76333 Коммитов

Автор SHA1 Сообщение Дата
Oliveira, Daniel f13cbb8d10 amd_smi_lib: Fix missing sym link causes segfault
Changes AMDSmiDrm to use the versioned library for its dependency

Code changes related to the following:
  * AMDSmiDrm::init()

Build changes related to the following: None

Change-Id: Ibd5b3dd88f679912acdfa292502003f58b28daf5
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>


[ROCm/amdsmi commit: e20fd12934]
2023-10-31 10:33:34 -04:00
JoseSantosAMD 74bb5f94f5 Fix dispatch notation
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>


[ROCm/rocprofiler-compute commit: a3dcfa8cb2]
2023-10-31 10:24:14 -04:00
JoseSantosAMD a3dcfa8cb2 Fix dispatch notation
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-10-31 10:24:14 -04:00
JoseSantosAMD f6955ba7e3 pytest scripts updated to revamp test cases
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>


[ROCm/rocprofiler-compute commit: d787bac913]
2023-10-31 10:24:14 -04:00
JoseSantosAMD d787bac913 pytest scripts updated to revamp test cases
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-10-31 10:24:14 -04:00
JoseSantosAMD 71bd81d92d Tests create difference logs calculated from a baseline
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>


[ROCm/rocprofiler-compute commit: 279552c03f]
2023-10-31 10:24:14 -04:00
JoseSantosAMD 279552c03f Tests create difference logs calculated from a baseline
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-10-31 10:24:14 -04:00
JoseSantosAMD 84a94a3e3e Roof only csvs updated
-  Removes dir if workload dir already present

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>


[ROCm/rocprofiler-compute commit: acd33f5347]
2023-10-31 10:24:14 -04:00
JoseSantosAMD acd33f5347 Roof only csvs updated
-  Removes dir if workload dir already present

Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-10-31 10:24:14 -04:00
JoseSantosAMD 6b067c1618 pytest now checks soc for soc specific testing
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>


[ROCm/rocprofiler-compute commit: 43781c0454]
2023-10-31 10:24:14 -04:00
JoseSantosAMD 43781c0454 pytest now checks soc for soc specific testing
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-10-31 10:24:14 -04:00
JoseSantosAMD 6e29311c07 Check if csvs populated
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>


[ROCm/rocprofiler-compute commit: 585b0f27fe]
2023-10-31 10:24:14 -04:00
JoseSantosAMD 585b0f27fe Check if csvs populated
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-10-31 10:24:14 -04:00
JoseSantosAMD 9b1ca277c4 Initial commit for pytest
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>


[ROCm/rocprofiler-compute commit: edaa6ad818]
2023-10-31 10:24:14 -04:00
JoseSantosAMD edaa6ad818 Initial commit for pytest
Signed-off-by: JoseSantosAMD <Jose.Santos@amd.com>
2023-10-31 10:24:14 -04:00
Bill(Shuzhou) Liu de5bc164de Query the CPU and GPU link type
The rsmi_topo_get_link_type() is extended to support query the CPU
and GPU link type by passing dv_ind_dst as 0xFFFFFFFF.

Change-Id: I1f212a01e8120adb70a08ab772fa9faaaecefa29
2023-10-31 10:17:24 -04:00
Bill(Shuzhou) Liu 4a67734b65 Query the CPU and GPU link type
The rsmi_topo_get_link_type() is extended to support query the CPU
and GPU link type by passing dv_ind_dst as 0xFFFFFFFF.

Change-Id: I1f212a01e8120adb70a08ab772fa9faaaecefa29


[ROCm/amdsmi commit: de5bc164de]
2023-10-31 10:17:24 -04:00
Bill(Shuzhou) Liu fee0c807ce Query the CPU and GPU link type
The rsmi_topo_get_link_type() is extended to support query the CPU
and GPU link type by passing dv_ind_dst as 0xFFFFFFFF.

