Commit Graph

5259 Commits

Author SHA1 Message Date
Anusha GodavarthySurya 2dccb30f6f SWDEV-485904 - propagate hsa_amd_vmem_address_free error to hip API
Unit_hipMemSetAccess_GrowVMM test fails with
HSA_STATUS_ERROR_RESOURCE_FREE silently

Change-Id: I7a78410e432de4a2e877062782abf8761645f392


[ROCm/clr commit: b498103f9b]
2024-10-21 10:12:32 -04:00
German Andryeyev 4a2687a450 SWDEV-486602 - Fix Windows 32 bit build
Windows alings fields to 8 bytes even with 32bit builds.
Add BUG_CLR_SYSMEM_POOL to cotnrol sysmempool.

Change-Id: I8622aabc9f7391ed7dd8583b252ce9eb41d62293


[ROCm/clr commit: 6bb7d1afdc]
2024-10-18 11:35:54 -04:00
German Andryeyev 640ba99b75 SWDEV-486602 - Change SysmemPool implementation
- Remove the list of all chunks and use embedded chunk
information in each allocation. That simplifies Free() logic,
avoiding expensive loop if for some reason the number of
outstanding allocations significantly grew.

Change-Id: I9ea84d314320ce356ed24dd3180f262e2116c59b


[ROCm/clr commit: ad18146d8f]
2024-10-17 12:39:39 -04:00
German Andryeyev 0a03665a3f SWDEV-491375 - Limit the SW batch size
Applications may submit commands withoout waits
for GPU. That causes a growth of SW unreleased commands.
Make sure runtime flushes SW queue, if it grows over some
threshold, controlled by DEBUG_CLR_MAX_BATCH_SIZE.

Change-Id: Ia4d85c24210ef91c394f638ab6b53b14323a0396


[ROCm/clr commit: 8657a77029]
2024-10-17 10:53:57 -04:00
German Andryeyev faea40cbb3 SWDEV-486602 - Optimize HSA callback performance
- Don't generate callbacks for HIP events
- Don't process profiling info in the callback for HIP events
- Wait for CPU status update of the submitted commands
every 50 calls. That will allow to drain the commands and
destroy HSA signals.

Change-Id: Ib601a350e7e7c2b6c6209a172385389baccf73a9


[ROCm/clr commit: 364dfb0ed1]
2024-10-11 14:50:25 -04:00
Todd tiantuo Li 170e45b879 SWDEV-472357 - support Rect copy with staging buffer for 2D & 3D memcpy in PAL
Change-Id: Ie32f3e5a6fa077f6b2db20fc1ab1e2e0da8344cb


[ROCm/clr commit: 41dc4545fc]
2024-10-10 18:00:19 -04:00
Jaydeep Patel 7983801b0c SWDEV-485866 - Return OOM if stream creation fails due to insufficient memory.
Change-Id: I4e57ecc81921bde274bb6a4e0890f0fc6a17955a


[ROCm/clr commit: 5ccc140e1b]
2024-10-10 00:44:54 -04:00
kjayapra-amd 3a2d835272 SWDEV-486573 - Check the return type of commit memory.
Change-Id: Id158cd7a0dff37b382b858cf7113aa4cf326300a


[ROCm/clr commit: 74ebbe17e9]
2024-10-09 05:10:03 -04:00
Branislav Brzak 491d3828dd SWDEV-482130 - Fix release of virtual mem obj
Change-Id: I893a8353aa1a25d00e36c8e601caf31cc0fc1f22


[ROCm/clr commit: 43fcac1739]
2024-10-08 01:37:39 -04:00
Saleel Kudchadker b9497ea70e SWDEV-301667 - Enable ROCr logging
- Use AMD_LOG_LEVEL=5 to dump AQL packets in ROCr

Change-Id: I2c044a5304c4eaf3d3af20e62d1f54c98d4fbaa4


[ROCm/clr commit: e36666e536]
2024-10-04 19:22:12 -04:00
Saleel Kudchadker 375ed9d848 SWDEV-478065 - Revert "SWDEV-478065 - Embed host thread in shared_ptr"
This reverts commit 274fd2628f.

