32_t)0x00000000);
+
+ i = v4f_zmask();
+ cast.f = v4f_x(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_y(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_w(i); CHECK(cast.i, (int32_t)0x00000000);
+
+ i = v4f_wmask();
+ cast.f = v4f_x(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_y(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(i); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_w(i); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ CHECK(v4f_mask_x(i), 0);
+ CHECK(v4f_mask_y(i), 0);
+ CHECK(v4f_mask_z(i), 0);
+ CHECK(v4f_mask_w(i), ~0);
+
+ i = v4f_mask(~0, 0, ~0, ~0);
+ j = v4f_mask(0, 0, 0, ~0);
+ k = v4f_or(i, j);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ CHECK(v4f_mask_x(i), ~0);
+ CHECK(v4f_mask_y(i), 0);
+ CHECK(v4f_mask_z(i), ~0);
+ CHECK(v4f_mask_w(i), ~0);
+
+ k = v4f_and(i, j);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+
+ k = v4f_xor(i, j);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0x00000000);
+
+ i = v4f_set(1.f, 2.f, 3.f, 4.f);
+ j = v4f_set(5.f, 6.f, 7.f, 8.f);
+ k = v4f_sel(i, j, v4f_mask(~0, 0, 0, ~0));
+ CHECK(v4f_x(k), 5.f);
+ CHECK(v4f_y(k), 2.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 8.f);
+
+ k = v4f_xayb(i, j);
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), 5.f);
+ CHECK(v4f_z(k), 2.f);
+ CHECK(v4f_w(k), 6.f);
+
+ k = v4f_xyab(i, j);
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), 2.f);
+ CHECK(v4f_z(k), 5.f);
+ CHECK(v4f_w(k), 6.f);
+
+ k = v4f_zcwd(i, j);
+ CHECK(v4f_x(k), 3.f);
+ CHECK(v4f_y(k), 7.f);
+ CHECK(v4f_z(k), 4.f);
+ CHECK(v4f_w(k), 8.f);
+
+ k = v4f_zwcd(i, j);
+ CHECK(v4f_x(k), 3.f);
+ CHECK(v4f_y(k), 4.f);
+ CHECK(v4f_z(k), 7.f);
+ CHECK(v4f_w(k), 8.f);
+
+ k = v4f_ayzw(i, j);
+ CHECK(v4f_x(k), 5.f);
+ CHECK(v4f_y(k), 2.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 4.f);
+
+ k = v4f_xbzw(i, j);
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), 6.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 4.f);
+
+ k = v4f_xycw(i, j);
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), 2.f);
+ CHECK(v4f_z(k), 7.f);
+ CHECK(v4f_w(k), 4.f);
+
+ k = v4f_xyzd(i, j);
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), 2.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 8.f);
+
+ k = v4f_048C(v4f_set1(1.f), v4f_set1(2.f), v4f_set1(3.f), v4f_set1(4.f));
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), 2.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 4.f);
+
+ i = v4f_set(-1.f, 2.f, -3.f, 4.f);
+ j = v4f_minus(i);
+ CHECK(v4f_x(j), 1.f);
+ CHECK(v4f_y(j), -2.f);
+ CHECK(v4f_z(j), 3.f);
+ CHECK(v4f_w(j), -4.f);
+
+ k = v4f_add(i, j);
+ CHECK(v4f_x(k), 0.f);
+ CHECK(v4f_y(k), 0.f);
+ CHECK(v4f_z(k), 0.f);
+ CHECK(v4f_w(k), 0.f);
+
+ k = v4f_sub(i, j);
+ CHECK(v4f_x(k), -2.f);
+ CHECK(v4f_y(k), 4.f);
+ CHECK(v4f_z(k), -6.f);
+ CHECK(v4f_w(k), 8.f);
+
+ k = v4f_mul(i, j);
+ CHECK(v4f_x(k), -1.f);
+ CHECK(v4f_y(k), -4.f);
+ CHECK(v4f_z(k), -9.f);
+ CHECK(v4f_w(k), -16.f);
+
+ k = v4f_div(k, i);
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), -2.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), -4.f);
+
+ k = v4f_madd(i, j, k);
+ CHECK(v4f_x(k), 0.f);
+ CHECK(v4f_y(k), -6.f);
+ CHECK(v4f_z(k), -6.f);
+ CHECK(v4f_w(k), -20.f);
+
+ k = v4f_abs(i);
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), 2.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 4.f);
+
