fc7eefb5c8
Cleanup files from code review.
...
- Remove some stale code
- Update docs
- Correct define for __HIP_ARCH_HAS_GLOBAL_INT64_ATOMICS__
Change-Id: Ic5e3cdb8269b1c18f6d2693700b55e08c4d0080e
[ROCm/clr commit: aa3e04cf9a
2016-10-15 11:51:20 -05:00
57adbf2a17
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/clr commit: dcadaadb24
2016-10-14 23:46:29 -05:00
4c69e2c2f8
Fix HIP_USE_PRODUCT_NAME detection.
...
Change-Id: I6879ec3a11845bea66a18a9328bd4eaf54713420
[ROCm/clr commit: 45bc107ad0
2016-10-13 11:51:53 -05:00
eecfd8e141
Add ifdef guard for the feature requires ROCm1.3
...
Change-Id: I7154517c47000c37fe5eb09a3c1cf2a9aacbe27c
[ROCm/clr commit: 0ac70e7184
2016-10-13 10:57:31 -05:00
b82a22ff7a
added constant memory property to 16KB
...
Change-Id: If067b4057c2e3fc0c26cf4604a1d4fac7f139b12
[ROCm/clr commit: e25a1e50b3
2016-10-13 10:47:40 -05:00
f638d13f7c
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/clr commit: 44cc44011b
2016-10-12 20:01:30 -05:00
cd32c9418e
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/clr commit: e5325a1ab4
2016-10-12 19:58:48 -05:00
caa6a298e7
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/clr commit: 2918ff273d
2016-10-12 19:08:34 -05:00
a79b334fbc
Add DISABLE_COPY_EXT option.
...
[ROCm/clr commit: 250f711ed0
2016-10-05 12:18:42 -05:00
8e0733f958
Add HIP_BLOCKING_SYNC environment var to control stream sync behavior.
...
[ROCm/clr commit: 6950d3f9e9
2016-10-05 12:18:42 -05:00
46feb7dcf2
Move include/* to include/hip/*
...
Change-Id: I7a7b2839b4df59c7a4c503550f99fdc9e45c0f54
[ROCm/clr commit: bbfc08f419
2016-10-04 22:17:18 +05:30
d5d764a4d4
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/clr commit: 806e58ca63
2016-09-27 15:45:40 -05:00
a0ec18c516
Add debug option to print ThreadID with each message.
...
Also print messages with single fprintf to prevents threads from
interleaving.
Change-Id: Ib3999fe6b1e67b4a16cd7dcde82f3dfc99dd48ff
[ROCm/clr commit: 4fd4168796
2016-09-27 15:45:40 -05:00
46a4854bae
Fix signal resource issue.
...
Remove memory leak with new hc::completion_future.
Implement HIP_LAUNCH_BLOCKING with queue-level wait.
Change-Id: I45975f81c4d239fdeed7776970988d28449865dc
[ROCm/clr commit: f6717e326e
2016-09-26 16:47:32 -05:00
4cf9803703
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/clr commit: 944d4eaa18
2016-09-22 14:21:19 -05:00
03866f0ee5
Remove unpinned_copy code. Other cleanup.
...
Change-Id: Ie3f71439cf1ba729ef223d078917c403d3de879a
[ROCm/clr commit: 926aefa930
2016-09-22 14:21:19 -05:00
8e55e13469
Cleanup. Remove cfs, ihipSignal_t, staging buffer calls.
...
Change-Id: I8bb67c484e3a65be06a03665f059217930da2bed
[ROCm/clr commit: 5bc18c8603
2016-09-22 14:21:19 -05:00
8340e57194
Cleanup: Remove HIP signal pool.
...
Change-Id: Icebfd0509d12396cc5933d5556d68b53e1be36e0
[ROCm/clr commit: 17e21309f1
2016-09-22 14:21:19 -05:00
dbbd5ce037
Remove HIP command dependency tracking.
...
