AI/rocm-systems
2
0
Rozštěpit 0
Zdrojový kód Úkoly Pull requesty Akce Balíčky Projekty Vydání Wiki Aktivita
13 197 Commity 3 Větve 0 Značky
f6c8bbf4dcc2ec0022ea4faa5a9d75afb2a58a11
Graf commitů

13197 Commity

Tato větev
Tato větev
Všechny větve
Autor SHA1 Zpráva Datum
Aaron En Ye Shi b6a8d471fb Merge "Make HIP C compliant" into amd-master-next 2020-05-05 13:54:24 -04:00
Christophe Paquot 3dfa56ac5c Merge "SWDEV-234029 - Remove module from module_map_ @ hipModuleUnload" into amd-master-next 2020-05-05 12:56:51 -04:00
Rahul Garg 19f7508bda Make HIP C compliant 
Change-Id: Ic2fa650675e68200c841ce3db622da836b169f33
 2020-05-05 12:49:40 -04:00
Saleel Kudchadker 0fbc0a895b Disable small copy optimization for now 
Change-Id: Ib7a4aa676bb60940e067c985eb19070bd63b2fc2
 2020-05-05 11:52:42 -04:00
kjayapra-amd 8931ac106c SWDEV-209747 - Enable DevLogs on DEBUG or DEV_LOG_ENABLE Compiletime var 
Change-Id: Ie5b7855c469f03947b680d4844c1657cbae55b11
 2020-05-05 09:55:54 -04:00
Karthik Jayaprakash 252b402ebc Merge "SWDEV-232464 - Memory Map modules loaded via file from hipModuleLoad" into amd-master-next 2020-05-05 09:20:14 -04:00
German Andryeyev c4c5f00fd4 Merge "Avoid null stream allocation in hipFree" into amd-master-next 2020-05-05 08:23:38 -04:00
Chauncey Hui 339a830bc0 SWDEV-2 - Change OpenCL version number from 3135 to 3136 2020-05-05 03:00:04 -04:00
kjayapra-amd 55826ac474 SWDEV-234029 - Remove module from module_map_ @ hipModuleUnload 
Change-Id: Ic01fdb88c658c68298bd51cab2da21dc3ff0e1f7
 2020-05-04 20:05:42 -04:00
Aaron En Ye Shi af618b3363 Merge "Add __HIP_VDI__ to hipconfig host flags for VDI" into amd-master-next 2020-05-04 19:07:28 -04:00
German Andryeyev fca05eae5f Avoid null stream allocation in hipFree 
- Add option to skip stream allocation on access.
- Avoid null stream allocation in ihipFree, so an inactive device
won't be initialized

Change-Id: Id24426640df59a5e7a08b2dd9dcd4d67758b84bf
 2020-05-04 17:17:36 -04:00
Aaron Enye Shi eb42a165b4 Add __HIP_VDI__ to hipconfig host flags for VDI 
Change-Id: Ia9582f2d51b50cbe151b4866ffbfc9514825f613
 2020-05-04 20:03:07 +00:00
Vlad Sytchenko b5fe52677e Fix even more typos from 53dd6b7a66 
Change-Id: I4f44261547b321a214348943ff5117eb5bd55b06
 2020-05-04 15:26:56 -04:00
kjayapra-amd 347e36e31b SWDEV-232464 - Memory Map modules loaded via file from hipModuleLoad 
Change-Id: I0e644a161c8000abe1b07fbec72de09f1c0a4b18
 2020-05-04 12:40:16 -04:00
kjayapra-amd 8e42d76c06 SWDEV-232464 - Memory Map modules loaded via file from hipModuleLoad 
Change-Id: Ibef8c28b764b8551529212d99a777ae5fe2dffda
 2020-05-04 11:46:59 -04:00
Christophe Paquot 2ff8f533a4 Merge "SWDEV-216213 - Delete kernel function_ in hip::Function destructor" into amd-master-next 2020-05-04 11:36:52 -04:00
Aaron En Ye Shi a131af098a Merge "find_package(hip) changes for clang" into amd-master-next 2020-05-04 10:19:51 -04:00
kjayapra-amd ac37f78acb SWDEV-216213 - Delete kernel function_ in hip::Function destructor 
Change-Id: I0f6c44927f453ac63b5b84552a5fba07f04a8a8e
 2020-05-03 23:08:58 -04:00
Vlad Sytchenko b848cf085a Fix invalid check in hipTexRefGetAddressMode() 
This resolves https://github.com/ROCm-Developer-Tools/HIP/issues/2048.

