提交線圖

233 次程式碼提交

作者 SHA1 備註 日期
Aditya Atluri 8580bba30c correct cachesize to output correct value
Change-Id: I5db031591eb718b0c12e78a35e4b19349de9526d


[ROCm/hip commit: 820a914b98]
2016-10-25 09:33:45 -05:00
Ben Sander 548a902c4b Fix P2P for async
Also improve HIP debug message: Add more DB_COPY1 messages. memcpyStr,
expand HIP_DB bitmask.


[ROCm/hip commit: 203348ac9b]
2016-10-20 10:02:23 -05:00
Ben Sander 56cc2e3deb Add HIP_WAIT_MODE env var.
Also weaken cases where hipSetDeviceFlags returns hipErrorInvalidValue.

Change-Id: I7f113338be6fe498eaf1ab40fd0fd6b23849bb5e


[ROCm/hip commit: 000d75de95]
2016-10-18 22:27:16 -05:00
Ben Sander 02123ae867 Add hipDeviceSchedule* support to queue wait
Change-Id: Iffa7a356500b026f3737c3f5719ca9f62b10d855


[ROCm/hip commit: 261ff423e1]
2016-10-18 22:27:16 -05:00
Ben Sander 35801146d2 Remove some TODO items
Change-Id: I7e9de2e43a8584f8dc9ee6d45c8ed00ca465f591


[ROCm/hip commit: d21d3ec222]
2016-10-18 22:27:16 -05:00
Ben Sander c11b6f511b Move some internal headers from "include/hip/" to src.
Change-Id: I7041bd5c803d9318979f4a7c1d658445c614691e


[ROCm/hip commit: 9315ac1a29]
2016-10-18 22:27:16 -05:00
Maneesh Gupta dd60b971d1 src/*: Update copyright header
Change-Id: I455f5d0d12fe9cb39a3ba873bd22b4c25ed07cbf


[ROCm/hip commit: 8471682f26]
2016-10-15 22:55:22 +05:30
Ben Sander a76cc1e850 Cleanup files from code review.
- Remove some stale code
- Update docs
- Correct define for __HIP_ARCH_HAS_GLOBAL_INT64_ATOMICS__

Change-Id: Ic5e3cdb8269b1c18f6d2693700b55e08c4d0080e


[ROCm/hip commit: c54220eca9]
2016-10-15 11:51:20 -05:00
Ben Sander 20b6547a91 Add code to use new HCC API accelerator_view::dispatch_hsa_kernel.
Disabed by default, can enable with USE_DISPATCH_HSA_KERNEL=1

Change-Id: I7a6ba76f2bada34952ed47f5335ce695fa2faea5


[ROCm/hip commit: 50e0a363ce]
2016-10-14 23:46:29 -05:00
Ben Sander 252e32859e Fix HIP_USE_PRODUCT_NAME detection.
Change-Id: I6879ec3a11845bea66a18a9328bd4eaf54713420


[ROCm/hip commit: 89012201c9]
2016-10-13 11:51:53 -05:00
pensun 7b8e824779 Add ifdef guard for the feature requires ROCm1.3
Change-Id: I7154517c47000c37fe5eb09a3c1cf2a9aacbe27c


[ROCm/hip commit: b70409f3ad]
2016-10-13 10:57:31 -05:00
Aditya Atluri d89712028a added constant memory property to 16KB
Change-Id: If067b4057c2e3fc0c26cf4604a1d4fac7f139b12


[ROCm/hip commit: 237837d9bd]
2016-10-13 10:47:40 -05:00
pensun 9544b72d94 Change to query device name using HSA_AMD_AGENT_INFO_PRODUCT_NAME;
Note: this commit depends on ROCR runtime in ROCm 1.3 release.

