<feed xmlns='http://www.w3.org/2005/Atom'>
<title>igt-gpu-tools.git/benchmarks, branch master</title>
<subtitle>DRM IGT GPU Tools</subtitle>
<id>https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/atom?h=master</id>
<link rel='self' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/atom?h=master'/>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/'/>
<updated>2019-05-07T21:37:56+00:00</updated>
<entry>
<title>Use gettid() wrapper everywhere</title>
<updated>2019-05-07T21:37:56+00:00</updated>
<author>
<name>Lyude Paul</name>
<email>lyude@redhat.com</email>
</author>
<published>2019-04-23T22:50:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=998288337d87b9fac8ae3a2f06ee97bfa9bfdfa3'/>
<id>urn:sha1:998288337d87b9fac8ae3a2f06ee97bfa9bfdfa3</id>
<content type='text'>
Currently we have multiple different parts of IGT that define their own
wrapper around the gettid() syscall (or just call it directly with no
wrapper).

Additionally, add the appropriate #includes for igt_aux.h to make sure
syscall() is available.

Reviewed-by: Petri Latvala &lt;petri.latvala@intel.com&gt;
Signed-off-by: Lyude Paul &lt;lyude@redhat.com&gt;
</content>
</entry>
<entry>
<title>Revert "lib/igt_device: Move intel_get_pci_device under igt_device"</title>
<updated>2019-03-29T20:23:27+00:00</updated>
<author>
<name>Ville Syrjälä</name>
<email>ville.syrjala@linux.intel.com</email>
</author>
<published>2019-03-27T18:52:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=e408d569973b610ba4aafdba016c48b25e563468'/>
<id>urn:sha1:e408d569973b610ba4aafdba016c48b25e563468</id>
<content type='text'>
One significant usecase for intel_reg/etc. is to be able to examine
the hardware state *before* loading the driver. If the tool forces
the driver to load we've totally lost that capability.

This reverts commit 8ae86621d6fff60b6e20c6b0f9b336785c935b0f.

Cc: Michał Winiarski &lt;michal.winiarski@intel.com&gt;
Cc: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
Signed-off-by: Ville Syrjälä &lt;ville.syrjala@linux.intel.com&gt;
Acked-by: Jani Nikula &lt;jani.nikula@intel.com&gt;
Acked-by: Michał Winiarski &lt;michal.winiarski@intel.com&gt;
</content>
</entry>
<entry>
<title>lib/igt_device: Move intel_get_pci_device under igt_device</title>
<updated>2019-03-20T09:36:36+00:00</updated>
<author>
<name>Michał Winiarski</name>
<email>michal.winiarski@intel.com</email>
</author>
<published>2019-03-12T12:48:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=8ae86621d6fff60b6e20c6b0f9b336785c935b0f'/>
<id>urn:sha1:8ae86621d6fff60b6e20c6b0f9b336785c935b0f</id>
<content type='text'>
It allows us to make things a little bit more generic. Also, we now
require fd rather than doing guesswork when it comes to pci address.

v2: Use readlinkat rather than string concat, move stuff around, provide
a version that does not assert. (Chris)
v3: Print addr on failure, avoid assignment in conditionals. (Chris)

Signed-off-by: Michał Winiarski &lt;michal.winiarski@intel.com&gt;
Cc: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
Reviewed-by: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
</content>
</entry>
<entry>
<title>automake: Make librt mandatory</title>
<updated>2019-03-04T07:01:17+00:00</updated>
<author>
<name>Tvrtko Ursulin</name>
<email>tvrtko.ursulin@intel.com</email>
</author>
<published>2019-03-01T10:25:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=a958d3f60b7718151fd0bafcdd1e4874262f51b8'/>
<id>urn:sha1:a958d3f60b7718151fd0bafcdd1e4874262f51b8</id>
<content type='text'>
librt is required by libintel_tools so express it as mandatory in autoconf
and also drop explicit mentions from Makefile.am.

This also fixes a build warning of:

  tests/Makefile.am:134: warning: variable 'pm_rc6_residency_LDADD' is defined but no program or
  tests/Makefile.am:134: library has 'pm_rc6_residency' as canonical name (possible typo)

Signed-off-by: Tvrtko Ursulin &lt;tvrtko.ursulin@intel.com&gt;
Reviewed-by: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
</content>
</entry>
<entry>
<title>gem_wsim: Remove some unused struct members</title>
<updated>2019-03-01T09:39:53+00:00</updated>
<author>
<name>Tvrtko Ursulin</name>
<email>tvrtko.ursulin@intel.com</email>
</author>
<published>2019-02-28T13:50:07+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=189956af183c245eb237b3be4fa22953ec93bbe0'/>
<id>urn:sha1:189956af183c245eb237b3be4fa22953ec93bbe0</id>
<content type='text'>
We do not bother explicitly unmapping memory on exit so no need to store
address and size in the workload step struct.

