Graf commitů

293 Commity

Autor SHA1 Zpráva Datum
Chris Freehill 42bbc5ee85 Undo temporary namespace change
Change-Id: I7f4c06f7037713db855b51367256cf4c7ba41860


[ROCm/ROCR-Runtime commit: 5a3230af66]
2017-10-20 20:02:13 -05:00
Chris Freehill ca41ce6730 Temporary change to namespaces to adjust for smi change
Change-Id: Ic91bfb678912a82214f0a462a4b57e531f12977a


[ROCm/ROCR-Runtime commit: 50a3d9402a]
2017-10-20 13:12:06 -04:00
Ramesh Errabolu a4d753615b Changes to support surfacing of link weight as part of link info
Change-Id: I1c0705a9374af1245f0419c51beded0d7ee10639


[ROCm/ROCR-Runtime commit: dccbc9f2af]
2017-10-20 12:09:31 -04:00
Chris Freehill 26ebd1727c Use Major/Minor/Step device numbers to differentiate gfx devices
Change-Id: I0901871971a5b33018917ada6c0e69ac7aa91944


[ROCm/ROCR-Runtime commit: a7cbe78366]
2017-10-13 16:18:24 -04:00
Sean Keely 93e58b9100 Capture more memory allocation types with the 2MB allocator.
TensorFlow was running out of VRAM due to padding up allocations
from legacy memory APIs.  These allocations have been added to
the fragment allocator to improve VRAM utilization.

Change-Id: Ic680fff576a0434b3b17a4c91746da44e09957fa


[ROCm/ROCR-Runtime commit: 4f299a9909]
2017-10-12 23:22:10 -04:00
Ramesh Errabolu e5a242acf5 Update Copy requests involving all pools i.e. options -a or -A
Change-Id: I0c8d8fbb39f43cd6a1f84ae6ae32337fa9b1f5e2


[ROCm/ROCR-Runtime commit: 703b1466c1]
2017-10-10 13:01:46 -04:00
Evgeny b07cbdc10e aqlprofile API: enabling privilege memory related counters
Change-Id: I28a24ad1a3ce78c5d8a6319635ae1ffd392ab690


[ROCm/ROCR-Runtime commit: fd99e909ff]
2017-10-09 17:34:54 -05:00
Chris Freehill 05e78f7910 Make rocrtst use new rocm_smi library
Change-Id: Id688d6d6d5ff106a23f5b55eaca4e723c39433a3


[ROCm/ROCR-Runtime commit: 75eb3316aa]
2017-10-06 09:41:10 -05:00
Ramesh Errabolu d4972f3c67 Benchmark copy of data from one pool to another pool either in
one or both directions. Users can enumerate the pools reported
  by system to specify which pools serve as source / destination

Change-Id: I8e6d0adb3743b3328dd3ce9152762ca840ea613b


[ROCm/ROCR-Runtime commit: c2caa5ae2c]
2017-10-04 20:53:25 -04:00
Ramesh Errabolu a45d32e59b Adding kernels to read / write buffers
Change-Id: Icad95c084e0fcd0bd9f86154e23ac8f54c24afbe


[ROCm/ROCR-Runtime commit: 34602f7e95]
2017-10-04 20:33:48 -04:00
Sean Keely 06c7997137 Release cached memory blocks when memory allocation fails and retry.
Change-Id: I6d96e136e147d8ffe9ff7baec26b4b5a678b739f


[ROCm/ROCR-Runtime commit: 9ba83d83f7]
2017-10-03 20:12:05 -04:00
Ramesh Errabolu 6497cf10b7 Cmake project to build Rocm Code Objects
Change-Id: If3a631615316c203318bb5ae1df328a66e2919b1


[ROCm/ROCR-Runtime commit: 2cab8307b9]
2017-10-03 17:53:56 -04:00
Chris Freehill a4bc830f61 Temporarily diable Max Memory alloc. test
Change-Id: I13cfc77bd5b823354e60a3023356255c72c1fd6c


