6cc5dc0326
Set event->_stream on hipHccModuleLaunchKernel path if start/stop used
...
Ensure _stream is always non-null in recorded events.
Fixes isDefaultStream fault.
2017-05-30 21:55:46 -05:00
445012d451
Disable normcdfinvf on __host__
...
Change-Id: If7bfc9826a09eb9b7675ea2a417b9418759b7912
2017-05-30 15:45:22 +05:30
942ec0eff8
Add event controls for release fences.
...
Env var : HIP_EVENT_SYS_RELEASE
Event allocation flags : hipEventReleaseToDevice, hipEventReleaseToSystem
(remove hipEventDisableSystemRelease)
Update test for new functionality.
2017-05-27 16:02:34 -05:00
c8178c6838
Cleanup hipEvent. (Intermediate checkpoint)
...
Support hipEventDisableSystemRelease flag.
Update test.
Remove stray printf
2017-05-27 16:02:34 -05:00
b2b620c12b
Add isDefaultStream() accessor.
...
Fix code that checked for stream==nullptr after stream had been
resolved to a "true stream".
2017-05-26 13:46:48 -05:00
a3595d2e8c
fix hip_fast_dsqrt* to call a double fp sqrt function
2017-05-25 23:15:30 -04:00
35212632e7
Remove HIP_NUM_KERNELS_INFLIGHT. (redundant with HCC controls)
2017-05-24 01:03:28 -05:00
dda70ae514
Add hipHostMallocCoherent, hipHostMallocNonCoherent
...
Provide per-allocation control over coherent/non-coherent mem.
These overrid the default HIP_COHERENT_HOST_ALLOC setting.
2017-05-24 00:48:10 -05:00
d43d57d39c
Remove HIP_MAX_QUEUES (replaced with HCC_MAX_QUEUES)
2017-05-23 23:48:01 -05:00
2d5b3359c6
Use accelerator_scope for create_marker and create_blocking_marker.
...
As optimization when system-scope is not needed.
2017-05-23 23:15:45 -05:00
ca07615c37
Fix trace category for hipHostMalloc
2017-05-23 23:15:45 -05:00
490355203b
fixed erfinv build error as it is implemented in hcc
...
Change-Id: I27a512147c53f658a63fdf3e90f5e9cfac09ada8
2017-05-23 09:32:19 -05:00
ae9f14ef9c
[HIP] [HIPIFY] [FIX] cuModuleLoadDataEx -> hipModuleLoadDataEx
...
https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP/issues/81
1. Do not use JIT options on HCC path, call hipModuleLoadData instead.
2. NVCC path is unchanged, to call cuModuleLoadDataEx with all options.
3. Get rid of manual hipification, based on #ifdef #else for NVCC/HIP.
4. Update documentation accordingly.
2017-05-19 17:22:14 +03:00
ee37a31799
Return precise address for hipHostGetDevicePointer.
2017-05-17 07:36:06 -05:00
93fa174900
changed vector types to make sure it generate proper llvm vector types
...
Change-Id: I6c4616dae137dc4eac35e5827dc5b7f3251e0247
2017-05-16 21:35:40 -05:00
fad9104b5f
Fix HIP_TRACE_API so kernel launch only printed when requested.
2017-05-16 19:04:25 -05:00
8bc6ee5932
Add initial HIP_SYNC_NULL_STREAM=0 mode.
...
This eliminates host-synchronization for null stream. Instead, the
null-stream uses GPU-side events to wait for other streams.
Default is OFF pending additional testing.
Add enhanced null-stream test.
Also refine HIP_TRACE_API.
2017-05-16 19:04:25 -05:00
7e7ba5027f
Add HIP_TRACE_API=4. Only display memory allocation/free apis.
2017-05-16 19:04:25 -05:00
a6dc00f167
added gfx900 to hipDeviceProp_t
...
Change-Id: I49e7a32f218926fd55f1c94c5dc2366d6c8ac4ca
2017-05-12 21:43:34 -05:00
c7c62dd022
Remove old USE_ switches no longer needed.
2017-05-12 16:06:03 -05:00
2c2625cb9e
Add hipEventDisableSystemRelease flag.
2017-05-12 16:06:03 -05:00
ff9bed6535
hipHostMalloc allocation are mapped to all devices by default.
...
Support hipHostMallocPortable flag.
Default flags are hipHostMallocPortable | hipHostMallocMapped.
Also:
-refactor tests to move addCount and addCountReverse into HipTest
namespace.
-test multi-GPU host memory.
2017-05-10 17:34:36 -05:00
9a026b62a8
Fix some typos, add additional guidance for -BSymbolic
2017-05-05 17:29:04 -05:00
b136e80a45
Added support for hipMemcpy2DAsync in HIP/HCC
...
Change-Id: Ia4a8306f2dc1e33a81a7195ec29aef652fcccc4b
2017-05-03 22:29:12 +05:30
208bdbbcbb
fixed hipFuncSetCacheConfig on rocm path
...
Change-Id: I937a3afbf115edc94a753a0beb2230ed60a6f021
2017-04-28 11:53:11 -05:00
f368271872
fixed fast math expf and exp10f
...
Change-Id: I73963220f902efebb0a7404c5f8966dffb4c35ca
2017-04-26 19:01:10 -05:00
3da8e94cbf
Tailor pointer info for src/dst before calling HCC copy routines.