Change-Id: I90385ef6d11ee8a1e8adae1d3fdf21747347544c


[ROCm/hip commit: c3f375327f]
2016-10-12 20:01:30 -05:00
Aditya Atluri ef0cb7d619 Added hipDeviceGetLimit api
1. hipDeviceGetLimit API for HCC path is added
2. Test for hipDeviceGetLimit API is added
3. The feature added only supports querying heap size
4. Corrected indents for malloc and free device functions
5. Removed redundant data structures
6. Added g_heap_malloc_size to store the heap size

Change-Id: If48d1b0ce9270e994f1c542cc283ddbb14746bbb


[ROCm/hip commit: 62ec53740c]
2016-10-12 19:58:48 -05:00
Aditya Atluri 6591712299 added malloc and free device functions
1. Added malloc and free device functions
2. Added test which check malloc and free functions
TODO: Need to add support for multiple device. Works only on one device (multi device support id NOT available).

Change-Id: Id11fc36463915d6ad46c264d5a20c8feb2d2c17c


[ROCm/hip commit: d24a7ef12b]
2016-10-12 19:08:34 -05:00
Ben Sander bb3ce0631d Add DISABLE_COPY_EXT option.
[ROCm/hip commit: dee364cb08]
2016-10-05 12:18:42 -05:00
Ben Sander cc0dab0113 Add HIP_BLOCKING_SYNC environment var to control stream sync behavior.
[ROCm/hip commit: 821080487a]
2016-10-05 12:18:42 -05:00
Maneesh Gupta fc58842fcf Move include/* to include/hip/*
Change-Id: I7a7b2839b4df59c7a4c503550f99fdc9e45c0f54


[ROCm/hip commit: b951cc99ed]
2016-10-04 22:17:18 +05:30
Ben Sander 7fc988bc45 Refactor asyncCopy and syncCopy to fix deadlock case.
- Minimize time that locks are held.
- Eliminate copy code that locked stream and ctx at same time.
    - Stream was locked to ensure thread-safe enqueue to the queue.
    - Devices were locked to query peer-lists.

Change-Id: Ibe8880bb7fb995a3da8f90ff911f212d81525018


[ROCm/hip commit: 4ff6dc8f38]
2016-09-27 15:45:40 -05:00
Ben Sander 7f7340fb29 Add debug option to print ThreadID with each message.
Also print messages with single fprintf to prevents threads from
interleaving.

Change-Id: Ib3999fe6b1e67b4a16cd7dcde82f3dfc99dd48ff


[ROCm/hip commit: 6de9136002]
2016-09-27 15:45:40 -05:00
Ben Sander 0dadf681db Fix signal resource issue.
Remove memory leak with new hc::completion_future.
Implement HIP_LAUNCH_BLOCKING with queue-level wait.

Change-Id: I45975f81c4d239fdeed7776970988d28449865dc


[ROCm/hip commit: 225e37fdc9]
2016-09-26 16:47:32 -05:00
Ben Sander a6f28e1708 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.


[ROCm/hip commit: c769abcbeb]
2016-09-22 14:21:19 -05:00
Ben Sander 21d1c29312 Remove unpinned_copy code. Other cleanup.
Change-Id: Ie3f71439cf1ba729ef223d078917c403d3de879a


[ROCm/hip commit: c645e53fdd]
2016-09-22 14:21:19 -05:00
Ben Sander b9a0abe32e Cleanup. Remove cfs, ihipSignal_t, staging buffer calls.
Change-Id: I8bb67c484e3a65be06a03665f059217930da2bed


[ROCm/hip commit: e0ce1d3954]
2016-09-22 14:21:19 -05:00
Ben Sander 41c4ea49ba Cleanup: Remove HIP signal pool.
Change-Id: Icebfd0509d12396cc5933d5556d68b53e1be36e0


[ROCm/hip commit: 12cb1d88aa]
2016-09-22 14:21:19 -05:00
Ben Sander a9e3786e0c Remove HIP command dependency tracking.
Change-Id: I991c13bc5108193959ba70f9f6f9c692c9ad3a5b


