8a2bcf2da3
Merge branch 'privatestaging' of https://github.com/AMDComputeLibraries/HIP-privatestaging into privatestaging
...
[ROCm/hip commit: c300ffe458
2016-02-26 06:15:09 -06:00
5ca4914e0e
Merge branch 'memtracker' into privatestaging
...
Conflicts:
src/hip_hcc.cpp
[ROCm/hip commit: 4adab7b7ef
2016-02-25 19:38:46 -06:00
ae365b4ae2
Improve memory copy and commands switching
...
- Add chicken bits to use host-side dependency management.
- Add optional PinInPlace path for unpinned copies
- Synchronize before pinned memcpy path.
- Add mutex to protect two threads launching to same stream.
[ROCm/hip commit: 8b64c0dc62
2016-02-25 19:19:49 -06:00
82900a1888
Attribute hipDeviceAttributeIsMultiGpuBoard for obtaining Device property isMultiGpuBoard is added.
...
On HIP path property obtaining done through hsa_iterate_agents and counting the devices of HSA_DEVICE_TYPE_GPU type.
P.S.
On multi-boards systems it might be problems with detection what board a GPU plugged into (not tested).
[ROCm/hip commit: 57e212606d
2016-02-25 23:44:39 +03:00
f0c734e256
Improve async copy implementation.
...
- Add device-side signal waits when transitioning between command classes
(Kernel, H2D copy, D2H copy).
- Support waiting in staged memory copies as well.
- Add several chicken bits to control implementation:
- HIP_DISABLE_ENQ_BARRIER
- HIP_DISABLE_BIDIR_MEMCPY
- HIP_ONESHOT_COPY_DEP
- Refactor signal pool to support efficient deallocation based on
signsequnm.
- Deallocate copy signals on eventSynchronize.
- Improve copy tests, add pingpong.
[ROCm/hip commit: 549b18ce77
2016-02-22 23:15:24 -06:00
d40b8d8fb0
Enable cospi,rsqrt,sinpi tests for HCC newer than 16073
...
[ROCm/hip commit: c5c11d3707
2016-02-22 15:13:23 +05:30
ebf2700936
Track last command to a stream.
...
Passing simple tests.
[ROCm/hip commit: d33d806a5b
2016-02-20 11:02:07 -06:00
0389b292a6
Resolve issues for hip_popc and hip_ballot on nvcc
...
[ROCm/hip commit: a7232c7f9e
2016-02-19 20:18:03 +08:00
c3a600c63b
Guard #ifdef USE_ROCR_20 is added for ROCR_20 device properties (memoryClockRate, memoryBusWidth)
...
By default isn't defined.
To add ROCR_20 support HIP have to be compiled as follows: make CXX_DEFINES+=-DUSE_ROCR_20
[ROCm/hip commit: 833c9e52ad
2016-02-19 13:27:03 +03:00
7f6001cb75
Describe how to update HTML docs
...
[ROCm/hip commit: d8cf65edac
2016-02-19 01:56:17 -06:00
4fcd9f2542
Device property memoryBusWidth implementation.
...
+ Device property memoryBusWidth is added to hipDeviceProp_t struct.
+ Device attribute hipDeviceAttributeMemoryBusWidth is added to hipDeviceAttribute_t struct.
+ Tests update.
[ROCm/hip commit: 1c19dbb807
2016-02-18 18:15:01 +03:00
a0cc7134e3
Device property memoryClockRate implementation.
...
+ Device property memoryClockRate is added to hipDeviceProp_t struct.
+ Device attribute hipDeviceAttributeMemoryClockRate is added to hipDeviceAttribute_t struct.
+ Tests update.
+ Rename hipDevAttrConcurrentKernels to hipDeviceAttributeConcurrentKernels.
[ROCm/hip commit: 5ea8543d2e
2016-02-18 17:25:28 +03:00
8c1a0d1924
Attribute hipDevAttrConcurrentKernels for obtaining Device property concurrentKernels is added.
...
[ROCm/hip commit: 2b6fda77ca
2016-02-18 14:34:18 +03:00
c989994613
Merge branch 'memtracker' of https://github.com/AMDComputeLibraries/HIP-privatestaging into memtracker
...
[ROCm/hip commit: ba224011b0
2016-02-17 23:06:51 -06:00
21b30996cf
Support HSA_PATH env, async path tweak
...
[ROCm/hip commit: f466b291d8
2016-02-17 21:22:07 -06:00
bb8a1fe72d
more work on async copies
...
[ROCm/hip commit: 59379ffb44
2016-02-17 00:59:12 -06:00
787078f0b3
Add comments to tests
...
[ROCm/hip commit: fb883d9d03
2016-02-16 01:58:24 -06:00
79a99f48f9
Remove old include path.
...
[ROCm/hip commit: 57274850f9
2016-02-15 05:40:37 -06:00
9ccdbdca71
Fix tests to account for multi-gpu
...
[ROCm/hip commit: 3ecd1b1539
2016-02-15 05:19:52 -06:00
9e60e519d4
Add multi-threading synchonization on staging buffers and signals.
...
Also pre-allocate a couple signals for copies.
[ROCm/hip commit: 6420655dc8
2016-02-13 03:18:01 -06:00
2d468c6ce2
D2H multi-buffer
...
[ROCm/hip commit: b314777bc1
2016-02-13 01:15:23 -06:00
a835134f8e
Improve copy testing
...
[ROCm/hip commit: 1bfd3cdbd0
2016-02-12 18:24:08 -06:00
83eb66eb8e
Improve copy testing implementation.
