Commit gráf

374 Commit-ok

Szerző SHA1 Üzenet Dátum
Ben Sander 1e5540e07f Add debug for Peer APIs. Enable PeerMemcpy APIs by default.
Change-Id: I46e39a9e7b07686a78484c1f3b5495b08e052fbb


[ROCm/hip commit: 3f0a2b8dc1]
2016-11-04 08:51:16 -05:00
pensun 9251040786 Update document for workaround suggestion on threadfence_system()
Change-Id: Icccab8270604a0e578a8614b9afb3f95372f4966


[ROCm/hip commit: 774de273d0]
2016-11-02 16:08:27 -05:00
pensun 959880e318 Update hipStreamNonBlocking to use cuda define on NV path
Change-Id: I74ea09db99d602ba1c5f192b36ff7f2781176e6a


[ROCm/hip commit: 4817131cdc]
2016-11-01 20:30:56 -05:00
Aditya Atluri 42130918bb added inter thread data movement intrinsics
Change-Id: I2a8a8ed49429cb7f96439bd28c4b83b5142737df


[ROCm/hip commit: f48c53534e]
2016-11-01 16:37:33 -05:00
Rahul Garg 0aa4468ac3 Added hipDeviceGetByPCIBusId in hip/hcc path
Change-Id: I3cca0dc533d0281689d8a407c7da16ca1ba6a3a8


[ROCm/hip commit: 2d15d0741c]
2016-11-01 10:57:48 +05:30
Ben Sander ae8d55ccc1 add hip_profile.h
Change-Id: Id43a4336db53567020584cb7842baf5c1649fd8e


[ROCm/hip commit: 87a2e8f12b]
2016-10-28 07:08:46 -05:00
Ben Sander 2cfd770f1b Add initial hipProfileStart/Stop
And modify sample to show how to use.
Still needs some work to understand interaction with CXL.

Change-Id: I2579824d2dd7863ea23874d34f0dabb3cb305d3e


[ROCm/hip commit: bb58f4f6fc]
2016-10-27 23:09:32 -05:00
pensun d449ce078c Add missing hipStream typedef for NV path
Change-Id: I915cd14a9ff32b55b0121062d7804a7fbbdc3341


[ROCm/hip commit: 334e9c6f8e]
2016-10-27 13:34:14 -05:00
pensun 75ccef39c9 Remove extra semicolons and extra spaces in header on NV path
Change-Id: Ib33aec2451a4e0b298d537dbb1b9df000405871b


[ROCm/hip commit: 8a7dcfce0b]
2016-10-25 15:29:52 -05:00
pensun 9f4cb7d4de Add workaround for hipStreamAddCallback function: call stream synchronize on host and then add execute the call back function
Change-Id: If361f8e053949904b19b9e09245d267f05e29f7b


[ROCm/hip commit: 1f11a9554e]
2016-10-22 23:59:39 -05:00
Aditya Atluri 417c0c18d0 Added support for constant memory
1. Added support for constant memory
2. Added test which uses memcpytosymbol for constant memory
3. Corrected code error on nvcc path

Change-Id: I2ab69f516832bf7a037132ac81273ea6f5107401


[ROCm/hip commit: 48f6d52e7c]
2016-10-20 09:57:53 -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 7bd9ca471a Update docs for event, review event TODO.
Change-Id: Iec491f9f22df163f01c0af6639fcbe33c81acdcc


[ROCm/hip commit: 61af94a555]
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 aab3c1b4bf Rename hipComplex.h -> hip_complex.h
Change-Id: I86af4ddccc6ebb19606156b459e3065d2c979108


[ROCm/hip commit: 2df7159ad7]
2016-10-16 11:02:36 +05:30
Maneesh Gupta 7ac85926b7 include headers: Update copyright header and fix line endings
Change-Id: If2b0855f4ebf1e966edb54de5667687d154cc574


[ROCm/hip commit: 9608fb93b5]
2016-10-15 22:52:10 +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
Maneesh Gupta 9f1c08ed64 Remove orphaned hip_blas.h from hcc_detail and nvcc_detail
Change-Id: I7e2dda475b538d30942c52d86fbdb213918c630c


[ROCm/hip commit: 84283d0801]
2016-10-14 12:55:50 +05:30
Maneesh Gupta 887ee3dbfe Remove incorrect executable-bit from non-executable files
Change-Id: Iacc434374721e01f7d75d0ab54bceabe0b337f54


[ROCm/hip commit: 6a14f39f8b]
2016-10-14 12:53:13 +05:30
Aditya Atluri cd73ab06db added limit enum to nvcc
Change-Id: If9cb6b1205631da36ec18a84f736f2f2f5155885


[ROCm/hip commit: e1929e8e82]
2016-10-13 15:15:02 -05:00
Aditya Atluri 5473ffc169 changed hipLimit to hipLimit_t and data type to enum
Change-Id: I94f408cdcac4b0bb38801d58709b68e9630d44d0


[ROCm/hip commit: 00c3db0e60]
2016-10-13 15:13:11 -05:00
Aditya Atluri d06509f680 added compiler flag for polaris
Change-Id: Ib14c14c0618982ac7b48f5bc704c04b54ff40ed9


[ROCm/hip commit: 90a71c4be4]
2016-10-13 14:16:48 -05:00
Ben Sander a20ed98897 Remove hipblas.h header - this is now hosted in the hcBlas repot.
Change-Id: I5b3350c900741cb1aee75faf4547f2682a9ec385