[ROCm/hip commit: 7530fa6dbe]
2016-09-22 14:21:19 -05:00
Ben Sander f145954a9d Cleanup, remove preCopyCommand.
Change-Id: I3768d3789a99be8136b43179d4152fa1875665cb


[ROCm/hip commit: 8c4cecf367]
2016-09-22 14:21:19 -05:00
Ben Sander 7be84ac76d Change HIP async copy to call av::copy_async.
Change-Id: I4274b63ced3940d5249c32bd9d156296529c70e8


[ROCm/hip commit: 9c9b0ab555]
2016-09-22 14:21:19 -05:00
Ben Sander d2461ff674 Use HCC's synchronous accelerator_view::copy
Replace large block of HIP code with a call to HCC av::copy().

Change-Id: Ic32e1801cf8d4cd116ac02b72c41b1a1e4b6065c


[ROCm/hip commit: da44f3f907]
2016-09-22 14:21:19 -05:00
Ben Sander d71686d4f5 Remove USE_AV_COPY, USE_PEER_TO_PEER fallback paths.
Change-Id: I9c20173e62029c4caebabc98784c6d7697758e4f


[ROCm/hip commit: e843d8cb51]
2016-09-22 14:21:19 -05:00
Ben Sander b7dda7be0d 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


[ROCm/hip commit: ccc1bbe6b1]
2016-09-22 14:21:18 -05:00
Ben Sander f7987aaa33 Move isLargeBar to UnpinnedCopyEngine constructor.
Change-Id: I7a7d3a40b1d4e0c6ec856658a6a70e5e70d287ce


[ROCm/hip commit: 442d74f027]
2016-09-22 14:21:18 -05:00
Ben Sander 7935c8b929 Refactor Staging Buffer CopyDeviceToHost
Use copyMode.  Embed algorithm selection inside the unpinned class.

Change-Id: Ic75fd5931717a3160904402794bbed3ccd445112


[ROCm/hip commit: e300cb4405]
2016-09-22 14:21:18 -05:00
Ben Sander fd5d85ee6b Refactor staging buffer CopyHostToDevice.
- Move algorithm selection inside Unpinned class.
- Refactor function names.
- Use size_t for size threshholds.

Change-Id: Iac4de652ac9d49acbf527aa0849e388b8ecd8486


[ROCm/hip commit: c532de9f5a]
2016-09-22 14:21:18 -05:00
Ben Sander f028a2e833 Updates docs for hipHcc* functions, move to header
[ROCm/hip commit: 83140f8423]
2016-09-22 13:05:47 -05:00
Aditya Atluri ba1c02dd50 added more error codes to hipErrorGetString
Change-Id: I80c675905d94813502040fd0caa07985fa8c7dcc


[ROCm/hip commit: 7407cb2600]
2016-09-15 11:28:18 -05:00
Aditya Atluri fd1437a95c added new error reporting case
Change-Id: I5f0a37dbe396412f5602d04df19d538e451c2696


[ROCm/hip commit: 8110f562ab]
2016-09-15 10:50:26 -05:00
Aditya Atluri 702225d58f Added signal management which passes stress tests
Change-Id: I7e1660a8ca2c5ee580a91f76eae9a58ca49f0457


[ROCm/hip commit: f03570d8cc]
2016-09-08 14:52:51 -05:00
Ben Sander 6445921e03 Add hipStreamQuery
Change-Id: Ib0813b1065feba4fe9ae861d24cfc6f9c5f580be


[ROCm/hip commit: 4e994a3025]
2016-09-07 15:18:34 -05:00
Ben Sander 4746d3002d refactor ihipPreLaunchKernel phase#1
- Fix calls to HIP_INIT_API to pass all function arguments.
- Change ihipFunction to follow coding convention:
    - leading underscore for member fields,
    - camelCase for member fields.
- move kernel print function inside ihipPreLaunchKernel.
- add HIP_TRACE_API_COLOR, control color of messages.
- add ihipLogStatus wrapper to hipDeviceSynchronize()