Change-Id: I1f212a01e8120adb70a08ab772fa9faaaecefa29


[ROCm/rocm_smi_lib commit: de5bc164de]
2023-10-31 10:17:24 -04:00
Ammar ELWazir d033cf3ab7 SWDEV-428381: Moving rocminfo to use the one available in the path
Change-Id: I736cc2ca9ddabf35cbb24d3fba553e2cbec5e396
2023-10-31 10:08:28 -04:00
Ammar ELWazir bff9a1bf61 SWDEV-428381: Moving rocminfo to use the one available in the path
Change-Id: I736cc2ca9ddabf35cbb24d3fba553e2cbec5e396


[ROCm/rocprofiler commit: d033cf3ab7]
2023-10-31 10:08:28 -04:00
sdashmiz 9b297f0006 SWDEV-417075 - add hipDrvAddMemCpyNode
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ie631d7b1788f10171a29d463759a3cba3b2b2007

SWDEV-417075 - add hipDrvGraphAddMemcpyNode

Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I6bab3310919643e119cd0004276907e223641cfb


[ROCm/clr commit: 9b567e1799]
2023-10-31 09:55:42 -04:00
sdashmiz 9b567e1799 SWDEV-417075 - add hipDrvAddMemCpyNode
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ie631d7b1788f10171a29d463759a3cba3b2b2007

SWDEV-417075 - add hipDrvGraphAddMemcpyNode

Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I6bab3310919643e119cd0004276907e223641cfb
2023-10-31 09:55:42 -04:00
Karl W Schulz c92af15df5 update branch for CI -> 2.x
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: 6fd2e44e5f]
2023-10-31 09:51:36 -04:00
Karl W Schulz 6fd2e44e5f update branch for CI -> 2.x
Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
2023-10-31 09:51:36 -04:00
Karl W Schulz 37382bf95f Introduce a cmake option to enable python code coverage. It now
defaults to being disabled and can be enabled via a
-DENABLE_COVERAGE=ON option (#194).  Introduce CI on mi100 that
leverages code coverage and publishes results along with a testing
report.

Signed-off-by: Karl W Schulz <karl.schulz@amd.com>


[ROCm/rocprofiler-compute commit: a39514f02f]
2023-10-31 09:51:36 -04:00
Karl W Schulz a39514f02f Introduce a cmake option to enable python code coverage. It now
defaults to being disabled and can be enabled via a
-DENABLE_COVERAGE=ON option (#194).  Introduce CI on mi100 that
leverages code coverage and publishes results along with a testing
report.

Signed-off-by: Karl W Schulz <karl.schulz@amd.com>
2023-10-31 09:51:36 -04:00
akolliasAMD 691df735a3 Revert "Introduce allgather for MSCCL on 8 sockets up to 320KB. (#931)" (#939)
This reverts commit 769f00db5c.

[ROCm/rccl commit: 9f02ee8dea]
2023-10-30 23:52:58 -06:00
akolliasAMD 9f02ee8dea Revert "Introduce allgather for MSCCL on 8 sockets up to 320KB. (#931)" (#939)
This reverts commit bfb8642450.
2023-10-30 23:52:58 -06:00
Galantsev, Dmitrii 6d7376a793 Fix python setup.cfg on rhel8
Change-Id: If06fd0e6f3a5574a9f318de23b9eaa712e1c03bb
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2023-10-30 22:28:23 -05:00
Galantsev, Dmitrii 91ef279bc4 Fix python setup.cfg on rhel8
Change-Id: If06fd0e6f3a5574a9f318de23b9eaa712e1c03bb
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 6d7376a793]
2023-10-30 22:28:23 -05:00
Maisam Arif 4dd7e8a41f Update python wrapper with esmi updates
Change-Id: I0274821f6525e60f76ec9ba9e4b2a50b19231031
Signed-off-by: Maisam Arif <maisarif@amd.com>
2023-10-30 20:10:44 -05:00
Maisam Arif 5e18c29b3b Update python wrapper with esmi updates
Change-Id: I0274821f6525e60f76ec9ba9e4b2a50b19231031
Signed-off-by: Maisam Arif <maisarif@amd.com>


