Revīziju grafs

64512 Revīzijas

Autors SHA1 Ziņojums Datums
Saleel Kudchadker 3dfef513b1 SWDEV-433634 - Check Relaxed capture interaction mode for the thread
- Allow capture to be less rectrictive if we set the global thread
interaction mode for the thread.

Change-Id: I84f65d9418ac26ada0477c85a45a3831c2351ce4


[ROCm/clr commit: 59a6a6c12e]
2023-12-06 22:35:20 +00:00
Saleel Kudchadker 59a6a6c12e SWDEV-433634 - Check Relaxed capture interaction mode for the thread
- Allow capture to be less rectrictive if we set the global thread
interaction mode for the thread.

Change-Id: I84f65d9418ac26ada0477c85a45a3831c2351ce4
2023-12-06 22:35:20 +00:00
Benjamin Welton ee77f548f7 Reduce max memory usage of buffer-parallel test (#280)
[ROCm/rocprofiler-sdk commit: 7ab334b432]
2023-12-06 14:00:22 -08:00
Benjamin Welton 7ab334b432 Reduce max memory usage of buffer-parallel test (#280) 2023-12-06 14:00:22 -08:00
sdashmiz 47c2968471 SWDEV-421027 - Add struct for graph node params
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ibe8dcabb3391c41bca0a0300bf5811d877a19d1b


[ROCm/hip commit: 19fcfbcfd2]
2023-12-06 16:06:47 -05:00
sdashmiz 19fcfbcfd2 SWDEV-421027 - Add struct for graph node params
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ibe8dcabb3391c41bca0a0300bf5811d877a19d1b
2023-12-06 16:06:47 -05:00
David Yat Sin ed1b0b9b1a Add queries for HSA Ext interface version
Change-Id: I26860fb1364cd3a33cdc9b284ac807b2702bb241
2023-12-06 13:58:52 -05:00
David Yat Sin ff72129092 Add queries for HSA Ext interface version
Change-Id: I26860fb1364cd3a33cdc9b284ac807b2702bb241


[ROCm/ROCR-Runtime commit: ed1b0b9b1a]
2023-12-06 13:58:52 -05:00
Ioannis Assiouras 1868de1f7d SWDEV-436236 - Fixed integer division to float result in Heap::FindMemory
Change-Id: Ic72cfdbe1f62fabd3e25d33bfa540d82a02480d0


[ROCm/clr commit: 2ede1c9adb]
2023-12-06 12:41:00 -05:00
Ioannis Assiouras 2ede1c9adb SWDEV-436236 - Fixed integer division to float result in Heap::FindMemory
Change-Id: Ic72cfdbe1f62fabd3e25d33bfa540d82a02480d0
2023-12-06 12:41:00 -05:00
Ioannis Assiouras 5a141cbda4 SWDEV-433821 - Make hipStreamWaitEvent flags a default argument
Change-Id: I0192c1c5f69a1bbcc3f9919f76c947dc40737cb8


[ROCm/clr commit: a562194562]
2023-12-06 12:37:35 -05:00
Ioannis Assiouras a562194562 SWDEV-433821 - Make hipStreamWaitEvent flags a default argument
Change-Id: I0192c1c5f69a1bbcc3f9919f76c947dc40737cb8
2023-12-06 12:37:35 -05:00
Youssef Aly 9f30432dd7 SWDEV-411647: enabling kernel trace flag with sys-trace option
To allow results_<XXXXX>.csv to be regenerated as it contains extra information not present in hcc_ops_trace, hip_api_trace, hsa_api_trace CSV files. The extra information is Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size.

Change-Id: Ief371b41aa41d77397c00e6b4281568e494b26dc
2023-12-06 12:29:57 -05:00
Youssef Aly 5f72f481ad SWDEV-411647: enabling kernel trace flag with sys-trace option
To allow results_<XXXXX>.csv to be regenerated as it contains extra information not present in hcc_ops_trace, hip_api_trace, hsa_api_trace CSV files. The extra information is Dispatch_ID,GPU_ID,Queue_ID,PID,TID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,Wave_Size.

