Kenneth Graunke [Sat, 30 Mar 2013 07:15:54 +0000 (00:15 -0700)]
i965: Implement 16-wide math on G45 and Ironlake.
[chrisf:]
Improves performance in CS:S video stress test by about 2%.
No piglit regressions on Ironlake.
Reviewed-by: Chris Forbes <chrisf@ijw.co.nz>
Matt Turner [Wed, 22 May 2013 21:57:04 +0000 (14:57 -0700)]
glsl: Disallow return with a void argument from void functions.
NOTE: This is a candidate for the stable branches.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Matt Turner [Wed, 22 May 2013 19:14:32 +0000 (12:14 -0700)]
glsl: Allow implicit conversion of return values.
Required by ARB_shading_language_420pack.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Matt Turner [Wed, 22 May 2013 17:56:25 +0000 (10:56 -0700)]
glsl: Add gl_{Max,Min}ProgramTexelOffset built-in constants.
Required by ARB_shading_language_420pack. Note that the 420pack spec
incorrectly specifies their values as (Min, Max) = (-7, 8) when they
should be (-8, 7) as listed in the GLSL 4.30 and ESSL 3.0 specs.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Matt Turner [Mon, 20 May 2013 18:01:37 +0000 (11:01 -0700)]
glsl: Allow swizzles on scalars.
Required by ARB_shading_language_420pack.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Matt Turner [Mon, 20 May 2013 16:18:01 +0000 (09:18 -0700)]
glsl: Allow .length() method on vectors and matrices.
Required by ARB_shading_language_420pack.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Todd Previte [Mon, 20 May 2013 15:41:18 +0000 (08:41 -0700)]
mesa: Add infrastructure for ARB_shading_language_420pack.
v2 [mattst88]
- Split infrastructure into separate patch.
- Add preprocessor #define.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chia-I Wu [Fri, 14 Jun 2013 16:56:17 +0000 (00:56 +0800)]
ilo: fix for half-float vertex arrays
Commit
6fe0453c339b6e894e0ee8d2200e7638a43ed21e broke half-float vertex
arrays. This reverts a part of that commit, and explains why.
Chia-I Wu [Fri, 14 Jun 2013 07:35:36 +0000 (15:35 +0800)]
ilo: add some assertions to help debugging
Assert that we do not support user vertex/index/constant buffers. Issue a
warning when a sampler view is created for a resource without
PIPE_BIND_SAMPLER_VIEW.
Chia-I Wu [Fri, 14 Jun 2013 07:26:07 +0000 (15:26 +0800)]
ilo: silence a compiler warning
The path should never be hit.
Vinson Lee [Fri, 7 Jun 2013 06:07:30 +0000 (23:07 -0700)]
glsl: Fix null check in read_dereference.
Fixes "Logically dead code" defect reported by Coverity.
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Reviewed-by: Brian Paul <brianp@vmware.com>
Chia-I Wu [Thu, 13 Jun 2013 05:18:15 +0000 (13:18 +0800)]
st/mesa: fix temp texture bindings in st_CopyPixels()
The temporary texture should have either PIPE_BIND_RENDER_TARGET or
PIPE_BIND_DEPTH_STENCIL set in addition to PIPE_BIND_SAMPLER_VIEW.
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Zack Rusin [Tue, 11 Jun 2013 03:36:59 +0000 (23:36 -0400)]
gallium/draw: add limits to the clip and cull distances
There are strict limits on those registers. Define the maximums
and use them instead of magic numbers. Also allows us to add
some extra sanity checks.
Suggested by Brian.
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Zack Rusin [Tue, 11 Jun 2013 02:59:33 +0000 (22:59 -0400)]
draw: cleanup the distance culling code a bit
We don't need the clamped variable, because we can just
return early. We should also do the regular culling after
the distance culling passes.
All spotted by Brian.
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Chia-I Wu [Thu, 13 Jun 2013 10:22:40 +0000 (18:22 +0800)]
ilo: mapping a resource may make some states dirty
When a resource is busy and is mapped with
PIPE_TRANSFER_DISCARD_WHOLE_RESOURCE, the underlying bo is replaced. We need
to mark states affected by the resource dirty.
With this change, we no longer have to emit vertex buffers and index buffer
unconditionally.
Chia-I Wu [Thu, 13 Jun 2013 09:48:00 +0000 (17:48 +0800)]
ilo: bump up PIPE_CAP_GLSL_FEATURE_LEVEL to 140
With UBO and TBO support, we are supposedly good to claim GLSL 1.40.
Chia-I Wu [Thu, 13 Jun 2013 09:46:58 +0000 (17:46 +0800)]
ilo: initialize dirty flags in ilo_init_states()
Now that we have a function to initialize states, initialize dirty flags there
too.
