Граф коммитов

13453 Коммитов

Автор SHA1 Сообщение Дата
Ben Sander ee41609b48 Refactor copy and P2P logic.
Prefer use of source-engine for DMA copies, even if user submits copy
in a stream attached to a different device.
The stream is now used only for synchronization, and HIP
makes the most optimal decision for which engine to perform the
copy - typically the source copy engine.

HIP now makes decision on which engine should perform the copy
and passes this to HCC using new apis.
HIP has additional information about peer
visibility and will make a decision which agent should perform
the copy .

Change-Id: I0cf4cfebeae256e6ca795f08a7ed7130f4857d1f


[ROCm/clr commit: e767e0032e]
2016-11-10 23:12:48 -06:00
Ben Sander ae2992bcb9 Improve memory debug
Change-Id: I0f033139aa4e4b47039eb016e404009127bd0a44


[ROCm/clr commit: e9835617f1]
2016-11-10 23:12:48 -06:00
foreman 6f056b585d P4 to Git Change 1339888 by lmoriche@lmoriche_opencl_dev on 2016/11/10 21:21:17
SWDEV-102510 - Need a way to control cl_khr/cl_amd extension macros
	- Use -cl-ext option to enable OpenCL extensions

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#44 edit


[ROCm/clr commit: 90d4cf8e78]
2016-11-10 21:30:26 -05:00
foreman 88cd2fd02a P4 to Git Change 1339730 by lmoriche@lmoriche_opencl_dev on 2016/11/10 16:37:37
SWDEV-103793 - [ROCm CQE][OCLonLC][ISV] QCDGPU test fails
	- The runtime should not report cl_amd_fp64, cl_khr_fp64 should be used instead.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#9 edit


[ROCm/clr commit: 30a6048658]
2016-11-10 17:04:27 -05:00
pensun 8ea566f2b2 Update depreciated information for threadfence_system()
Change-Id: Id13d2f81edb51eb42b896a5c06913d59ec907c55


[ROCm/clr commit: 9aa2269d5c]
2016-11-10 11:55:12 -06:00
foreman 99bc0b1ba1 P4 to Git Change 1339431 by gandryey@gera-w8 on 2016/11/10 10:47:43
SWDEV-86035 - Add PAL backend to OpenCL
	- Fix a regression after LC path integration

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#24 edit


[ROCm/clr commit: a9885c5273]
2016-11-10 11:02:24 -05:00
Maneesh Gupta df096e871e CMakeLists.txt: Cascade CMAKE_BUILD_TYPE to tests
Change-Id: I53a3ea951c1fd57e43a02381a457c1dedc1a34f7


[ROCm/clr commit: cdcf04d744]
2016-11-10 21:26:34 +05:30
foreman 12616db224 P4 to Git Change 1339294 by johtaylo@johtaylo-jtincrementor-increment on 2016/11/10 03:00:04
SWDEV-2 - Change OpenCL version number from 2270 to 2271.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2017 edit


[ROCm/clr commit: 655d43d311]
2016-11-10 03:13:54 -05:00
Rahul Garg cd7ad3d620 hipDeviceGetByPCIBusId support for HIP/NVCC
Change-Id: I8f82890e88d2a15f592bff192179e7d5c5362722


[ROCm/clr commit: f86c7b5b3c]
2016-11-10 11:40:59 +05:30
Maneesh Gupta d55b32b765 hipcc: Default to HIP_LIB_TYPE=1
Change-Id: I83b05accd76f7bc94bd724c66ae060fa0095bc8d


[ROCm/clr commit: 462ffb8117]
2016-11-10 11:34:00 +05:30
Maneesh Gupta 99678b0000 hcc_dialects/Makefile: use clamp-config
Change-Id: I86df82f75b75125825e22d0545209a19386d9936


[ROCm/clr commit: 052a580d5b]
2016-11-10 11:31:50 +05:30
pensun daf19a2dbb resolve conflicts for git pull
Change-Id: Ie353b831e2241bc28042069b6cc7405257e871e1


[ROCm/clr commit: bbb619c732]
2016-11-09 21:38:43 -06:00
pensun ce1b4bdc06 Add documentation on threadfence_system workaround guidelines.
Change-Id: I9636a3808798f3dabe992285ce5652187cee6eb8