Change-Id: Ief371b41aa41d77397c00e6b4281568e494b26dc


[ROCm/rocprofiler commit: 9f30432dd7]
2023-12-06 12:29:57 -05:00
Benjamin Welton b98dc4453c Reduce gate capacity further for NAVI3 cards (#277)
[ROCm/rocprofiler-sdk commit: b19b4eddc7]
2023-12-06 07:55:21 -08:00
Benjamin Welton b19b4eddc7 Reduce gate capacity further for NAVI3 cards (#277) 2023-12-06 07:55:21 -08:00
Jatin Chaudhary 07237ed91d SWDEV-435702 - the functions in bf16 header need to be static
If the compiler decides not to inline these functions, we might break ODR (one definition rule) due to this file being included in multiple files and being linked together

Change-Id: Iacbfdabb53f5b4e5db8c690b23f3730ec9af16c0


[ROCm/clr commit: 77c581a3eb]
2023-12-06 03:59:54 -05:00
Jatin Chaudhary 77c581a3eb SWDEV-435702 - the functions in bf16 header need to be static
If the compiler decides not to inline these functions, we might break ODR (one definition rule) due to this file being included in multiple files and being linked together

Change-Id: Iacbfdabb53f5b4e5db8c690b23f3730ec9af16c0
2023-12-06 03:59:54 -05:00
Galantsev, Dmitrii bb50cf42a2 TESTS - Fix overdrive error on not-supported
Change-Id: I47e7f499229b47b151f4ba4d5fa9c59ac04d6816
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/rocm_smi_lib commit: 102c2c692a]
2023-12-06 02:43:04 -06:00
Galantsev, Dmitrii 102c2c692a TESTS - Fix overdrive error on not-supported
Change-Id: I47e7f499229b47b151f4ba4d5fa9c59ac04d6816
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2023-12-06 02:43:04 -06:00
Satyanvesh Dittakavi 70ee947527 Revert "SWDEV-419480 - HIPRTC implementation of standard headers shouldn't be in std namespace"
This reverts commit 239fdc3bfd.

Reason for revert: This is considered a breaking change and requires
multiple apps to change their behavior. This will be reintroduced in later releases.

Change-Id: I3481627115af1872785585a155cc6a0ecfbe1372


[ROCm/clr commit: 7febad13be]
2023-12-06 03:11:59 -05:00
Satyanvesh Dittakavi 7febad13be Revert "SWDEV-419480 - HIPRTC implementation of standard headers shouldn't be in std namespace"
This reverts commit 353dbe6e3b.

Reason for revert: This is considered a breaking change and requires
multiple apps to change their behavior. This will be reintroduced in later releases.

Change-Id: I3481627115af1872785585a155cc6a0ecfbe1372
2023-12-06 03:11:59 -05:00
Anusha GodavarthySurya 183bc0a591 SWDEV-351966 - Remove hipRegisterTracerCallback from dispatch table
Change-Id: Ib343e2c8414a98c0cee6c60fb74a47bb859d8f45


[ROCm/clr commit: d347f1d67d]
2023-12-06 01:23:33 -05:00
Anusha GodavarthySurya d347f1d67d SWDEV-351966 - Remove hipRegisterTracerCallback from dispatch table
Change-Id: Ib343e2c8414a98c0cee6c60fb74a47bb859d8f45
2023-12-06 01:23:33 -05:00
Alex Sierra 803e37ded5 core dump: Generates a core dump from a fault event
Extracts and creates a core dump ELF file from a fault event, using
core dump front end.