Chia-I Wu [Thu, 13 Jun 2013 02:10:17 +0000 (10:10 +0800)]
ilo: re-emit states that involve resources
Even with hardware contexts, since we do not pin resources, we have to re-emit
the states so that the resources are referenced (by cp->bo) and their offsets
are updated in case they are moved. This also allows us to elimiate cp flush
in is_bo_busy().
Chia-I Wu [Thu, 13 Jun 2013 04:57:07 +0000 (12:57 +0800)]
ilo: fix for util_blitter_clear() changes
It has been broken since
17350ea979b883662573dac136cd9efb49938210.
Manfred Ernst [Thu, 13 Jun 2013 03:03:02 +0000 (20:03 -0700)]
mesa: Fix bug in unclamped float to ubyte conversion.
Problem: The IEEE float optimized version of UNCLAMPED_FLOAT_TO_UBYTE
in macros.h computed incorrect results for inputs in the range
0x3f7f0000 (=0.
99609375) to 0x3f7f7f80 (=0.
99803924560546875)
inclusive. 0x3f7f7f80 is the IEEE float value that results in 254.5
when multiplied by 255. With rounding mode "round to closest even
integer", this is the largest float in the range 0.0-1.0 that is
converted to 254 by the generic implementation of
UNCLAMPED_FLOAT_TO_UBYTE. The IEEE float optimized version
incorrectly defined the cut-off for mapping to 255 as 0x3f7f0000
(=255.0/256.0). The same bug was present in the function
float_to_ubyte in u_math.h.
Fix: The proposed fix replaces the incorrect cut-off value by
0x3f800000, which is the IEEE float representation of 1.0f. 0x3f7f7f81
(or any value in between) would also work, but 1.0f is probably
cleaner.
The patch does not regress piglit on llvmpipe and on i965 on sandy
bridge.
Tested-by Stéphane Marchesin <marcheu@chromium.org>
Reviewed-by Stéphane Marchesin <marcheu@chromium.org>
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Sat, 1 Jun 2013 01:19:21 +0000 (03:19 +0200)]
st/dri: if flushing a drawable, don't set reason=SWAPBUFFERS
0 means SWAPBUFFERS.
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Sat, 1 Jun 2013 01:18:04 +0000 (03:18 +0200)]
st/dri: resolve the back buffer only in SwapBuffers
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Fri, 31 May 2013 20:48:48 +0000 (22:48 +0200)]
st/dri: manually swap MSAA front and back buffers in SwapBuffers
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Fri, 31 May 2013 19:52:01 +0000 (21:52 +0200)]
st/dri: always copy new DRI front and back buffers to corresponding MSAA buffers
This commit fixes these piglit tests with an MSAA visual forced on:
- read-front
- glx-copy-sub-buffer
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Fri, 31 May 2013 19:43:50 +0000 (21:43 +0200)]
st/dri: refactor dri_msaa_resolve
The generic blit will be used by the following commit.
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Sat, 1 Jun 2013 00:04:56 +0000 (02:04 +0200)]
st/dri: reuse depth-stencil and MSAA resources after DRI2 invalidate event
Page flipping generates an invalidate event every frame, causing reallocations
of all private resources (MSAA and depth-stencil).
Reusing the resources may improve performance (especially under memory
pressure).
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Wed, 29 May 2013 21:08:11 +0000 (23:08 +0200)]
st/dri: fix MSAA resolving of buffers with height > width
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Fri, 31 May 2013 18:26:39 +0000 (20:26 +0200)]
st/mesa: make generic CopyPixels path work with MSAA visuals
We have to use pipe->blit, not resource_copy_region, so that the read buffer
is resolved if it's multisampled. I also removed the CPU-based copying,
which just did format conversion (obsoleted by the blit).
Also, the layer/slice/face of the read buffer is taken into account (this was
ignored).
Last but not least, the format choosing is improved to take float and integer
read buffers into account.
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Fri, 31 May 2013 13:13:46 +0000 (15:13 +0200)]
st/mesa: don't use blit_copy_pixels if an occlusion query is active
CopyPixels, just as DrawPixels, should count the samples that passed
depth test.
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Thu, 30 May 2013 19:34:06 +0000 (21:34 +0200)]
st/mesa: rework blit_copy_pixels to use pipe->blit
There were 2 issues with it:
- resource_copy_region doesn't allow different sample counts of both src
and dst, which can occur if we blit between a window and a FBO, and
the window has an MSAA colorbuffer and the FBO doesn't.
(this was the main motivation for using pipe->blit)
- blitting from or to a non-zero layer/slice/face was broken, because
rtt_face and rtt_slice were ignored.
blit_copy_pixels is now used even if the formats and orientation of
framebuffers don't match.
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Wed, 29 May 2013 18:12:27 +0000 (20:12 +0200)]
r600g: upsample and downsample MSAA resources for transfers
We did downsample (=resolve) MSAA resources to make ReadPixels work with MSAA
GLX visuals, which was enough for read-only color-only transfers.