...
HCC sometimes uses the srcPtrInfo or dstPtrInfo to determine the
pointer. Make sure these use the actual pointer and not the base
of the allocation.
2017-04-24 22:30:54 -05:00
dfacfbb641
Fix hip debug for case where copyAgent is null (host-to-host)
2017-04-24 22:30:54 -05:00
fb7eee01ff
Fix hipMalloc to return error code if allocation fails.
2017-04-24 22:30:54 -05:00
1f532b06f6
fixed build issues with hipPointerGetAttributes
...
Change-Id: I3f5fbc05bdaef720884ba949075928752a070377
2017-04-24 15:31:07 -05:00
85c189c846
changed arguments for hipPointerGetAttributes
...
Change-Id: Ia7a7c4722c1f7d0a23f0e5cc3dd6dea6c01c1fd8
2017-04-24 15:24:16 -05:00
8bd34535b4
Add integer abs (initial implementation, can be optimized with OCML)
...
Change-Id: I1f568c8c0e2333af1fda4c313dc48ea0c5b6ab00
2017-04-11 01:16:28 +00:00
f699e02715
update GGL to log launched kernel information
...
Change-Id: Ied0aa6055673c687071b4a579aecd17f0f3f09ce
2017-04-07 14:06:31 -05:00
e9eaadd135
Finish adding start/stop event support to hipHccModuleLaunchKernel.
...
Change interface to use hipEvent_t rather than hipEvent_t*
Change-Id: I259062dc087a13d51dc27f84e1e8861f332a104d
2017-04-06 21:02:50 -05:00
f442e975c6
Refactor events and add initial event option for hipHccModuleLaunchKernel
...
- Change hipEvent_t to a class.
- Move event logic inside the class.
- Add _type to support Independent, StartCommand, StopCommand events.
StartCommand returns start timestamp from events.
Change-Id: I4ddd694f2645a3ff7170c9111dc1d3e39931ca21
2017-04-06 21:02:50 -05:00
4906cd5f0d
mgpu IPC support fix
...
Change-Id: I12e4b2fd189c3658efd3b07defa18ece3853b0eb
2017-04-04 15:51:10 +05:30
a7d7797781
Fix warpSize, for related issue in hipeigen and torch
...
Change-Id: Ic66b24923a363304dca189011869ba7a0a6f8895
2017-04-01 15:42:53 -05:00
9762667431
Add copy right in grid_launch.cpp
...
Change-Id: I7de3fc32f13182b5c41a4e44147b642ba15e8636
2017-04-01 15:12:00 -05:00
ae8448a9af
Add grid_launch.cpp for GGL
...
Change-Id: I87ff9b3f1203d0909f998c96c839f7b321fc3f09
2017-04-01 14:57:47 -05:00
81d3725a16
added debug support for HIP sample
...
Change-Id: Ia7265234082039b68114f7421f4dbcb7149d4d2b
2017-03-31 14:13:46 -05:00
3859f59189
Fixed copyright and header names
...
Change-Id: Id595c65ea3b7289e87be4c42db5d8a31905a4fdd
2017-03-31 12:40:29 -05:00
1cead6a4cd
added new api hipHccModuleLaunchKernel
...
1. hipHccModuleLaunchKernel is same as hipModuleLaunchKernel with OpenCL workitem model
2. Added copy right
3. Fixed header naming
Change-Id: I6a7c35a3566e2f8d3f5056613e34193775d4b236
2017-03-31 12:11:34 -05:00
4e5861df7a
disabled metadata apis
...
Change-Id: Ifb8839c581644cccc2afcd18c38a866f649a4144
2017-03-28 10:46:31 -05:00
abf369049b
Re-enabled metadata parsing in HIP
...
Change-Id: If8caa844571cb8581450df9ffdb76e2445c75f13
2017-03-27 11:00:39 -05:00
41f0ebebf0
Fix for MemcpyFromSymbol on HIP/NVCC path
...
Change-Id: Ice38307f72870ae468cbf0861e104f0fa46dfd56
2017-03-27 00:35:10 +05:30
33a8cdc6d3
Added support for Primary Context Management APIs
...
Change-Id: I70f91b4492e112dd8e12ecf511fdc18a27944a06
2017-03-26 23:45:54 +05:30
dfa516f804
Fix for hipMemcpyFromSymbolAsync
...
Change-Id: I449c669c8f0ef041deaf0a1bc812a71b2f0cc5a6
2017-03-24 10:30:33 +05:30
5a0685c137
removed llvm dependency and metadata functionality
...
Change-Id: Ib9783b75d326559ed29c5aa2218aed40d20ad0fb
2017-03-23 10:16:37 -05:00
e22044de36
Fix for hipMemcpyFromSymbol (sync)
...
Change-Id: I66afec5443ce904a63ced1fafece5144ca59393e
2017-03-21 23:48:04 +05:30
52859a8a40
added support for lgammaf and lgamma
...
1. Implementation inside HIP
Change-Id: I657263b7276a57c56081d3336fef816b5f204eff
2017-03-17 18:26:10 -05:00
Ben Sander
Maneesh Gupta
Siu Chi Chan
Aditya Atluri
Evgeny Mankov
Rahul Garg
Sun, Peng