Filip Hazubski
4d76fe93b0
Add Math::divideAndRoundUp usage
...
Change-Id: Iae7775a61f7d12dd43d9253498fe388956af2fc4
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2019-10-10 12:25:15 +02:00
Filip Hazubski
81cd28e0f4
Add Math::divideAndRoundUp helper function
...
Add usage of the function where applicable
Change-Id: I9c41ad37009d1f088fa1917d30525194a10d3061
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2019-10-09 13:25:39 +02:00
Dunajski, Bartosz
9d6dcd6fff
Use Kernels maxKernelWorkGroupSize to compute WG size
...
Change-Id: I947b5612f36cd2437e1ead98712c914ffe4b5b15
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2019-09-17 08:39:05 +02:00
Dunajski, Bartosz
d31ba78221
Remove maxWorkGroupSize parameter from provideLocalWorkGroupSizeHints
...
Change-Id: I2317fce1c39800b9c94678e6c4c5c32a8d26d6a1
Signed-off-by: Dunajski, Bartosz <bartosz.dunajski@intel.com>
2019-09-13 14:46:36 +02:00
Mateusz Jablonski
9c200530c8
Remove not needed inclusions of device.h
...
Change-Id: Idfd8122592f58539a569143146443c08a18dace9
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2019-09-09 15:05:29 +02:00
Jobczyk, Lukasz
882a216688
Move Debug helpers to the core dir
...
Related-To: NEO-3677
Change-Id: I2c98595190fadfa8ffd9e378e774c0d4485cbf9e
Signed-off-by: Jobczyk, Lukasz <lukasz.jobczyk@intel.com>
2019-09-05 16:00:35 +02:00
Mateusz Jablonski
b8fb5e683b
Move basic_math.h and vec.h to core directory
...
Change-Id: I143b7af450ff48d4958b4bc7137b393a2dc0eb64
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
2019-05-14 21:32:55 +02:00
Piotr Fusik
8cf7cea1e9
Simplify bit operations.
...
Change-Id: If1401f32df5ebcb3abf614832152abf029a9c5e6
Signed-off-by: Piotr Fusik <piotr.fusik@intel.com>
2019-03-27 17:11:29 +01:00
Maciej Plewka
9e52684f5b
Change namespace from OCLRT to NEO
...
Change-Id: If965c79d70392db26597aea4c2f3b7ae2820fe96
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
2019-03-26 15:48:19 +01:00
Filip Hazubski
8b57d28116
clang-format: enable sorting includes
...
Include files are now grouped and sorted in following order:
1. Header file of the class the current file implements
2. Project files
3. Third party files
4. Standard library
Change-Id: If31af05652184169f7fee1d7ad08f1b2ed602cf0
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
2019-02-27 11:50:07 +01:00
Mrozek, Michal
274c8084a3
For devices with small HW thread count, limit the available pool of LWS.
...
Change-Id: Ib3c0fea3e0422dae3bc93b891aab087ad597776e
2018-01-24 14:30:39 +01:00
Mrozek, Michal
41f0ac3019
Check if we do not access outside of array.
...
Change-Id: I3357b745d36398ad52777054f64a7915278c0463
2018-01-17 09:33:57 +01:00
Mrozek, Michal
dd601ff73a
Utilize shortened version of optimal HW thread count in nx4 scenarios.
...
- also clean early return if simd size = 0
Change-Id: I9b01df091ab6dd6a3066d1a8762c7fb1530c2804
2018-01-16 14:47:07 +01:00
Mrozek, Michal
ee250be942
Fix num thread per slice computation.
...
- It should use thread count not EU count.
- change variable name to reflect that we work on sublices.
- fix test description, add missing test
- change hasBarrier variable to be boolean
Change-Id: I627bdf17b661d2f9b5eb3d8cd6ca53eba5d46b81
2018-01-16 13:06:31 +01:00
Mrozek, Michal
7640201585
Allow squared algorithm to work together with base one.
...
Change-Id: I9087957bb427a422b1be632f6375c96b8f91a492
2018-01-12 12:05:04 +01:00
Mrozek, Michal
c8d9846d50
Enhance search pattern for early LWS finding path.
...
- Allows to find larger LWS in multiple cases.
Change-Id: I645f5bca5c8ccdcf8e0d4861e47fcbcad0395e7a
2018-01-10 08:20:02 +01:00
Mrozek, Michal
94ae9a3d1b
Add debug functionality to dump LWS sizes.
...
- Refactor of LWS tests.
Change-Id: Ic47c88996a658f2168cc425f4598e91eced4756d
2018-01-09 15:41:11 +01:00
Brandon Fliflet
7e9ad41290
Initial commit
...
Change-Id: I4bf1707bd3dfeadf2c17b0a7daff372b1925ebbd
2017-12-21 00:45:38 +01:00