This commit makes write color transfers and depth-stencil transfers work
in a similar manner. It does downsampling in transfer_map and upsampling
in transfer_unmap.
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Wed, 29 May 2013 17:26:56 +0000 (19:26 +0200)]
gallium/u_format: add a new helper for initializing pipe_blit_info::mask
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Wed, 29 May 2013 13:51:20 +0000 (15:51 +0200)]
gallium/u_blitter: make clearing independent of the colorbuffer format
There isn't any difference between 32_FLOAT and 32_*INT in vertex fetching.
Both of them don't do any format conversion.
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Wed, 29 May 2013 13:35:38 +0000 (15:35 +0200)]
gallium/u_blitter: make clearing independent of the number of bound colorbuffers
We can use the fragment shader TGSI property WRITES_ALL_CBUFS.
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Wed, 29 May 2013 12:11:58 +0000 (14:11 +0200)]
gallium/util: make WRITES_ALL_CBUFS optional in the passthrough fragment shader
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Wed, 29 May 2013 15:32:44 +0000 (17:32 +0200)]
mesa: fix OES_EGL_image_external being partially allowed in the core profile
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Ian Romanick [Mon, 10 Jun 2013 17:39:28 +0000 (10:39 -0700)]
glsl: Generate smaller values for uniform locations
Previously we would generate uniform locations as (slot << 16) +
array_index. We do this to handle applications that assume the location
of a[2] will be +1 from the location of a[1]. This resulted in every
uniform location being at least 0x10000. The OpenGL 4.3 spec was
amended to require this behavior, but previous versions did not require
locations of array (or structure) members be sequential.
We've now encountered two applications that assume uniform values will
be "small." As far as we can tell, these applications store the GLint
returned by glGetUniformLocation in a int16_t or possibly an int8_t.
THIS BEHAVIOR IS NOT GUARANTEED OR IMPLIED BY ANY VERSION OF OpenGL.
Other implementations happen to have both these behaviors (sequential
array elements and small values) since OpenGL 2.0, so let's just match
their behavior.
Fixes "3D Bowling" on Android.
NOTE: This is a candidate for stable release branches.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-and-tested-by: Chad Versace <chad.versace@linux.intel.com>
Ian Romanick [Mon, 10 Jun 2013 17:35:05 +0000 (10:35 -0700)]
glsl: Add gl_shader_program::UniformLocationBaseScale
This is used by _mesa_uniform_merge_location_offset and
_mesa_uniform_split_location_offset to determine how the base and offset
are packed. Previously, this value was hard coded as (1U<<16) in those
functions via the shift and mask contained therein. The value is still
(1U<<16), but it can be changed in the future.
The next patch dynamically generates this value.
NOTE: This is a candidate for stable release branches.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-and-tested-by: Chad Versace <chad.versace@linux.intel.com>
Ian Romanick [Mon, 10 Jun 2013 17:33:59 +0000 (10:33 -0700)]
glsl: Add a gl_shader_program parameter to _mesa_uniform_{merge,split}_location_offset
This will be used in the next commit.
NOTE: This is a candidate for stable release branches.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-and-tested-by: Chad Versace <chad.versace@linux.intel.com>
Roland Scheidegger [Wed, 12 Jun 2013 22:40:34 +0000 (00:40 +0200)]
util: new util_fill_box helper
Use new util_fill_box helper for util_clear_render_target.
(Also fix off-by-one map error.)
v2: handle non-zero z correctly in new helper
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Roland Scheidegger [Wed, 12 Jun 2013 22:40:24 +0000 (00:40 +0200)]
gallivm: (trivial) remove duplicated code block (including comment)
Paul Berry [Tue, 21 May 2013 18:58:38 +0000 (11:58 -0700)]
i965/gen7: Enable support for fast color clears.
This patch adds code to place mcs_state into INTEL_MCS_STATE_RESOLVED
for miptrees that are capable of supporting fast color clears. This
will have no effect on buffers that don't undergo a fast color clear;
however, for buffers that do undergo a fast color clear, an MCS
miptree will be allocated (at the time of the first fast clear), and
will be used thereafter.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Tue, 21 May 2013 21:21:44 +0000 (14:21 -0700)]
i965/gen7+: Disable fast color clears on shared regions.
In certain circumstances the memory region underlying a miptree is
shared with other miptrees, or with other code outside Mesa's control.
This happens, for instance, when an extension like GL_OES_EGL_image or
GLX_EXT_texture_from_pixmap extension is used to associate a miptree
with an image existing outside of Mesa.
When this happens, we need to disable fast color clears on the miptree
in question, since there's no good synchronization mechanism to ensure
that deferred clear writes get performed by the time the buffer is
examined from the other miptree, or from outside of Mesa.
