3ae839c85b
Add a test case for async double memset
...
Change-Id: I8a1df610c8d3d942651f258e7812e8697067c347
2020-05-20 12:52:29 -04:00
2ce6bbebc4
Fix async mem clear
...
Optimization for the fence release removed a sync for mem fill.
Add simple const buffer management forr the filled pattern to avoid
pattern overwriting with the async fills.
Change-Id: I63773ac09ceec31d5396d24570e4647ff096326b
2020-05-20 11:13:41 -04:00
a38144dec7
Don't add_subdirectory on a binary directory
...
This doesn't make sense and didn't do anything.
Change-Id: If6cbcd9269d8d45b091f100318afd3ab9ec6ceec
2020-05-20 09:01:08 -04:00
0af9c06968
Modified IpcDetach to return status instead of void.
...
Change-Id: I68ed94b93f0383babe25eb046b4047d249a0fdc1
2020-05-20 03:38:21 -04:00
60d6a28dc9
SWDEV-2 - Change OpenCL version number from 3144 to 3145
2020-05-20 03:00:03 -04:00
7273fdedfe
Fix include directories for cltrace
...
Change-Id: I8de82fa4b6ce7e1e869f1001d1710dc8673b7be5
2020-05-19 21:41:16 -04:00
1d267c9c08
Remove include/ from #includes
...
These are unnecessary and an obstacle to producing a relocatable
package.
Change-Id: I0059bf7a2d11fcece0cd7ab47d7545d0df4d7099
2020-05-19 19:35:09 -04:00
abc115bda8
Revert "Reenable cooperative groups"
...
This reverts commit 82dc1a6343
2020-05-19 18:21:48 -04:00
49224d95c7
SWDEV-236894 - Rename LOG_LEVEL to AMD_LOG_LEVEL
...
Change-Id: Ibdfaf0fb615ac343c05d0fa3c3ace9cbb592ecf3
2020-05-19 17:32:24 -04:00
601cf7d4bb
Add dlerror to ICD to help future diagnosis
...
Change-Id: Ieb95252ab671ff666fceee3349637683078a0f89
2020-05-19 10:49:19 -04:00
4ed5c887c0
enable occupancy sample on HIP-Clang
...
Change-Id: I236daad743bbbc7f8daa41e8157a4ff73058518b
2020-05-19 03:08:19 -04:00
9f9d35ad86
Restore attempt to use find_package for ROCclr
...
94b20323
2020-05-18 14:34:35 -04:00
cd2a713d63
Add major/minor/stepping to device layer
...
Change-Id: If82ea55a46b166b243a98089a6e9c40ccfdb479f
2020-05-17 12:57:34 -04:00
90c975224f
SWDEV-2 - Change OpenCL version number from 3143 to 3144
2020-05-16 03:00:03 -04:00
e1961c838f
Fix hipMemset for unaligned ptr, correct offset required by ROCclr per aligment and testcase to validate unaligned ptr
...
Change-Id: Ib1a0f9d1556d09cf72a12a90cad2e27c6d9c6a1c
2020-05-16 02:38:14 -04:00
42150302e6
Remove dependency on hsa-ext-rocr-dev package
...
Change-Id: I1b4032390c128e71a2f9a743b9db9b7bf7713e91
2020-05-15 16:56:30 -05:00
9b5e1fec6c
Correct the way to get subtarget
...
Change-Id: I47805424c0bd69547cff0ab71c369552016052b5
2020-05-15 17:18:39 -04:00
4932115d6d
[hip] Skip lang guess if -x <lang> is specified.
...
Change-Id: If5cbdd1e5d36d2d8b83f3eadd0598162691167aa
2020-05-15 17:07:40 -04:00
8edad73f14
Remove empty file
...
Looks accidentally added
Change-Id: Ib7dce6ffe9c131b08674a1e304b561fbd940362e
2020-05-15 16:30:37 -04:00
fed94b8604
Add support for setting CU mask on ROCclr for ROCm backend
...
Change-Id: I0dbe2eeb33467fc0f24b26929119c10e9b455da7
2020-05-15 14:23:43 -04:00
206810e014
Include interface directories from rocclr target
...
This is overly painful because this is an object library.
Change-Id: I618843b810549876053212bf24efff18aece9470
2020-05-15 13:17:13 -04:00
82dc1a6343
Reenable cooperative groups
...
Change-Id: Ia43049ef550bffa6d21704dbd306ddb9c1d56af0
2020-05-15 12:41:12 -04:00
6a5af4056e
Use system scope for packet following sdma copies
...
SWDEV-234947
SWDEV-236298
Instead of forcing a barrier packet, just inject system scope on the next packet.
Change-Id: If9bcee23e08dfe5db731235e2fcb30582cbd4c1c
2020-05-15 12:20:06 -04:00
0a9d550d9b
load functions when registered if lazy load is disabled
...
Change-Id: I6f10a72f7643e476407af03b04ef52e59741be45
2020-05-15 12:15:32 -04:00
ae65b83869
Merge "SWDEV-235875:Fix rocALUTION build error" into amd-master-next
2020-05-15 12:10:02 -04:00
8b52d70b9b
Merge "API tracing instrumentation" into amd-master-next
2020-05-15 11:18:14 -04:00
ef87227a3f
Merge branch 'amd-master-next' into amd-npi-next
...