...
- add tests for (unpinned/pinned) x H2H x D2D.
- Free memory at end of test.
[ROCm/hip commit: 134d7975ce
2016-02-12 18:24:08 -06:00
c441d5ec29
Step1 in staging buffer copy.
...
- use StagingBuffer class for copies.
- refactor g_device to use array rather than vector.
(keeps pointers from moving).
[ROCm/hip commit: 24c1fdb864
2016-02-12 18:24:08 -06:00
b9dc0e9497
Query tracked memory sizes.
...
Support more accurate hipMemGetInfo. Add test to hipPointerAttrib.
[ROCm/hip commit: d7396b5af3
2016-02-12 18:24:08 -06:00
680b600b4a
Tracker improvements
...
- add API to add / remove user-pointers from the tracker.
- test for thread-safety with MultiThreadtest_2 - rapid
insertions/removal.
- add mutex to provide thread-safety.
- rename tracker interface to "memtracker_..." for consistency.
- add am_memtracker_reset, connect to hipDeviceReset.
-
[ROCm/hip commit: de45e2291e
2016-02-12 18:24:08 -06:00
d4a90f8afd
Create address tracker for am_alloc.
...
Tracks device where memory is allocated, pinned-host or device, and
more.
Uses memory-range-based lookups - so pointers that exist anywhere in
the range of hostPtr + size will find the associated AmPointerInfo.
The insertions and lookups use a self-balancing binary tree and
should support O(logN) lookup speed.
[ROCm/hip commit: 4ee2a5229b
2016-02-12 18:24:08 -06:00
fcd154097f
Fix typo: maxThreadsPerMultiProcessor -> MaxSharedMemoryPerMultiprocessor
...
Device property MaxSharedMemoryPerMultiprocessor set equal to totalGlobalMem (HIP path).
Reason: MaxSharedMemoryPerMultiprocessor should be as the same as group memory size. Group memory will not be paged out, so, the physical memory size = total shared memory size = group region size. NVCC path remains untouched: CUDA's device property MaxSharedMemoryPerMultiprocessor is reported.
hipify is updated as well.
[ROCm/hip commit: ea8f99702d
2016-02-12 01:29:20 +03:00
4eade0ce83
BDFID (BusID/DeviceID/FunctionID) support.
...
Except FunctionID (or DomainID in CUDA) support, because cudaDeviceProp::pciDomainID is not reported by CUDA.
[ROCm/hip commit: 33f60c300d
2016-02-11 22:26:01 +03:00
f8290141b1
Updated readme for test
...
[ROCm/hip commit: a87c7988e8
2016-02-11 13:06:58 +05:30
4c861f0284
Remove test for atomicInc and atomicDec
...
[ROCm/hip commit: 51bff8757c
2016-02-10 21:02:52 +08:00
1c89a8853a
Updated readme for test
...
[ROCm/hip commit: 6f2a94fb93
2016-02-10 20:05:59 +08:00
837875df37
Resolved test issues
...
[ROCm/hip commit: 4035b71df4
2016-02-10 20:01:16 +08:00
902c5aa972
Rename test hipInfo as hipGetDeviceAttribute
...
[ROCm/hip commit: 5aa254f32f
2016-02-09 13:19:32 +08:00
473a40af80
Test fixes:
...
- Remove reference to missing test.
- Add hipMemset back.
- Parse --gpu option to specify default starting GPU.
[ROCm/hip commit: 0c74d3fc44
2016-02-08 22:55:23 -06:00
f9f308c48d
in HIPCHECK, only run command once even if error occurs
...
[ROCm/hip commit: b8f7126662
2016-02-08 21:45:49 -06:00
c54d10e92a
Fix HIP_PLATFORM detection
...
[ROCm/hip commit: 272ae52506
2016-02-05 07:15:46 -06:00
2306293526
Implementation of hipDeviceGetAttribute()
...
[ROCm/hip commit: 0a27507208
2016-02-04 17:39:27 +03:00
2bf594e928
Merge branch 'master' into privatestaging
...
[ROCm/hip commit: 1327d3e03d
2016-02-03 09:39:19 -06:00
57d88913f8
Remove warning on ballot/any/all and pop/clz.
...
Since these are supported in HIP no reason to emit warnings.
[ROCm/hip commit: 3898f6af3c
2016-02-02 10:02:48 -06:00
19d0b8095f
Added test for ballot and removing HIP_FUNCTION from hipSampleAtomicsTest.cpp -sandeep
...
[ROCm/hip commit: 2b02fe082f
2016-02-02 14:50:55 +05:30
9ed3ef50fe
Add double and integer intrinsics to test
...
[ROCm/hip commit: 861cba6f75
2016-02-01 16:00:45 +05:30
79a0c836be
Disable sincosf which has trouble on hcc now.
...
[ROCm/hip commit: 93d1801a30
2016-02-01 17:42:37 +08:00
af51dd0a72
Split math function tests into several smaller tests
...
[ROCm/hip commit: 4d9e8b8673
2016-02-01 14:36:50 +05:30
bf51551d22
Disable testing of unsupported single precision intrinsics
...
[ROCm/hip commit: 276e20d4db
2016-02-01 14:34:28 +05:30
97cf8b8ac9
Initial commit for GPUOpen Launch
...
[ROCm/hip commit: f38e63ff18
2016-01-26 20:14:33 -06:00
Ben Sander
Evgeny Mankov
Maneesh Gupta
streamhsa
Sam Kolton
Jack Chung