Fortunately, this should not be a performance hit for most
applications, since most applications that use these extensions use
them for importing textures into Mesa, rather than for exporting
rendered images out of Mesa. So most of the time the miptrees
involved will never experience a clear.
v2: Rework based on the fact that we have decided not to use an
accessor function to protect access to the region.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Tue, 7 May 2013 21:55:42 +0000 (14:55 -0700)]
i965/gen7+: Resolve color buffers when necessary.
Resolve color buffers that have been fast-color cleared:
1. before texturing from the buffer (brw_predraw_resolve_buffers())
2. before using the buffer as the source in a blorp blit
(brw_blorp_blit_miptrees())
3. before mapping the buffer's miptree (intel_miptree_map_raw(),
intel_texsubimage_tiled_memcpy())
4. before accessing the buffer using the hardware blitter
(intel_miptree_blit(), do_blit_bitmap())
v2: Rework based on the fact that we have decided not to use an
accessor function to protect access to the region.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Tue, 7 May 2013 22:38:45 +0000 (15:38 -0700)]
i965/gen7+: Ensure that front/back buffers are fast-clear resolved.
We already had code in intel_downsample_for_dri2_flush() for
downsampling front and back buffers when multisampling was in use.
This patch extends that function to perform fast color clear resolves
when necessary.
To account for the additional functionality, the function is renamed
to simply intel_resolve_for_dri2_flush().
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Mon, 6 May 2013 17:37:04 +0000 (10:37 -0700)]
i965/blorp: Write blorp code to do render target resolves.
This patch implements the "render target resolve" blorp operation.
This will be needed when a buffer that has experienced a fast color
clear is later used for a purpose other than as a render target
(texturing, glReadPixels, or swapped to the screen). It resolves any
remaining deferred clear operation that was not taken care of during
normal rendering.
Fortunately not much work is necessary; all we need to do is scale
down the size of the rectangle primitive being emitted, run the
fragment shader with the "Render Target Resolve Enable" bit set, and
ensure that the fragment shader writes to the render target using the
"replicated color" message. We already have a fragment shader that
does that (the shader that we use for fast color clears), so for
simplicity we re-use it.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Mon, 6 May 2013 16:38:42 +0000 (09:38 -0700)]
i965/blorp: Expand clear class hierarchy to prepare for RT resolves.
The fragment shaders that to do color clears will be re-used to
perform so-called "render target resolves" (the resolves associated
with fast color clears). To prepare for that, this patch expands the
class hierarchy for blorp params by adding
brw_blorp_const_color_params (which will be used for all blorp
operations where the fragment shader outputs a constant color).
Some other data structures and functions were also renamed to use
"const_color" nomenclature where appropriate.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Wed, 1 May 2013 15:04:12 +0000 (08:04 -0700)]
i965/gen7+: Implement fast color clear operation in BLORP.
Since we defer allocation of the MCS miptree until the time of the
fast clear operation, this patch also implements creation of the MCS
miptree.
In addition, this patch adds the field
intel_mipmap_tree::fast_clear_color_value, which holds the most recent
fast color clear value, if any. We use it to set the SURFACE_STATE's
clear color for render targets.
v2: Flag BRW_NEW_SURFACES when allocating the MCS miptree. Generate a
perf_debug message if clearing to a color that isn't compatible with
fast color clear. Fix "control reaches end of non-void function"
build warning.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Wed, 1 May 2013 01:51:51 +0000 (18:51 -0700)]
i965/gen7+: Create helper functions for single-sample MCS buffers.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Wed, 1 May 2013 14:16:52 +0000 (07:16 -0700)]
i965/gen7+: Set up MCS in SURFACE_STATE whenever MCS is present.
On Gen7+, MCS buffers are used both for compressed multisampled color
buffers and for "fast clear" of single-sampled color buffers.
Previous to this patch series, we didn't support fast clear, so we
only used MCS with multisampled bolor buffers.
As a first step to implementing fast clears, this patch modifies the
code that sets up SURFACE_STATE so that it configures the MCS buffer
whenever it is present, regardless of whether we are multisampling or
not.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Tue, 7 May 2013 21:04:29 +0000 (14:04 -0700)]
i965/gen7+: Create an enum for keeping track of fast color clear state.
This patch includes code to update the fast color clear state
appropriately when rendering occurs. The state will also need to be
updated when a fast clear or a resolve operation is performed; those
state updates will be added when the fast clear and resolve operations
are added.
v2: Create a new function, intel_miptree_used_for_rendering() to
handle updating the fast color clear state when rendering occurs.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Mon, 20 May 2013 20:29:39 +0000 (13:29 -0700)]
intel: Conditionally compile mcs-related code for i965 only.
This patch ifdefs out intel_mipmap_tree::mcs_mt when building the i915
(pre-Gen4) driver (MCS buffers aren't supported until Gen7, so there
is no need for this field in the i915 driver). This should make it a
bit easier to implement fast color clears without undue risk to i915.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Tue, 28 May 2013 20:29:53 +0000 (13:29 -0700)]
intel: Keep region name in intel_miptree_create_for_dri2_buffer().
