AI/rocm-systems
2
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
903 Commits 3 Branches 0 Tags
2230af4b1dda200c31c812ef80a94398bbd85d89
Commit Graph
259 Commits
Author SHA1 Message Date
Lang Yu 2230af4b1d SWDEV-467545 - Add rocprofiler support for gfx1150/gfx1151 
Change-Id: I2cddc36981f6d815c865d180a1daf1b8a7e0633f
Signed-off-by: Lang Yu <lang.yu@amd.com>


[ROCm/rocprofiler commit: 7313e52f35]
 2024-07-09 22:40:10 -04:00
Giovanni LB e4e1e4857e SWDEV-470113: Fixing hang on navi33 
Change-Id: I5c1d30547039a6f23ab5974f43ea63f971573108


[ROCm/rocprofiler commit: 7e199e6b7a]
 2024-07-05 20:39:56 -04:00
Giovanni LB d29580c94e SWDEV-470113: Swapping test order and resetting queue.cpp variables 
Change-Id: I20f3fa3cbf389ab89ba8ea8e430819c4ef837ad0


[ROCm/rocprofiler commit: 70fedc5195]
 2024-07-03 15:41:37 -03:00
Giovanni LB 8ca515087a SWDEV-470113: Waiting on active signals 
Change-Id: Ie99477a2f031fa0dbb7ff7c860f8b780177e6e9d


[ROCm/rocprofiler commit: 8d2f139005]
 2024-06-27 15:17:56 -03:00
jatang c8d58d1986 SWDEV-458392 - Add gfx12 support. 
Change-Id: I91bb6a3329bf77f26005a345c18b63b86922028a


[ROCm/rocprofiler commit: e7b96b1e71]
 2024-06-17 13:24:48 -04:00
Giovanni LB 4a09c57f1a SWDEV-468021: Improving profiler performance 
Change-Id: I91921160a19aaea1fedfa40d11b83114d6a6fc65


[ROCm/rocprofiler commit: 4d0fee6637]
 2024-06-14 15:29:27 -03:00
Saurabh Verma c41bbe21d0 SWDEV-457922: Temporary fix to prevent multiple instances of either rocprofiler v1 or v2 to be running, whether it's interception or standalone mode. 
The fix works by using a pid file and a lock file, similar to how firefox prevents multiple instances.

Change-Id: I4974a80bf920eaf0376a53410573c1cc74ec17ac


[ROCm/rocprofiler commit: 056156135d]
 2024-06-10 12:49:29 -04:00
gobhardw a67f4fdd93 SWDEV-465520: RHEL9 toolchain doesnt seem to support experimental filesystem 
Change-Id: I6b1e7f42c49b1c7af412c0b68851724861c9970a


[ROCm/rocprofiler commit: 1e69b3e2f6]
 2024-06-05 12:50:48 -04:00
Giovanni LB 607cfb9ee1 SWDEV-464906: Swap read and stop packets in queue.cpp 
Change-Id: I2dd33a71c0cbe69fe6c2cfaf523b9f8c6500093f


[ROCm/rocprofiler commit: 140f658820]
 2024-06-05 09:11:59 -04:00
Ammar ELWazir d0dfb4f3e2 Adding JSON & Major fixes 
Adding Chrome Tracing JSON for V2
Some fixes for the Kernel Dispatch tracing
Changes related to the HIP Runtime Destruction fix

Change-Id: I2fe1f1ef66b415df17c503a4a9fadcfa107d8c49


[ROCm/rocprofiler commit: b8726a6225]
 2024-05-29 01:21:52 -04:00
Giovanni LB d24a280079 Setting output buffer to always local 
Change-Id: I82bf9f4cb922221d4a2b7ae15adb0f208a0ba70e


[ROCm/rocprofiler commit: b354c54ed7]
 2024-05-27 14:53:32 -04:00
Saurabh Verma 150869be6a Fix for crash Error: HsaRsrcFactory::SignalWait: signal_value(1), ret_value(-1) 
Context::GetData() would crash when it tries to wait on the completion signal of the stop packet. The expected signal value after waiting in HsaRsrcFactory::SignalWait() is supposed to be 0 but sometimes it comes up as -1. The signal being checked has already decremented before. Profile::Finalize() was assigning the same completion signal to the read and stop packet. So those two packets have been assigned different completion signals. This fix only affects standalone profiling mode.