Signed-off-by: Tvrtko Ursulin &lt;tvrtko.ursulin@intel.com&gt;
Reviewed-by: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
</content>
</entry>
<entry>
<title>gem_wsim: Round mmap to page size</title>
<updated>2019-03-01T09:39:35+00:00</updated>
<author>
<name>Tvrtko Ursulin</name>
<email>tvrtko.ursulin@intel.com</email>
</author>
<published>2019-02-26T12:17:25+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=24366f0868c6a33f9f246446c9f322163429ee01'/>
<id>urn:sha1:24366f0868c6a33f9f246446c9f322163429ee01</id>
<content type='text'>
mmap(2) mandates size is page aligned.

Signed-off-by: Tvrtko Ursulin &lt;tvrtko.ursulin@intel.com&gt;
Reviewed-by: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
</content>
</entry>
<entry>
<title>lib/i915: Move mmap IOCTLs wrappers into separate file</title>
<updated>2019-02-26T18:05:17+00:00</updated>
<author>
<name>Antonio Argenziano</name>
<email>antonio.argenziano@intel.com</email>
</author>
<published>2019-02-26T17:30:44+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=1d8f3320cbc06fa73ad1487453a63993f17b9d57'/>
<id>urn:sha1:1d8f3320cbc06fa73ad1487453a63993f17b9d57</id>
<content type='text'>
Move all mmap flavours and support function to separate file in i915
folder. This helps with moving i915 specific functions away from common
libraries.

v2:
	- Autotools still exists. (Petri)
	- Include gem_mman.h directly. (Chris)

v3:
	- Keep includes explicit. (Chris)

Signed-off-by: Antonio Argenziano &lt;antonio.argenziano@intel.com&gt;
Cc: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
Cc: Petri Latvala &lt;petri.latvala@intel.com&gt;
Reviewed-by: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
</content>
</entry>
<entry>
<title>benchmarks/meson: Stop renaming benchmarks</title>
<updated>2019-02-20T06:38:19+00:00</updated>
<author>
<name>Arkadiusz Hiler</name>
<email>arkadiusz.hiler@intel.com</email>
</author>
<published>2019-02-19T10:51:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=daa38baa64d3a049e9e0d00ec8d763884ac7d187'/>
<id>urn:sha1:daa38baa64d3a049e9e0d00ec8d763884ac7d187</id>
<content type='text'>
Meson 0.46.0 fixes the issue that forced us to do the renaming.

Cc: Daniel Vetter &lt;daniel@ffwll.ch&gt;
Cc: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
Signed-off-by: Arkadiusz Hiler &lt;arkadiusz.hiler@intel.com&gt;
Acked-by: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
</content>
</entry>
<entry>
<title>automake: Ditch all EXTRA_DIST directives</title>
<updated>2019-01-29T10:10:49+00:00</updated>
<author>
<name>Daniel Vetter</name>
<email>daniel.vetter@ffwll.ch</email>
</author>
<published>2019-01-22T13:42:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=434af38f8d19c61fdcfa611644c29dbe73f9f3a9'/>
<id>urn:sha1:434af38f8d19c61fdcfa611644c29dbe73f9f3a9</id>
<content type='text'>
We're not using automake to build tarballs anymore.

Acked-by: Petri Latvala &lt;petri.latvala@intel.com&gt;
Signed-off-by: Daniel Vetter &lt;daniel.vetter@intel.com&gt;
</content>
</entry>
<entry>
<title>benchmarks/gem_userptr_benchmark: Correctly free memory</title>
<updated>2019-01-21T11:51:01+00:00</updated>
<author>
<name>Petri Latvala</name>
<email>petri.latvala@intel.com</email>
</author>
<published>2019-01-16T11:20:41+00:00</published>
<link rel='alternate' type='text/html' href='https://git.etezian.org/cgit.cgi/igt-gpu-tools.git/commit/?id=72964897ce92525ea62e1e1b1b7df24b6c6125dd'/>
<id>urn:sha1:72964897ce92525ea62e1e1b1b7df24b6c6125dd</id>
<content type='text'>
if (p) free(p) does a useless check, free(NULL) is a valid call. Also
assign NULL so we don't end up double-freeing memory if anyone
reorders nr_bos to have a 0 after other values.

Signed-off-by: Petri Latvala &lt;petri.latvala@intel.com&gt;
Cc: Tvrtko Ursulin &lt;tvrtko.ursulin@intel.com&gt;
Reviewed-by: Tvrtko Ursulin &lt;tvrtko.ursulin@intel.com&gt;
</content>
</entry>
</feed>