Change-Id: Iba3653b011434a450a5c3ce10cfd4aa39d318527
 2020-05-03 14:48:32 -04:00
kjayapra-amd 8d6478a051 SWDEV-231874 - Make hipMemset patten size 8byte aligned when possible 
Change-Id: Ida98bd89212af9b00f3c9c7c5d22ae81f3b5396a
 2020-05-01 23:04:04 -04:00
Alex Xie 044a7e55ad SWDEV-221166 - Detect support for large bar access through HIP runtime API 
Change-Id: Iaa9756c1b5e40c1ab5afb38e44a6699fa5f6c13f
 2020-05-01 20:39:52 -04:00
Michael Hong Bin Liao a94de6d463 Merge "Fix more typos from 53dd6b7a669e78035dffcd138053f7413d48d736." into amd-master-next 2020-05-01 19:35:53 -04:00
agodavar ce8a5af666 find_package(hip) changes for clang 
Change-Id: I9dc1be1dd5f9424e26ebcd2961207e1c4467550f
 2020-05-01 20:48:32 +00:00
Matt Arsenault 80bc98afee Fix installing generated header to include/include 
This isn't the ideal solution, but a lot more cleanups are needed for
how install is used.

Change-Id: I63a9c1a46d0da13ee4373038ece228005207271a
 2020-05-01 12:43:49 -04:00
Michael LIAO 6bfedf1a1d Fix more typos from 53dd6b7a66. 
Change-Id: I75ed28a5862daffc0778910d7ba3b97f51a87949
 2020-05-01 12:19:30 -04:00
Matt Arsenault 36432be962 Don't directly link pthreads 
This was already searching for the right threads library, but ignoring
the result.

Change-Id: I10d898245696135c1ef928c7715efce8ec6b939f
 2020-05-01 08:28:36 -04:00
Matt Arsenault b618939e2e Don't emit generated hip_prof_str.h to source directory 
The build should never touch the source directory, and only write
generated files to the output directory.

Also track the dependency with a custom command and target, as is the
normal method for dependencies on generated files.

Change-Id: I9d835256c643aeef241d26ca05ab390ebba65111
 2020-05-01 08:24:56 -04:00
Chauncey Hui 6d0fa49c5d SWDEV-2 - Change OpenCL version number from 3134 to 3135 2020-05-01 03:00:03 -04:00
Payam 94b203235e name change vdi to rocclr 
Change-Id: I59650f7082dd118c1fe92309b76a5bdb20eee3c1
 2020-04-30 19:06:58 -04:00
Matt Arsenault bd4ec781f2 Find python to generate prof API headers. 
Don't rely on shell commands. On Ubuntu 20.04, /usr/bin/python no
longer exists, so I'm seeing some failures from somewhere assuming the
path.

The top level CMakeLists also repeats exactly this, which should be
fixed.

Change-Id: I56b26742920f0dc40b363b409892bd41cfa485ef
 2020-04-30 18:21:03 -04:00
Aaron En Ye Shi c1d5ba1d0a Merge "Update hipcc to use HIP_COMPILER variable" into amd-master-next 2020-04-30 17:31:33 -04:00
Michael Hong Bin Liao 977efb14c6 Merge "[vdi] Skip null texture object in hipDestroyTextureObject." into amd-master-next 2020-04-30 16:07:58 -04:00
Aaron Enye Shi c729d52681 Update hipcc to use HIP_COMPILER variable 
This will update the hipcc script so that it will use HIP_PLATFORM, HIP_COMPILER, and HIP_RUNTIME variables correctly based on updated hipconfig file.

Removing HIP_PLATFORM=clang, only use hcc and nvcc for now. HIP_PLATFORM should eventually switch to amd or nvcc.

Change-Id: Ie527d07a1add974cc3aab8e9f61b0518147d7602
 2020-04-30 15:31:20 -04:00
German Andryeyev 7302ebcfbc Optimize synch operations 
- Stall the queue only for HSA copy operations

Change-Id: Ia3debcc0f36284c5f8cd2776d31674f3aeed04ea
 2020-04-30 11:17:48 -04:00
Alex Xie 6c5a42b33c SWDEV-232894 Port hipMemcpy optimizations from HCC to VDI 
Apply the optimization to change for OpenCL too.
Clean up some unnecessary checks.