Reason for revert: This blocks multithreaded callbacks

Change-Id: I9944417e4fb63c9eea2b286c828c7dfa621c4fe8


[ROCm/clr commit: d3d0ca5fc6]
2024-10-04 19:19:28 -04:00
Saleel Kudchadker 5296c77138 SWDEV-301667 - Logging upgrades
- Use AMD_LOG_LEVEL_SIZE in MBs to set log file size truncation, by default its 2048 MB

Change-Id: Ia2f87e8c6b94148e30edfb602b279f93630817c3


[ROCm/clr commit: 35e03ea0d0]
2024-10-04 13:26:25 -04:00
Jaydeep Patel 91b343c758 SWDEV-471422 - Free memory being double deducted on APUs due to system_total_alloced var holds local memory.
Change-Id: I3fbbc8f8aaa156881ff95cad6a4f82fd3df651d1


[ROCm/clr commit: 292842ad28]
2024-10-04 04:49:20 -04:00
Ioannis Assiouras 00cb623a67 SWDEV-488851 - Correctly remove the queue from the active set on windows
Change-Id: I4d21743ecf7a44636121f85566f898e62ff61e97


[ROCm/clr commit: 07bcc283f9]
2024-10-02 12:06:59 +01:00
Rahul Manocha 9f10e89d97 SWDEV-487903 - Fix for Empty Kernel Segfault in PAL
Change-Id: Ia1c19cf4ea24188cdb2d374b07f975f794e02dba


[ROCm/clr commit: 9da90fe848]
2024-09-30 13:00:15 -04:00
Anusha GodavarthySurya c0ceb1cf12 SWDEV-477324 - Capture Memcpy1D pinned H2D D2H
Change-Id: I1f4744f20a9caeed005ec68da44e5fde737e09f7


[ROCm/clr commit: 742b0210d3]
2024-09-30 01:01:30 -04:00
Vladana Stojiljkovic 887b11894b SWDEV-482086 - Fix hipGraphInstantiate leak
* In a scenario where kernel is launched with hipExtLaunchKernelGGL and stop event is used, hipGraphInstantiate leaks. Since stop event is used, profiling is enabled and Timestamp (ReferencedCountedObject) is created, but it doesn't get released.
* The idea behind this solution is that profiling should be disabled when command is captured, hence the timestamp should not be created. Because information about capturing isn't available when kernel command is created, packet capturing state is used to determine whether to create a timestamp or not.

Change-Id: Ia23adac4592ded4fb5e236acf99e12e729f63692


[ROCm/clr commit: da5f1a6146]
2024-09-29 11:36:53 -04:00
Ajay 98a1b3b42a SWDEV-486816 - RenderOpDispatch usage in pal client
Change-Id: I11cae3e625b287b998c9500c547efdacf1034a2b


[ROCm/clr commit: 7a288ea8bf]
2024-09-24 14:28:16 -04:00
German Andryeyev f8fc11c2d8 SWDEV-483586 - Unblock staging H2D transfers
Although unpinned copies require synchronizations
in HIP, runtime can avoid syncs for H2D copies with
a staging buffer

Change-Id: If2203c6bc0cbd89742823688dc8e89e9acd873b2


[ROCm/clr commit: 29cc678d8d]
2024-09-21 10:25:27 -04:00
Maneesh Gupta e87bf2096d SWDEV-485179 - Revert "SWDEV-459254 - Overwrite cacheline size to 256 for gfx12, as it is used for kernarg alignment."
This reverts commit 1f63650bf96e01e48f879aa58b80e2130dd4a567.

Reason for revert: <INSERT REASONING HERE>

Change-Id: I6d7ed87c09d9b77116548dce1f30ac4711c2c09d


[ROCm/clr commit: 2d1c6ee23e]
2024-09-20 11:33:34 -04:00
Anusha GodavarthySurya f278ac9ea0 SWDEV-485904 - Fix virtual,physical mem obj leaks
Change-Id: Ie0456b5dcfec206ae54a6aabfc2a15a620cac693


[ROCm/clr commit: 870842201d]
2024-09-19 23:04:20 -04:00
kjayapra-amd f19260d568 SWDEV-480772 - Remove name variable from amd::Monitor class.
Change-Id: Ie2a4fa44f485786227230f8a892e090e718aa30e


[ROCm/clr commit: 12a39fbf22]
2024-09-19 11:55:01 -04:00
pghafari 3fc58e93b3 SWDEV-444447 - Fix regression for verbose printing for AMD_LOG_LEVEL=4
Change-Id: Id245caef711b7ccdf4e999e934993beb43d7c3d5


[ROCm/clr commit: 365ffd4805]
2024-09-18 13:08:10 -04:00
Rahul Manocha e46733affe SWDEV-439234 - Fix for Segfault in ValidateMemAccess
Change-Id: I251d277eb5af16ba5c0de85ffd142a5f64fa469d


[ROCm/clr commit: 07261002b1]
2024-09-18 10:52:32 -04:00
Daniel Livingston 7c0ff614a2 SWDEV-77148 - Add UberTrace support to PAL device
This PR adds UberTrace-based tracing support to ROCclr's PAL device class.
Legacy RGP-based tracing is still available and is the default.
If UberTrace support is enabled tool-side, this new code path will activate.