[ROCm/amdsmi commit: 4dd7e8a41f]
2023-10-30 20:10:44 -05:00
Deepak Mewar 78b2db036b Updated README for esmi python wrappers
Change-Id: I95d345c12040a2163131bd48c5a687ccf734edd0
2023-10-30 20:59:21 -04:00
Deepak Mewar 37f1dc3441 Updated README for esmi python wrappers
Change-Id: I95d345c12040a2163131bd48c5a687ccf734edd0


[ROCm/amdsmi commit: 78b2db036b]
2023-10-30 20:59:21 -04:00
Deepak Mewar 28f6383639 Esmi Auxillary API wrappers removed from amdsmi library
that are called during amdsmi inititalization
    amdsmi_get_cpu_family,
    amdsmi_get_cpu_model,
    amdsmi_get_cpu_threads_per_core,
    amdsmi_get_number_of_cpu_cores,
    amdsmi_get_number_of_cpu_sockets

Added amdsmi_get_cpucore_info to amdsmi library

Change-Id: Ib88d580e1d85afdf578963247e585cfae05c58ad
2023-10-30 20:59:21 -04:00
Deepak Mewar a09863f550 Esmi Auxillary API wrappers removed from amdsmi library
that are called during amdsmi inititalization
    amdsmi_get_cpu_family,
    amdsmi_get_cpu_model,
    amdsmi_get_cpu_threads_per_core,
    amdsmi_get_number_of_cpu_cores,
    amdsmi_get_number_of_cpu_sockets

Added amdsmi_get_cpucore_info to amdsmi library

Change-Id: Ib88d580e1d85afdf578963247e585cfae05c58ad


[ROCm/amdsmi commit: 28f6383639]
2023-10-30 20:59:21 -04:00
Ammar ELWazir a276ef5fcf Update .gitignore (#161)
[ROCm/rocprofiler-sdk commit: d6e24d1fe0]
2023-10-30 17:40:49 -07:00
Ammar ELWazir d6e24d1fe0 Update .gitignore (#161) 2023-10-30 17:40:49 -07:00
Galantsev, Dmitrii 88d5e011e6 SWDEV-424983 - Fix supported metrics api checks
Change-Id: I5c95bb3057dd7546036cbd87bbf7025469d2b3d5
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2023-10-30 17:28:59 -04:00
Galantsev, Dmitrii 21fa9c0950 SWDEV-424983 - Fix supported metrics api checks
Change-Id: I5c95bb3057dd7546036cbd87bbf7025469d2b3d5
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 88d5e011e6]
2023-10-30 17:28:59 -04:00
Mythreya 46e02a9866 Add MI200/MI300 counters
Revision - Addition [Impact SoC: MI200, MI300]
    Note: this set of counters are important help understand the
          bottleneck.
    1.	TCC_TAG_STALL
        a.	Metric:  TCC_TAG_STALL/TCC_CYCLE: percentage of time TCC
            tag lookup pipeline is stalled
    2.	TCP_TCR_TCP_STALL_CYCLES
        a.	Metric: TCP_TCR_TCP_STALL_CYCLES/TCP_GATE_EN1: percentage
            of time TCP is stalled by TCR

Revision - Addition [Impact SoC: MI300]
    3.	TCC_BUBBLE:
        a.	Definition: Number of 128-byte read requests sent to EA
        b.	Revised Metric #1, TCC-EA Read BW:
        ReadBW =   128 * TCC_BUBBLE
                + 64 * (TCC_EA0_RDREQ - TCC_BUBBLE - TCC_EA0_RDREQ_32B)
                + 32 * TCC_EA0_RDREQ_32B
        c.	Revised Metric #2: TCC_EA Read Latency
        ReadLatency = TCC_EA0_RDREQ_LEVEL / (TCC_BUBBLE + TCC_EA0_RDREQ)

    /* [Fineprint] More detailed arithmetic:
    * ReadLatency = TCC_EA0_RDREQ_LEVEL / (#32B_req + #64B_req + #128B_req * 2)
    */