When processing a buffer received from the X server,
intel_process_dri2_buffer() examines intel_region::name to determine
whether it's received a brand new buffer, or the same buffer it
received from the X server the last time it made a request.
However, this didn't work properly, because in the call to
intel_miptree_create_for_dri2_buffer(), we create a fresh intel_region
object to represent the buffer, and this was causing us to forget the
buffer's previous name.
This patch fixes things by copying over the region name when creating
the fresh intel_region object.
At the moment, this is just a minor performance optimization.
However, when fast color clears are added, it will be necessary to
ensure that the fast color clear state for a buffer doesn't get
discarded the next time we receive that buffer from the X server.
Reviewed-by: Eric Anholt <eric@anholt.net>
Chia-I Wu [Wed, 12 Jun 2013 09:05:26 +0000 (17:05 +0800)]
winsys/intel: make struct intel_bo alias drm_intel_bo
There is really nothing in struct intel_bo, and having it alias drm_intel_bo
makes the winsys impose almost zero overhead.
We can make the overhead gone completely by making the functions static
inline, if needed.
Chia-I Wu [Wed, 12 Jun 2013 08:56:49 +0000 (16:56 +0800)]
winsys/intel: reorganize functions
Move functions around to match the order of the declarations in the header.
Chia-I Wu [Wed, 12 Jun 2013 08:38:38 +0000 (16:38 +0800)]
ilo: update winsys interface
The motivation is to kill tiling and pitch in struct intel_bo. That requires
us to make tiling and pitch not queryable, and be passed around as function
parameters.
Chia-I Wu [Wed, 12 Jun 2013 08:21:00 +0000 (16:21 +0800)]
ilo: get rid of function tables in winsys
We are moving toward making struct intel_bo alias drm_intel_bo. As a first
step, we cannot have function tables.
Chia-I Wu [Tue, 11 Jun 2013 11:00:32 +0000 (19:00 +0800)]
ilo: access bo size directly
buf->bo_size is readily avaiable, no need to go via buf->bo->get_size().
Chia-I Wu [Tue, 11 Jun 2013 10:51:22 +0000 (18:51 +0800)]
ilo: remove unnecessary tex_set_bo/buf_set_bo
Merge the bodies to tex_create_bo/buf_create_bo respectively.
Kenneth Graunke [Sat, 8 Jun 2013 20:20:43 +0000 (13:20 -0700)]
i965: Emit the depth/stencil state pointer directly, not via atoms.
See two commits ago for the rationale. This allows us to delete the
whole gen7_cc_state.c file.
This does move these commands before the depth stall flushes from
brw_emit_depthbuffer, which may be a problem. The documentation for
3DSTATE_DEPTH_BUFFER mentions that depth stall flushes are required
before changing any depth/stencil buffer state, but explicitly lists
3DSTATE_DEPTH_BUFFER, 3DSTATE_HIER_DEPTH_BUFFER, 3DSTATE_STENCIL_BUFFER,
and 3DSTATE_CLEAR_PARAMS. It does not mention this particular packet
(_3DSTATE_DEPTH_STENCIL_STATE_POINTERS).
No observed Piglit regressions on Sandybridge or Ivybridge.
Together with the last two commits, this makes a cairo-gl benchmark
faster by 0.324552% +/- 0.258355% on Ivybridge. No statistically
significant change on Sandybridge. (Thanks to Eric for the numbers.)
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 20:14:41 +0000 (13:14 -0700)]
i965: Emit the CC state pointer directly rather than via atoms.
See the previous commit for the rationale.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 19:58:17 +0000 (12:58 -0700)]
i965: Emit the BLEND_STATE pointer directly rather than via atoms.
Previously, we would:
1. Emit the new indirect state.
2. Flag CACHE_NEW_BLEND_STATE.
3. Rely on later state atoms to notice CACHE_NEW_BLEND_STATE and emit a
pointer to the new indirect state.
This is rather cumbersome: it requires two state atoms instead of one,
and there's a strict ordering dependency in the list. Plus, the code
gets spread across two functions (or even files in the case of Gen7+).
Gen7+ has a packet to update just the blend state pointer, so it makes a
lot of sense to simply emit that right away. Gen6 has a combined packet
which updates blending, the color calculator, and depth/stencil state;
however, each can still be modified independently.
This drops the Gen6 micro-optimization where we tried to only emit one
packet that changed all three states. State updates are pretty cheap.
CACHE_NEW_BLEND_STATE is no longer necessary, so drop it.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Zack Rusin [Thu, 6 Jun 2013 13:07:33 +0000 (09:07 -0400)]
draw: implement distance culling
Works similarly to clip distance. If the cull distance is negative
for all vertices against a specific plane then the primitive
is culled.
