Commit graph

6826 Commits

Autor SHA1 Nachricht Datum
Anusha GodavarthySurya 13e2e797c0 SWDEV-469422 - Derive GraphExec from Graph and ChildGraphNode from GraphExec
Change-Id: I54d67a1665355579bc249d8ff4f9806e9ee14588
2024-12-16 00:43:57 -05:00
Istvan Kiss 3c863dad91 SWDEV-502543 - Update doxygen to surface funtions and Coop Group API
Change-Id: Id4df63b8ae64a1113f85d89aa250ac9f7cc8b9bb
2024-12-14 14:11:37 -05:00
Sourabh Betigeri f1c05e9026 SWDEV-421020 - Adds hipGraphAddBatchMemOp, SetGetParams and execSetParams APIs
Change-Id: Ieccecfe6173cc68fd3c01f86c99f7cc09fe194a3
2024-12-13 06:23:39 +00:00
Sourabh Betigeri 03dbcd8ca7 SWDEV-440866 - [hip-roclr] Adds support to batch memory operations APIs
Change-Id: I5ac63a6626af8c2b4ac382c52dfe1aaf0b3716b8
2024-12-12 19:29:24 -05:00
Tao Sang 3ad8f1b811 SWDEV-496667 - Support gfx9-4-generic target
Support gfx9-4-generic target to cover mi3XX.
Support features sramecc and xnack in generic target.
Improve some code formats.
Add more log on compiler.

Change-Id: I6b3c6af55c60cffd43ce6f17b75998f751b75713
2024-12-12 14:43:39 -05:00
Saleel Kudchadker 537f2fffc9 SWDEV-301667 - Improve logging for hip_memory
Change-Id: Id624b2c91e6b701bc0ee561a0c193f2c66654890
2024-12-12 14:42:00 -05:00
Anusha GodavarthySurya 28cbf2bc4f SWDEV-469422 - Refacor childgraph node
Remove static functions in graph

Change-Id: I4df94915f81f250acaea60398aea32ef0ed658e2
2024-12-12 12:38:24 -05:00
Jaydeep Patel c8afd7109d SWDEV-496544 - Sync with stream if it is different than srcMemory stream.
Change-Id: I9c0f94a9531555278a51202ec7203961e1344c2e
2024-12-12 06:17:39 -05:00
Maneesh Gupta 072f94c204 Revert "SWDEV-491314 - enable _sync() functions with 64-bit mask argument"
This reverts commit 4e2fd192eb.

Reason for revert: Introduces regression SWDEV-503319

Change-Id: I888c5b95d904146e4782e8c57d736878fcdde678
2024-12-11 11:16:48 -05:00
Jatin Chaudhary 98b33886cd SWDEV-503299 - Do not use operator to check for nan
Some libs use __HIP_NO_HALF_OPERATORS__ and __HIP_NO_HALF_CONVERSIONS__
which results in operators being hidden and can cause errors.

Change-Id: I83c194d7d727cba30b46d7c296f7d396549f5fca
2024-12-11 00:33:44 -05:00
Todd tiantuo Li def369a010 SWDEV-489099 - Deprecate AMDGPU_TARGETS in lieu of supporting GPU_TARGETS
Change-Id: I184cd18e47b1618bcad0fadc8984de54d2a00a9b
2024-12-10 12:38:37 -05:00
Branislav Brzak 89dfdc4dbe SWDEV-490860 - Do signal_is_required detection post graph schedule
Change-Id: Iaf1067a811aeac3d16c08de954036e219b545e07
2024-12-09 03:57:44 -05:00
Jaydeep Patel 0d4823ff88 SWDEV-502532 - Exit graph launch in case of empty graph.
Change-Id: Ifb6ab14ca6810cbc1c9e38c59d1d9e7d367358d9
2024-12-07 12:27:53 -05:00
Ioannis Assiouras e80442fdbf SWDEV-497759 - Fix memObj offset computation for hipHostRegister on Windows mgpu
On Windows, hipHostRegister may add a single object in the MemObjMap
that maps to memory that is allocated on different devices.
This change ensures that the offset that is returned from
getMemoryObject() is computed relative to the memory that is allocated
on the current device.