+ i = v4f_set(4.f, 9.f, 16.f, 25.f);
+ k = v4f_sqrt(i);
+ CHECK(v4f_x(k), 2.f);
+ CHECK(v4f_y(k), 3.f);
+ CHECK(v4f_z(k), 4.f);
+ CHECK(v4f_w(k), 5.f);
+
+ k = v4f_rsqrte(i);
+ CHECK(eq_eps(v4f_x(k), 1.f/2.f, 1.e-3f), 1);
+ CHECK(eq_eps(v4f_y(k), 1.f/3.f, 1.e-3f), 1);
+ CHECK(eq_eps(v4f_z(k), 1.f/4.f, 1.e-3f), 1);
+ CHECK(eq_eps(v4f_w(k), 1.f/5.f, 1.e-3f), 1);
+
+ k = v4f_rsqrt(i);
+ CHECK(eq_eps(v4f_x(k), 1.f/2.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), 1.f/3.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), 1.f/4.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), 1.f/5.f, 1.e-6f), 1);
+
+ k = v4f_rcpe(i);
+ CHECK(eq_eps(v4f_x(k), 1.f/4.f, 1.e-3f), 1);
+ CHECK(eq_eps(v4f_y(k), 1.f/9.f, 1.e-3f), 1);
+ CHECK(eq_eps(v4f_z(k), 1.f/16.f, 1.e-3f), 1);
+ CHECK(eq_eps(v4f_w(k), 1.f/25.f, 1.e-3f), 1);
+
+ k = v4f_rcp(i);
+ CHECK(eq_eps(v4f_x(k), 1.f/4.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), 1.f/9.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), 1.f/16.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), 1.f/25.f, 1.e-6f), 1);
+
+ i = v4f_set(0.f, 1.f, 2.f, 4.f);
+ j = v4f_set(1.f, 2.f, -1.f, 1.f);
+ k = v4f_lerp(i, j, v4f_set1(0.5f));
+ CHECK(v4f_x(k), 0.5f);
+ CHECK(v4f_y(k), 1.5f);
+ CHECK(v4f_z(k), 0.5f);
+ CHECK(v4f_w(k), 2.5f);
+
+ k = v4f_sum(j);
+ CHECK(v4f_x(k), 3.f);
+ CHECK(v4f_y(k), 3.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 3.f);
+
+ k = v4f_dot(i, j);
+ CHECK(v4f_x(k), 4.f);
+ CHECK(v4f_y(k), 4.f);
+ CHECK(v4f_z(k), 4.f);
+ CHECK(v4f_w(k), 4.f);
+
+ k = v4f_len(i);
+ CHECK(eq_eps(v4f_x(k), (float)sqrt(21.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), (float)sqrt(21.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), (float)sqrt(21.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), (float)sqrt(21.0), 1.e-6f), 1);
+
+ i = v4f_set(0.f, 4.f, 2.f, 3.f);
+ k = v4f_normalize(i);
+ CHECK(eq_eps(v4f_x(k), 0.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), 0.742781353f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), 0.371390676f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), 0.557086014f, 1.e-6f), 1);
+
+ i = v4f_set(1.f, 4.f, 2.f, 3.f);
+ k = v4f_sum2(i);
+ CHECK(v4f_x(k), 5.f);
+ CHECK(v4f_y(k), 5.f);
+ CHECK(v4f_z(k), 5.f);
+ CHECK(v4f_w(k), 5.f);
+
+ j = v4f_set(2.f, 3.f, 5.f, 1.f);
+ k = v4f_dot2(i, j);
+ CHECK(v4f_x(k), 14.f);
+ CHECK(v4f_y(k), 14.f);
+ CHECK(v4f_z(k), 14.f);
+ CHECK(v4f_w(k), 14.f);
+
+ k = v4f_len2(i);
+ CHECK(eq_eps(v4f_x(k), (float)sqrt(17.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), (float)sqrt(17.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), (float)sqrt(17.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), (float)sqrt(17.0), 1.e-6f), 1);
+
+ i = v4f_set(1.f, -2.f, 2.f, 5.f);
+ j = v4f_set(3.f, 1.f, 1.f, 5.f);
+ k = v4f_cross2(i, j);
+ CHECK(v4f_x(k), 7.f);
+ CHECK(v4f_y(k), 7.f);
+ CHECK(v4f_z(k), 7.f);
+ CHECK(v4f_w(k), 7.f);
+
+ k = v4f_cross2(j, i);
+ CHECK(v4f_x(k), -7.f);
+ CHECK(v4f_y(k), -7.f);
+ CHECK(v4f_z(k), -7.f);
+ CHECK(v4f_w(k), -7.f);
+
+ i = v4f_set(0.f, 4.f, 5.f, 7.f);
+ k = v4f_normalize2(i);
+ CHECK(eq_eps(v4f_x(k), 0.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), 1.f, 1.e-6f), 1);
+
+ k = v4f_sum3(i);
+ CHECK(v4f_x(k), 9.f);
+ CHECK(v4f_y(k), 9.f);
+ CHECK(v4f_z(k), 9.f);
+ CHECK(v4f_w(k), 9.f);
+
+ i = v4f_set(2.f, 3.f, 2.f, 4.f);
+ j = v4f_set(0.f, 4.f, 2.f, 19.f);