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Zack Rusin [Thu, 6 Jun 2013 13:04:11 +0000 (09:04 -0400)]
gallium: add a cull distance semantic
cull distance is analogous to clip distance. If a register is
given this semantic, then the values in it are assumed to be a
float32 distance to a plane. Primitives will be completely
discarded if the plane distance for all of the vertices in
the primitive are < 0.
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Zack Rusin [Thu, 6 Jun 2013 12:49:09 +0000 (08:49 -0400)]
draw: fix clipper invocation statistics
We need to figure out the number of invocations of the clipper
before the emit, because in the emit we are after clipping
where the number of primitives will be equal to number of clipper
invocations minus the clipped primitives. So our computations
were always off by the number of clipped primitives.
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Zack Rusin [Thu, 6 Jun 2013 03:17:10 +0000 (23:17 -0400)]
draw: enable user plane clipping when clipdistance is used
Draw depended on clip_plane_enable being set in the rasterizer
to use clipdistance registers for clipping. That's really
unfriendly because it requires that rasterizer state to have
variants for every shader out there. Instead of depending on
the rasterizer lets extract the info from the available state:
if a shader writes clipdistance then we need to use it and we
need to clip using a number of planes equal to the number
of writen clipdistance components. This way clipdistances
just work.
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Zack Rusin [Wed, 5 Jun 2013 22:06:06 +0000 (18:06 -0400)]
draw: make sure clipdistances work with geometry shaders
we were always fetching the info from the vertex shader, but if
geometry shader is present it should be used as the source of
that info.
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Kenneth Graunke [Tue, 11 Jun 2013 17:31:39 +0000 (10:31 -0700)]
Revert "i965: Disable unused pipeline stages once at startup on Gen7+."
This reverts commit
6c966ccf07bcaf64fba1a9b699440c30dc96e732.
Apparently causes GPU hangs.
Conflicts:
src/mesa/drivers/dri/i965/brw_state.h
src/mesa/drivers/dri/i965/brw_state_upload.c
Brian Paul [Mon, 10 Jun 2013 14:36:33 +0000 (07:36 -0700)]
swrast: add texfetch code for some XBGR formats
Fixes piglit texture-packed-formats regression. We need to implement
more XBGR formats here eventually, but many are UINT/SINT formats
which swrast doesn't handle yet anyway (integer textures).
Bugzilla https://bugs.freedesktop.org/show_bug.cgi?id=64935
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Brian Paul [Sun, 9 Jun 2013 16:13:00 +0000 (09:13 -0700)]
mesa: add missing texture strings in tex_target_name()
And add a static assert for the future.
Alex Deucher [Fri, 7 Jun 2013 17:55:27 +0000 (13:55 -0400)]
winsys/radeon: add env var to disable VM on Cayman/Trinity
Set env var RADEON_VA=0 to disable VM on Cayman/Trinity.
Useful for debugging.
Note: this is a candidate for the 9.1 branch.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Eric Anholt [Thu, 6 Jun 2013 06:19:27 +0000 (23:19 -0700)]
mesa: Add a _mesa_problem to document a piglit failure on i965.
Having figured out what was going on with piglit fbo-depth copypixels
GL_DEPTH_COMPONENT32F (falling all the way back to swrast on CopyPixels to
a float depth buffer), I'm not inclined to fix the problem currently but
it seems worth saving someone else the debug time.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Eric Anholt [Sat, 8 Jun 2013 01:29:50 +0000 (18:29 -0700)]
i965/vs: Avoid the MUL/MACH/MOV sequence for small integer multiplies.
We do a lot of multiplies by 3 or 4 for skinning shaders, and we can avoid
the sequence if we just move them into the right argument of the MUL.
On pre-IVB, this means reliably putting a constant in a position where it
can't be constant folded, but that's still better than MUL/MACH/MOV.
Improves GLB 2.7 trex performance by 0.788648% +/- 0.23865% (n=29/30)
v2: Fix test for pre-sandybridge.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com> (v1)
Eric Anholt [Sat, 8 Jun 2013 00:58:18 +0000 (17:58 -0700)]
i965/vs: Allow copy propagation into MUL/MACH.
This is a trivial port of
1d6ead38042cc0d1e667d8ff55937c1e32d108b1 from
the FS.
No significant performance difference on trex (misplaced the data, but it
was about n=20).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Eric Anholt [Thu, 6 Jun 2013 17:14:41 +0000 (10:14 -0700)]
i965/vs: Use the MAD instruction when possible.
This is different from how we do it in the FS - we are using MAD even when
some of the args are constants, because with the relatively unrestrained
ability to schedule a MOV to prepare a temporary with that data, we can
get lower latency for the sequence of instructions.