Change-Id: I268b2dcef70e850a50e2caef8355f38bf51d4641


[ROCm/clr commit: e550032d25]
2024-09-17 16:06:37 -04:00
Jatin Chaudhary 274fd2628f SWDEV-478065 - Embed host thread in shared_ptr
This shows up in some valgrind runs. Make sure the resources are
released.

Change-Id: I34c25c00370a221585895655744831215136d5f4


[ROCm/clr commit: 4b03017e8a]
2024-09-17 09:53:51 -04:00
Ioannis Assiouras b5a8d775d6 SWDEV-476929 - Introduce an activeQueues set
The new set tracks only the queues that have a command
submitted to them. This allows for fast iteration
in waitActiveStreams.

Change-Id: I2c832eefa01280d9a87a5f57874d36d2e9441de7


[ROCm/clr commit: bcc545e6b8]
2024-09-16 15:53:49 -04:00
kjayapra-amd 196e2a53bc SWDEV-484188 - Change few std::array style globals to C style to avoid optimization on Static Libs.
Change-Id: Iab6d3c040b8d088013daa08093898be99dd3a971


[ROCm/clr commit: d81c5d3d7f]
2024-09-16 09:46:56 -04:00
kjayapra-amd e05182981a SWDEV-484188 - Moving std::maps into struct const and into amd::Kernel class.
Change-Id: Ie4d5a64511412fdb498b045aaffb52c3a1286de6


[ROCm/clr commit: 4ecd77df5e]
2024-09-15 09:14:51 -04:00
Ajay d7f4f778b3 SWDEV-465215 - hipFuncSetAttribute hipFuncGetAttributes fixes
Change-Id: I2151e4470d63918ff6b809a8fdeaae5bea5cc899


[ROCm/clr commit: c9955a1cea]
2024-09-13 14:05:25 -04:00
Saleel Kudchadker 343bdf3187 SWDEV-478624 - Use readback workaround to ensure kernel arg coherence
Use env var DEBUG_CLR_KERNARG_HDP_FLUSH_WA=1 to fall back to HDP flush
workaround. The default is 0

Change-Id: I7bdb9be61da60c30d15ac9991b7cd27351e1831c


[ROCm/clr commit: 9de6d4d46c]
2024-09-11 14:53:15 -04:00
Ajay 2a79ff2bca SWDEV-471863 - avoid copy of invisibleHeap
Change-Id: Ieb0aa22ac6d0d01cb9ca7fbf1305df03a1ab3cdf


[ROCm/clr commit: 5a810f789a]
2024-09-11 13:24:31 -04:00
Jaydeep Patel 7fa7a7cae5 SWDEV-475938 - Update dynamic stack in submit kernel internal.
Change-Id: I816bf9cfe8aaac5486ff3b719dbdc4f4d6134e01


[ROCm/clr commit: 9c90bc43a5]
2024-09-11 00:59:45 -04:00
Chong Li 4979c2f206 SWDEV-478929 - Benchmark ReallyQuickPureX Failed
Ensure the member function Alloc() and Free() of command_pool_ will not be
accessed after command_pool_ be destructed.

Signed-off-by: Chong Li <chongli2@amd.com>
Change-Id: Ic2d36423302518a030bd61fa399290ebe2ed8194


[ROCm/clr commit: e6a5c81221]
2024-09-10 22:08:18 -04:00
Saleel Kudchadker a3dc515316 SWDEV-301667 - Improve kernel logging
Change-Id: I4b2b1950e3ab7124fd41af9a92a677c48d6da5eb


[ROCm/clr commit: abc80fcc2f]
2024-09-10 13:43:58 -04:00
Saleel Kudchadker 95c84bef10 SWDEV-481974 - Clear dependent signal bit for barrier value
Change-Id: I3ffda051fa8538970fbb1964beb1f538fce0782c


[ROCm/clr commit: 62a7fed90d]
2024-09-10 13:43:04 -04:00
kjayapra-amd eecbcddaf3 SWDEV-439234 - Access check before memcpy and kernel operations.
Change-Id: I7057125c03460db205409e19980145298c190fe2


[ROCm/clr commit: 6211037f63]
2024-09-06 14:30:00 -04:00
victzhan fde29b7c06 Revert "SWDEV-458943 - make new AMD_MONITOR on"
This reverts commit 47dcfbae6b.