+ k = v4f_dot3(i, j);
+ CHECK(v4f_x(k), 16.f);
+ CHECK(v4f_y(k), 16.f);
+ CHECK(v4f_z(k), 16.f);
+ CHECK(v4f_w(k), 16.f);
+
+ k = v4f_len3(j);
+ CHECK(eq_eps(v4f_x(k), (float)sqrt(20.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), (float)sqrt(20.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), (float)sqrt(20.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), (float)sqrt(20.0), 1.e-6f), 1);
+
+ k = v4f_normalize3(j);
+ CHECK(eq_eps(v4f_x(k), 0.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), 0.8944271910f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), 0.4472135995f, 1.e-6f), 1);
+
+ i = v4f_set(1.f, -2.f, 2.f, 4.f);
+ j = v4f_set(3.f, 1.f, -1.5f, 2.f);
+ k = v4f_cross3(i, j);
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), 7.5f);
+ CHECK(v4f_z(k), 7.f);
+
+ i = v4f_set((float)PI/2.f, (float)PI/3.f, (float)PI/4.f, (float)PI/6.f);
+ k = v4f_cos(i);
+ CHECK(eq_eps(v4f_x(k), (float)cos(PI/2.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), (float)cos(PI/3.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), (float)cos(PI/4.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), (float)cos(PI/6.0), 1.e-6f), 1);
+
+ k = v4f_sin(i);
+ CHECK(eq_eps(v4f_x(k), (float)sin(PI/2.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), (float)sin(PI/3.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), (float)sin(PI/4.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), (float)sin(PI/6.0), 1.e-6f), 1);
+
+ v4f_sincos(i, &k, &j);
+ CHECK(eq_eps(v4f_x(k), (float)sin(PI/2.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), (float)sin(PI/3.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), (float)sin(PI/4.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), (float)sin(PI/6.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_x(j), (float)cos(PI/2.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(j), (float)cos(PI/3.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(j), (float)cos(PI/4.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(j), (float)cos(PI/6.0), 1.e-6f), 1);
+
+ i = v4f_set((float)PI/8.f, (float)PI/3.f, (float)PI/4.f, (float)PI/6.f);
+ k = v4f_tan(i);
+ CHECK(eq_eps(v4f_x(k), (float)tan(PI/8.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), (float)tan(PI/3.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), (float)tan(PI/4.0), 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), (float)tan(PI/6.0), 1.e-6f), 1);
+
+ k = v4f_acos(v4f_cos(i));
+ CHECK(eq_eps(v4f_x(k), PI/8.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), PI/3.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), PI/4.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), PI/6.f, 1.e-6f), 1);
+
+ k = v4f_asin(v4f_sin(i));
+ CHECK(eq_eps(v4f_x(k), PI/8.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), PI/3.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), PI/4.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), PI/6.f, 1.e-6f), 1);
+
+ k = v4f_atan(v4f_tan(i));
+ CHECK(eq_eps(v4f_x(k), PI/8.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_y(k), PI/3.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_z(k), PI/4.f, 1.e-6f), 1);
+ CHECK(eq_eps(v4f_w(k), PI/6.f, 1.e-6f), 1);
+
+ i = v4f_set(1.f, 2.f, 3.f, 4.f);
+ j = v4f_set(-2.f, -4.f, 3.f, 6.f);
+ k = v4f_eq(i, j);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0x00000000);
+
