mesa/src/gallium
Roland Scheidegger 8aa168eb8f llvmpipe: use vector loads for (optimized) tri raster funcs
When we switched to 64bit rasterization, we could no longer use straight
aligned loads for loading the plane data. However, what the code actually
does for loading 3 planes, is 12 scalar loads + 9 unpacks, and then there's
another 8 unpacks for the transpose we need (!).

It would be possible to do the (scalar) loads of course already transposed
(at least saving the additional unpacks), however instead just use
(un)aligned vector loads, and recalculate the eo values, which is much less
instructions (note in case of the triangle_32_3_4 case, the eo values are
not even used, making the scalar loads + unpacks for them all the more
pointless).

This drops execution time of the triangle_32_3_4 function considerably,
albeit it doesn't really make a measurable difference (for small tris we're
essentially limited by vertex throughput in any case), for triangle_32_3_16
it's essentially noise (the loop is more costly than the initial code there).

(I'm thinking about just ditching storing the eo values in the plane data,
so could switch back to using aligned planes, however right now they are
still used in the other raster functions dealing with planes with scalar
code. Also not touching the ppc code, might not be that bad there in any
case.)

Reviewed-by: Brian Paul <brianp@vmware.com>
2016-02-02 05:58:19 +01:00
..
auxiliary mesa: fix typo in python scripts 2016-02-02 05:58:19 +01:00
docs tgsi: add MEMBAR opcode to handle memoryBarrier* GLSL intrinsics 2016-01-29 21:04:36 -05:00
drivers llvmpipe: use vector loads for (optimized) tri raster funcs 2016-02-02 05:58:19 +01:00
include st/mesa: add shader buffer barrier bit 2016-01-29 21:05:47 -05:00
state_trackers st/va: fix motion adaptive deinterlacing 2016-01-19 17:28:38 +01:00
targets virgl: also build vtest for Android 2016-02-02 09:58:51 +10:00
tests gallium/tests: fix build with clang compiler 2016-01-03 12:18:00 +01:00
tools gallium: add an index argument to create_query 2014-07-01 11:34:31 -04:00
winsys virgl: also build vtest for Android 2016-02-02 09:58:51 +10:00
Android.common.mk android: enable the radeonsi driver 2015-06-09 12:25:50 -07:00
Android.mk virgl: also build vtest for Android 2016-02-02 09:58:51 +10:00
Automake.inc gallium: keep the libdrm link alongside libkmsdri.la 2015-11-21 12:52:18 +00:00
Makefile.am automake: remove no longer needed HAVE_LOADER_GALLIUM conditional 2015-11-21 12:52:19 +00:00
README.portability gallium: replace INLINE with inline 2015-07-21 17:52:16 -04:00
SConscript pipe-loader: add preliminary scons support 2015-11-21 12:52:20 +00:00

	      CROSS-PLATFORM PORTABILITY GUIDELINES FOR GALLIUM3D 


= General Considerations =

The state tracker and winsys driver support a rather limited number of
platforms. However, the pipe drivers are meant to run in a wide number of
platforms. Hence the pipe drivers, the auxiliary modules, and all public
headers in general, should strictly follow these guidelines to ensure


= Compiler Support =

* Include the p_compiler.h.

* Cast explicitly when converting to integer types of smaller sizes.

* Cast explicitly when converting between float, double and integral types.

* Don't use named struct initializers.

* Don't use variable number of macro arguments. Use static inline functions
instead.

* Don't use C99 features.

= Standard Library =

* Avoid including standard library headers. Most standard library functions are
not available in Windows Kernel Mode. Use the appropriate p_*.h include.

== Memory Allocation ==

* Use MALLOC, CALLOC, FREE instead of the malloc, calloc, free functions.

* Use align_pointer() function defined in u_memory.h for aligning pointers
 in a portable way.

== Debugging ==

* Use the functions/macros in p_debug.h.

* Don't include assert.h, call abort, printf, etc.


= Code Style =

== Inherantice in C ==

The main thing we do is mimic inheritance by structure containment.

Here's a silly made-up example:

/* base class */
struct buffer
{
  int size;
  void (*validate)(struct buffer *buf);
};

/* sub-class of bufffer */
struct texture_buffer
{
  struct buffer base;  /* the base class, MUST COME FIRST! */
  int format;
  int width, height;
};


Then, we'll typically have cast-wrapper functions to convert base-class 
pointers to sub-class pointers where needed:

static inline struct vertex_buffer *vertex_buffer(struct buffer *buf)
{
  return (struct vertex_buffer *) buf;
}


To create/init a sub-classed object:

struct buffer *create_texture_buffer(int w, int h, int format)
{
  struct texture_buffer *t = malloc(sizeof(*t));
  t->format = format;
  t->width = w;
  t->height = h;
  t->base.size = w * h;
  t->base.validate = tex_validate;
  return &t->base;
}

Example sub-class method:

void tex_validate(struct buffer *buf)
{
  struct texture_buffer *tb = texture_buffer(buf);
  assert(tb->format);
  assert(tb->width);
  assert(tb->height);
}


Note that we typically do not use typedefs to make "class names"; we use
'struct whatever' everywhere.

Gallium's pipe_context and the subclassed psb_context, etc are prime examples 
of this.  There's also many examples in Mesa and the Mesa state tracker.