Signed-off-by: Alex Sierra <Alex.Sierra@amd.com>
Change-Id: Ibbbe41b3d13dd3fcb90161e927d48c329cf513a9
2023-12-05 23:19:14 -05:00
Alex Sierra 9aa39b0979 core dump: Generates a core dump from a fault event
Extracts and creates a core dump ELF file from a fault event, using
core dump front end.

Signed-off-by: Alex Sierra <Alex.Sierra@amd.com>
Change-Id: Ibbbe41b3d13dd3fcb90161e927d48c329cf513a9


[ROCm/ROCR-Runtime commit: 803e37ded5]
2023-12-05 23:19:14 -05:00
Alex Sierra 54604654bd reports KFD core dump support through hsakmt API
Member added to KFDVersion to report if KFD supports core dump
mechanism. This is done through hsaKmtRuntimeEnable API call while
the topology is being built. It also dictates if core dump will be
generated by either KFD or hsa-runtime.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I2e9d4166563402f78613d728446feb692c52d9d1
2023-12-05 23:19:14 -05:00
Alex Sierra 4370aa1364 reports KFD core dump support through hsakmt API
Member added to KFDVersion to report if KFD supports core dump
mechanism. This is done through hsaKmtRuntimeEnable API call while
the topology is being built. It also dictates if core dump will be
generated by either KFD or hsa-runtime.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I2e9d4166563402f78613d728446feb692c52d9d1


[ROCm/ROCR-Runtime commit: 54604654bd]
2023-12-05 23:19:14 -05:00
Alex Sierra 91f2a70817 core dump: ulimit check mechanism added
Core dump generation considers ulimit to generate the proper size
file.

Signed-off-by: Alex Sierra <Alex.Sierra@amd.com>
Change-Id: I61d991fc003b173f9075b66bff6a931447720695
2023-12-05 23:19:14 -05:00
Alex Sierra ba0e2d3664 core dump: ulimit check mechanism added
Core dump generation considers ulimit to generate the proper size
file.

Signed-off-by: Alex Sierra <Alex.Sierra@amd.com>
Change-Id: I61d991fc003b173f9075b66bff6a931447720695


[ROCm/ROCR-Runtime commit: 91f2a70817]
2023-12-05 23:19:14 -05:00
Alex Sierra 514b222368 core dump: Front end core dump API
This API consists in one function to be called from a fault event at the
hsa-runtime to generate a core dump.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: Ib1b90d5beb13f93c4e8ebd21fd61705ebb12ca5d
2023-12-05 23:19:14 -05:00
Alex Sierra f4f6a49cbd core dump: Front end core dump API
This API consists in one function to be called from a fault event at the
hsa-runtime to generate a core dump.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: Ib1b90d5beb13f93c4e8ebd21fd61705ebb12ca5d


[ROCm/ROCR-Runtime commit: 514b222368]
2023-12-05 23:19:14 -05:00
Alex Sierra 1083d5c35f core dump: SegmentBuilder classes added
SegmentBuilder classes are used to get core dump data from the GPUs.
So far, it uses thunk API calls and smaps to collect all data from
the Hardware.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I2ad70ca5a951885181d3142653b186b0f6be739e
2023-12-05 23:19:14 -05:00
Alex Sierra 663e42663b core dump: SegmentBuilder classes added
SegmentBuilder classes are used to get core dump data from the GPUs.
So far, it uses thunk API calls and smaps to collect all data from
the Hardware.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I2ad70ca5a951885181d3142653b186b0f6be739e


[ROCm/ROCR-Runtime commit: 1083d5c35f]
2023-12-05 23:19:14 -05:00
Rahul Garg 8a0d73882a SWDEV-427855 - hipamd change for profiler and TF fix
This reverts commit e1889b77b4.

Change-Id: Id69e47a1afd336ae1edb9c8e173be27e7b9dcc8d


[ROCm/clr commit: afc28b091e]
2023-12-05 20:33:48 -05:00
Rahul Garg afc28b091e SWDEV-427855 - hipamd change for profiler and TF fix
This reverts commit 57cb840058.