+ k = v4f_neq(i, j);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+
+ k = v4f_gt(i, j);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0x00000000);
+
+ k = v4f_lt(i, j);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+
+ k = v4f_ge(i, j);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0x00000000);
+
+ k = v4f_le(i, j);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+
+ i = v4f_set(1.01f, 2.01f, 3.02f, 0.02f);
+ j = v4f_set(1.f, 2.f, 3.f, 0.f);
+ k = v4f_set(0.f, 0.01f, 0.02f, 0.f);
+ k = v4f_eq_eps(i, j, k);
+ cast.f = v4f_x(k); CHECK(cast.i, (int32_t)0x00000000);
+ cast.f = v4f_y(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_z(k); CHECK(cast.i, (int32_t)0xFFFFFFFF);
+ cast.f = v4f_w(k); CHECK(cast.i, (int32_t)0x00000000);
+
+ i = v4f_set(1.f, 2.f, 3.f, 4.f);
+ j = v4f_set(-2.f, -4.f, 3.f, 6.f);
+ k = v4f_min(i, j);
+ CHECK(v4f_x(k), -2.f);
+ CHECK(v4f_y(k), -4.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 4.f);
+
+ k = v4f_max(i, j);
+ CHECK(v4f_x(k), 1.f);
+ CHECK(v4f_y(k), 2.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 6.f);
+
+ l = v4f_to_v4i(j);
+ CHECK(v4i_x(l), -2);
+ CHECK(v4i_y(l), -4);
+ CHECK(v4i_z(l), 3);
+ CHECK(v4i_w(l), 6);
+
+ k = v4i_to_v4f(l);
+ CHECK(v4f_x(k), -2.f);
+ CHECK(v4f_y(k), -4.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), 6.f);
+
+ k = v4f_xxxx(j);
+ CHECK(v4f_x(k), -2.f);
+ CHECK(v4f_y(k), -2.f);
+ CHECK(v4f_z(k), -2.f);
+ CHECK(v4f_w(k), -2.f);
+
+ k = v4f_yyxx(j);
+ CHECK(v4f_x(k), -4.f);
+ CHECK(v4f_y(k), -4.f);
+ CHECK(v4f_z(k), -2.f);
+ CHECK(v4f_w(k), -2.f);
+
+ k = v4f_wwxy(j);
+ CHECK(v4f_x(k), 6.f);
+ CHECK(v4f_y(k), 6.f);
+ CHECK(v4f_z(k), -2.f);
+ CHECK(v4f_w(k), -4.f);
+
+ k = v4f_zyzy(j);
+ CHECK(v4f_x(k), 3.f);
+ CHECK(v4f_y(k), -4.f);
+ CHECK(v4f_z(k), 3.f);
+ CHECK(v4f_w(k), -4.f);
+
+ k = v4f_wyyz(j);
+ CHECK(v4f_x(k), 6.f);
+ CHECK(v4f_y(k), -4.f);
+ CHECK(v4f_z(k), -4.f);
+ CHECK(v4f_w(k), 3.f);
+
+ i = v4f_xyz_to_rthetaphi(v4f_set(10.f, 5.f, 3.f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 11.575836f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.308643f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 0.463647f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(8.56f, 7.234f, 33.587f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 35.407498f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 0.322063f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 0.701638f, 1.e-5f), 1);
+
+ i = v4f_xyz_to_rthetaphi(v4f_set(0.f, 0.f, 0.f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 0.f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 0.f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 0.f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(4.53f, 0.f, 0.f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 4.53f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.570796f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 0.f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(0.f, 7.2f, 0.f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 7.2f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.570796f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 1.570796f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(4.53f, 7.2f, 0.f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 8.506521f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.570796f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 