[ROCm/clr commit: 94dfff9db2]
2016-11-09 21:36:30 -06:00
pensun 61635b585f Add option to alloc fingrained system memory
Change-Id: Ia13c8e058cb988b5857e75a590a4d67411362ae1


[ROCm/clr commit: 23de0e1b50]
2016-11-09 21:36:30 -06:00
Maneesh Gupta 68b4d20b26 Merge branch 'rocm-rel-1.3' into amd-develop
Conflicts:
	include/hip/nvcc_detail/hip_runtime_api.h

Change-Id: I990a7d008da9e8dcc68250cebbc8ee6e723c7e01


[ROCm/clr commit: e3b5eef7c9]
2016-11-10 08:56:38 +05:30
foreman b3860e965d P4 to Git Change 1339111 by lmoriche@lmoriche_opencl_dev on 2016/11/09 19:34:29
SWDEV-95488 - Limiting max cap Context on ROCm, it is limited to 100
	- Re-order the member variables to match the initializer list.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#8 edit


[ROCm/clr commit: 1f5d19b75b]
2016-11-09 19:58:26 -05:00
foreman 26f7f88e77 P4 to Git Change 1339076 by scharupa@scharupa_temp on 2016/11/09 18:21:08
SWDEV-95488 -  Replacing gpuDevice_ with roc_device_

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#5 edit


[ROCm/clr commit: 672d37d9b7]
2016-11-09 18:36:38 -05:00
foreman 9322526a03 P4 to Git Change 1339014 by scharupa@scharupa_temp on 2016/11/09 17:18:01
SWDEV-95488 - Fixing build issues

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#8 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#17 edit


[ROCm/clr commit: 18f7cb7b5a]
2016-11-09 17:50:11 -05:00
foreman 01527e35e9 P4 to Git Change 1338994 by scharupa@scharupa_temp on 2016/11/09 16:52:17
SWDEV-95488 - fixing build issues introduced at 1338972

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#7 edit


[ROCm/clr commit: d833468ea5]
2016-11-09 17:30:22 -05:00
foreman 8606cc8f53 P4 to Git Change 1338972 by scharupa@scharupa_temp on 2016/11/09 16:33:58
SWDEV-95488 - Limiting max cap Context on ROCm, it is limited to 100

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.cpp#204 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#279 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocsettings.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#16 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.hpp#4 edit


[ROCm/clr commit: 2d64dbab44]
2016-11-09 17:07:33 -05:00
pensun 85fa855e18 fix hipProfiler* apis on NV path
Change-Id: I6adca6151fef3a9b35348163eb6bd13f5c414172


[ROCm/clr commit: 4a8a6a4697]
2016-11-09 15:44:01 -06:00
pensun 12a5923a2b fix for hipcallback function on NV path
Change-Id: If80c0cfe60b1f3b1a71627b5f3f79503cba4d491


[ROCm/clr commit: e5277ab4b6]
2016-11-09 11:33:23 -06:00
foreman 5e63fbe507 P4 to Git Change 1338735 by gandryey@gera-w8 on 2016/11/09 10:46:19
SWDEV-86035 - Add PAL backend to OpenCL
	- Enable split logic in PAL

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#38 edit


[ROCm/clr commit: 621f70b372]
2016-11-09 10:55:17 -05:00
foreman ae239a55ee P4 to Git Change 1338576 by johtaylo@johtaylo-jtincrementor-increment on 2016/11/09 03:00:05
SWDEV-2 - Change OpenCL version number from 2269 to 2270.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2016 edit


[ROCm/clr commit: 0428dca9f2]
2016-11-09 03:12:34 -05:00
foreman c59607b856 P4 to Git Change 1338072 by wchau@wchau_WIN_OCL_HSA on 2016/11/08 10:02:39
SWDEV-95007 - OpenCL on PAL - DVR

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#14 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevicegl.cpp#3 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.hpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#16 edit


[ROCm/clr commit: 94bf561bd7]
2016-11-08 10:11:21 -05:00
Maneesh Gupta ded929878c Update release notes for 1.0 release
Change-Id: I74fa2b41afc334a76c309b125c27aa141cd59554


