| Age | Commit message (Collapse) | Author |
|---|
|
This is a set of changes that optimizes the memory use of fragment
operation programs (by using and transmitting only as much memory as is
needed for the fragment ops programs, instead of maximal sizes), as well
as eliminate the dependency on hard-coded maximal program sizes. State
that is not dependent on fragment facing (i.e. that isn't using
two-sided stenciling) will only save and transmit a single
fragment operation program, instead of two identical programs.
- Added the ability to emit a LNOP (No Operation (Load)) instruction.
This is used to pad the generated fragment operations programs to
a multiple of 8 bytes, which is necessary for proper operation of
the dual instruction pipeline, and also required for proper SPU-side
decoding.
- Added the ability to allocate and manage a variant-length
struct cell_command_fragment_ops. This structure now puts the
generated function field at the end, where it can be as large
as necessary.
- On the PPU side, we now combine the generated front-facing and
back-facing code into a single variant-length buffer (and only use one
if the two sets of code are identical) for transmission to the SPU.
- On the SPU side, we pull the correct sizes out of the buffer,
allocate a new code buffer if the one we have isn't large enough,
and save the code to that buffer. The buffer is deallocated when
the SPU exits.
- Commented out the emit_fetch() static function, which was not being used.
|
|
With these changes, the tests/stencil_twoside test now works.
- Eliminate blending from the stencil_twoside test, as it produces an
unneeded dependency on having blending working
- The spe_splat() function will now work if the register being splatted
and the destination register are the same
- Separate fragment code generated for front-facing and back-facing
fragments. Often these are the same; if two-sided stenciling is on,
they can be different. This is easier and faster than generating
code that does both tests and merges the results.
- Fixed a cut/paste bug where if the back Z-pass stencil operation
were different from all the other operations, the back Z-fail
results were incorrect.
|
|
Two definitive bugs in stenciling were fixed.
The first, reversed registers in the generated Select Bytes (selb)
instruction, caused the stenciling INCR and DECR operations to
fail dramatically, putting new values in where old values were
supposed to be and vice versa.
The second caused stencil tiles to not be read and written from
main memory by the SPUs. A per-spu flag, spu.read_depth, was used
to indicate whether the SPU should be reading depth tiles, and was set
only when depth was enabled. A second flag, spu.read_stencil, was
set when stenciling was enabled, but never referenced.
As stenciling and depth are in the same tiles on the Cell, and there
is no corresponding TAG_WRITE_TILE_STENCIL to complement
TAG_WRITE_TILE_COLOR and TAG_WRITE_TILE_Z, I fixed this by
eliminating the unused "spu.read_stencil", renaming "spu.read_depth"
to "spu.read_depth_stencil", and setting it if either stenciling or
depth is enabled.
I also added an optimization to the fragment ops generation code,
that avoids calculating stencil values and/or stencil writemask
when the stencil operations are all KEEP.
|
|
If we delete a texture, we need to keep the underlying tiled data buffer
around until any rendering that references it has completed.
Keep a list of buffers referenced by a rendering batch. Unref/free them when
the associated batch's fence is executed/signalled.
|
|
|
|
Distinguish among texture targets in codegen.
progs/demos/cubemap.c runs correctly now too.
|
|
|
|
|
|
|
|
|
|
|
|
Though, progs/demos/cubemap.c doesn't quite work right...
|
|
glDrawPixels works now.
|
|
|
|
Though, only GL_MIPMAP_NEAREST / GL_LINEAR works right now.
|
|
|
|
|
|
|
|
|
|
|
|
This set of code changes are for stencil code generation
support. Both one-sided and two-sided stenciling are supported.
In addition to the raw code generation changes, these changes had
to be made elsewhere in the system:
- Added new "register set" feature to the SPE assembly generation.
A "register set" is a way to allocate multiple registers and free
them all at the same time, delegating register allocation management
to the spe_function unit. It's quite useful in complex register
allocation schemes (like stenciling).
- Added and improved SPE macro calculations.
These are operations between registers and unsigned integer
immediates. In many cases, the calculation can be performed
with a single instruction; the macros will generate the
single instruction if possible, or generate a register load
and register-to-register operation if not. These macro
functions are: spe_load_uint() (which has new ways to
load a value in a single instruction), spe_and_uint(),
spe_xor_uint(), spe_compare_equal_uint(), and spe_compare_greater_uint().
- Added facing to fragment generation. While rendering, the rasterizer
needs to be able to determine front- and back-facing fragments, in order
to correctly apply two-sided stencil. That requires these changes:
- Added front_winding field to the cell_command_render block, so that
the state tracker could communicate to the rasterizer what it
considered to be the front-facing direction.
- Added fragment facing as an input to the fragment function.
- Calculated facing is passed during emit_quad().
|
|
|
|
32-byte boundary
To make sure even/odd instructions hit the right pipes.
|
|
TGSI shaders are translated into SPE instructions which are then sent to
the SPEs for execution. Only a few opcodes work, no swizzling yet, no
support for constants/immediates, etc.
|
|
|
|
|
|
Do code generation for alpha test, z test, stencil, blend, colormask
and framebuffer/tile read/write as a single code block.
Ian's previous blend/z/stencil test code is still there but mostly disabled
and will be removed soon.
|
|
|
|
|
|
Precompute tiles_per_row. Use ushort multiplies in a few places. New comments.
|
|
|
|
|
|
|
|
|
|
This also implements code-gen for the float-to-packed color
conversion. It's currently hardcoded for A8R8G8B8, but that can
easily be fixed as soon as other color depths are supported by the
Cell driver.
|
|
Previously the constant color blend factor was compiled into the
generated code. This meant that the code had to be regenerated each
time the constant color was changed. This doesn't fit with the model
used in Gallium.
As-is, the code could be better. The constant color is loaded for
every quad processed, even if it is not used. Also, if a lot of (1-x)
blend factors are used, 1.0 will be loaded and reloaded into registers
many times.
|
|
So far this is only tested when GL_BLEND is disabled.
|
|
Alpha test is currently broken because all per-fragment testing occurs
before alpha is calculated.
Stencil test is currently broken because the Z-clear code asserts if
there is a stencil buffer.
|
|
|
|
|
|
Update the Makefiles and includes for the new paths.
Note that there hasn't been no separation of the Makefiles yet, and make is
jumping all over the place. That will be taken care shortly. But for now, make
should work. It was tested with linux and linux-dri. Linux-cell and linux-llvm
might require some minor tweaks.
|
|
This is in a separate commit to ensure renames are properly preserved.
|