[ROCm/hip commit: 586bcdc8dc]
2016-10-13 11:51:25 -05:00
Aditya Atluri a4c5402bf4 Added HIP_SYMBOL macro to act as a wrapper between HCC and NVCC symbol name parameters
Change-Id: I008d028b1e29d5a00d0e449af388216396ad2f75


[ROCm/hip commit: 36b73ed8d9]
2016-10-13 10:31:56 -05:00
Aditya Atluri 50db853e0b added limit api support for nvcc
Change-Id: Ib6c939e44343158a70e0de7f107d21afc0d0efba


[ROCm/hip commit: ecf347a942]
2016-10-12 21:06:30 -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 218b4034bc Added copyright for headers
Change-Id: I35843d8d3b6acd9553ce00150868e15e2baee1da


[ROCm/hip commit: 7cf8ea5c64]
2016-10-12 19:12:35 -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
Aditya Atluri 0c2d2a4945 changed memcpy and memset device functions
Change-Id: Ia7f450536a75fad4fe13c7fcf5e9e7a9b5450f52


[ROCm/hip commit: 288f024d00]
2016-10-11 17:43:15 -05:00
Aditya Atluri a8a315ff80 changed hipTestDeviceSymbol test to compile for both nvcc and hcc path
Change-Id: I041770ad59d4f88d0c8d27d90cdc8a799935ada1


[ROCm/hip commit: d71c0d10de]
2016-10-11 13:50:31 -05:00
Aditya Atluri 25dddf5a9b added hipMemcpySymbol feature to nvcc path
Change-Id: I78d45036083fba62d2b2e4e58f9c72cb4e6eb54f


[ROCm/hip commit: e3712197ca]
2016-10-11 13:34:54 -05:00
Aditya Atluri 62e25cc961 added more changes to memcpytosymbol
1. Refactored code to use HCC internal APIs rather than HCC copy APIs
2. Added hipMemcpyToSymbolAsync
3. Added test for hipMemcpyToSymbolAsync
4. Added new error hipErrorInvalidSymbol

Change-Id: I0e359b2d0ff5d682bbccdf9c2923e16b35e39497


[ROCm/hip commit: 3c4af7c371]
2016-10-11 13:29:46 -05:00
Aditya Atluri 3cddc50058 Added feature for memcpy to Symbol
1. Currently works only for __attribute__((addrspace(1))
2. Need to pass in string for name of the variable
3. Added test to check functionality

Change-Id: I4c3cc1bf151cb5423e4aef59fcc4ad5693b31641


[ROCm/hip commit: 6952b59401]
2016-10-11 12:09:58 -05:00
Aditya Atluri cb75432ac4 added threadfence feature for hcc
1. Added feature for __threadfence and __threadfence_block
2. Added feature for using LLVM IR files directly while compilation
3. Added test for threadfence and threadfence_block

Change-Id: Ib7e5d89b4cca1a135952b317e5809cd05b56a3c9


[ROCm/hip commit: dc1042ce6d]
2016-10-10 15:29:50 -05:00
Maneesh Gupta eebcf24ee0 Add back deprecated hipHostAlloc, hipMallocHost, hipFreeHost
Change-Id: Ib8494078c852b07e1958c3acc21fa1866542122c


[ROCm/hip commit: 7c943ef20a]
2016-10-09 16:30:46 +05:30
Elias Konstantinidis 7d0d42712e Added support for __mul24 and __umul24
[ROCm/hip commit: 2bc541e15f]
2016-10-06 09:29:36 +05:30
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 e99878f5fb Fix hipMemSetAsync compilation, bounds check on name copy
[ROCm/hip commit: 88fb0efa6d]
2016-10-03 19:05:19 -05:00
Aditya Atluri dd55ba8b5d Stream fix on nvcc hipMemsetAsync
Change-Id: Ia0eb81dff0f422af55d93b4635d42e9aa6921377


[ROCm/hip commit: 9f05eca0a0]
2016-10-03 12:38:41 -05:00
Ben Sander 679b9be947 disable DB_SHOW_TID
Change-Id: Ia415437e8ba9903de149997380f61f1272488642


[ROCm/hip commit: d4a6010e2d]
2016-10-02 05:56:38 -05:00
Aditya Atluri 2083f2c29e added vector types for C path
Change-Id: I4ccd4082f1b2ce4f0f4fd9fb498506234783a803


[ROCm/hip commit: 2835e86e39]
2016-09-29 19:44:00 -05:00
Aditya Atluri e4e4c54055 Added C guard for math headers
Change-Id: I0e71819c6436b3e6c99b2deddb2ee2d2a16acedd


[ROCm/hip commit: e04b8d6aa7]
2016-09-29 13:54:34 -05:00
Aditya Atluri d31206acb8 Fixed issue on git #39
Change-Id: I5b507fc2b544df0cd3a900a2763c7a3ad6295c13


[ROCm/hip commit: 1e56dead78]
2016-09-29 10:06:26 -05:00
pensun 04871c910b add hipEvent* macros on NV path
Change-Id: I28ff0fa24f69560e13366e7cd8d3a485665c67e1


[ROCm/hip commit: 4fa5e980ef]
2016-09-29 01:22:19 -05:00
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
Rahul Garg f80ea5aa78 Doxygen documentation changes for hipCtxXXX APIs
Change-Id: I1e5e3a621b732bd8bdeef1c607c004d6adfdab32


[ROCm/hip commit: 280249918f]
2016-09-26 23:11:07 +05:30