[ROCm/clr commit: 01a38c82a6]
2016-11-08 16:31:56 +05:30
foreman 64eb9eb9b9 P4 to Git Change 1337979 by johtaylo@johtaylo-jtincrementor-increment on 2016/11/08 03:00:04
SWDEV-2 - Change OpenCL version number from 2268 to 2269.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2015 edit


[ROCm/clr commit: 79459fbd6d]
2016-11-08 03:12:47 -05:00
foreman 2de09599ad P4 to Git Change 1337788 by asalmanp@asalmanp-opencl-stg on 2016/11/07 17:39:47
SWDEV-95903 - Fixing a regression in Conf RQ on Vega10 introduced by CL#1333973. The SVM size was changed from 4096 MB to 16384 MB in this CL and causing a memory allocation failure (out of VA space) when running conformance (test_basic). Change the size back to 4096 MB for now to unblock testing Vega10 with OCL ToT.
	ReviewBoardURL = http://ocltc.amd.com/reviews/r/11775/

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#260 edit


[ROCm/clr commit: 12242ad8de]
2016-11-07 17:49:07 -05:00
foreman 2b284193ab P4 to Git Change 1337771 by gandryey@gera-w8 on 2016/11/07 17:16:58
SWDEV-106509 - [CQE OCL][OpenCL on PAL][QR] 3 Conformance tests are failing/crashing
	- Add missing constant argument into the qualifiers lookup
	- Initialize rtCU count to the internal constant

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#33 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#23 edit


[ROCm/clr commit: 7f539761ca]
2016-11-07 17:32:56 -05:00
foreman ee6eeddee1 P4 to Git Change 1337394 by johtaylo@johtaylo-jtincrementor-increment on 2016/11/07 03:00:04
SWDEV-2 - Change OpenCL version number from 2267 to 2268.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2014 edit


[ROCm/clr commit: 3459794cb3]
2016-11-07 03:08:11 -05:00
Ben Sander 3d4a76d560 Fix tests to read warpSize from device props.
Change-Id: I9583577793afad49f9eb1ee9069bd4c6963a6023


[ROCm/clr commit: a13ec441bf]
2016-11-06 04:26:28 -06:00
Ben Sander 445f888d97 Update gitignore for some common output files
Change-Id: I9cd60f042af4dba07fe0fdbd2ee442936ff8c7bd


[ROCm/clr commit: 0e5cfed3eb]
2016-11-06 04:26:15 -06:00
Ben Sander 03fcf556e9 Improve Peer support and testing.
Change-Id: Icadc65988aaf145a265587ab0357c5bf4d26f3eb


[ROCm/clr commit: f3d38c2615]
2016-11-06 03:22:36 -06:00
foreman bff4a7cd44 P4 to Git Change 1337201 by johtaylo@johtaylo-jtincrementor-increment on 2016/11/06 02:00:04
SWDEV-2 - Change OpenCL version number from 2266 to 2267.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2013 edit


[ROCm/clr commit: 4d705d6ca0]
2016-11-06 02:06:11 -05:00
foreman d3c10e1af2 P4 to Git Change 1337110 by johtaylo@johtaylo-jtincrementor-increment on 2016/11/05 03:00:03
SWDEV-2 - Change OpenCL version number from 2265 to 2266.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2012 edit


[ROCm/clr commit: 0d9068fa5a]
2016-11-05 03:11:03 -04:00
Ben Sander 0af2722827 Set forceHostCopyEngine for other copy dirs. Support HIP_FORCE_P2P_HOST
Also: more debug for copy and P2p.

Change-Id: I87030c525410e041b2a00baaf6c68e6c0977ff42


[ROCm/clr commit: 06ecfa3975]
2016-11-04 19:53:23 -05:00
foreman 998266c90f P4 to Git Change 1337009 by gandryey@gera-w8 on 2016/11/04 18:04:52
SWDEV-79445 - OCL generic changes and code clean-up
	- Use uint64_t for the scratch buffer size calculation

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#558 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#162 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.cpp#175 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gslbe/src/rt/GSLDevice.h#63 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#32 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#13 edit


[ROCm/clr commit: b8040b3d6a]
2016-11-04 18:18:13 -04:00
Ben Sander 2bf51afaa1 Expand hipP2PSimple testing.
Cover cases where P2P is used for H2D copies, where host is pinned
but not accessible to the copy agent.