Change-Id: I5fd3af200bf6f4926fdeaea12dcb9d0154d3a843
2024-12-05 16:18:10 -05:00
Marko Arandjelovic 78f62d3230 SWDEV-495609 - Change include path for rocclr/utils
- Header files inside rocclr/utils when included from hipamd or opencl should be included as #include "rocclr/utils/xxx.h" instead of "utils/xxx.h"

Change-Id: Ic0760c33b9d091f5620dec67e5482c9698d22093
2024-12-05 11:44:20 -05:00
Jatin Chaudhary 5122b8c999 SWDEV-501779 - add correct function qualifier for fp16 functions
Some functions were __device__ only, but should be __host__ and
__device__, changed them to __HOST_DEVICE__.
Some functions were __HOST_DEVICE__ but were using ockl functions,
changed them to __device__ only.

Change-Id: Ife9e7abe60415bda68f5f9a101e6e7c39ad51064
2024-12-05 10:17:18 -05:00
Branislav Brzak f2dba978f5 SWDEV-490860 - Include signal_is_required in dot file dumps
Change-Id: Iec4b433b11fbecb71a4ce68beb7d6f681d25b8e6
2024-12-05 04:51:59 -05:00
Shane Xiao 231b2410a0 SWDEV-492049 - Remove the handle of Phy Mem from Memobj
The hipGraph will use VMM by default when allocating memory.
However, the handle of Phy mem has been added to Memobj by default.
Since the Memobj will track the whole address range from handle to
handle + size, this needs the system to reserve the whole address
range. If the system range have not reserved by the system, then it
will have the potential issue that clr finds the Memobj incorrectly.

This patch removes the handle from the Memobj to fix this potential
issue.

Change-Id: I2da38e6b2d11d0d48e1afe66c46899500c290624
2024-12-04 19:39:52 -05:00
German Andryeyev efd3ea4b30 SWDEV-501403 - Switch to std::shared_mutex for streamSetLock
Shared mutex allows to have access to the list of streams  from
multiple threads at the same time.

Change-Id: Ibee64b846cde03321d5b17dbee2829c0bab7e7d6
2024-12-04 12:06:51 -05:00
Anusha GodavarthySurya b89977d518 SWDEV-469422 - Always schedule graph nodes
Change-Id: Icc636527fa19e7bf3eb111bc4b1bb9a5f9acff73
2024-12-03 23:44:23 -05:00
Saleel Kudchadker 6611cc015d SWDEV-494149 - Improve hipGet/Set Device
Change-Id: If8975687a3ba9caadafc48a0066f19a4ebaab9e2
2024-12-03 13:36:38 -05:00
Sourabh Betigeri 2ca644cf22 Revert "SWDEV-440866 - [hip-roclr] Adds support to batch memory operations APIs"
This reverts commit bd5d8e9baf.

