Doing matrix multiplies with DP4s is fewer instructions than MUL/ADD,
especially since we don't support MAD in the vertex shader.
Not observed to improve performance in any fixed function applications,
but is useful for the next patch.
Signed-off-by: Kenneth Graunke kenn...@whitecape.org
---
This pass flips (matrix * vector) operations to (vector *
matrixTranspose) for certain built-in matrices (currently
gl_ModelViewProjectionMatrix and gl_TextureMatrix).
This is equivalent, but results in dot products rather than multiplies
and adds. On some hardware, this is more efficient.
This
Am 03.04.2013 02:17, schrieb Matt Turner:
On Tue, Apr 2, 2013 at 4:19 PM, Christian König deathsim...@vodafone.de wrote:
diff --git a/configure.ac b/configure.ac
index 81d4a3f..93ec1d2 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1814,6 +1814,7 @@ if test x$with_gallium_drivers != x; then
On Die, 2013-04-02 at 18:56 -0400, Tom Stellard wrote:
From: Marek Olšák mar...@gmail.com
Ported from r600g commit:
8891b2f9c91b2f6c8625184c23a10b8e55875dc0
NOTE: This is a candidate for the stable branches.
Just for the 9.1 branch.
I wasn't hitting this problem, maybe because I'm
On Tue, Apr 02, 2013 at 06:46:32PM -0700, Eric Anholt wrote:
This still fails, since 8192*4bpp == 32768, which is too big to use the
blitter on.
Reviewed-by: Kenneth Graunke kenn...@whitecape.org
---
src/mesa/drivers/dri/intel/intel_mipmap_tree.c | 21 +
1 file
On Tue, Apr 02, 2013 at 06:46:32PM -0700, Eric Anholt wrote:
This still fails, since 8192*4bpp == 32768, which is too big to use the
blitter on.
Meh, I should take coffee first before doing reviews ...
Iirc on gen4+ for tiled src/dst the blt stride limit is 128k (since the
stride is supplied
Am 03.04.2013 10:21, schrieb Michel Dänzer:
On Die, 2013-04-02 at 18:56 -0400, Tom Stellard wrote:
From: Marek Olšák mar...@gmail.com
Ported from r600g commit:
8891b2f9c91b2f6c8625184c23a10b8e55875dc0
NOTE: This is a candidate for the stable branches.
Just for the 9.1 branch.
I wasn't
https://bugs.freedesktop.org/show_bug.cgi?id=47607
--- Comment #8 from bartosz.brzos...@11bitstudios.com ---
(In reply to comment #0)
The game Anomaly Warzone Earth from the previous Humble Android Bundle
does not work with Mesa.
Guys, we solved the crash and updated the Steam version first.
Hi all!
i'm trying to build latest mesa release 9.1.1 on my arm board i.mx6
and i got
.c -fPIC -DPIC -o .libs/xorg_driver.o
In file included from xorg_driver.c:36:0:
/usr/include/xorg/xf86PciInfo.h:50:2: warning: #warning xf86PciInfo.h is
deprecated. For greater compatibility, drivers should
On Mit, 2013-04-03 at 14:40 +0400, Alexander Khryukin wrote:
Hi all!
i'm trying to build latest mesa release 9.1.1 on my arm board i.mx6
and i got
.c -fPIC -DPIC -o .libs/xorg_driver.o
In file included from xorg_driver.c:36:0:
/usr/include/xorg/xf86PciInfo.h:50:2: warning: #warning
On Mit, 2013-03-27 at 17:57 +0100, Christian König wrote:
the attached patches dynamically adjust the writemask of MIMG
instructions depending on the used components. Additional to that it
also adjust the register class of MIMG instruction so that we also
reduce register pressure.
