AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
12,441 Commits 3 Branches 0 Tags
bee336d3607cec325902e3fdff18b87f2960e1f4
Commit Graph

11723 Commits

Author SHA1 Message Date
Evgeny Mankov 3faa6fd86c Attribute hipDevAttrConcurrentKernels for obtaining Device property concurrentKernels is added. 
[ROCm/clr commit: d4bd94e9a0]
 2016-02-18 14:34:18 +03:00
Ben Sander a3ec0ae280 remove extra : 
[ROCm/clr commit: 866e64f6e2]
 2016-02-18 03:05:53 -06:00
Ben Sander 3888f4e212 Tweak version numbers 
[ROCm/clr commit: 53f37712bd]
 2016-02-18 21:29:51 -06:00
foreman 81e88cdc3c P4 to Git Change 1238217 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/18 03:00:11 
SWDEV-2 - Change OpenCL version number from 2037 to 2038.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1784 edit


[ROCm/clr commit: 992ecc19f9]
 2016-02-18 03:11:19 -05:00
Ben Sander 7760c82196 Merge branch 'memtracker' of https://github.com/AMDComputeLibraries/HIP-privatestaging into memtracker 
[ROCm/clr commit: d0f9881d60]
 2016-02-17 23:06:51 -06:00
Ben Sander f19c6d8342 Enable Tracker and ROCR by default, verify with HCC 
[ROCm/clr commit: 400dcb8bcb]
 2016-02-17 23:03:37 -06:00
Ben Sander 8ed32daefa Remove HIP-local AM tracker (now in HCC) 
[ROCm/clr commit: b08e468c06]
 2016-02-17 21:33:32 -06:00
Ben Sander 98e608a5ce USE_AM_TRACKER=0 works 
[ROCm/clr commit: 354c9f945a]
 2016-02-17 21:23:36 -06:00
Ben Sander f8d9017103 Tweak full formatting 
[ROCm/clr commit: d75279c8eb]
 2016-02-17 21:22:31 -06:00
Ben Sander 527d64a2da Support HSA_PATH env, async path tweak 
[ROCm/clr commit: 9a82d316c3]
 2016-02-17 21:22:07 -06:00
foreman d5ccaf288f P4 to Git Change 1237953 by kzhuravl@win-kzhuravl-stg-sc on 2016/02/17 13:32:36 
SWDEV-76911 - Remove HSART_NO_LARGE_BAR_SUPPORT define and do necessary updates (comes in 3 separate parts: stg sc, hsa, opencl changelists) [opencl part]

	ReviewBoardURL: http://ocltc.amd.com/reviews/r/9769/
	Testing: http://ocltc:8111/viewModification.html?modId=66952&personal=true&init=1&tab=vcsModificationBuilds

Affected files ...

... //depot/stg/opencl/drivers/opencl/compiler/sc/HSAIL/ext/loader/executable.cpp#19 integrate
... //depot/stg/opencl/drivers/opencl/compiler/sc/HSAIL/ext/loader/loaders.cpp#9 integrate
... //depot/stg/opencl/drivers/opencl/compiler/sc/HSAIL/ext/loader/loaders.hpp#9 integrate
... //depot/stg/opencl/drivers/opencl/compiler/sc/HSAIL/include/amd_hsa_kernel_code.h#10 integrate
... //depot/stg/opencl/drivers/opencl/compiler/sc/HSAIL/include/amd_hsa_loader.hpp#8 integrate
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpuprogram.hpp#64 edit


[ROCm/clr commit: e5635ffbe4]
 2016-02-17 13:40:22 -05:00
dfukalov 222206d3d8 Adding lit tests 
[ROCm/clr commit: cdcb45d9f2]
 2016-02-17 19:05:18 +03:00
atimofee 50f5ba8276 Hipify tool in it current state 
[ROCm/clr commit: 5cd248c55f]
 2016-02-17 18:34:58 +03:00
pensun 60f00e4e8a 1. Bug fix 
2. passed initial tests on different sets of
HIP_VISIBLE_DEVICES: (0),(1),(0,1),(1,2),(2,3),(1,2,3),(2,3,4),(1,5,2,3)
and achieved expected choice of GPU devices at the runtime.
3. Passed HIP test suite.


[ROCm/clr commit: c1da0f1e12]
 2016-02-17 09:32:50 -06:00
pensun afc377b2bc Implementation of HIP_VISIBLE_DEVICES in runtime 
[ROCm/clr commit: 43785243a5]
 2016-02-17 06:59:18 -06:00
foreman dc461f368a P4 to Git Change 1237747 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/17 03:00:10 
SWDEV-2 - Change OpenCL version number from 2036 to 2037.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1783 edit


[ROCm/clr commit: d1b2399af8]
 2016-02-17 03:06:09 -05:00
Ben Sander 6856d28ca3 more work on async copies 
[ROCm/clr commit: 0cdbe1ff05]
 2016-02-17 00:59:12 -06:00
pensun 31bba31b90 modify to add remove invalid devices numbers 
[ROCm/clr commit: 7309e9ea6a]
 2016-02-16 10:00:05 -06:00
pensun 07e4d8261c Implement to read HIP_VISIBLE_DEVICES to internal global variable 
[ROCm/clr commit: 45d863851d]
 2016-02-16 07:39:04 -06:00
foreman 4032693c05 P4 to Git Change 1237301 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/16 03:00:11 
SWDEV-2 - Change OpenCL version number from 2035 to 2036.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1782 edit


[ROCm/clr commit: a097a6e2ed]
 2016-02-16 03:10:40 -05:00
Ben Sander 0e83efe14d Add per-stream pool for hsa_signals. 
[ROCm/clr commit: 5d721a2649]
 2016-02-16 01:59:13 -06:00
Ben Sander d0b29d9192 Add comments to tests 
[ROCm/clr commit: 731a2a58d3]
 2016-02-16 01:58:24 -06:00
Ben Sander f8f40e07bf Update before checkin to HCC. 
Add support for USE_AM_TRACKER=2 (HCC version).
Add AM_ALLOC, AM_FREE indirection to ease swapping AM implementations.