Reason for revert: hipInfo fails on windows. Updating llvm amd-mainline-closed

Change-Id: I57e1fa1945188b0bc0a799c4f3d540f2b7713003
2024-12-02 16:46:12 -05:00
Marko Arandjelovic 08aee16573 SWDEV-499794 - Update AQL packet after updating GraphNode
Change-Id: I332d70bdf42a276894a548a02d636e370c2ca08c
2024-12-02 12:29:35 -05:00
Sameer Sahasrabuddhe 4e2fd192eb SWDEV-491314 - enable _sync() functions with 64-bit mask argument
Change-Id: Ieb13a9e1b2fc49ff225a05a51056d1212d95ae57
2024-12-01 10:16:59 -05:00
Sourabh Betigeri bd5d8e9baf SWDEV-440866 - [hip-roclr] Adds support to batch memory operations APIs
Change-Id: I449ffca44bbb04d13348d112e896d603c70fd485
2024-11-30 17:54:32 -05:00
Anusha GodavarthySurya c47f9dda58 SWDEV-469422 - Cleanup graph code remove parallellists and nodewaitlists
Change-Id: I00c7b2894333bd13d47b913d3fcdd6e1ffcb741f
2024-11-30 04:40:51 -05:00
taosang2 f1f4f40c5b SWDEV-447973 - Support generic targets
Change-Id: I32db83843e45e0f013591493aafd7a532c881e16
2024-11-29 10:12:10 -05:00
Vladana Stojiljkovic b75b0d9a53 SWDEV-494612- Add capture support for hipLaunchCooperativeKernel
Change-Id: I6b3c6af55c60cffd43ce6f47b75998f750b75703
2024-11-29 08:17:41 -05:00
Anusha GodavarthySurya fb7ad8361c SWDEV-489084 - Update max streams for graph
Change-Id: I6d0992b2e80ebf3184911593a4f3574327b2e9c3
2024-11-29 08:16:16 -05:00
Anusha GodavarthySurya 06e6561eb5 SWDEV-489084 - Avoid using queue colliding with the graph launch stream
Change-Id: I3ecaf8836c8e0883441275139041c702aba0937e
2024-11-29 08:15:58 -05:00
Sebastian Luzynski 019abdc3bd SWDEV-465085 - replace asserts inside API calls
This change replaces some asserts, that were only available in debug
mode, with standard error handling.

Signed-off-by: Sebastian Luzynski <Sebastian.Luzynski@amd.com>
Change-Id: I112f9e56f921abd72daf0d11e4ecdcb7b1a9f9e6
2024-11-29 04:11:39 -05:00
Marko Arandjelovic e94d9b1763 SWDEV-489617 - Make any host to any host memcpy synchronous
Change-Id: I2a29d1a433508f9b4b67b48c47bb4a4eebac0cb3
2024-11-29 03:48:28 -05:00
Satyanvesh Dittakavi e3b8754448 SWDEV-477584 - Match hipGetLastError behavior with CUDA using env var
Change-Id: I4c5acff180ae904028f7c5fdf4e109ffd1f0c4ef
2024-11-28 01:33:52 -05:00
Anusha GodavarthySurya 17e7b7c2ef SWDEV-472840 SWDEV-461980 - Fix null stream sync performance
=> If null stream is not created during sync skip nullstrm creation
=> Do cpu wait on blocking & null stream if it exists

Change-Id: I90d6ced6a2dd1782ba58f3fed4e3608fc0efa55a
2024-11-27 10:29:15 -05:00
Aidan Belton-Schure 9652d69575 SWDEV-436099 Use new amdgcn_ballot builtin
Change-Id: I024fabc6c5b3f39c66885eb7615953f4d0432e9a
2024-11-27 04:34:50 -05:00
Satyanvesh Dittakavi 70b20857e9 SWDEV-494808 - Do not allow hipMallocAsync/hipFreeAsync when another stream is capturing
hipMallocAsync/hipFreeAsync APIs should return error stating
operation is not supported, if a stream is actively capturing
and is different from the passed stream

Change-Id: I2a1b8260c5eb22d99a936ac529d6788a83f81a17
2024-11-26 12:12:56 -05:00
Rahul Manocha 1ac9286b5a SWDEV-497288 - Fix Segfault when kernel param is nullptr
1) for case where kernelParam_.func = nullptr, the validation
fails in setParam call and memory is not alloced for kernelParams
2) destructor path segfaults trying to free the kernelParams memory.
3) copy of params is done after function validation is successful.

