summaryrefslogtreecommitdiffstats
path: root/src/mesa/x86
Commit message (Collapse)AuthorAgeFilesLines
* re-enable ASSIGN_NORM_GROUP( 3dnow )Brian Paul2002-08-211-8/+4
|
* change GLvector3f to GLvector4f for normal transformationBrian Paul2002-08-081-3/+3
|
* change dest stride to 16 bytes instead of 12Brian Paul2002-08-081-35/+35
|
* changed normal stride from 12 to 16 bytes since normals are now GLfloat[4] ↵Brian Paul2002-08-071-7/+7
| | | | (for vertex program)
* applied Eric Anholt's patch for Athlon SSEBrian Paul2002-07-112-3/+28
|
* Implemented GL_EXT_multi_draw_arrays: glMultiDrawArraysEXT() and ↵Brian Paul2002-06-301-0/+12
| | | | glMultiDrawElementsEXT().
* Applied Matt Sealey's patch to remove/isolate all stdio.h function calls.Brian Paul2002-06-291-1/+2
| | | | Instead of mstdio.[ch], use imports.[ch] to isolate these functions.
* Fix NASM problems, remove static var in SSE detection code. (Josh Vanderhoof)Brian Paul2002-06-114-764/+769
|
* NASM fix for *_CONTENT() macros (Josh Vanderhoof)Brian Paul2002-06-061-1/+10
|
* use CONTENT() macro on line 205 (Josh Vanderhoof)Brian Paul2002-06-041-4/+4
|
* Added GL_NV_point_sprite functions: glPointParameteri[v]NV().Brian Paul2002-05-291-0/+12
| | | | Removed dead ARB_window_pos functions (we alias the MESA_window_pos funcs).
* updated vertex program dispatchBrian Paul2002-05-271-130/+130
|
* Re-scheduling of the instructions according to the MMX pairing rules. This ↵Jose Fonseca2002-04-191-42/+36
| | | | is dificult to quantify but the improvemnet reaches about of 0.7% in some cases in a Pentium III. In older Pentiums the improvements could be quite substancial due less capable integer pipelines.
* Added min and max blend functions.Jose Fonseca2002-04-192-10/+77
| | | | Slight optimization of _mesa_mmx_blend_add.
* MMX add blending function added.Jose Fonseca2002-04-192-2/+21
|
* MMX modulate belding function added.Jose Fonseca2002-04-193-47/+59
| | | | Factorization of more common MMX code.
* Definition of several utility macros for self-contained MMX operations such ↵Jose Fonseca2002-04-182-305/+339
| | | | | | | | | as scaling and lerping. Restructured the MMX blending function to use a template, being only necessary to specify the main loop, which is also used for making the runin and runout sections. Optimization of the MMX function after remembering that the multiplication was commutative (how can somebody forget this..) resulting in less register usage. Now there is no need for generate or read from memory any constant inside the loop. Assemblers other than the GNU assembler can choke on the output of the C preprocessor since it was necessary to add line separators ';' to the defined macros.
* Removed code that was proven to have faster alternatives to reduce ↵Jose Fonseca2002-04-181-69/+0
| | | | complexity and facilitate reusability.
* Remaining patch for the 255x255=255 identity correction beJose Fonseca2002-04-141-0/+12
| | | | made also in the runin and runout section of the code.
* Jose's latest patch (GMBT_GEOMETRIC_CORRECTION)Brian Paul2002-04-121-1/+17
|
* new MMX blend code (Jose Fonseca)Brian Paul2002-04-101-336/+378
|
* remove dead vertex assemblyKeith Whitwell2002-04-098-77/+8
|
* more blending updates from JoseBrian Paul2002-04-021-19/+22
|
* DJGPP updatesBrian Paul2002-04-022-3/+3
|
* updates from Jose FonsecaBrian Paul2002-04-021-25/+30
|
* syntax fixes for Solaris (David Dawes)Brian Paul2002-03-076-613/+726
|
* updated VERT_BIT_* definitionsBrian Paul2002-02-151-28/+28
|
* Clean-up/renaming of the per-vertex attribute bits, specifically, theBrian Paul2002-01-221-2/+2
| | | | | | VERT_BIT_* flags are new and used in many places (esp in T&L code). Updated some comments for doxygen. Various code clean-ups.
* fix bug 498555 - test for __GNUC__Brian Paul2002-01-041-2/+2
|
* Replace old matrix stacks with new code based on struct matrix_stack.Brian Paul2001-12-181-2/+2
| | | | | | Moved vertex program hash table into shared context state. Implemented reference counting for vertex programs. Replaced tnl "ProjectedClip" with "Ndc" (normalized device coordinates).
* updated vertex buffer identifiersBrian Paul2001-12-161-12/+13
|
* vertex program check-inBrian Paul2001-12-141-0/+384
|
* dispatch changes to minimize hassle with XFree86 libGLBrian Paul2001-12-041-296/+290
|
* 3dnow normalize_normals broken, disableKeith Whitwell2001-11-191-2/+4
|
* added test implementation of GL_ARB_window_posBrian Paul2001-11-181-0/+96
|
* API dispath updatesBrian Paul2001-11-181-331/+347
|
* applied Andrew Lewycky's patchesBrian Paul2001-10-223-179/+104
|
* added new entrypoints for 1.3Brian Paul2001-10-171-0/+278
|
* Remove _BaseAlpha, fix reflect lighting bug.Keith Whitwell2001-07-281-2/+1
|
* test for X86_FXSR_MAGIC to be sure we have the _fpstate.magic field, needed ↵Brian Paul2001-06-061-5/+5
| | | | for SSE signal handler
* replaced #ifdef 0 with #if 0Brian Paul2001-05-311-2/+2
|
* Initial commit of cliptest work. More to come shortly.Gareth Hughes2001-05-213-36/+29
| | | | | | | | - Add debug, benchmark code. - Change linux/x86 FAST_MATH code to GCC/x86, and clear FP exceptions before exiting the fast math block. - Remove divide-by-zero test in x86 cliptest, and set clipped vertices to [0,0,0,1] instead of leaving them uninitialized.
* Fix long-standing FP exception bug in _mesa_x86_cliptest_points4().Gareth Hughes2001-05-132-5/+17
|
* Remove all traces of CULL_MASK_ACTIVE.Gareth Hughes2001-03-306-218/+135
|
* Consolidation of asm code in 3.5Gareth Hughes2001-03-2920-139/+6916
|
* Make generation of matypes.h more transparent.Gareth Hughes2001-03-291-2/+1
|
* New type system for assembly code. Asm files should now includeGareth Hughes2001-03-2815-178/+465
| | | | | matypes.h, which includes assyntax.h and is generated from the core Mesa header files.
* Undo -D_POSIX_SOURCE change, fix the way the katmai support test isGareth Hughes2001-03-121-2/+2
| | | | done.
* replaced gl_test_os_katmai*() with _mesa_test_os_katmai*()Brian Paul2001-03-051-5/+5
|
* more clean-upsBrian Paul2001-03-037-43/+39
|
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-26 08:47:50 +0000