Граф коммитов

159 Коммитов

Автор SHA1 Сообщение Дата
Jason Tang 6f8eaff4df Use ARCTURUS
Change-Id: Ib25d150c9314180178d5cf00835a06e47c02c2a9
2020-08-07 11:14:24 -04:00
Jason Tang f8f6bc16a1 SWDEV-246565 - Remove passing -msram-ecc to Comgr
Change-Id: I1604a0014186a5779561da3ec3eefec65aff5c37
2020-08-06 12:48:53 -04:00
Jatin Chaudhary 2f3df8e691 Adding device memory channel information
Change-Id: I47dfa3daff97b1e3f42484dde5a4aa64244ac544
2020-08-06 06:54:35 -04:00
Saleel Kudchadker ec73340348 Add Queue profling param and toggle for HIP
Use signal timestamps if NDRange command takes forceProfile flag.

Change-Id: Ib7f187d781fd78a7346818afb3344a9378f4c104
2020-08-06 03:09:53 -04:00
Anusha Godavarthy Surya 093f7fa3ca SWDEV-244600 - HIP BLIT code object needs to have reserved symbol name
Change-Id: I8401fea5eab71c0f7414eec0666066d9553a6622
2020-08-06 01:14:06 -04:00
Jason Tang 8ef5da00c7 SWDEV-246687 - Do not use std::vector reference as class member cuMask_
The current implementation creates default reference in the stack and assigns it to class member cuMasks_, so whenever the content of the stack changes, cuMask_ would change.

Change-Id: Iefab63c335d504b83c4ae90bd34ae76c6afb8f3c
2020-08-05 16:57:36 -04:00
German Andryeyev 91a25df04f Process cache coherency before mem dependency tracker
Optimizaiton to remove extra syncs uncovered a bug with the cache
coherency layer, there runtime could lose the track of mem address
if coherency layer performed a sync.

Change-Id: I25647cfa4a4be9cdbd8577ff076a740bbdac79c8
2020-08-04 16:33:18 -04:00
Vlad Sytchenko 9d0b0c32a9 Fix typo
Change-Id: I8b659508f567afa126aeb7749b536b443935e3df
2020-08-04 11:15:21 -04:00
Vlad Sytchenko 24c1c48db7 Only enable HIP for Vega20 on non-ROCm platforms
SWDEV-245906

All asics will still be supported for developer builds.

Change-Id: I0eac2246162d133fe63449c200d996fe05bd51bd
2020-07-27 13:09:58 -04:00
Tao Sang fdef6f722f Apply constexpr on global constant varaibles
When HIP_ENABLE_DEFERRED_LOADING=0, many global variables will be
referenced but they are not initialized in that early time. The patch
will use constexpr to initialze global constant varables in compile
time.

Change-Id: I9d538b7abc6a0ce700ec3332b97fc144db5fc1ef
2020-07-22 22:14:13 -04:00
Jason Tang 2800fc2fa3 SWDEV-232197 - Fix PAL build
Change-Id: Iad306077cadfd8de1491ac0a188eee4802d8ce1f
2020-07-22 17:10:03 -04:00
Jason Tang 65f4230494 SWDEV-232197 - Use TargetID for action_info_set_isa_name()
Change-Id: I6661a2bbc2e55586c1b5029694d67cb54a4f23a6
2020-07-22 13:47:17 -04:00
Freddy Paul 6b8ae3dd77 Align to new hsa cmake target usage.
HIP or any ROCm component above HIP may not be calling
hsa-runtime directly. OpenCl and HIP are the two components
calling ROCclr and to bring in the transitive dependency of
thunk,ROCR,amd_comgr it is better to have the dependency
chain set correctly in the ROCclr cmake target. With this
change OpenCl or HIP should not be setting ROCR dependency
directly.

This helps to link OpenCl(libamdocl.so) link statically with
comgr,hsa,thunk.

Change-Id: I0d538b7abc6a0ce700ec3332b97fc144db5fc5ff
2020-07-22 11:21:09 -04:00
Jatin Chaudhary 48690f29e9 Adding AnyOrder Flag
Change-Id: I6baaef42b98adfbc8cf2605e175ec007e008045f
2020-07-22 00:25:04 -04:00
Tao Sang 214827defa Add numa lib detection in cmake
If numa lib is in building system, define ROCCLR_NUMA_SUPPORT to
support numa; otherwise, don't support numa.