https://bugs.freedesktop.org/show_bug.cgi?id=63078
Priority: medium
Bug ID: 63078
Assignee: mesa-dev@lists.freedesktop.org
Summary: EGL X11 Regression: Maximum swap interval is 0 (worked
with 9.0)
Severity: normal
Am 03.04.2013 15:19, schrieb Michel Dänzer:
On Mit, 2013-03-27 at 17:57 +0100, Christian König wrote:
the attached patches dynamically adjust the writemask of MIMG
instructions depending on the used components. Additional to that it
also adjust the register class of MIMG instruction so that we
On Mit, 2013-04-03 at 15:38 +0200, Christian König wrote:
Am 03.04.2013 15:19, schrieb Michel Dänzer:
On Mit, 2013-03-27 at 17:57 +0100, Christian König wrote:
the attached patches dynamically adjust the writemask of MIMG
instructions depending on the used components. Additional to that it
I only had time to skim through your changes but the series looks great, Roland.
If it's not too much trouble, could you please add a piglit test for explicit
cube derivatives? Also, please confirm there are no piglit regressions.
Jose
- Original Message -
From: Roland Scheidegger
- Original Message -
I think this was there before and got accidently
removed during a merge. Same code as for the GS
context, which is also using an enum instead of
hardcoded numbers.
Signed-off-by: Zack Rusin za...@vmware.com
---
src/gallium/auxiliary/draw/draw_llvm.c |8
From: Brian Paul bri...@vmware.com
The functions are prototyped in u_transfer.h and are related to the
other functions in u_transfer.c.
The next patch will re-use the u_resource.c file for new code.
---
src/gallium/auxiliary/util/u_resource.c | 76 +--
From: Brian Paul bri...@vmware.com
---
src/gallium/auxiliary/util/u_resource.c | 65 ++-
src/gallium/auxiliary/util/u_resource.h | 34
2 files changed, 98 insertions(+), 1 deletion(-)
create mode 100644 src/gallium/auxiliary/util/u_resource.h
From: Brian Paul bri...@vmware.com
To track the amount of memory used by all pipe_resources (textures
and buffers).
---
src/gallium/drivers/svga/svga_context.h |1 +
src/gallium/drivers/svga/svga_pipe_query.c | 11 +++
src/gallium/drivers/svga/svga_resource_buffer.c
The way we were allocating registers before, packing into low register
numbers for Ironlake, resulted in an overly-constrained dependency graph
for instruction scheduling. Improves GLBenchmark 2.1 performance by
3.4% +/- 0.6% (n=26)
---
src/mesa/drivers/dri/i965/brw_fs_reg_allocate.cpp |2 ++
Cc: Christian König deathsim...@vodafone.de
---
src/gallium/drivers/r600/r600_pipe.c | 63 +++---
src/gallium/drivers/r600/r600_pipe.h |1 +
2 files changed, 60 insertions(+), 4 deletions(-)
diff --git a/src/gallium/drivers/r600/r600_pipe.c
On Wed, Apr 3, 2013 at 5:25 AM, Michel Dänzer mic...@daenzer.net wrote:
On Mit, 2013-04-03 at 14:40 +0400, Alexander Khryukin wrote:
Hi all!
i'm trying to build latest mesa release 9.1.1 on my arm board i.mx6
and i got
.c -fPIC -DPIC -o .libs/xorg_driver.o
In file included from
Cc: Christian König deathsim...@vodafone.de
---
Note: Compile tested only
src/gallium/drivers/radeonsi/radeonsi_pipe.c | 39 --
src/gallium/drivers/radeonsi/radeonsi_pipe.h |1 +
2 files changed, 37 insertions(+), 3 deletions(-)
diff --git
On Wed, Apr 3, 2013 at 10:25 AM, Eric Anholt e...@anholt.net wrote:
The way we were allocating registers before, packing into low register
numbers for Ironlake, resulted in an overly-constrained dependency graph
for instruction scheduling. Improves GLBenchmark 2.1 performance by
3.4% +/- 0.6%
On Tue, Apr 2, 2013 at 2:28 PM, Tom Stellard t...@stellard.net wrote:
On Tue, Apr 02, 2013 at 01:38:07PM -0700, Matt Turner wrote:
---
Nice catch, will this change have any affect on the compiled code?