Change-Id: I840261fe35baeeadeba7388e86779d482f509aad
 2020-04-30 11:06:28 -04:00
Chauncey Hui 1de8abd031 SWDEV-2 - Change OpenCL version number from 3133 to 3134 2020-04-30 03:00:03 -04:00
Payam Ghafari aa950adc73 Merge "renaming vdi to rocclr, part 1" into amd-master-next 2020-04-29 19:42:20 -04:00
Vlad Sytchenko e97809ca7a Merge branch 'amd-master-next' into amd-npi-next 
Change-Id: Icd651e93f0c28eb2859f4997377379d0698ce84e
 2020-04-29 18:54:58 -04:00
Vlad Sytchenko d420baf664 Fix order initialization warning 
Change-Id: I77ddf1dbec2d11c273163efae6526d3deca92dbf
 2020-04-29 18:52:41 -04:00
Laurent Morichetti 4591b7469e Don't make a copy of the embedded device binaries 
Embedded device binaries should not be cloned if we want the ROCR's
code object URI for this binary to point to the container (host
executable or shared library) instead of a memory location.

Depends-On: I7973bb0243f5a2d1b639b8a88445cfe6af919dd7
Change-Id: Id3afc981e027e5371114d011f2caaa6414f5fc58
 2020-04-29 18:40:18 -04:00
Laurent Morichetti 9e1964ddaa Make the device binary copy optional 
Device binaries that are embedded inside the host binary do not
require a copy. Their lifetime is guaranteed to exceed that of the
loaded executable.

Add a 'make_copy' parameter to amd::Program::addDeviceProgram. If
make_copy is false the original image will be used and will not
get freed when the amd::Program is destroyed.

Change-Id: I7973bb0243f5a2d1b639b8a88445cfe6af919dd7
 2020-04-29 18:39:57 -04:00
Payam cb7d3227e8 renaming vdi to rocclr, part 1 
Change-Id: Idec9be2b6174217abcebaa1776e59168670740b1
 2020-04-29 17:54:37 -04:00
Saleel Kudchadker f52b2d4504 Fix error code when hipEventRecord is not called 
Change-Id: I6672d4320280fd87fd2786bc54214d40944da845
 2020-04-29 13:13:52 -04:00
Michael LIAO db4bcda1bf [vdi] Skip null texture object in hipDestroyTextureObject. 
- To match both CUDA and HCC runtime behavior.

Change-Id: I072b006dd554e17f8341f391d33bf6224a125a7e
 2020-04-29 12:20:42 -04:00
Christophe Paquot b54c3f7db9 Couple of cleanups. 
Remove queue limitation since we loop through HW queues now.
Add a DevLogError if we fail to create the hsa_queue. A ticket showed a regression there.

Change-Id: I4f58e405f88e75600a762f6d6352838c969cdb5e
 2020-04-29 09:18:07 -07:00
German Andryeyev bc65ca64fc Clean-up the list of blocking streams 
- Insert the stream into the list on the host queue creation,
instead of stream creation

Change-Id: Ib25053019f7df97e5bc786922a6587b9514852d3
 2020-04-29 11:37:43 -04:00
Chauncey Hui 860ba6f0a1 SWDEV-2 - Change OpenCL version number from 3132 to 3133 2020-04-29 03:00:03 -04:00
Vlad Sytchenko 89b9befe42 Fix order initialization warning 
Change-Id: I77ddf1dbec2d11c273163efae6526d3deca92dbf
 2020-04-28 20:07:51 -04:00
Saleel Kudchadker 5f64e6e7ad Add a threshold for forcing ROCr to take blit path 
This workaround is to avoid performance penalty of SDMA engine
taking a while to clock up from a lower DPM state. Add env var
GPU_FORCE_BLIT_COPY_SIZE (1024 by default for HIP in KB). Forcing
Src and Dst agent to be amdgpu makes ROCr take blit copy path for
what otherwise should have been SDMA copy

Change-Id: I222f687155f86000d17d66d25182e490b6710463
 2020-04-28 17:11:24 -04:00
Matt Arsenault 585741a040 Use find_package to find rocclr 
Maintain compatability with current hardcoded scheme for now for
commit order convenience.

Change-Id: I0b8299fceab1cc405ae5f26a129f2f1ea3d56773
 2020-04-28 16:41:53 -04:00