Change-Id: I9464b787228b40f93473708c3fde9726e1986365


[ROCm/clr commit: 60a8a5405d]
2016-11-04 16:13:32 -05:00
Ben Sander 06b9391974 Refactor resolve-mem step1
Change-Id: I7b8b2bbb56d7b31a97b48ebd42002641cd07a460


[ROCm/clr commit: 926e63c655]
2016-11-04 09:37:56 -05:00
Ben Sander 74c9c6e591 Add debug for Peer APIs. Enable PeerMemcpy APIs by default.
Change-Id: I46e39a9e7b07686a78484c1f3b5495b08e052fbb


[ROCm/clr commit: 00276d141e]
2016-11-04 08:51:16 -05:00
Ben Sander 43723d77cc Print non-peers too
Change-Id: I2a6905edcdf144aa732ae3120c17780477f232ac


[ROCm/clr commit: 44aee4b61c]
2016-11-04 06:34:07 -05:00
Ben Sander 97d9a5722e Pre-pend HIP_PATH/lib to linker, so we find developer object code
Previously might pick up libs from /opt/rocm/lib.

Change-Id: Ia7adb345defe433d5952aa61706fe03fd7cbcd35


[ROCm/clr commit: d1db786910]
2016-11-04 06:06:04 -05:00
foreman a1f425887c P4 to Git Change 1336502 by johtaylo@johtaylo-jtincrementor-increment on 2016/11/04 03:00:03
SWDEV-2 - Change OpenCL version number from 2264 to 2265.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2011 edit


[ROCm/clr commit: 0794d6b50b]
2016-11-04 02:06:26 -05:00
foreman 6d277ef77e P4 to Git Change 1336353 by lmoriche@lmoriche_opencl_dev on 2016/11/03 18:47:50
SWDEV-105604 - [OCL-LC-PAL] OpenCL program manager for LC on PAL
	- Finish the implementation of the program manager to support separare compilation and binary loading.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.hpp#13 edit


[ROCm/clr commit: 065133bbc0]
2016-11-03 18:56:31 -04:00
foreman 5a2827406e P4 to Git Change 1336294 by gandryey@gera-w8 on 2016/11/03 17:50:35
SWDEV-86035 - Add PAL backend to OpenCL
	- Use size() method in the segment freeze instead of vmSize(), because vmSize() is aligned in PAL and different heaps may have different alignments

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#21 edit


[ROCm/clr commit: 30b62e264c]
2016-11-03 18:14:18 -04:00
foreman bad810bb2f P4 to Git Change 1336110 by gandryey@gera-w8 on 2016/11/03 15:21:09
SWDEV-86035 - Add PAL backend to OpenCL
	- Update printf initialization to match the GSL backend

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palkernel.cpp#22 edit


[ROCm/clr commit: 4d82398e1f]
2016-11-03 15:41:39 -04:00
foreman e8886648c6 P4 to Git Change 1335811 by lmoriche@lmoriche_opencl_lc on 2016/11/03 03:28:18
SWDEV-105604 - [OCL-LC-PAL] OpenCL program manager for LC on PAL
	- Fix the corrupted HSACO file when using -save-temps/-save-temps-all on Windows.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcompiler.cpp#10 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#20 edit


[ROCm/clr commit: 9227e8ede5]
2016-11-03 02:35:28 -05:00
foreman 7de2ef329d P4 to Git Change 1335796 by johtaylo@johtaylo-jtincrementor-increment on 2016/11/03 03:00:11
SWDEV-2 - Change OpenCL version number from 2263 to 2264.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2010 edit


[ROCm/clr commit: 99b5c92998]
2016-11-03 03:11:48 -04:00
pensun 8911a02b17 Update document for workaround suggestion on threadfence_system()
Change-Id: Icccab8270604a0e578a8614b9afb3f95372f4966


[ROCm/clr commit: 212fa7033c]
2016-11-02 16:08:27 -05:00
foreman 99fbf62c0f P4 to Git Change 1335201 by johtaylo@johtaylo-jtincrementor-increment on 2016/11/02 03:00:03
SWDEV-2 - Change OpenCL version number from 2262 to 2263.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2009 edit


[ROCm/clr commit: 5208f758c7]
2016-11-02 03:06:44 -04:00