I think so, in this block:
if (benefit / cost best_benefit) {
best_benefit = benefit /
GCC 4.8 now warns about typedefs that are local to a scope and not
used anywhere within that scope. This produced spurious warnings with
the STATIC_ASSERT() macro (which used a typedef to provoke a compile
error in the event of an assertion failure).
This patch switches to a simpler technique
On 04/02/2013 01:38 PM, Matt Turner wrote:
Candidate for stable branches?
---
src/mesa/program/register_allocate.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/src/mesa/program/register_allocate.c
b/src/mesa/program/register_allocate.c
index a9064c3..7d11b73
On 04/03/2013 12:22 PM, Paul Berry wrote:
GCC 4.8 now warns about typedefs that are local to a scope and not
used anywhere within that scope. This produced spurious warnings with
the STATIC_ASSERT() macro (which used a typedef to provoke a compile
error in the event of an assertion failure).
On 04/02/2013 10:58 AM, Kenneth Graunke wrote:
On 04/01/2013 11:25 AM, Ian Romanick wrote:
From: Ian Romanick ian.d.roman...@intel.com
Previously the shader
uniform float x[6];
void main() { gl_Position.x = x[1.0]; }
would have generated the errors
0:2(33): error: array index must be
On 04/01/2013 02:42 PM, Alexander Monakov wrote:
On Mon, Apr 1, 2013 at 11:05 PM, Alexander Monakov amona...@gmail.com wrote:
https://bugs.freedesktop.org/show_bug.cgi?id=47478
https://bugs.freedesktop.org/show_bug.cgi?id=62999 (dup of the above)
I don't have commit access so please push if
FYI this and the radeonsi patch assume that the kernel driver with UVD
support reports version 2.31.0 (needs to be bumped)
2013/4/3 Andreas Boll andreas.boll@gmail.com
Cc: Christian König deathsim...@vodafone.de
---
src/gallium/drivers/r600/r600_pipe.c | 63
This is mesa match for 2d tiling, it's missing change to configure.ac
to require proper libdrm. Will respin once i know.
Cheers,
Jerome
___
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
From: Jerome Glisse jgli...@redhat.com
Signed-off-by: Jerome Glisse jgli...@redhat.com
---
src/gallium/drivers/radeonsi/r600_texture.c | 4 +-
src/gallium/drivers/radeonsi/si_state.c | 83 +
2 files changed, 14 insertions(+), 73 deletions(-)
diff --git
To match the FREE() called used later. Fixes things on Windows.
---
src/gallium/auxiliary/hud/hud_context.c |2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/src/gallium/auxiliary/hud/hud_context.c
b/src/gallium/auxiliary/hud/hud_context.c
index 5511f8e..b417f5d 100644
The former just checks that the given block is valid by checking
the header and footer.
The later sets the memory block's tag. With extra debug code, we
can use that for monitoring/checking particular allocations.
---
src/gallium/auxiliary/os/os_memory_debug.h |6 +++
---
src/gallium/state_trackers/wgl/stw_context.c |2 +-
src/gallium/state_trackers/wgl/stw_context.h |4 +++-
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/src/gallium/state_trackers/wgl/stw_context.c
b/src/gallium/state_trackers/wgl/stw_context.c
index 1488bee..5e5b41f
---
src/gallium/state_trackers/wgl/stw_context.c |9 +
src/gallium/state_trackers/wgl/stw_context.h |3 +++
src/gallium/state_trackers/wgl/stw_framebuffer.c |9 +
src/gallium/state_trackers/wgl/stw_st.c | 13 +
It's part of SM4 (http://goo.gl/4IpeK). It's also fairly
painful to emulate without branching. Most hardware
supports it natively and even llvm has a 'select' opcode
which can handle it without too much hassle.
Signed-off-by: Zack Rusin za...@vmware.com
---
https://bugs.freedesktop.org/show_bug.cgi?id=63097
Priority: medium
Bug ID: 63097
Assignee: mesa-dev@lists.freedesktop.org
Summary: libegl1-mesa-drivers from git (xedgers ppa) can't be
installed due to dependencie change on ubuntu
39 matches
Mail list logo