| Age | Commit message (Collapse) | Author |
|---|
|
- emit prediction
- fixes to emit_sizes for data
- clean up of excesive use of radeonEnsureCmdBufferSpace
Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
|
|
|
|
This merges lots of the hw state atom emission and firevertices code.
it also removes a lot of the extra radeon crap from r300
and merge scissor
|
|
This fixes a whole bunch of regressions in piglit
|
|
This should be working gears on radeon state
|
|
|
|
Not tested but ripped out lots of stuff unneeded anymore time to test later
|
|
this gets back a lot of the lots speed in gears on r500 at least
I also fixed the legacy bufmgr to deal when the dma space fills up
|
|
|
|
|
|
Cherry-picked from gallium-0.1
Conflicts:
src/glu/sgi/libnurbs/interface/bezierEval.h
src/glu/sgi/libnurbs/interface/bezierPatch.h
src/glu/sgi/libnurbs/interface/bezierPatchMesh.h
src/glu/sgi/libnurbs/internals/dataTransform.h
src/glu/sgi/libnurbs/internals/displaymode.h
src/glu/sgi/libnurbs/internals/sorter.h
src/glu/sgi/libnurbs/nurbtess/definitions.h
src/glu/sgi/libnurbs/nurbtess/directedLine.h
src/glu/sgi/libnurbs/nurbtess/gridWrap.h
src/glu/sgi/libnurbs/nurbtess/monoChain.h
src/glu/sgi/libnurbs/nurbtess/monoPolyPart.h
src/glu/sgi/libnurbs/nurbtess/monoTriangulation.h
src/glu/sgi/libnurbs/nurbtess/partitionX.h
src/glu/sgi/libnurbs/nurbtess/partitionY.h
src/glu/sgi/libnurbs/nurbtess/polyDBG.h
src/glu/sgi/libnurbs/nurbtess/polyUtil.h
src/glu/sgi/libnurbs/nurbtess/primitiveStream.h
src/glu/sgi/libnurbs/nurbtess/quicksort.h
src/glu/sgi/libnurbs/nurbtess/rectBlock.h
src/glu/sgi/libnurbs/nurbtess/sampleComp.h
src/glu/sgi/libnurbs/nurbtess/sampleCompBot.h
src/glu/sgi/libnurbs/nurbtess/sampleCompRight.h
src/glu/sgi/libnurbs/nurbtess/sampleCompTop.h
src/glu/sgi/libnurbs/nurbtess/sampleMonoPoly.h
src/glu/sgi/libnurbs/nurbtess/sampledLine.h
src/glu/sgi/libnurbs/nurbtess/searchTree.h
src/glu/sgi/libnurbs/nurbtess/zlassert.h
src/glu/sgi/libutil/error.c
src/glu/sgi/libutil/glue.c
src/glu/sgi/libutil/gluint.h
src/glu/sgi/libutil/project.c
src/glu/sgi/libutil/registry.c
src/glx/x11/glxclient.h
src/glx/x11/glxext.c
src/mesa/drivers/dri/ffb/ffb_dd.h
src/mesa/drivers/dri/ffb/ffb_points.h
src/mesa/drivers/dri/gamma/gamma_context.h
src/mesa/drivers/dri/gamma/gamma_macros.h
src/mesa/drivers/dri/i810/i810context.h
src/mesa/drivers/dri/r128/r128_dd.h
src/mesa/drivers/dri/tdfx/tdfx_dd.h
|
|
Makefile.template
|
|
|
|
* Fix crash at context creation in most drivers supporting vblank.
* Don't pass vblank sequence or flags to functions that get passed the drawable
private already.
* Attempt to initialize vblank related drawable private fields just once
per drawable. May need more work in some drivers.
|
|
request at least drmMinor 6 anyway.
|
|
|
|
radeon/r200AllocDmaRegionVerts function. No longer compile the radeon_compat stuff which was for drm 1.1 compatibility presumably but unused since about forever into the driver.
|
|
|
|
state in a ready-to-emit cmdbuf, which avoids the issue Nicolai Haehnle reported
where the check() could return differently during backup-and-emit than it should
have if it were called at the right time. Move the lit emission before most of
the TCL state emission on r200, which fixes neverball issues.
Tested with: r100/r200 with neverball, tuxracer, chromium, quake3, ipers
|
|
a new cmdbuf, to ensure that state wasn't lost across UNLOCK/LOCK pairs (in the
case of context switching). This was rather inefficient. Instead, after
flushing a cmdbuf, mark the state as needing to be saved on unlock. Then, at
the beginning of flushing a cmdbuf, if we actually have lost the context, go
back and emit a new cmdbuf with the full set of state, before continuing with
the cmdbuf flush. Provides a 10-15% improvement in ipers performance in my
tests, along with other apps.
Tested with: ipers, glxgears, quake3
|
|
errors on r100 and rendering errors and hangs on r200 (same for R100 without
OLD_PACKETS).
If a command buffer filled after some state (EmitState or a VBPNTR write) was
emitted, the lock was grabbed, the buffer flushed, a new buffer prepared, and
the lock dropped. Another client could come in, set its own state as part of
rendering, and when the first client flushed the rendering commands depending
on the previous state, it got the 2nd client's state. This is fixed by checking
for enough space before beginning a set of state emits and rendering, and
flushing the buffer first if so. This guarantees that the buffer won't wrap.
Also, move the "lost_context = 1" from the end of cmdbuf flushing to
UNLOCK_HARDWARE for clarity (at a minimum) that any time the lock is dropped,
state may get overwritten. We don't have enough information at the point of the
LOCK_HARDWARE to reset our state to the last UNLOCK_HARDWARE point in the case
that we did lose our context, but saving the information to rebuild that state
may be a useful optimization (ipers data suggests up to 5%).
|
|
|