Change-Id: I991c13bc5108193959ba70f9f6f9c692c9ad3a5b
[ROCm/clr commit: c365785c5c
2016-09-22 14:21:19 -05:00
bafa586cf5
Cleanup, remove preCopyCommand.
...
Change-Id: I3768d3789a99be8136b43179d4152fa1875665cb
[ROCm/clr commit: b0509c5a58
2016-09-22 14:21:19 -05:00
c291e03ce8
Change HIP async copy to call av::copy_async.
...
Change-Id: I4274b63ced3940d5249c32bd9d156296529c70e8
[ROCm/clr commit: 3596901c3d
2016-09-22 14:21:19 -05:00
8240ac127f
Use HCC's synchronous accelerator_view::copy
...
Replace large block of HIP code with a call to HCC av::copy().
Change-Id: Ic32e1801cf8d4cd116ac02b72c41b1a1e4b6065c
[ROCm/clr commit: 8598d8c6d3
2016-09-22 14:21:19 -05:00
2f4c30ff79
Remove USE_AV_COPY, USE_PEER_TO_PEER fallback paths.
...
Change-Id: I9c20173e62029c4caebabc98784c6d7697758e4f
[ROCm/clr commit: 60f797cc5a
2016-09-22 14:21:19 -05:00
16f818b60f
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/clr commit: 39750da9a5
2016-09-22 14:21:18 -05:00
872c63b03a
Move isLargeBar to UnpinnedCopyEngine constructor.
...
Change-Id: I7a7d3a40b1d4e0c6ec856658a6a70e5e70d287ce
[ROCm/clr commit: 17d7fc586e
2016-09-22 14:21:18 -05:00
435c528fd4
Refactor Staging Buffer CopyDeviceToHost
...
Use copyMode. Embed algorithm selection inside the unpinned class.
Change-Id: Ic75fd5931717a3160904402794bbed3ccd445112
[ROCm/clr commit: 77c86934c1
2016-09-22 14:21:18 -05:00
91b43c493b
Refactor staging buffer CopyHostToDevice.
...
- Move algorithm selection inside Unpinned class.
- Refactor function names.
- Use size_t for size threshholds.
Change-Id: Iac4de652ac9d49acbf527aa0849e388b8ecd8486
[ROCm/clr commit: e77d75c1c1
2016-09-22 14:21:18 -05:00
6b6b0d6b58
Updates docs for hipHcc* functions, move to header
...
[ROCm/clr commit: b4bc101c96
2016-09-22 13:05:47 -05:00
29a9549a47
added more error codes to hipErrorGetString
...
Change-Id: I80c675905d94813502040fd0caa07985fa8c7dcc
[ROCm/clr commit: 6cb5a13a2b
2016-09-15 11:28:18 -05:00
18756a8e91
added new error reporting case
...
Change-Id: I5f0a37dbe396412f5602d04df19d538e451c2696
[ROCm/clr commit: 2c12394d52
2016-09-15 10:50:26 -05:00
a482dd2ae0
Added signal management which passes stress tests
...
Change-Id: I7e1660a8ca2c5ee580a91f76eae9a58ca49f0457
[ROCm/clr commit: 5845a2d8c6
2016-09-08 14:52:51 -05:00
c75953a822
Add hipStreamQuery
...
Change-Id: Ib0813b1065feba4fe9ae861d24cfc6f9c5f580be
[ROCm/clr commit: fd67689114
2016-09-07 15:18:34 -05:00
c5f7fd723a
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/clr commit: 745310399d
2016-09-07 15:18:34 -05:00
a4934a7c66
Fixed group and private memory size to AQL
...
Change-Id: I6e721f63fe5697b7b90a7d25add9aa024d9dc429
[ROCm/clr commit: 26215c515d
2016-09-07 12:57:18 -05:00
f3da27cd5a
Fix double-lock of stream on hipModuleLaunchKernel
...