Change-Id: Ie692324c8cf6215bf6cf87de0d5e3aa1bdfd5ea1
2020-05-15 11:15:27 -04:00
b9f0b54cae
Merge "Fix missing hip_version.h install and package" into amd-master-next
2020-05-15 10:38:09 -04:00
1a48abfdd6
Fix missing hip_version.h install and package
...
Change-Id: I7182518f8c0dea6e00ffd649d1a29027fdc78b24
2020-05-14 21:54:28 +00:00
3624b8df16
Fix missing target includes for GL/EGL headers
...
Change-Id: I9a31eae40cb7187dd0264ad5b9577fab96464b41
2020-05-14 16:56:34 -04:00
945726f870
SWDEV-235875:Fix rocALUTION build error
...
Change-Id: I2f2a15687e943a860ff6ca05f22422f791a36c0a
2020-05-14 14:43:25 -04:00
4638f0f11c
updating envar to HIP_ROCCLR_HOME
...
Change-Id: Ic0bbf40638538307377e6db1a7379fb23dec8306
2020-05-14 12:59:51 -04:00
10cb7645dc
API tracing instrumentation
...
Change-Id: I257409b9fe299b009ded3e3a43287322d5f93a70
2020-05-14 11:03:09 -05:00
345a8a89b3
SWDEV-2 - Change OpenCL version number from 3142 to 3143
2020-05-14 03:00:03 -04:00
3a7f2e3682
Improve usage of target_include_directories
...
Eliminates most of the global include_directories. The install header
paths are different from the build directory, so we have to separate
those for the exported target include paths.
Change-Id: I13e4c56c1218cb31c29a316422dc5fd1d09d8b1b
2020-05-13 17:25:58 -04:00
6152b200cb
adding support to disable lazy loading, HIP_ENABLE_LAZY_KERNEL_LOADING
...
Change-Id: Iafe0f396570ee2bccf642b537cbf9aad967e1370
2020-05-13 17:18:48 -04:00
614aaa8409
Load versioned comgr library
...
Change-Id: I4cc81f33e6889ac81a82747159bc210256f33c21
2020-05-13 16:46:35 -04:00
199f6114d0
Move top.hpp into include directory
...
This partially avoids a difference in the include paths between a
build and install tree, and simplifies the install configuration.
Change-Id: If8119507594e0d284ac08c141c6c51c88ec619ef
2020-05-13 16:30:43 -04:00
9726cb85d4
Merge "Fix missing hip_prof_str.h in hip-base package" into amd-master-next
2020-05-13 16:25:06 -04:00
a48ba48773
Merge "Correct mgpu coop launch test" into amd-master-next
2020-05-13 16:20:24 -04:00
8904848abc
Set CPU access flag for SVM
...
Make sure all GPUs have CPU access flag for the fine grain buffer.
Change-Id: Ifc843c2807e70a271b269192ae7859205ff458f3
2020-05-13 16:05:46 -04:00
e61b8dc425
Fix missing hip_prof_str.h in hip-base package
...
Change-Id: Icd163ff83fadc2ee0e68f5755c652a45d2e781e5
2020-05-13 19:13:16 +00:00
999295b3fa
Correct mgpu coop launch test
...
When the original size is devided accross all GPUs rounding can
occur, causing incorrect validation. Readjust the final value
for comparison to the new size accordingly.
Change-Id: I9b42149e33dfcb328de7419e546a0202a69a8610
2020-05-13 14:39:11 -04:00
5067cd1dd1
Correctly check if env vars are set
...
Change-Id: I365da786c822e9395aec5c6b75753ba297da3f64
2020-05-13 14:08:03 -04:00
a3b730b595
adding HIP_ENABLE_LAZY_KERNEL_LOADING flag
...
Change-Id: Ia4425e00d97a25bcea656e2ade5cd3a5d92b4de6
2020-05-13 13:06:55 -04:00
2cc0fb9381
Make sure to remove the global var from amd::MemObjMap
...
We need this otherwise ROCr can give us a matching address
for another allocation and doing "insert" in ROCclr will not
update the map with the newest object. We would then end up
using stale objects (yikes)
SWDEV-234992
Change-Id: I3475adf9781a9309d64a024fae45181d7e5afb04
2020-05-13 00:26:19 -07:00
c15d217f1a
SWDEV-2 - Change OpenCL version number from 3141 to 3142
2020-05-13 03:00:03 -04:00
374fd36f31
Add lock to addFatBinary and removeFatBinary
...
In case hipModule(Un)Load is called from different thread as hipInit we need to grab the lock
as both are going to modify modules_
Also add some logging for __hipExtractCodeObjectFromFatBinary in case binary isn't found for GPU
SWDEV-236032
Change-Id: Icbd72b412502df80d5066cea42a4fbcd5b0b8a98
2020-05-12 16:04:08 -07:00
4fa2ce777a
Merge "search path logic updated for extractkernel SWDEV-230929" into amd-master-next
2020-05-12 17:59:47 -04:00
93dcace83c
Merge "SWDEV-235495 Fix elapsed time calculation" into amd-master-next
2020-05-12 15:23:23 -04:00
German Andryeyev
Matt Arsenault
Chauncey Hui
Aakash Sudhanwa
Jason Tang
Dittakavi Satyanvesh
agodavar
Ramesh Errabolu
Christophe Paquot
Aryan Salmanpour
Payam
Icarus Sparry
Aaron En Ye Shi
Vlad Sytchenko
Aaron Enye Shi
Evgeny
Saleel Kudchadker