Commit Graph

12401 Commits

Author SHA1 Message Date
foreman 1197b3c361 P4 to Git Change 1319074 by gandryey@gera-w8 on 2016/09/26 19:39:26
SWDEV-101621 - [CQE OCL][OpenCL on PAL] 6 WF Conformance tests are failing
	- Some tests may call syncFromCache and if SDMA can't perform that transfer kernel will be used. Kernel used in the transfer may break memory dependency tracking, because sync is done during memory objects processing. Use local variable for memory list and add mem objects to the tracker at the end of processMemObjectsHSA()

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#24 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#12 edit
2016-09-26 19:48:04 -04:00
Ben Sander f6717e326e Fix signal resource issue.
Remove memory leak with new hc::completion_future.
Implement HIP_LAUNCH_BLOCKING with queue-level wait.

Change-Id: I45975f81c4d239fdeed7776970988d28449865dc
2016-09-26 16:47:32 -05:00
Ben Sander 061bcc6a5c Small tool, doc, sample enhancements.
- Expand message when HIP version mismatch detected.
- Doc touchup.
- change sorting of hipBusBandwidth so byte results shown at top.
-

Change-Id: Ifb4e44a5fdfb65d59c4994b11e5f13385705f7e0
2016-09-26 16:36:01 -05:00
pensun 5bdb9e349c fix of HIPCC on libc++ option on HCC path
Change-Id: Ie0d3213a165fa13f033b777b490eb60b980d02da
2016-09-26 14:39:57 -05:00
Rahul Garg 3d1a61f1d9 Doxygen documentation changes for hipCtxXXX APIs
Change-Id: I1e5e3a621b732bd8bdeef1c607c004d6adfdab32
2016-09-26 23:11:07 +05:30
Rahul Garg 25e9308831 Doxygen related document updates for texture/ array related functions
Change-Id: Iedc5b6512b5ddecb98c0e51a353957f08b955fde
2016-09-26 16:18:53 +05:30
foreman 1064863737 P4 to Git Change 1318652 by johtaylo@johtaylo-jtincrementor-increment on 2016/09/26 03:00:04
SWDEV-2 - Change OpenCL version number from 2225 to 2226.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1972 edit
2016-09-26 03:11:51 -04:00
Rahul Garg c313836013 Removed deprecated hipHostAlloc
Change-Id: Ia592a3545c5d72f37e049ce29f910e404323c01c
2016-09-26 10:58:46 +05:30
Rahul Garg f5b463702e Removed deprecated hipMallocHost
Change-Id: I3141fe05a34b6a306297a30721509965f49ccb97
2016-09-26 05:52:21 +05:30
Rahul Garg 3a6acd044b Removed deprecated hipFreeHost
Change-Id: I9747ea3993090e0da6a2e1f5e9ce318762bc03e1
2016-09-26 05:35:14 +05:30
foreman 1f0499f75b P4 to Git Change 1318553 by johtaylo@johtaylo-jtincrementor-increment on 2016/09/25 03:00:05
SWDEV-2 - Change OpenCL version number from 2224 to 2225.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1971 edit
2016-09-25 03:11:23 -04:00
foreman 8d50678adb P4 to Git Change 1318482 by johtaylo@johtaylo-jtincrementor-increment on 2016/09/24 03:00:07
SWDEV-2 - Change OpenCL version number from 2223 to 2224.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1970 edit
2016-09-24 03:10:04 -04:00
foreman 0fb0fb1d8b P4 to Git Change 1318412 by lmoriche@lmoriche_opencl_dev on 2016/09/23 17:57:01
SWDEV-94610 - Remove the padding at the end of the kernargs (It was for the hidden arguments, but now, LC reports the correct size). Set the LLVM triple to amdgcn-amd-amdhsa-opencl when building the built-in library.

Affected files ...