Change-Id: I4ca164971c25f4eb8fbcca11d6258367bb3d2ab4
[ROCm/clr commit: 0fdb5bf517
2016-09-02 12:47:49 -05:00
98019e5f79
Only use ihipLogStatus from top-level HIP functions.
...
Change-Id: I07e9c088d5c16a79ed52cb008a798889a656016c
[ROCm/clr commit: 9ee9284306
2016-09-02 09:46:59 -05:00
fe85edad3f
Use create_blocking_marker for WaitEvent implementation
...
Change-Id: Ib3113f69a14e48b9fe0558d7b455148e478d8eed
[ROCm/clr commit: 9a99000a62
2016-09-02 09:46:59 -05:00
938933ca2f
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/clr commit: 02f65a483c
2016-09-02 09:46:59 -05:00
eb6863017c
remove HIP_INIT_API from ihipSynchronize
...
Change-Id: Ibe0739efe55573c023212d9c28ba847c777e434c
[ROCm/clr commit: 7fdebfb8e3
2016-08-29 21:42:22 -05:00
78cfa5f6d6
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/clr commit: fa9b95838a
2016-08-29 18:37:57 -05:00
fa734c5a6a
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/clr commit: f722a132a4
2016-08-26 13:11:01 -05:00
82deaeb581
Changed how hipEvent_t is typedefed internall
...
- Mapped hipEvent_t directly to ihipEvent_t* instead of a handle
Change-Id: I5a8bcca0ef962932e0738c03eb1fc914d23022ae
[ROCm/clr commit: 25be4fb532
2016-08-25 14:34:41 -05:00
52305186ef
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/clr commit: c0fbe7891c
2016-08-22 14:17:55 -05:00
f1f04949ac
Added support for hipCtxSynchronize and hipCtxGetFlags,modified hipDeviceSynchronize
...
Change-Id: If7bac667a262fa8c0cb3dc93e97f2534855acd07
[ROCm/clr commit: b0ba622ed5
2016-08-22 16:15:27 +05:30
a4bfccf628
Context update.
...
- Remove tls_deviceID.
- Add first passing test.
Change-Id: If3e2f254abf589028cfe4f9e6369745f04160de0
[ROCm/clr commit: a9bcee3d77
2016-08-10 08:59:47 -05:00
dbf9fd8312
Changed StagingBuffer class to UnpinnedCopyEngine
...
Change-Id: I1e212bfc8030dcf225ecf78fd7b23fda9b1de92f
[ROCm/clr commit: d08b1239ee
2016-08-09 21:29:42 +05:30
cb771c60d3
Moved sync copy decision logic to staging buffer class
...
Change-Id: I5c398772375fcc1f174a7597eea1215ce7bf80b4
[ROCm/clr commit: 4044cb412c
2016-08-09 09:28:18 +05:30
0c8ca4b37d
Add initial context implementation.
...
APIs: hipInit, hipCtxCreate.
Track TLS default ctx. Set deviceID now changes the ctx.
Add first context test.
Change-Id: If1cb9989b5a04a36147e25e84904336c7b6f3d88
[ROCm/clr commit: f19f2248bf
2016-08-08 17:49:02 -05:00
c85f34bf8a
Code cleanup, use camelCase where appropriate.
...
Change-Id: I5a7ec50df8bbb3e7a3b313c0b12e2dd55ae4a09c
[ROCm/clr commit: ac173c3ae8
2016-08-08 14:54:38 -05:00
3ee6e7f8ab
Split ihipCtx_t into ihipCtx_t and ihipDevice_t .
...
Major change to existing code base.
Ctx holds streams, enables peers, and flags.
Device holds accelerator, hsa-agent, device props.
Add hipCtx_t.
Add peer APIs that accept hipCtx_t (in addition to deviceId)
Compiles and passes directed tests.
Change-Id: Iddab1eb9edbf90caad2ef5959c6b811d658197f1
[ROCm/clr commit: d09b19bb6c
2016-08-08 11:55:57 -05:00
Ben Sander
pensun
Aditya Atluri
Maneesh Gupta
Rahul Garg