1.009206f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(0.f, 0.f, 3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 3.1f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 0.f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 0.f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(4.53f, 0.f, 3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 5.489162f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 0.970666f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 0.f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(0.f, 7.2f, 3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 7.839005f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.164229f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 1.570796f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(4.53f, 7.2f, 3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 9.053778f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.221327f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 1.009206f, 1.e-5f), 1);
+
+ i = v4f_xyz_to_rthetaphi(v4f_set(-4.53f, 7.2f, 3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 9.053778f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.221327f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 2.132386f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(-4.53f, -7.2f, 3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 9.053778f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.221327f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), -2.132386f, 1.e-5f) ||
+ eq_eps(v4f_z(i), 2*PI - 2.132386f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(4.53f, -7.2f, 3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 9.053778f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.221327f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), -1.009206f, 1.e-5f) ||
+ eq_eps(v4f_z(i), 2*PI - 1.009206f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(4.53f, 7.2f, -3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 9.053778f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.920264f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 1.009206f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(-4.53f, 7.2f, -3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 9.053778f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.920264f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), 2.132386f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(4.53f, -7.2f, -3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 9.053778f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.920264f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), -1.009206f, 1.e-5f) ||
+ eq_eps(v4f_z(i), 2*PI - 1.009206f, 1.e-5f), 1);
+ i = v4f_xyz_to_rthetaphi(v4f_set(-4.53f, -7.2f, -3.1f, 0.f));
+ CHECK(eq_eps(v4f_x(i), 9.053778f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_y(i), 1.920264f, 1.e-5f), 1);
+ CHECK(eq_eps(v4f_z(i), -2.132386f, 1.e-5f) ||
+ eq_eps(v4f_z(i), 2*PI - 2.132386f, 1.e-5f), 1);
+ return 0;
+}
+
diff --git a/src/test_v4i.c b/src/test_v4i.c
@@ -0,0 +1,155 @@
+/* Copyright (C) 2014 Vincent Forest (vaplv@free.fr)
+ *
+ * The RSIMD library is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * The RSIMD library 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License
+ * along with the RSIMD library. If not, see <http://www.gnu.org/licenses/>. */
+
+#include "rsimd.h"
+
+int
+main(int argc, char** argv)