No significant performance difference on GLB2.7 trex (n=33/34), though it
doesn't have that many MADs. I noticed MAD opportunities while reading
the code for the DOTA2 bug.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Richard Sandiford [Thu, 25 Apr 2013 20:50:07 +0000 (16:50 -0400)]
draw: Add A8R8G8B8 to draw_print_arrays
Reviewed-by: Adam Jackson <ajax@redhat.com>
Signed-off-by: Richard Sandiford <r.sandiford@uk.ibm.com>
Richard Sandiford [Tue, 4 Jun 2013 20:19:41 +0000 (21:19 +0100)]
draw: Fix type mismatch between draw_private.h and LLVM
draw_vertex_buffer declared the size field to be a size_t, but the LLVM
code used an int32 instead. This caused problems on big-endian 64-bit
targets, because the first 32-bit chunk of the 64-bit size_t was always 0.
In one sense size_t seems like a good choice for a size, so one fix
would have been to try to get the LLVM code to use the equivalent of
size_t too. However, in practice, the size is taken from things like ~0
or width0, both of which are int-sized, so it seemed simpler to make the
size field int-sized as well.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Signed-off-by: Richard Sandiford <rsandifo@linux.vnet.ibm.com>
Richard Sandiford [Wed, 5 Jun 2013 14:38:27 +0000 (15:38 +0100)]
util: Use sizeof(void *) rather than 0 as the fallback cache line size
Without this, llvmpipe ends up giving a zero size to all uncompressed textures
on non-x86 systems, since align() cannot handle a 0 alignment.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Signed-off-by: Richard Sandiford <rsandifo@linux.vnet.ibm.com>
Richard Sandiford [Fri, 7 Jun 2013 12:31:58 +0000 (13:31 +0100)]
llvmpipe: Use saturating add/sub for UNORM formats
lp_build_add and lp_build_sub have fallback code for cases
that cannot be handled by known intrinsics. For UNORM formats,
this code was using modulo rather than saturating arithmetic.
This fixes some rendering issues for a gnome session on System z.
It also fixes various piglit tests on z, such as
spec/ARB_color_buffer_float/GL_RGBA8-render.
The patch deliberately doesn't tackle the more complicated
SNORM case.
Tested against piglit on x86_64 and System z with no regressions.
Reviewed-by: Adam Jackson <ajax@redhat.com>
Signed-off-by: Richard Sandiford <rsandifo@linux.vnet.ibm.com>
Kenneth Graunke [Sat, 8 Jun 2013 17:17:22 +0000 (10:17 -0700)]
intel: Reserve less batchbuffer space.
Now that Gen6+ relies on hardware contexts, we don't need to record an
occlusion query value at the end of each batch. That means we no longer
need to reserve space for the absurd number of PIPE_CONTROLs required to
do that on Sandybridge.
See commit
4e087de51ad0e7ba4a7199d3664e1d096f8dc510, which bumped this
up to 60 bytes. This is not quite a revert, as it uses 24 bytes instead
of 16, and saves the comments. As far as I can tell, the old value of
16 bytes was just wrong, so we shouldn't go back to that.
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 17:06:21 +0000 (10:06 -0700)]
i965: Allocate push constant L3 space once at startup on Gen7+.
We always allocate the maximum amount of space and never change it, so
it makes sense to do it once. Programming it on startup also lets us
skip re-programming it from BLORP.
This removes a tiny amount of overhead from our drawing loop.
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 16:57:54 +0000 (09:57 -0700)]
i965: Disable unused pipeline stages once at startup on Gen7+.
This removes a tiny bit of code from our drawing loop.
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 17:01:34 +0000 (10:01 -0700)]
i965: Don't emit PIPELINE_SELECT from BLORP.
Now that we emit invariant state at startup (and never select the media
pipeline), the 3D pipeline will always already be selected, even if BLORP
is the first operation. So this is unnecessary.
v2: Fix unused variable warning (intel_context is no longer used).
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 16:55:36 +0000 (09:55 -0700)]
i965: Emit invariant state once at startup on Gen6+.
Now that we have hardware contexts, we can safely initialize our GPU
state once at startup, rather than needing a state atom with the
BRW_NEW_CONTEXT flag set.
This removes a tiny bit of code from our drawing loop.
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 16:31:31 +0000 (09:31 -0700)]
i965: Delete some dead state atom prototypes.
These atoms don't actually exist.
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 15:48:18 +0000 (08:48 -0700)]
i965: Change return type of check_state() to bool.
The existing code already returned a boolean; this just clarifies that.
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 15:46:14 +0000 (08:46 -0700)]
i965: Remove unused second parameter of brw_print_dirty_count().
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 07:06:52 +0000 (00:06 -0700)]
glsl: Allow the use of determinant() in GLSL 1.50.
We already implemented this for ES3, so we just need to turn it on.
Fixes 6 Piglit tests:
spec/glsl-1.50/compiler/built-in-functions/determinant-mat[234].{vert,frag}
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 05:04:23 +0000 (22:04 -0700)]
glcpp: Automatically #define GL_core_profile 1 on GLSL 1.50+.
