Media
/
compute-runtime
mirror of https://github.com/intel/compute-runtime.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
5,588 Commits 36 Branches 610 Tags 177 MiB
Commit Graph

27 Commits

Author SHA1 Message Date
Artur Harasimiuk fa6b181120 do not use absolute path when including hw_cmds.h 
Change-Id: I59a825f25d6572f7dfb0c80211a6e3652e2827c5
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
 2020-08-04 13:27:29 +02:00
Mateusz Hoppe c3a128f9f4 Refactor StateBaseAddressHelper 
Change-Id: I5071a1a4a067b8f0e880a4f7e1d65e79eeb77c47
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2020-08-04 11:09:41 +02:00
Mateusz Hoppe 0ed1db0b46 Insert PC before SBA in cmdlist 
Related-To: NEO-4916

Change-Id: I7024ff173ad97d4c42a5fa6d7ea0d0ee665a87d9
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2020-07-31 13:09:57 +02:00
Zbigniew Zdanowicz 2fca4e3477 Refactor programming of additional data of interface descriptor 
Related-To: NEO-4570

Change-Id: I3338046f037878085eddaaeb2c8bbdd821fc1515
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2020-07-24 14:25:39 +02:00
Zbigniew Zdanowicz 134462919d Move barrier programming to Encode class 
Related-To: NEO-4576

Change-Id: I34b93b3118528b449c4e1b81826f9784633377a9
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2020-07-17 14:28:46 +02:00
Mateusz Hoppe ca39301ed8 Reserve SSH space for bindless mode 
Related-To: NEO-4767

Change-Id: Id7876ea5a5a4fc12ab0b3192548b006fc1eea75c
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2020-07-17 13:26:28 +02:00
Zbigniew Zdanowicz bac5506b62 Modify function dispatching cross and per-thread data 
Related-To: NEO-4585

Change-Id: Ia6b54b8d0c868cab5403332411655dc8c9ef4c8d
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2020-07-08 19:30:23 +02:00
Jaime Arteaga 8113fafe53 Disable cross-device indirect access 
Change-Id: I57655abfc02785dfd68384a1546ee4cfdbea938a
Signed-off: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
 2020-06-30 21:42:47 +02:00
Zbigniew Zdanowicz c4cb8c1c81 Add thread programming to Encode class 
Related-To: NEO-4585

Change-Id: I45e57038af23a60f52b57eb1888f8220b77f5e56
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2020-06-29 20:24:26 +02:00
Maciej Plewka a822503b41 Use encoder to program buffer surface state 
Change-Id: Ibe66bd9906743b021a04f1d9aad1aae4127a4f71
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2020-06-25 12:32:29 +02:00
Konstanty Misiak e0f2656513 Move shared tests to the new target [n/n] 
Related-To: NEO-4780

Change-Id: I6b44d45909c9973d2ff18096839550a6d2641b02
Signed-off-by: Konstanty Misiak <konstanty.misiak@intel.com>
 2020-06-23 20:47:54 +02:00
Zbigniew Zdanowicz 77de2dd770 Move SLM functions to HwHelper class 
Related-To: NEO-4585

Change-Id: I073e4138ef34584780a10a63ba8a2eb57eaa11bd
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
 2020-06-09 12:51:49 +02:00
Konstanty Misiak aa8e9fb634 Rename ocl DeviceFixture and add shared tests specific one 
Change-Id: Ib61e987388ba14b721a573e3e84332a7f6c9ef9c
Signed-off-by: Konstanty Misiak <konstanty.misiak@intel.com>
 2020-06-01 15:44:05 +02:00
Mateusz Hoppe 77e4ac0a18 Bindless addressing support in EncodeDispatchKernel 
Related-To: NEO-4607

Change-Id: Ib89b07f71f32c3a623f86212b5305b4aa02e1fb7
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2020-05-12 21:02:06 +02:00
Maciej Plewka 691a4ea823 Add blit copy implementation for L0 
Change-Id: I327a4cf977e166cb648ee9f3a79374f7cefa7b1b
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
 2020-04-09 13:36:09 +02:00
Jaroslaw Chodor 2c25777f3c DispatchKernelEncoder refactor 
Replacing parts of DispatchKernelEncoder with KernelDescriptor