Change-Id: I6338e0c89f259632e4115f0508e2f240bc207fd9
2024-11-26 11:34:41 -05:00
Rahul Manocha e0c11624e5 SWDEV-497288 - Enable hipGraphExecSetParams for Ext SemWait and SemSignal Nodes
Change-Id: I7184a3a04ac17d3d841222ae1559db66d73a429c
2024-11-26 11:34:18 -05:00
kjayapra-amd 39b64b57d9 SWDEV-496106 - Use lock_ops to avoid race condition in safe_stream.
Change-Id: I5e98c34a41434e2f7d2e6406ea30ddcf01b1091c
2024-11-26 06:56:56 -05:00
Anusha GodavarthySurya 25a893658a SWDEV-491643 - DEBUG_HIP_FORCE_GRAPH_QUEUES is 1 enable capture path
Change-Id: Ibddd50592232b090bf5eab8395fe78a36bb3a14a
2024-11-25 05:21:10 -05:00
Maneesh Gupta ec6f83b544 Revert "SWDEV-475482 - hipTexObjectCreate align with cuda"
This reverts commit efce2f77c4.

Reason for revert: Even though this change is valid, this would break backward compatibility.

Change-Id: I9c7cab83198c8d5c8485b11194099162e3e7a874
2024-11-21 00:55:32 -05:00
Rahul Manocha efce2f77c4 SWDEV-475482 - hipTexObjectCreate align with cuda
Support zero width and height for hipTextObjectCreate to align
with cuda.

Change-Id: I5d4c48625faf5f060ed2a7e634ec65e4ecac9da5
2024-11-19 23:28:55 -05:00
Rahul Manocha a2d8199402 SWDEV-494409 - Fix destructor path for Static and Dynamic CO
1) For Dynamic CO variables, free the device pointer in
   DynCO destructor instead of DeviceVar destructor.
2) For Static CO Remove Fatbinary,
   only call hipFree for valid device Vars instead of all devices.

Change-Id: I84291f5371b2c05d1d0bcdb4f9c6bd122e7c9b21
2024-11-19 13:04:44 -05:00
Jaydeep Patel d997f78be4 SWDEV-498077 - Check topoOrder_ before accessing it.
Change-Id: I10e3c24ca8dc1009b8ac8ac27b3e9a6296f9a7ee
2024-11-19 04:50:47 -05:00
Ioannis Assiouras 1a710dabcf SWDEV-496003 - Add support for dynamic functions in hipFuncSetAttribute
Modified hipFuncSetAttribute to handle pointers to dynamic functions
returned by hipModuleGetFunction.

Change-Id: I54b98f9d31a79630dd7edcd363fad81f1d89219b
2024-11-19 04:50:15 -05:00
Julia Jiang 3bd32d7d4b SWDEV-497618 - Define GL group of doxygen for HIP API
Change-Id: Ia43f25201df960b905e5fd45481f486e7bffabdb
2024-11-15 11:25:51 -05:00
Jaydeep Patel 24c57cb984 SWDEV-496544 - Reset mem alloc node count for AutoFreeOnLaunch.
Change-Id: Ib32b04584548a46632606ecd85b58c6ce4a5894d
2024-11-11 11:03:32 +00:00
Saleel Kudchadker 582dc7dd6d SWDEV-446123 - Revert "Match hipGetLastError behavior with CUDA using env var"
This reverts commit 5f477900a3.

Reason for revert: <INSERT REASONING HERE>

Change-Id: I11a456655393bcf4b82d749ce7259bc1b78d1424
2024-11-08 20:35:13 -05:00
Satyanvesh Dittakavi 5f477900a3 SWDEV-446123 - Match hipGetLastError behavior with CUDA using env var
Change-Id: Iaec697c1304d746376ecf2bfe2ad683b15ee189f
2024-11-07 12:02:34 -05:00
Branislav Brzak 6e55f40313 Revert "SWDEV-465201 - Match negative hipModuleLoad return with Cuda"
This reverts commit 68e5aeb93d.

Reason for revert: Breaking change that will be merged in at a later date

Change-Id: Idd300492cc08a57c50decc22df287ddcc5463c88
2024-11-07 09:51:50 -05:00