... //depot/stg/opencl/drivers/opencl/opencldefs#186 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#20 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocprogram.cpp#37 edit
2016-09-23 18:18:01 -04:00
foreman 27bc59ab60 P4 to Git Change 1318397 by gandryey@gera-rcf-lnx on 2016/09/23 17:46:56
SWDEV-86035 - Add PAL backend to OpenCL
	- Fix more strict compilation rules in C++11

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/pal/build/Makefile.pal#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palcounters.hpp#7 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevicegl.cpp#2 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palresource.cpp#12 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palsettings.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palthreadtrace.hpp#4 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#11 edit
2016-09-23 18:05:10 -04:00
foreman 6e1e293bd7 P4 to Git Change 1318204 by gandryey@gera-w8 on 2016/09/23 13:14:59
SWDEV-86035 - Add PAL backend to OpenCL
	- Avoid malloc()/free() calls during the dispatch

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#161 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.hpp#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#23 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#10 edit
2016-09-23 13:29:09 -04:00
Maneesh Gupta da6183a194 hip_tests: Scan for tests recursively in tests/src
Change-Id: I0297e6c94de3ea446ce99cce0aa641e74dad0d13
2016-09-23 22:42:52 +05:30
Maneesh Gupta 9216464861 directed tests: Enabled top-level uncategorized tests in HIT
Change-Id: If37cbd00244ebfa0e5bff8362820aa68aaa163f1
2016-09-23 16:15:31 +05:30
Maneesh Gupta a8a8ebed10 HIT: Fix logic in HIT_ADD_DIRECTORY_RECURSIVE
Change-Id: I066787aaeec2a1562aa36527e60291594da31f83
2016-09-23 15:13:12 +05:30
Maneesh Gupta 121edb35d9 Add target test that uses HIT to the top-level HIP cmake
Change-Id: Idae1c0b39e6c4deb9f8fdb192bab17b0904941d7
2016-09-23 14:46:48 +05:30
Maneesh Gupta f82e26bbe2 Initial implementation of HIT infrastructure
Change-Id: Icaef40cca67715fe3ec4ce3479d0f80f391f3917
2016-09-23 14:44:51 +05:30
foreman 7f531afdb4 P4 to Git Change 1317944 by johtaylo@johtaylo-jtincrementor-increment on 2016/09/23 03:00:05
SWDEV-2 - Change OpenCL version number from 2222 to 2223.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1969 edit
2016-09-23 03:18:40 -04:00
Maneesh Gupta 6254131dfd CMakeLists.txt: No need to define HIP_HCC
Change-Id: I0aa149bf3ffd4ee665bf3b822e178b3d74efe2af
2016-09-23 10:44:39 +05:30
Maneesh Gupta b088ca2a53 hipcc: Don't try to linking unpinned_copy_engine
Change-Id: Iaa4d8b4f6dbb7940bba553f82c157a2ee9468c9e
2016-09-23 10:43:09 +05:30
foreman c5b3373da2 P4 to Git Change 1317781 by lmoriche@lmoriche_opencl_dev on 2016/09/22 19:28:45
SWDEV-94610 - Add runtime support for Printf. Parse the metadata strings and build the PrintInfo structure expected by the runtime.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/amdgpu_metadata.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/amdgpu_metadata.hpp#5 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.cpp#16 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rockernel.hpp#10 edit
2016-09-22 19:35:10 -04:00
Ben Sander 944d4eaa18 Peer-to-Peer improvements.
- Bug fix for peer visibility.  Now contexts correctly detect when they can use SDMA for P2P vs staging buffers.
- Interface to new HCC copy_ext function.
- Improve context and peer print /debug options.
- Add comments and usage to hipPeerToPeer_simple test.
2016-09-22 14:21:19 -05:00
Ben Sander a397e60ba9 Add kind translation for hipMemcpyDeviceToDevice 2016-09-22 14:21:19 -05:00
Ben Sander fd6c09602f Fix HIP_INIT_API and ihipLogStatus calls 2016-09-22 14:21:19 -05:00
Ben Sander 926aefa930 Remove unpinned_copy code. Other cleanup.
Change-Id: Ie3f71439cf1ba729ef223d078917c403d3de879a
2016-09-22 14:21:19 -05:00
Ben Sander 5bc18c8603 Cleanup. Remove cfs, ihipSignal_t, staging buffer calls.
Change-Id: I8bb67c484e3a65be06a03665f059217930da2bed
2016-09-22 14:21:19 -05:00
Ben Sander 17e21309f1 Cleanup: Remove HIP signal pool.
Change-Id: Icebfd0509d12396cc5933d5556d68b53e1be36e0
2016-09-22 14:21:19 -05:00
Ben Sander c365785c5c Remove HIP command dependency tracking.
Change-Id: I991c13bc5108193959ba70f9f6f9c692c9ad3a5b
2016-09-22 14:21:19 -05:00
Ben Sander b0509c5a58 Cleanup, remove preCopyCommand.
Change-Id: I3768d3789a99be8136b43179d4152fa1875665cb
2016-09-22 14:21:19 -05:00
Ben Sander 3596901c3d Change HIP async copy to call av::copy_async.
Change-Id: I4274b63ced3940d5249c32bd9d156296529c70e8
2016-09-22 14:21:19 -05:00
Ben Sander 8598d8c6d3 Use HCC's synchronous accelerator_view::copy
Replace large block of HIP code with a call to HCC av::copy().