Change-Id: I3848d7fdec5a3813ff1edad9b71ff04372dc0b9a
2020-07-21 14:58:56 -04:00
Rahul Garg 60473ae542 Handle size 0 symbols
Change-Id: I1629c5027ec5f9af48c8e9e0696829b844423096
2020-07-21 10:10:36 -04:00
Jason Tang 8b7e0f3cfe SWDEV-232197 - Use HSA_ISA_INFO_NAME as the TargetID
TargetID will be passed to LC compiler.

Change-Id: I0385634922c11d53b57ebd596047698c47bda72b
2020-07-21 09:24:03 -04:00
Matt Arsenault 5577eabcea Fix -Wmissing-braces
Change-Id: I2394b6923c789f36e72242f4b196844cc0ee90ba
2020-07-15 16:51:03 -04:00
Jason Tang 5e0bb5bd39 SWDEV-244000 - Print freeMem_ for memory accounting
Change-Id: I5bbce213236a109e9aa69766d2d4d370b58d0d08
2020-07-15 13:44:05 -04:00
kjayapra-amd e993bf9f47 SWDEV-243423 - Avoid repeated metadata processing if the unbundled binary_ptr is same.
Change-Id: I71e008021b728dec61187d9ff29483ad8c4cad5c
2020-07-10 10:35:16 -04:00
agodavar de31b341d2 SWDEV-242592:Remove define of UndefinedVars in setKernels
Change-Id: I51b0c5ac6c4cb2564a53f7c45fdf8a893a5edbd3
2020-07-09 23:15:31 -04:00
kjayapra-amd 16e6b65b5c SWDEV-240165 - Move all amd::MemObjMap_ reference to ROCclr and only allow base ptr to get ipc handle.
Change-Id: I9de10a0c4ba4dee3b3c8b972966840ab807001d8
2020-07-09 21:19:45 -04:00
Jatin Chaudhary cd1e364911 Replacing deprecated HSA API calls with newer ones
Change-Id: Iebe2c00e717ab0e47c61611752b717966c719994
2020-07-08 00:32:24 -04:00
Aryan Salmanpour 4a901f3dd3 Always print error message with the returned error code before abort
Change-Id: I8479abc586937a50c90b2785c4ce7364e6e9732b
2020-07-07 16:28:30 -04:00
Tao Sang f7bf882981 Fix static lib crash by setting top init_priority
Set top init_priority on affecting global variables so that
they will be created firstly and destroyed lastly.

Change-Id: Ied59fbecab66ba8195c4a7a02b6bef9fa2fad3af
2020-07-06 16:54:10 -04:00
Matt Arsenault cfed3f310d Remove .value_type from code object v3 metadata
This seems to not actually have any function. The OpenCL API test
passes without it, and the way it's produced is problematic.

Change-Id: I384bfa01dee7023484348b184ddd1b2d44a91f7d
2020-07-06 11:07:30 -04:00
Matt Arsenault c56a82fd05 Fix unused function warnings for conditionally used functions
Change-Id: Ied23c571b949abef1816914986f19b14aca3d2f3
2020-07-06 10:28:43 -04:00
Matt Arsenault 9e3e41ca2e Remove unused functions
Change-Id: I55db791019c511de83d8b895e3a48b3d7475aeac
2020-07-06 10:27:29 -04:00
German Andryeyev 059832b526 Return always true for P2P validation under ROCr
Change-Id: Id32a5a94a642e708d1d042c5247af38501bec153
2020-07-04 11:38:04 -04:00
Aryan Salmanpour 34b82eb998 remove unused argument from enableHostcalls/disableHostcalls functions
Change-Id: I351a6b4e23cd9f118310c5c79b1afcb4758fde1b
2020-06-26 16:33:30 -04:00
Tao Sang da94cd0de1 Support numa policy set by user
Add hostNumaAlloc() to support numa policy set by user