[ROCm/ROCR-Runtime commit: 0adfe5a18e]
2017-10-03 00:19:08 -04:00
Chris Freehill 76b9f76690 Add IPC test to rocrtst
Change-Id: I6a40375790a184df11afc88b863cafc3d244e92a


[ROCm/ROCR-Runtime commit: c8b92c5087]
2017-10-01 11:01:31 -04:00
Chris Freehill 55a09b6818 Fix build error in release version
Change-Id: I5b8378e4e771369ff2b2cc64ddfb44dde38d8d44


[ROCm/ROCR-Runtime commit: 3fa0b7e5b4]
2017-09-28 23:47:51 -04:00
Sean Keely 21a65a1233 Support hsa_amd_agents_allow_access on page fragments.
Since access may only be manipulated on whole pages, suballocator fragments must cooperate to set the page's access.
Since the KFD does not migrate memory on access changes this implementation makes agent access sticky across the requests in a fragmented page.

Change-Id: I88479ed45fb40e9782b704526a7b8ffb22e7bd76


[ROCm/ROCR-Runtime commit: e9a6f2c3e6]
2017-09-27 19:04:04 -05:00
Evgeny 64b516415c removing graphics specific block RMI, ennabling memory related blocks
Change-Id: I477adc49b9ee3c8593c193bdc69c0deb4a9726e1


[ROCm/ROCR-Runtime commit: 0e88414f5c]
2017-09-25 10:49:22 -05:00
Sean Keely 36d1168183 Fix assert in simple_heap.
Also add comments to clarify pointer info constraints.

Change-Id: I8d07831a0e953d667c84c96fe53ed07c18ba115c


[ROCm/ROCR-Runtime commit: 476c8e36bf]
2017-09-21 00:47:18 -04:00
Evgeny 4c5404b89d adding hsa_ven_amd_aqlprofile.h to the packaging
Change-Id: I3b69396e3cea129106d47be53218213e29de9843


[ROCm/ROCR-Runtime commit: fcaecfee80]
2017-09-20 14:40:49 -04:00
Sean Keely 595c7130d2 Enable use of CLOCK_MONOTONIC_RAW for post 4.4 kernels.
Change-Id: I3c1f27c7e639df5128c36d81f715fa16e6c1cf13


[ROCm/ROCR-Runtime commit: 30fce248c6]
2017-09-20 14:28:23 -04:00
Chris Freehill 6c0e9b2c6f Use relative dir. instead of abs. (2nd instance)
Change-Id: I778a59e94efdd0845249473d92eaedd172429a48


[ROCm/ROCR-Runtime commit: 7d46a02df4]
2017-09-19 21:38:38 -04:00
Chris Freehill 27631645c4 Use rel. dir instead of abs. in CMake;Have a default number if iterations
Change-Id: I097fd229338ed520196cc4ed1ef1d00fe538e50c


[ROCm/ROCR-Runtime commit: 7d84190c4e]
2017-09-19 14:13:49 -04:00
Chris Freehill 5a31817b33 Use relative path for symlink instead of absolute
Change-Id: I165f38df43afd554f022bb3bac54546c7bc5e806


[ROCm/ROCR-Runtime commit: 2d58324ac8]
2017-09-19 09:25:43 -04:00
Sean Keely c5f1027982 Improve branch elimination in ScopedAcquire.
GCC can't reasonably be told that the lock ptr isn't null.  Adding a private bool
allows the branch to be eliminated, along with the bool.