Change-Id: I2a7ddb2d4340224f43749a2ea91a894a8a95b83b


[ROCm/clr commit: 7a01db98e9]
2024-09-05 10:10:50 -04:00
Jimbo Xie 2036d66b95 SWDEV-403363 - add gfx1152 runtime support
Change-Id: I2f59ddb38a98d9f8edec5d1548232d4d826b7d04
(cherry picked from commit 5e94656f744e315ee7ae1285d3e6dd515f9d66a8)


[ROCm/clr commit: 3bdbc1eaf3]
2024-09-03 17:12:24 -04:00
Rahul Manocha c430e1c44d SWDEV-478921 - Destroy Queue created by Coop Launch
Change-Id: I7f31ce05421479ff1de138cae26aafa071e956e2


[ROCm/clr commit: ddbd7039b0]
2024-09-02 02:35:08 -04:00
Julia Jiang 71d97112cc SWDEV-476623 - correct the format on the fix for clCopyImage
Change-Id: I3a3fb2eaa338ff4e298a43e583fcf94ec7cabdf6


[ROCm/clr commit: 417d3279f9]
2024-08-28 16:16:24 -04:00
Julia Jiang 049a21f3da SWDEV-476623 - Fix test failures for clCopyImage
Change-Id: I971c5be98304bdbef0feec73e15ebd61a131b12f


[ROCm/clr commit: c3c41dae0d]
2024-08-27 11:43:12 -04:00
kjayapra-amd afd72f9ad0 SWDEV-478099 - Fix multiple mapping case on PAL/Windows backend.
Change-Id: Id1fe7939fbf90649cda1848890b3b4ca9a1fcd00


[ROCm/clr commit: 2a9cb89228]
2024-08-27 11:19:39 -04:00
Ioannis Assiouras a00f071579 SWDEV-470372 - Added hipExtHostAlloc API
This change adds a new HIP API `hipExtHostAlloc` which preserves
the functionality of `hipHostMalloc`.

Change-Id: I13504c6fc13465ddd7aed329795bb4f2fef1baff


[ROCm/clr commit: 2c84211b58]
2024-08-27 08:26:03 -04:00
ksankisa 3bcd901f06 [SWDEV-469495] Compile blit kernels with -fsanitize=address when asan is enabled.
Change-Id: I96e1abef43317cd58329c4a159f807878bc48cf4


[ROCm/clr commit: e76bf653fb]
2024-08-27 01:27:31 -04:00
kjayapra-amd f370cced08 SWDEV-479620 - Change argument type to size_t from uint64_t in nonTemporalMemcpy function.
Change-Id: I31f8a2b00685789b027d78be40a9f82c235f51b9


[ROCm/clr commit: 00eb038eec]
2024-08-24 07:42:37 -04:00
Ajay c774a3470d SWDEV-478881 - Fix log AMD_LOG file corruption
hiprtc and hip APIs use the same file.
Append to file instead of start of file

Change-Id: I2703f9bb67f0c51b557a058daab129679a0b5dd9


[ROCm/clr commit: e07172ff57]
2024-08-23 11:19:48 -04:00
kjayapra-amd 2af78c954b SWDEV-478097 - Check for parents size in case of VA Mem object.
Change-Id: Icfdeabeb178c0dcc8c3a4bc48eec40067985794e


[ROCm/clr commit: d7b097c994]
2024-08-22 14:18:51 -04:00
Shane Xiao 06912065d9 [SWDEV-479204] Fix the hipGraph AQL package fill issue
This patch fixes this potential issue that filling AQL header before
filling the AQL body. The hsa spec specifies "Packet processors may
process AQL packets after the packet format field is updated, but
before the doorbell is signaled."
However, the hipGraph AQL package with valid header will be filled
before fill the body, which may have the potential issue that CP
receive invalid AQL body.

Change-Id: I84af798c19ee2b8805ba19732b0eabdea2958a96


[ROCm/clr commit: 3959b5be1e]
2024-08-21 21:49:11 -04:00
Rahul Manocha 1b14058283 SWDEV-474617 SWDEV-464679 - Fix segfault in palvirtual due to peer memory access
Change-Id: Ib8b641712d78acf8bc073ca5705dea97af6f944a


[ROCm/clr commit: 432bdd7bf2]
2024-08-21 11:34:15 -04:00