Change-Id: Ib6c3e838aa53e3d9b3db9735c585df46a1c98944
2020-06-23 18:57:03 -04:00
Dittakavi Satyanvesh 7a3b8c6dd2 SWDEV-240566 adds error message before abort
Change-Id: I4dbd089daa5e6fde5e8722dc2395225dd822561c
2020-06-22 10:12:49 -04:00
Jason Tang 532083f87c For apu: call commitSvmMemory() from Device::svmAlloc()
Change-Id: Ic6e9b2ad4624e7e1c50835d3825254c76e764bf0
2020-06-22 10:09:32 -04:00
Jason Tang 138b2d3ce2 Set the tiled_ flag according to ImageCreateInfo
Change-Id: I3e1b2fdd15e32c3c24f4341001b068738c98e388
2020-06-19 12:34:07 -04:00
kjayapra-amd 71c05075ba SWDEV-229840 - Add Debug prints when the element is already present in MemObjMap_
Change-Id: I21129d087e73cc2a9e35f03e6a1a2dc527626f48
2020-06-19 12:33:20 -04:00
German Andryeyev 01fcf82448 Switch PAL to interface 610
Change-Id: Ida563f38513789f5ba105ac92a9737c59cd5d90d
2020-06-19 11:40:12 -04:00
Jason Tang 155ff5bdcc Merge pal Resource mapLayers/unmapLayers logic into map/unmap
Change-Id: I0198fb96f104539fb557f91160665e60ba576132
2020-06-19 10:51:48 -04:00
Aryan Salmanpour 1bd265f8d6 move hostcall-based implementation of messages/printf from rocm backend to the common device layer
SWDEV-232428

Change-Id: I14b774e66a1783569c6d34d8759c1faa5f340e27
2020-06-18 13:49:28 -04:00
Saleel Kudchadker d8efc31c34 Reset GPU_FORCE_BLIT_COPY_SIZE as its fixed in KFD
Commit ebcfa85cf7ebb26c96fca48a34292d88e74dd675
fixes programming of SDMA*_ULV_CNTL.HYSTERIS register

Change-Id: Ibb1d824bf3f8e351f840adbc099601b322f935f6
2020-06-17 13:23:41 -07:00
Vlad Sytchenko 5b9af8f28d Fix some -Wunused-but-set-variable warnings
Change-Id: I281583b5abdfc09d5dd8b7dfb20b8821581db193
2020-06-15 17:51:01 -04:00
German Andryeyev afe825c506 Fix compile error in ATI make build
Change-Id: Id9d23b8f46bf1b97c0f02c8ae0edd94e6963b1b5
2020-06-15 10:31:57 -04:00
Tao Sang b14d9e0a36 Deduce hops from numa distance
Rocr won't return real hops so that we have to deduce hops from
numa distance as a workaround. This will be subject to change
as driver team will provide a long term solution in rocm3.7

Change-Id: Ifb939ed848db190c3d544bb7f30a5821161921e6
2020-06-13 17:04:17 -04:00
Jason Tang 30e36a4925 Get gpu asicRevision_
Change-Id: I8afb53e027d912843655823eebaec29901c33d28
2020-06-12 14:51:52 -04:00
German Andryeyev c5afd5d412 Initial HMM support
- Expose ROCclr interfaces for HIP usage
- ROCr interfaces aren't available in staging, thus control the
build with AMD_HMM_SUPPORT define

Change-Id: Iadc2bcc230e78d3b0dc22b235189c8cc80843446
2020-06-12 09:06:07 -04:00
Rahul Garg 617538074c Fix IPC create memory failure
ROCr expects granular size in hsa_amd_ipc_memory_create

Change-Id: I7c266aa2eef8304f105298a7a668f4c4b3fb5f5a
2020-06-11 13:02:54 -04:00
Saleel Kudchadker 2b771d2f5f Add logging support for AQL packet
Use AMD_LOG_LEVEL=4 and AMD_LOG_MASK=8 to print AQL log
explicitly
Change-Id: I4209d91b460e64be44261d3ab773580067e47c29
2020-06-10 14:04:47 -07:00
Aryan Salmanpour 5203c5271b reuse available queue with the same priority if queue creation fails
Change-Id: I1522935ce1a73c4724135668d039e88a9097710b
2020-06-09 17:56:18 -04:00
Aryan Salmanpour 1d938697a1 fix a build error on TeamCity due to order of initialization in rocm Device class
Change-Id: I2e45e71e53272b7a7813422d3b949e3835077ab0
2020-06-08 13:56:39 -04:00
kjayapra-amd 1b0882e061 SWDEV-239327 - Dont call hsa_amd_memory_pool_free from ~amd::Memory() for obj created by passing devptr.
Change-Id: I315fd502df6bb1bf66dd24eac9325f1439e432ad
2020-06-05 18:42:03 -04:00
German Andryeyev 3828a61413 Make sure runtime sync before CPU access
Change-Id: I52882788ded187b3f735257a188b1b08d8502147
2020-06-05 12:00:08 -04:00