Change-Id: I0605d69474d6a6e6951be93c0af1d8caf3f77124


[ROCm/ROCR-Runtime commit: 9dfdce5b3c]
2017-09-19 06:08:36 -04:00
Sean Keely 3aeea948cb Add env key to disable 2MB suballocation.
Change-Id: Icca3041c3578aa180a656c01aae62f2ad6e8b583


[ROCm/ROCR-Runtime commit: 4275661682]
2017-09-19 06:08:36 -04:00
Sean Keely 9fd778eec1 Add suballocator for ordinary VRAM allocations smaller than 2MB.
Track pointer info for sub 2MB fragment allocations in allocation_map_.

Add fragment support to IPC.

Change-Id: I00cfc2e2fa289aac90a4718c392f9bb056a61a87


[ROCm/ROCR-Runtime commit: 117be0b55a]
2017-09-19 06:08:36 -04:00
Chris Freehill 0ae72ff335 Remove reliance on env. variables to build rocrtst
Change-Id: I451dc9da4e810db51a4ec19e17a9b5206d09a224


[ROCm/ROCR-Runtime commit: ae4a9c4d91]
2017-09-16 23:58:20 -04:00
hthangir 3dc1b18d54 Use non-RAW version in clock_getres to workaround bug in older kernels
Change-Id: Ice0606a42cd7054f0804baf4af3521ffae3b7d50


[ROCm/ROCR-Runtime commit: 87d2df3da3]
2017-09-14 13:56:15 -05:00
Chris Freehill b22f297ea2 Remove use of tools library
Change-Id: I80eb95987e1e91c67bd6c3e4b12df934860940f1


[ROCm/ROCR-Runtime commit: b4f2e8d8f1]
2017-09-13 13:49:56 -05:00
Chris Freehill c937b65f2f Adjust CMakefile to use defines instead of env. vars.
Change-Id: If5e97269774416eb65ab2d6d3f9e299b950c63a4


[ROCm/ROCR-Runtime commit: 0cb7db7d7e]
2017-09-13 09:33:18 -04:00
Chris Freehill 14e7851781 Modified to build within Jenkins
Change-Id: I70c9c6b690f198c41641432478343d3714e26ab0


[ROCm/ROCR-Runtime commit: 80a7bdf66b]
2017-09-08 12:57:23 -05:00
Sean Keely e150edc48c Report tools library load failures in debug builds.
Change-Id: Ie1ff313e929fc46134e58730a1d370c5d7ace8db


[ROCm/ROCR-Runtime commit: f1a661dedb]
2017-08-31 21:32:48 -04:00
Laurent Morichetti b2cb6bca96 Include <errno.h> for EBUSY
Change-Id: I9fa3417445866f3ce37af2169f623afa8e92e873


[ROCm/ROCR-Runtime commit: 0f05ef73ac]
2017-08-31 07:32:51 -07:00
Chris Freehill af02d06972 Async mem. copy test with NUMA awareness
Change-Id: If655ac4c087be2d379e868aad83812f2437d78b9


[ROCm/ROCR-Runtime commit: 92e46584f8]
2017-08-30 21:35:37 -04:00
Ramesh Errabolu 39f0c3e821 Add Iommu Perf Cntrs
Change-Id: I1cf3f00a959a923462634a62263707a267ae18af


[ROCm/ROCR-Runtime commit: 3980b4268b]
2017-08-28 12:57:11 -05:00
Evgeny e18c7098a3 aqlprofile api: adding gfx8 mc counters
Change-Id: I84dc06c24b7961dfe665cf7e2ae6cc9ae3b7326b


[ROCm/ROCR-Runtime commit: 09c732c2f9]
2017-08-23 15:23:05 -05:00
Sean Keely 4ff7a53721 Correct vm_fault signal cleanup.
Change-Id: Id2f14b911e3991a76771425bc09f38a613280e6b


[ROCm/ROCR-Runtime commit: 0cb1e8cb35]
2017-08-18 22:12:38 -04:00
Chris Freehill 90b3fee7f5 Remove dependency on hsa-runtime-tools
Change-Id: Ic4ce2bcbf1176e7eb859db39f21e7185691837e1