Change-Id: Ic32e1801cf8d4cd116ac02b72c41b1a1e4b6065c
2016-09-22 14:21:19 -05:00
Ben Sander 60f797cc5a Remove USE_AV_COPY, USE_PEER_TO_PEER fallback paths.
Change-Id: I9c20173e62029c4caebabc98784c6d7697758e4f
2016-09-22 14:21:19 -05:00
Ben Sander 39750da9a5 Remove HIP_STAGING_BUFFER
Code simplification/cleanup:
Remove stale fallback paths that uses something besides the unpinned engine.
Remove HIP_STAGING_BUFFER env var - now is const 2, 0 no longer has
special meaning.

Change-Id: I7d24cdd1067dd0c244e87b6a83897cb135d307e7
2016-09-22 14:21:18 -05:00
Ben Sander 271e2357e0 Fix bugs for different CopyModes
Change-Id: Ie59fb3b36a9ff2de178307a6d5756b5c71e0306b
2016-09-22 14:21:18 -05:00
Ben Sander 17d7fc586e Move isLargeBar to UnpinnedCopyEngine constructor.
Change-Id: I7a7d3a40b1d4e0c6ec856658a6a70e5e70d287ce
2016-09-22 14:21:18 -05:00
Ben Sander 77c86934c1 Refactor Staging Buffer CopyDeviceToHost
Use copyMode.  Embed algorithm selection inside the unpinned class.

Change-Id: Ic75fd5931717a3160904402794bbed3ccd445112
2016-09-22 14:21:18 -05:00
Ben Sander e77d75c1c1 Refactor staging buffer CopyHostToDevice.
- Move algorithm selection inside Unpinned class.
- Refactor function names.
- Use size_t for size threshholds.

Change-Id: Iac4de652ac9d49acbf527aa0849e388b8ecd8486
2016-09-22 14:21:18 -05:00
Ben Sander e8beacbfb1 Sample improvements.
- Enable -O3 for hipDispatchLatency.
- Use nearly-null kernel to prevent it from being optimized away.
- Formatting for hipDispatchLatency.
- Formatting for hipInfo.
2016-09-22 13:05:47 -05:00
Ben Sander 6126d73778 Doc update for faq. 2016-09-22 13:05:47 -05:00
Ben Sander 7ec4b65786 Doc update: release reminder, compare hip against other porting tools. 2016-09-22 13:05:47 -05:00
Ben Sander b4bc101c96 Updates docs for hipHcc* functions, move to header 2016-09-22 13:05:47 -05:00
Aditya Atluri 470a1583d1 added ipc runtime api for nvcc backend
Change-Id: I3297c4c9db34e7bc3267fec64a6757f9ebf91905
2016-09-22 12:55:41 -05:00
Aditya Atluri c0babe6b0a Fixed typo in function return
Change-Id: I8905bfdbc162815ac10c926e77a9bab432932c9c
2016-09-22 09:30:05 -05:00
Maneesh Gupta e51e268f24 Fix bug in defining HIP_VERSION_*
Change-Id: I52fcd78386ee4b5035aba4c9bced3372b7894650
2016-09-22 16:32:05 +05:30
Rahul Garg 86e441c769 Added hipRuntimeGetVersion function
Change-Id: I59ec2beacb5a94439deed0dcc8eb37d6de1cc900
2016-09-22 15:21:23 +05:30
foreman 4dd808cd6d P4 to Git Change 1317395 by johtaylo@johtaylo-jtincrementor-increment on 2016/09/22 03:00:04
SWDEV-2 - Change OpenCL version number from 2221 to 2222.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1968 edit
2016-09-22 03:11:20 -04:00
Maneesh Gupta ba9d9708f7 Expose HIP_VERSION_* to HIP source and HIP applications
Change-Id: I6fb0d6711642c4fad2cd89b98707ee4b548b7243
2016-09-22 12:27:07 +05:30