Change-Id: Id69e47a1afd336ae1edb9c8e173be27e7b9dcc8d
2023-12-05 20:33:48 -05:00
Rahul Garg bf38b8c38e SWDEV-427855 - hip change for profiler and TF fix
This reverts commit bc9d9ec3ae.

Change-Id: I423d97faba4040ddb96fc7c910c1fbab4e730f13


[ROCm/hip commit: 8499557191]
2023-12-05 20:33:31 -05:00
Rahul Garg 8499557191 SWDEV-427855 - hip change for profiler and TF fix
This reverts commit 4f17f91f4f.

Change-Id: I423d97faba4040ddb96fc7c910c1fbab4e730f13
2023-12-05 20:33:31 -05:00
Youssef Aly bfd4730cb0 Disabling Tracer Gtest: Async_mem_copy
Test fails with a generic HsA_STATUS_ERROR

Change-Id: Icf076124304797169f848cdc524f3d52f161f54e
2023-12-06 00:30:35 +00:00
Youssef Aly 286450a07a Disabling Tracer Gtest: Async_mem_copy
Test fails with a generic HsA_STATUS_ERROR

Change-Id: Icf076124304797169f848cdc524f3d52f161f54e


[ROCm/rocprofiler commit: bfd4730cb0]
2023-12-06 00:30:35 +00:00
Ioannis Assiouras d614ceced0 SWDEV-433317 - Added compilation flag to report an error if vla is used
Change-Id: I8a03e1fece88ec52261c53684c9f66bbfc401a12


[ROCm/hip-tests commit: 3ae4d80e86]
2023-12-05 17:53:18 -05:00
Ioannis Assiouras 3ae4d80e86 SWDEV-433317 - Added compilation flag to report an error if vla is used
Change-Id: I8a03e1fece88ec52261c53684c9f66bbfc401a12
2023-12-05 17:53:18 -05:00
colramos-amd 65114f64bd Added missing hasattr checker
Signed-off-by: colramos-amd <colramos@amd.com>


[ROCm/rocprofiler-compute commit: cddc57bf08]
2023-12-05 13:06:44 -06:00
colramos-amd cddc57bf08 Added missing hasattr checker
Signed-off-by: colramos-amd <colramos@amd.com>
2023-12-05 13:06:44 -06:00
Giovanni LB 71bc875ccd Adding coordinate query to aqlprofile
Change-Id: I9f2fee62a24cf2a4784ba9e8c813b7b7296d034b
2023-12-05 13:25:30 -05:00
Giovanni LB 952f750a77 Adding coordinate query to aqlprofile
Change-Id: I9f2fee62a24cf2a4784ba9e8c813b7b7296d034b


[ROCm/ROCR-Runtime commit: 71bc875ccd]
2023-12-05 13:25:30 -05:00
Giovanni LB e8920cacc8 : Adding ATT API extension to aqlprofile
Change-Id: Ic511cf871d5d98638d7041ca277f945ae8ced3a5
2023-12-05 13:25:10 -05:00
Giovanni LB a633cba5ea : Adding ATT API extension to aqlprofile
Change-Id: Ic511cf871d5d98638d7041ca277f945ae8ced3a5


[ROCm/ROCR-Runtime commit: e8920cacc8]
2023-12-05 13:25:10 -05:00
Rahul Manocha b821fdbfba [SWDEV-431345][SWDEV-432633] toplevel cmake for hip samples
Change-Id: If22e7e96604f184458cc6ab6bb9945152f9359e0


[ROCm/hip-tests commit: 7481de706f]
2023-12-05 11:36:15 -05:00
Rahul Manocha 7481de706f [SWDEV-431345][SWDEV-432633] toplevel cmake for hip samples
Change-Id: If22e7e96604f184458cc6ab6bb9945152f9359e0
2023-12-05 11:36:15 -05:00