mirror of
https://gitlab.freedesktop.org/mesa/mesa.git
synced 2026-05-26 08:08:09 +02:00
It appears that storage for varyings in a wave has an upper
limit of wavesize * max_a831 where max_a831 is 64.
Exceeding the limit seam to force gpu to reduce primitives
processed per wave, at least calculations make sense with
such interpretation.
With blob SP_HS_UNKNOWN_A831 never exceeds 64 and setting
it to 65 in freedreno leads to a hang.
On A630 tests (patch_size=3 + gl_Position + array of vec4)
have shown such relation:
| Num of vec4 | A831 | PC_HS_INPUT_SIZE |
|-------------|------|------------------|
| 1 | 0x10 | 0xc |
| 2 | 0x14 | 0xf |
| 3 | 0x18 | 0x12 |
| 4 | 0x1c | 0x15 |
| 5 | 0x20 | 0x18 |
| 6 | 0x24 | 0x1b |
| 7 | 0x28 | 0x1e |
| 8 | 0x2c | 0x21 |
| 9 | 0x30 | 0x24 |
| 10 | 0x34 | 0x27 |
| 11 | 0x38 | 0x2a |
| 12 | 0x3c | 0x2d |
| 13 | 0x3f | 0x30 |
| 14 | 0x40 | 0x33 |
| 15 | 0x3d | 0x36 |
| 16 | 0x3d | 0x39 |
| 17 | 0x40 | 0x3c |
| 18 | 0x3f | 0x3f |
| 19 | 0x3e | 0x42 |
| 20 | 0x3d | 0x45 |
| 21 | 0x3f | 0x48 |
| 22 | 0x3d | 0x4b |
| 23 | 0x40 | 0x4e |
| 24 | 0x3d | 0x51 |
| 25 | 0x3f | 0x54 |
| 26 | 0x3c | 0x57 |
| 27 | 0x3e | 0x5a |
| 28 | 0x40 | 0x5d |
| 29 | 0x3c | 0x60 |
| 30 | 0x3e | 0x63 |
| 31 | 0x40 | 0x66 |
|-------------|------|------------------|
Brief tests with high patch sizes also confirm that formula
matches blob behaviour.
A831 is not a limit for storage available for one thread, so
naming it as SP_HS_WAVE_INPUT_SIZE would make more sense.
Fixes:
|
||
|---|---|---|
| .. | ||
| auxiliary | ||
| drivers | ||
| frontends | ||
| include | ||
| targets | ||
| tests | ||
| tools | ||
| winsys | ||
| Android.common.mk | ||
| Android.mk | ||
| meson.build | ||
| README.portability | ||
| SConscript | ||
CROSS-PLATFORM PORTABILITY GUIDELINES FOR GALLIUM3D
= General Considerations =
The frontend 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.