+{
+ v4i_T i, j, k;
+ (void)argc, (void)argv;
+
+ i = v4i_set(1, 2, 3, 4);
+ CHECK(v4i_x(i), 1);
+ CHECK(v4i_y(i), 2);
+ CHECK(v4i_z(i), 3);
+ CHECK(v4i_w(i), 4);
+
+ i = v4i_set1(-1);
+ CHECK(v4i_x(i), -1);
+ CHECK(v4i_y(i), -1);
+ CHECK(v4i_z(i), -1);
+ CHECK(v4i_w(i), -1);
+
+ i = v4i_zero();
+ CHECK(v4i_x(i), 0);
+ CHECK(v4i_y(i), 0);
+ CHECK(v4i_z(i), 0);
+ CHECK(v4i_w(i), 0);
+
+ i = v4i_set(0x00010203, 0x04050607, 0x08090A0B, 0x0C0D0E0F);
+ j = v4i_set(0x01020401, 0x70605040, 0x0F1F2F3F, 0x00000000);
+ k = v4i_or(i, j);
+ CHECK(v4i_x(k), (int32_t)0x01030603);
+ CHECK(v4i_y(k), (int32_t)0x74655647);
+ CHECK(v4i_z(k), (int32_t)0x0F1F2F3F);
+ CHECK(v4i_w(k), (int32_t)0x0C0D0E0F);
+
+ k = v4i_and(i, j);
+ CHECK(v4i_x(k), (int32_t)0x00000001);
+ CHECK(v4i_y(k), (int32_t)0x00000000);
+ CHECK(v4i_z(k), (int32_t)0x08090A0B);
+ CHECK(v4i_w(k), (int32_t)0x00000000);
+
+ k = v4i_andnot(i, j);
+ CHECK(v4i_x(k), (int32_t)0x01020400);
+ CHECK(v4i_y(k), (int32_t)0x70605040);
+ CHECK(v4i_z(k), (int32_t)0x07162534);
+ CHECK(v4i_w(k), (int32_t)0x00000000);
+
+ k = v4i_xor(i, j);
+ CHECK(v4i_x(k), (int32_t)0x01030602);
+ CHECK(v4i_y(k), (int32_t)0x74655647);
+ CHECK(v4i_z(k), (int32_t)0x07162534);
+ CHECK(v4i_w(k), (int32_t)0x0C0D0E0F);
+
+ k = v4i_not(i);
+ CHECK(v4i_x(k), (int32_t)0xFFFEFDFC);
+ CHECK(v4i_y(k), (int32_t)0xFBFAF9F8);
+ CHECK(v4i_z(k), (int32_t)0xF7F6F5F4);
+ CHECK(v4i_w(k), (int32_t)0xF3F2F1F0);
+
+ i = v4i_set(1, 2, 3, 4);
+ j = v4i_set(-2, -4, 3, 6);
+ k = v4i_add(i, j);
+ CHECK(v4i_x(k), -1);
+ CHECK(v4i_y(k), -2);
+ CHECK(v4i_z(k), 6);
+ CHECK(v4i_w(k), 10);
+
+ k = v4i_sub(i, j);
+ CHECK(v4i_x(k), 3);
+ CHECK(v4i_y(k), 6);
+ CHECK(v4i_z(k), 0);
+ CHECK(v4i_w(k), -2);
+
+ k = v4i_eq(i, j);
+ CHECK(v4i_x(k), (int32_t)0x00000000);
+ CHECK(v4i_y(k), (int32_t)0x00000000);
+ CHECK(v4i_z(k), (int32_t)0xFFFFFFFF);
+ CHECK(v4i_w(k), (int32_t)0x00000000);
+
+ k = v4i_neq(i, j);
+ CHECK(v4i_x(k), (int32_t)0xFFFFFFFF);
+ CHECK(v4i_y(k), (int32_t)0xFFFFFFFF);
+ CHECK(v4i_z(k), (int32_t)0x00000000);
+ CHECK(v4i_w(k), (int32_t)0xFFFFFFFF);
+
+ k = v4i_gt(i, j);
+ CHECK(v4i_x(k), (int32_t)0xFFFFFFFF);
+ CHECK(v4i_y(k), (int32_t)0xFFFFFFFF);
+ CHECK(v4i_z(k), (int32_t)0x00000000);
+ CHECK(v4i_w(k), (int32_t)0x00000000);
+
+ k = v4i_lt(i, j);
+ CHECK(v4i_x(k), (int32_t)0x00000000);
+ CHECK(v4i_y(k), (int32_t)0x00000000);
+ CHECK(v4i_z(k), (int32_t)0x00000000);
+ CHECK(v4i_w(k), (int32_t)0xFFFFFFFF);
+
+ k = v4i_ge(i, j);
+ CHECK(v4i_x(k), (int32_t)0xFFFFFFFF);
+ CHECK(v4i_y(k), (int32_t)0xFFFFFFFF);
+ CHECK(v4i_z(k), (int32_t)0xFFFFFFFF);
+ CHECK(v4i_w(k), (int32_t)0x00000000);
+
+ k = v4i_le(i, j);
+ CHECK(v4i_x(k), (int32_t)0x00000000);
+ CHECK(v4i_y(k), (int32_t)0x00000000);
+ CHECK(v4i_z(k), (int32_t)0xFFFFFFFF);
+ CHECK(v4i_w(k), (int32_t)0xFFFFFFFF);
+
+ k = v4i_sel(i, j, v4i_set(~0, 0, ~0, 0));
+ CHECK(v4i_x(k), -2);
+ CHECK(v4i_y(k), 2);
+ CHECK(v4i_z(k), 3);
+ CHECK(v4i_w(k), 4);
+
+ k = v4i_xxxx(i);
+ CHECK(v4i_x(k), 1);
+ CHECK(v4i_y(k), 1);
+ CHECK(v4i_z(k), 1);
+ CHECK(v4i_w(k), 1);
+
+ k = v4i_wwxy(i);
+ CHECK(v4i_x(k), 4);
+ CHECK(v4i_y(k), 4);
+ CHECK(v4i_z(k), 1);
+ CHECK(v4i_w(k), 2);
+
+ k = v4i_xyxy(i);
+ CHECK(v4i_x(k), 1);
+ CHECK(v4i_y(k), 2);
+ CHECK(v4i_z(k), 1);
+ CHECK(v4i_w(k), 2);
+
+ k = v4i_wyyz(i);
+ CHECK(v4i_x(k), 4);
+ CHECK(v4i_y(k), 2);
+ CHECK(v4i_z(k), 2);
+ CHECK(v4i_w(k), 3);
+ return 0;
+}
+