Change-Id: I20bbb644da213f821404648945197254e3648fc9


[ROCm/hip commit: 48b1f7a6ea]
2016-09-07 15:18:34 -05:00
Aditya Atluri 8a50f6465e Fixed group and private memory size to AQL
Change-Id: I6e721f63fe5697b7b90a7d25add9aa024d9dc429


[ROCm/hip commit: 2c2f6ab078]
2016-09-07 12:57:18 -05:00
Ben Sander 5820670910 Fix double-lock of stream on hipModuleLaunchKernel
Change-Id: I4ca164971c25f4eb8fbcca11d6258367bb3d2ab4


[ROCm/hip commit: cdba60a566]
2016-09-02 12:47:49 -05:00
Ben Sander d3fb92374d Only use ihipLogStatus from top-level HIP functions.
Change-Id: I07e9c088d5c16a79ed52cb008a798889a656016c


[ROCm/hip commit: db9fe9f494]
2016-09-02 09:46:59 -05:00
Ben Sander 71f898d534 Use create_blocking_marker for WaitEvent implementation
Change-Id: Ib3113f69a14e48b9fe0558d7b455148e478d8eed


[ROCm/hip commit: aa823871db]
2016-09-02 09:46:59 -05:00
Ben Sander bb0afa4e38 Refactor for stream->_av.
- move _av into stream critical section.  ( HCC accelerator_view is not
  thread-safe but HIP steram is. )
- Refactored many places in code that need to acquire critical section.
some were previously thread races, ie enqueueing marker.

-remove support for GRID_LAUNCH_VERSION < 20
-Enable USE_AV_COPY based on HCC work-week.
- Review hipModule docs, some calrity/editing.

Change-Id: I3ce7c25ece048c3504f55ecd4683e506bb1fc8b6


[ROCm/hip commit: e76a272d48]
2016-09-02 09:46:59 -05:00
Aditya Atluri bc1abd10f5 remove HIP_INIT_API from ihipSynchronize
Change-Id: Ibe0739efe55573c023212d9c28ba847c777e434c


[ROCm/hip commit: 1769c4b4b2]
2016-08-29 21:42:22 -05:00
Ben Sander 6c2759e70d Refactor trace code for hipLaunchKernel.
- Use standard print functions for streams.
- Add HIP_INIT macro, for cases where we want to initialize HIP but not
  log an API (ihipPreKernelLaunch).

Change-Id: If43cf8a363d918bcd3722a2e6a965d4cfa2e03e7


[ROCm/hip commit: 21e5c25225]
2016-08-29 18:37:57 -05:00
Aditya Atluri 2efa60a37e Added explicit memory copy direction apis
- Fixed stale printf in context api
- Added 4 sync memcpy apis
  1. hipMemcpyHtoD
  2. hipMemcpyDtoH
  3. hipMemcpyDtoD
  4. hipMemcpyHtoH
- Added test for added apis

Change-Id: I4a9c382445b62631f8d0bcbb9a670322288b72b1


[ROCm/hip commit: 4152746e26]
2016-08-26 13:11:01 -05:00
Aditya Atluri 69d6645be6 Changed how hipEvent_t is typedefed internall
- Mapped hipEvent_t directly to ihipEvent_t* instead of a handle

Change-Id: I5a8bcca0ef962932e0738c03eb1fc914d23022ae


[ROCm/hip commit: 842553a6e1]
2016-08-25 14:34:41 -05:00
Aditya Atluri 138b5b83d2 Added stream synchronisation for hipLaunchModuleKernel
- The module kernel launch is now in sync with commands in its stream
- Moved launch kernel inside ihipStream

Change-Id: Ic00cfcf4882bf81b6203c36881a52575ea68b529


[ROCm/hip commit: 8f0f97f8f9]
2016-08-22 14:17:55 -05:00