[ROCm/ROCR-Runtime commit: c85322d93d]
2017-08-17 15:39:35 -04:00
Evgeny 1fcbd14d89 AqlProfile API, commenting out hanging GFX9 blocks, ATC, GCEA, RPB
Change-Id: I411fb33f77c9538ca236b9b6b09c7dfe75220c02


[ROCm/ROCR-Runtime commit: fb4afca8c3]
2017-08-15 12:44:00 -05:00
Sean Keely 468313f9b5 Simplify pointer info version check.
Change-Id: I0ed363f1261ffc041547f313970ca67298ace56c


[ROCm/ROCR-Runtime commit: dec5c52e07]
2017-08-12 03:14:39 -04:00
Sean Keely 546c179cfc Initial IPC signal support.
Added an API for creating signals with attributes.
Added two APIs for IPC operations on signals.
Initial use of exceptions for error handling.

Add ref counting to signals.
Removed spin loops from signal destructors.
Signals are no longer to be destroyed with delete, use DeleteSignal instead.
Added delete safety to doorbells.
Added secondary hsa_signal_t -> Signal* translation path for IPC enabled signals.

Change-Id: Id59065d002f0c2566b0a9425694da2ed27cb7d7f


[ROCm/ROCR-Runtime commit: c9642cf7af]
2017-08-11 18:41:34 -05:00
Sean Keely 550547f404 Initial exception support for signals.
Also separate signal ABI block allocations from the runtime interface object.

Change-Id: If16763338db664f29163a1348f8f4c38cf0597b2


[ROCm/ROCR-Runtime commit: 2732b18092]
2017-08-11 18:41:34 -05:00
Sean Keely 76e67099b3 Update ipc test to use IPC signals.
Change-Id: Id5984093de45b08261d3196cc6fc3d597324edf4


[ROCm/ROCR-Runtime commit: d6acd0edfc]
2017-08-11 17:29:55 -04:00
Evgeny ce72ce0c92 adding aqlprofile member to HsaApiTable
Change-Id: Id674186dfa2e83295a51f770ccc0400f1cb51a98


[ROCm/ROCR-Runtime commit: 287afd3a52]
2017-08-09 16:09:39 -05:00
Evgeny 200067f1be Adding HSA_API macro to the API method declarations to be consistent with other HSA header files, TCS removing
Change-Id: Ic217d3b2bdbb22d3600c5ecaacb7ab53bf26096a


[ROCm/ROCR-Runtime commit: 4824a2db0b]
2017-08-08 10:46:12 -04:00
Chris Freehill e16e5fb048 Remove build of non-existent project
Change-Id: I6b2c59e67c2d2a320e705b725f8c779b9913759a


[ROCm/ROCR-Runtime commit: 783a28b68c]
2017-08-08 10:03:36 -04:00
Evgeny c0c32288ac aqlprofile block list, explicit numbers assigned, IA removed
Change-Id: I9f9358f8e03e13eb81845de2e33dd5f3da27811a


[ROCm/ROCR-Runtime commit: 47322942b3]
2017-08-03 11:39:21 -04:00
Evgeny d224dc274f aql-profile api: reducing blocks list to compute only and new gfx9 blocks
Change-Id: Ib506b82ea407afec4f5d4bcad755d4d57b92e34b


[ROCm/ROCR-Runtime commit: c66f68041c]
2017-08-02 12:21:24 -04:00
Chris Freehill aca0282c61 Clearer/more concise variable names
Change-Id: Ib92211977066b728f19b2a7fe40639160a8262b3


[ROCm/ROCR-Runtime commit: ab2248132a]
2017-08-01 10:38:26 -05:00
Chris Freehill 9aae431f6d Added max. single mem. allocation test.
Change-Id: Ie81c6af0502fde56225b1e197801cf04b474feb2


[ROCm/ROCR-Runtime commit: cf24f7bb78]
2017-07-31 12:04:55 -05:00