Change-Id: I0a2dfc1b64ca97023b1e8ba0f9830330b3034946
2023-10-30 15:38:46 -04:00
Mythreya 6a4321c4e3 Add MI200/MI300 counters
Revision - Addition [Impact SoC: MI200, MI300]
    Note: this set of counters are important help understand the
          bottleneck.
    1.	TCC_TAG_STALL
        a.	Metric:  TCC_TAG_STALL/TCC_CYCLE: percentage of time TCC
            tag lookup pipeline is stalled
    2.	TCP_TCR_TCP_STALL_CYCLES
        a.	Metric: TCP_TCR_TCP_STALL_CYCLES/TCP_GATE_EN1: percentage
            of time TCP is stalled by TCR

Revision - Addition [Impact SoC: MI300]
    3.	TCC_BUBBLE:
        a.	Definition: Number of 128-byte read requests sent to EA
        b.	Revised Metric #1, TCC-EA Read BW:
        ReadBW =   128 * TCC_BUBBLE
                + 64 * (TCC_EA0_RDREQ - TCC_BUBBLE - TCC_EA0_RDREQ_32B)
                + 32 * TCC_EA0_RDREQ_32B
        c.	Revised Metric #2: TCC_EA Read Latency
        ReadLatency = TCC_EA0_RDREQ_LEVEL / (TCC_BUBBLE + TCC_EA0_RDREQ)

    /* [Fineprint] More detailed arithmetic:
    * ReadLatency = TCC_EA0_RDREQ_LEVEL / (#32B_req + #64B_req + #128B_req * 2)
    */

Change-Id: I0a2dfc1b64ca97023b1e8ba0f9830330b3034946


[ROCm/rocprofiler commit: 46e02a9866]
2023-10-30 15:38:46 -04:00
Wenkai Du b736b506c0 NPkit: misc fixes for MSCCL (#936)
* msccl: add xcc_id to timestamp sync

* NPKit: add timestamp for rrc operator

* NPKit: add timestamp for MSCCL init

[ROCm/rccl commit: a497722894]
2023-10-30 10:00:12 -07:00
Wenkai Du a497722894 NPkit: misc fixes for MSCCL (#936)
* msccl: add xcc_id to timestamp sync

* NPKit: add timestamp for rrc operator

* NPKit: add timestamp for MSCCL init
2023-10-30 10:00:12 -07:00
Ammar ELWazir 56d5b93339 Fixing initialization of ROCTx for the tool in the default constructor
Change-Id: I12a3bbde4420a9eb8d734c546169a11cb23237dd


[ROCm/roctracer commit: dbfe955d57]
2023-10-30 16:53:21 +00:00
Ammar ELWazir dbfe955d57 Fixing initialization of ROCTx for the tool in the default constructor
Change-Id: I12a3bbde4420a9eb8d734c546169a11cb23237dd
2023-10-30 16:53:21 +00:00
taosang2 c709808166 SWDEV-364236 - Fix device buffer to/from image issue
Fix offset of device buffer copied to/from image.

Change-Id: I149a8629769cd0d5848ffefb04f1752668a685b9


[ROCm/clr commit: 9a24e1fb30]
2023-10-30 12:17:14 -04:00
taosang2 9a24e1fb30 SWDEV-364236 - Fix device buffer to/from image issue
Fix offset of device buffer copied to/from image.

Change-Id: I149a8629769cd0d5848ffefb04f1752668a685b9
2023-10-30 12:17:14 -04:00
gobhardw 49bd09b46c SWDEV-429377 : Fixing kernel name truncation for plugins
Change-Id: I5875048d1773959fdd73cbff5498854e61b92af8
2023-10-30 10:52:31 -04:00
gobhardw 7aaf49a641 SWDEV-429377 : Fixing kernel name truncation for plugins
Change-Id: I5875048d1773959fdd73cbff5498854e61b92af8


[ROCm/rocprofiler commit: 49bd09b46c]
2023-10-30 10:52:31 -04:00