[ROCm/clr commit: 1ed431c0f6]
 2016-02-15 21:16:00 -06:00
Ben Sander 93c07bc3d1 Move warpSize to header, have shuffles use default warpsize. 
[ROCm/clr commit: bd7e3b83b9]
 2016-02-15 05:41:09 -06:00
Ben Sander dc6f0ef3a6 Remove old include path. 
[ROCm/clr commit: 3b2d4acabc]
 2016-02-15 05:40:37 -06:00
Ben Sander 84810268c0 Update docs, cleanup 
[ROCm/clr commit: 322a3bd9b2]
 2016-02-15 05:40:12 -06:00
Ben Sander 7e46e90591 Fix tests to account for multi-gpu 
[ROCm/clr commit: afbe451b0d]
 2016-02-15 05:19:52 -06:00
Evgeny Mankov 979a875bb5 Formatting, no functional changes. 
[ROCm/clr commit: 763aa5ea5a]
 2016-02-15 13:16:05 +03:00
Ben Sander ed618e637e Add multi-threading synchonization on staging buffers and signals. 
Also pre-allocate a couple signals for copies.


[ROCm/clr commit: 8939b4f0e5]
 2016-02-13 03:18:01 -06:00
Ben Sander 275a36ee47 Enable -O3, style points on array size 
[ROCm/clr commit: 56b3d2e7c4]
 2016-02-13 03:17:42 -06:00
foreman c78c311475 P4 to Git Change 1236970 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/13 03:00:12 
SWDEV-2 - Change OpenCL version number from 2034 to 2035.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1781 edit


[ROCm/clr commit: 4ae7b701de]
 2016-02-13 03:09:10 -05:00
Ben Sander 61b2c054a2 D2H multi-buffer 
[ROCm/clr commit: a002833a89]
 2016-02-13 01:15:23 -06:00
Ben Sander e7666bd9d0 Result formatting 
[ROCm/clr commit: 8e3dd664eb]
 2016-02-13 01:14:01 -06:00
Ben Sander 6096173cd1 Add D2H test 
[ROCm/clr commit: 1cd35f6371]
 2016-02-12 22:47:26 -06:00
Ben Sander 06e7be346a Add D2H test 
[ROCm/clr commit: 81c275da13]
 2016-02-12 22:46:34 -06:00
Ben Sander ea298fae23 Add Bus Bandwidth test, leveraged from SHOC. 
[ROCm/clr commit: ba7497b409]
 2016-02-12 21:30:43 -06:00
Ben Sander b8ea1ec374 Improve copy testing 
[ROCm/clr commit: 2353cbb028]
 2016-02-12 18:24:08 -06:00
Ben Sander 4dfe77a99b Improve copy testing implementation. 
- add tests for (unpinned/pinned) x H2H x D2D.
- Free memory at end of test.


[ROCm/clr commit: 1128610801]
 2016-02-12 18:24:08 -06:00
Ben Sander 89e461988e Step1 in staging buffer copy. 
- use StagingBuffer class for copies.
- refactor g_device to use array rather than vector.
   (keeps pointers from moving).


[ROCm/clr commit: 90af462b85]
 2016-02-12 18:24:08 -06:00
Ben Sander 5978d5f372 Query tracked memory sizes. 
Support more accurate hipMemGetInfo.  Add test to hipPointerAttrib.


[ROCm/clr commit: f464cedcf4]
 2016-02-12 18:24:08 -06:00
Ben Sander 80d7c867d1 Remove ! USE_PINNED_HOST support 
[ROCm/clr commit: f2c1bf3bc0]
 2016-02-12 18:24:08 -06:00
Ben Sander 712750e1a5 Use memtracker 'appID' to store deviceID associated with ptr 
[ROCm/clr commit: c04b5d3afb]
 2016-02-12 18:24:08 -06:00
Ben Sander 2089e549eb 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/clr commit: 7216727fba]
 2016-02-12 18:24:08 -06:00
Ben Sander fe67be1134 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/clr commit: 721508cc2f]
 2016-02-12 18:24:08 -06:00
Ben Sander a50fa0f78e Fix bug in device bounds comparison. 
Shows up in multi-GPU.


[ROCm/clr commit: f1bc9af294]
 2016-02-12 18:24:08 -06:00
Maneesh Gupta 00d106a777 Documented supported fastmath functions 
[ROCm/clr commit: c82511258c]
 2016-02-12 14:21:58 +05:30
Maneesh Gupta 7c93bdebaf Updated integer intrinsics documentation 
[ROCm/clr commit: 2659e70d48]
 2016-02-12 13:58:35 +05:30
foreman 5a0961fdec P4 to Git Change 1236626 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/02/12 03:00:10 
SWDEV-2 - Change OpenCL version number from 2033 to 2034.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1780 edit


[ROCm/clr commit: 0b9a71219a]
 2016-02-12 03:09:11 -05:00
foreman b1845e0784 P4 to Git Change 1236618 by weizhang@msdnweizhang-opencl on 2016/02/11 22:12:34 
SWDEV-78299 - Back out changelist 1236441 since OCLCreateBuffer fails.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#541 edit


[ROCm/clr commit: fffbe5bb3b]
 2016-02-11 22:20:56 -05:00
Evgeny Mankov 6add51ef8c 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/clr commit: 460b501cbb]
 2016-02-12 01:29:20 +03:00