Change-Id: I1c780b04a2d3d1de0fb75d5413a0dde8b41bbe07
 2020-04-08 16:19:21 +02:00
Lukasz Jobczyk 07dc91df72 Use proper FamilyType template argument 
Change-Id: I0f2d132d0e0c9831e1c13266e5131db6123f473d
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2020-04-02 16:10:11 +02:00
Lukasz Jobczyk d1bc7199de Switch to 3D pipeline to program selected commands - part 2 
Resolves: NEO-4447

Change-Id: I1dd6a9694cdf3be19aadec1cd139c466baecbcd7
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
 2020-04-01 10:42:55 +02:00
Mateusz Hoppe 0791b25214 Move cmd parse files to shared directory 
Related-To: NEO-4519

Change-Id: Id055631d68f1d73ae39c4976843080b8f8e05f1c
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
 2020-03-31 23:31:29 +02:00
Filip Hazubski a5c4ad1e2e Remove unnecessary includes from MockDevice files 
Related-To: NEO-3938

Change-Id: I3805bcedcdd95828b79e9b6a6bd572f20234d7de
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
 2020-03-19 21:47:34 +01:00
chmielew e28419fc91 moving ocloc to shared folder 
Change-Id: Ic739cf747f7e6fae2c0cd57f0bc1aa0899d3aa53
 2020-02-27 18:46:00 +01:00
Sebastian Sanchez 61ba7a838f Define MI_MATH greaterThan() function 
Define MI_MATH "greater than" function and simplify code
in encodeGreaterThanPredicate().

Change-Id: Ib1d0a3f712e672f105d0697a105e4d9b14301172
Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
 2020-02-27 10:07:53 +01:00
Sebastian Sanchez 54b2763466 Enforce ALU register type for EncodeMath interface 
General purpose register cannot be used for MI_MATH
calculations. ALU registers must be used.

To prevent passing general purpose register into the
EncodeMath interface, enforce a ALU register type
at compile time.

Change-Id: I98aa8605cde27e7003029d33b3ef3bcfb2306878
Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
 2020-02-27 08:33:04 +01:00
Sebastian Sanchez 1187eb0375 Fix encodeMulRegVal() calculation 
encodeMulRegVal() makes extensive use of encodeAluAdd().

The following problems are addressed:

* encodeAluAdd() performs an addition and saves the
  calculated result to the first register. Saving the
  result to the first register clears the calculated result.

* An array of MI_MATH buffers is setup prior to performing a
  series of encodeAluAdd()'s where the same registers are
  reused for the calculations. For calculated results to be
  carried over from one encodeAluAdd() operation to subsequent
  encodeAluAdd() operations, the MI_MATH buffer needs to be
  setup per encodeAluAdd().

Create EncodeMath<Family>::addition() to reserve a MI_MATH buffer
and performs the addition by calling encodeAluAdd().
Modify encodeAluAdd() to save calculated result to a third
register. Then, after EncodeMath<Family>::addition() is called
in encodeMulRegVal(), copy the calculated result from the result
register to the first register from the EncodeMath<Family>::addition()
operation. This will allow the calculated value to be carried over
to subsequent addition operations.

Change-Id: I9c6f8362a1ca2f7e3361aaa48d8748dd6ff0f4c8
Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
 2020-02-25 14:13:35 -08:00
Mateusz Jablonski 9dbeeea18f Clang-format: restore sorting includes 
Change-Id: I34eb993b562c77f56d8fbd51a02ee266c1f76678
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2020-02-24 10:22:30 +01:00
Mateusz Jablonski ee5ebde417 Add absolute include paths 
Change-Id: I5b8631603b0f0b2ed8eb1a61f7e7770b27867423
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
 2020-02-24 01:21:00 +01:00
kamdiedrich 9e97b42ee6 Reorganization directory structure [4/n] 
Change-Id: Ib868ed62d12ea8f9f123644219ba299e86a658ac
 2020-02-24 01:04:42 +01:00