Page 17 of the GLSL 1.50.11 specification states:
"There is a built-in macro definition for each profile the
implementation supports. All implementations provide the following
macro:
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 04:28:59 +0000 (21:28 -0700)]
glsl: Parse "#version 150 core" directives.
Previously we only supported "#version 150". This patch recognizes
"compatibility" to give the user a more descriptive error message.
Fixes Piglit's version-150-core-profile test.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Sat, 8 Jun 2013 04:46:04 +0000 (21:46 -0700)]
glsl: Bail on parsing if the #version directive is bogus.
If we didn't successfully parse the #version line, there's no point in
continuing with parsing and compiling: it's already failed.
Furthermore, it can actually be harmful: right after handling #version,
we call _mesa_glsl_initialize_types(), which checks state->es_shader and
language_version. If it isn't valid, it hits an assertion failure.
Fixes Piglit's "invalid-version-es." When processing "#version 110 es",
our code set state->es_shader and state->language_version = 110. It
then properly determined that this was invalid and flagged an error.
Since we continued anyway, we hit the assertion mentioned above.
NOTE: This is a candidate for the 9.1 branch.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Sun, 9 Jun 2013 21:17:16 +0000 (09:17 +1200)]
dlist: fix save_SamplerParameteri
This was building the temporary array to pass to
save_SamplerParameteriv, and then not passing it.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Vinson Lee <vlee@freedesktop.org>
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Vinson Lee [Thu, 6 Jun 2013 06:01:00 +0000 (23:01 -0700)]
mesa: Prevent possible out-of-bounds read by save_SamplerParameteriv.
Fixes "Out-of-bounds access" defect reported by Coverity.
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Reviewed-by: Brian Paul <brianp@vmware.com>
Maarten Lankhorst [Sat, 8 Jun 2013 18:09:25 +0000 (20:09 +0200)]
nvc0: fix up video buffer alignment requirements
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Rob Clark [Sat, 1 Jun 2013 18:16:30 +0000 (14:16 -0400)]
freedreno: better scissor fix
Actually respect rasterizer state.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Mon, 27 May 2013 00:36:35 +0000 (20:36 -0400)]
freedreno: gmem bypass
The GPU (at least a3xx, but I think also a2xx) can render directly to
memory, bypassing tiling. Although it can't do this if blend, depth,
and a few other features of the pipeline are enabled. This direct
memory mode can be faster for some sorts of operations, such as simple
blits. In particular, this significantly speeds up XA by avoiding to
pull the entire dest pixmap into GMEM, render tiles, and write it all
back out again. This should also speed up resource copy-region and
blit.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Sun, 26 May 2013 21:13:44 +0000 (17:13 -0400)]
freedreno: add a3xx support
The adreno a3xx GPU is found in newer snapdragon devices, such as the
nexus4. The a3xx is GLESv3 and OpenCL capable, although that is not
enabled yet in gallium.
Compared to a2xx, it introduces an entirely new unified shader ISA, and
re-shuffles all or nearly all of the registers. The good news is that
(for the most part) the registers are more orthogonal, not combining
unrelated state in a single register. And that there is a lot more
flexibility, so we don't need to patch and re-emit the shader like we
did on a2xx.
The shader compiler is currently quite dumb, there would be a lot of
room for improvement with an optimizing pass. Despite that, with the
a320 in my nexus4 it seems to be ~2-3x faster compared to the a220 in my
HP touchpad.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Sun, 26 May 2013 21:13:27 +0000 (17:13 -0400)]
freedreno: prepare for a3xx
Split the parts that are specific to adreno a2xx series GPUs from the
parts that will be in common with a3xx, so that a3xx support can be
added more cleanly.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Roland Scheidegger [Fri, 7 Jun 2013 19:20:01 +0000 (21:20 +0200)]
gallivm: work around slow code generated for interleaving 128bit vectors
We use 128bit vector interleave for untwiddling in the blend code (with
256bit vectors). llvm generates terrible code for this for some reason,
so instead of generating a shuffle for 2 128bit vectors use a
extract/insert shuffle instead (it only seems to matter we're not using
128bit wide vectors for the shuffle). This decreases instruction count of
the blend code generated for a rgba8 render target without blending from
169 to 113 with llvm 3.1 and from 136 to 114 in llvm 3.2/3.3, and I got
a ~8% (llvm 3.1) and ~5% (3.2/3.3) performance improvement in gears.
(The generated code is still not terribly good as we could actually avoid
the interleaving completely but llvm can't know this.)
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
José Fonseca [Sat, 8 Jun 2013 07:55:06 +0000 (08:55 +0100)]
scons: Fix implicit python dependency discovery on Windows.
Probably due to CRLF endings, the discovery of python import statements
was not working on Windows builds, causing incremental builds to often
fail unless one wiped out the build directory.
NOTE: This is a candidate for stable branches.