<feed xmlns='http://www.w3.org/2005/Atom'>
<title>external_mesa3d/src/intel/vulkan/gen7_cmd_buffer.c, branch replicant-6.0</title>
<subtitle>external/mesa3d
</subtitle>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/'/>
<entry>
<title>anv/cmd_buffer: Unify flush_compute_state across gens</title>
<updated>2016-10-18T00:41:35+00:00</updated>
<author>
<name>Jason Ekstrand</name>
<email>jason.ekstrand@intel.com</email>
</author>
<published>2016-10-17T17:03:16+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=1f3e6468d2a3efd9f2da99fa337dfe4b804bcda6'/>
<id>1f3e6468d2a3efd9f2da99fa337dfe4b804bcda6</id>
<content type='text'>
With one small genxml change, the two versions were basically identical.
The only differences were one #define for HSW+ and a field that is missing
on Haswell but exists everywhere else.

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Anuj Phogat &lt;anuj.phogat@gmail.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
With one small genxml change, the two versions were basically identical.
The only differences were one #define for HSW+ and a field that is missing
on Haswell but exists everywhere else.

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Anuj Phogat &lt;anuj.phogat@gmail.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>anv/cmd_buffer: Add code for performing HZ operations</title>
<updated>2016-10-07T19:54:18+00:00</updated>
<author>
<name>Nanley Chery</name>
<email>nanley.g.chery@intel.com</email>
</author>
<published>2016-10-07T19:07:27+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=134d181be1e3023b0ca36ccaa777105e37e23a82'/>
<id>134d181be1e3023b0ca36ccaa777105e37e23a82</id>
<content type='text'>
Create a function that performs one of three HiZ operations -
depth/stencil clears, HiZ resolve, and depth resolves.

Signed-off-by: Nanley Chery &lt;nanley.g.chery@intel.com&gt;
Reviewed-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Chad Versace &lt;chadversary@chromium.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Create a function that performs one of three HiZ operations -
depth/stencil clears, HiZ resolve, and depth resolves.

Signed-off-by: Nanley Chery &lt;nanley.g.chery@intel.com&gt;
Reviewed-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Chad Versace &lt;chadversary@chromium.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>anv: Move cmd_buffer_config_l3 into anv_cmd_buffer.c</title>
<updated>2016-09-03T15:23:07+00:00</updated>
<author>
<name>Jason Ekstrand</name>
<email>jason.ekstrand@intel.com</email>
</author>
<published>2016-08-23T00:13:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=7e891f90c701aa1c851f1846857daa75bbb65876'/>
<id>7e891f90c701aa1c851f1846857daa75bbb65876</id>
<content type='text'>
This is the only remaining part of genX_l3.c and there's really no good
reason for it to be in its own file.

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This is the only remaining part of genX_l3.c and there's really no good
reason for it to be in its own file.

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>anv/cmd: Move emit_descriptor_pointers to genX_cmd_buffer.c</title>
<updated>2016-06-21T23:45:25+00:00</updated>
<author>
<name>Jason Ekstrand</name>
<email>jason.ekstrand@intel.com</email>
</author>
<published>2016-06-21T22:31:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=2bfe0c33748b9fd96d48cb93656b6dc643bf024e'/>
<id>2bfe0c33748b9fd96d48cb93656b6dc643bf024e</id>
<content type='text'>
It's tiny and fully generic so there's really no reason for it to be in a
gen7-specific file.

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
It's tiny and fully generic so there's really no reason for it to be in a
gen7-specific file.

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>anv/cmd: Move flush_descriptor_sets to anv_cmd_buffer.c</title>
<updated>2016-06-21T23:45:25+00:00</updated>
<author>
<name>Jason Ekstrand</name>
<email>jason.ekstrand@intel.com</email>
</author>
<published>2016-06-21T22:28:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=9df4d6bb36268d5dd248b872611e3787de9608be'/>
<id>9df4d6bb36268d5dd248b872611e3787de9608be</id>
<content type='text'>
There's no good reason for recompiling it

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
There's no good reason for recompiling it

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>i965: Fix shared local memory size for Gen9+.</title>
<updated>2016-06-12T07:38:26+00:00</updated>
<author>
<name>Kenneth Graunke</name>
<email>kenneth@whitecape.org</email>
</author>
<published>2016-06-09T05:21:22+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=87d062a94080373995170f51063a9649c96c6dea'/>
<id>87d062a94080373995170f51063a9649c96c6dea</id>
<content type='text'>
Skylake changes the representation of shared local memory size:

 Size   | 0 kB | 1 kB | 2 kB | 4 kB | 8 kB | 16 kB | 32 kB | 64 kB |
 -------------------------------------------------------------------
 Gen7-8 |    0 | none | none |    1 |    2 |     4 |     8 |    16 |
 -------------------------------------------------------------------
 Gen9+  |    0 |    1 |    2 |    3 |    4 |     5 |     6 |     7 |

The old formula would substantially underallocate the amount of space.
This fixes GPU hangs on Skylake when running with full thread counts.

v2: Fix the Vulkan driver too, use a helper function, and fix the table
    in the comments and commit message.

Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
Signed-off-by: Kenneth Graunke &lt;kenneth@whitecape.org&gt;
Reviewed-by: Francisco Jerez &lt;currojerez@riseup.net&gt;
Reviewed-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Skylake changes the representation of shared local memory size:

 Size   | 0 kB | 1 kB | 2 kB | 4 kB | 8 kB | 16 kB | 32 kB | 64 kB |
 -------------------------------------------------------------------
 Gen7-8 |    0 | none | none |    1 |    2 |     4 |     8 |    16 |
 -------------------------------------------------------------------
 Gen9+  |    0 |    1 |    2 |    3 |    4 |     5 |     6 |     7 |

The old formula would substantially underallocate the amount of space.
This fixes GPU hangs on Skylake when running with full thread counts.

v2: Fix the Vulkan driver too, use a helper function, and fix the table
    in the comments and commit message.

Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
Signed-off-by: Kenneth Graunke &lt;kenneth@whitecape.org&gt;
Reviewed-by: Francisco Jerez &lt;currojerez@riseup.net&gt;
Reviewed-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>genxml/gen6,7,75: s/BackFace/Backface</title>
<updated>2016-06-04T02:29:28+00:00</updated>
<author>
<name>Jason Ekstrand</name>
<email>jason.ekstrand@intel.com</email>
</author>
<published>2016-06-01T05:15:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=fdc3c5dd05dc072fe9b4975091308d02e6df6037'/>
<id>fdc3c5dd05dc072fe9b4975091308d02e6df6037</id>
<content type='text'>
This is more consistent with gen8+

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Kenneth Graunke &lt;kenneth@whitecape.org&gt;
Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This is more consistent with gen8+

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Kenneth Graunke &lt;kenneth@whitecape.org&gt;
Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>anv: Support new local ID generation &amp; cross-thread constants</title>
<updated>2016-06-02T02:29:02+00:00</updated>
<author>
<name>Jordan Justen</name>
<email>jordan.l.justen@intel.com</email>
</author>
<published>2016-05-27T07:53:27+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=3ba9594f32239031ddeff764e9896d48d05125d0'/>
<id>3ba9594f32239031ddeff764e9896d48d05125d0</id>
<content type='text'>
The cross thread constant support appears on Haswell. It allows us to
upload a set of uniform data for all threads without duplicating it
per thread.

We also support per-thread data which allows us to store a per-thread
ID in one of the uniforms that can be used to calculate the
gl_LocalInvocationIndex and gl_LocalInvocationID variables.

v4:
 * Support the old local ID push constant layout as well (Jason)

Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
Signed-off-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
Reviewed-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The cross thread constant support appears on Haswell. It allows us to
upload a set of uniform data for all threads without duplicating it
per thread.

We also support per-thread data which allows us to store a per-thread
ID in one of the uniforms that can be used to calculate the
gl_LocalInvocationIndex and gl_LocalInvocationID variables.

v4:
 * Support the old local ID push constant layout as well (Jason)

Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
Signed-off-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
Reviewed-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>i965: Store number of threads in brw_cs_prog_data</title>
<updated>2016-06-02T02:29:02+00:00</updated>
<author>
<name>Jordan Justen</name>
<email>jordan.l.justen@intel.com</email>
</author>
<published>2016-05-26T20:49:07+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=1b79e7ebbd77a7e714fafadd91459059aacf2407'/>
<id>1b79e7ebbd77a7e714fafadd91459059aacf2407</id>
<content type='text'>
Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
Signed-off-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
Reviewed-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Cc: "12.0" &lt;mesa-stable@lists.freedesktop.org&gt;
Signed-off-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
Reviewed-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>anv/cmd_buffer: Only emit PIPE_CONTROL on-demand</title>
<updated>2016-05-27T22:18:09+00:00</updated>
<author>
<name>Jason Ekstrand</name>
<email>jason.ekstrand@intel.com</email>
</author>
<published>2016-05-20T18:49:12+00:00</published>
<link rel='alternate' type='text/html' href='https://git.replicant.us/replicant/external_mesa3d/commit/?id=3a83c176eab8c513eb723554a240af1a7308d701'/>
<id>3a83c176eab8c513eb723554a240af1a7308d701</id>
<content type='text'>
This is in contrast to emitting it directly in vkCmdPipelineBarrier.  This
has a couple of advantages.  First, it means that no matter how many
vkCmdPipelineBarrier calls the application strings together it gets one or
two PIPE_CONTROLs.  Second, it allow us to better track when we need to do
stalls because we can flag when a flush has happened and we need a stall.

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This is in contrast to emitting it directly in vkCmdPipelineBarrier.  This
has a couple of advantages.  First, it means that no matter how many
vkCmdPipelineBarrier calls the application strings together it gets one or
two PIPE_CONTROLs.  Second, it allow us to better track when we need to do
stalls because we can flag when a flush has happened and we need a stall.

Signed-off-by: Jason Ekstrand &lt;jason@jlekstrand.net&gt;
Reviewed-by: Jordan Justen &lt;jordan.l.justen@intel.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