Change-Id: I4b16825019e58d95d70188a72b2cc5871e09dd81


[ROCm/rocprofiler commit: 34606db8c3]
 2024-05-26 13:31:39 -04:00
Ammar ELWazir a36338a7a6 Temporary fix for SWDEV-459354 
Change-Id: I13d7d600ab72d873d1dbc5d5e9b72c2ca5941488


[ROCm/rocprofiler commit: b6576393a2]
 2024-05-24 10:39:32 -04:00
Giovanni LB 6cf9df4ff0 Fixing occupancy metrics for MI300 
Change-Id: I25a150dbcd3582cd397a658aa9a991956577cfa8


[ROCm/rocprofiler commit: 604738fd8d]
 2024-04-30 15:23:42 -04:00
Giovanni LB c0cb1373a4 SWDEV-452226: Changing ATT dispatch IDs to match previous kernel-trace change 
Change-Id: Ifd00160f2e8705e9ef11d41d284f6625b70de389


[ROCm/rocprofiler commit: 3ae1b6af74]
 2024-04-29 11:56:32 -04:00
gobhardw 1f797ac1d1 SWDEV-452226-dispatch ids to start from 0 for v1 parity 
Change-Id: Ib60a6c108131f67395ab1f9d35ad605859d39987


[ROCm/rocprofiler commit: dc09052d82]
 2024-04-23 00:41:55 -04:00
Giovanni LB e64e15aba4 Re-enabling ATT tests 
Change-Id: Ied23410d40eecbbfb8972d36ed065289f74aaa0c


[ROCm/rocprofiler commit: 97c6b0b867]
 2024-04-17 18:49:55 -03:00
Giovanni LB 998fce25e0 Fixing XCC-based metrics 
Change-Id: I7451355b5b5eeefbd1c78b996d4ca5c4b770246a


[ROCm/rocprofiler commit: bf749ba8d6]
 2024-03-27 16:17:24 -04:00
Giovanni LB 227e49b3fd Updating to load_delta. Fixing perfetto plugin. 
Change-Id: If893f84b0ff108cfa0ccdcf717ee8592aa621032


[ROCm/rocprofiler commit: 4dd21807c0]
 2024-03-07 15:21:37 -03:00
Giovanni LB 83c4b3a21e SWDEV-445711: Workaround for race condition on exit 
Change-Id: I7391637005ccc7ea89611f28691c02e569197dff


[ROCm/rocprofiler commit: 4711a083de]
 2024-02-27 14:45:47 -05:00
Giovanni LB fe83593ccc Adding late-replace envvar filenames to ATT 
Change-Id: I5df51934ffa25358503013e1a230adb894d6ff94


[ROCm/rocprofiler commit: fe00badc6e]
 2024-02-22 10:02:32 -05:00
Manjunath-Jakaraddi afae19671e SWDEV-445654: Adding metrics to MI300 
Change-Id: I7c3d78d8739ad219fc05bd99d7fc11d1f023aadc


[ROCm/rocprofiler commit: 8d705f8b96]
 2024-02-14 13:17:15 -05:00
Giovanni LB 825227ee6a Adding bank conflict and other MI300 missing metrics to rocprofv2 
Change-Id: Ibb7fb6163aa3bd7742f199a03600c737720e3c61


[ROCm/rocprofiler commit: 95b49ca593]
 2024-02-14 13:15:54 -05:00
gobhardw 5690f979a5 node id to be reported as gpu id 
Change-Id: I237281b33cfb5bdad67b7d6e8b69e9a86d62ca5d


[ROCm/rocprofiler commit: 28871e661a]
 2024-02-12 12:26:41 +05:30
Giovanni LB 175f4e024e Fixing SE numbering and cache invalidade parsing 
Change-Id: Ie63c68a0b2b07427586faaf69b68a19c315387e3


[ROCm/rocprofiler commit: 363abb238b]
 2024-01-31 13:11:19 -03:00
Giovanni LB 68cfdd66ba SWDEV-439757: Remove codeobj marker on last kernel. Fixed codeobj size limit. ATT version bump. 
Change-Id: Ie0b9c4de6c37acaaad4ae7d8d774d234a3847b7c


[ROCm/rocprofiler commit: 067071f669]
 2024-01-17 05:01:50 -03:00
Saurabh Verma 492f3740b3 Supporting UMC counters in rocprofv2 
Change-Id: Ic96c33244d78ac5031cfd99ac2be0c12c774d1b0


[ROCm/rocprofiler commit: 5676c27c02]
 2024-01-04 12:33:08 -05:00
Ammar ELWazir 80329e8364 Fixing ROCProfilerV2 to match versioning changes in HIP Runtime 
Change-Id: Ifb0f98356acebcb7cf5372340b36178de000405d


[ROCm/rocprofiler commit: a59d56f9bc]
 2024-01-03 12:28:08 -06:00
Giovanni LB 064f77ecf3 SWDEV-437776: Fixing typo for in stitch.py. Fixing singleDispatch kernel name. 
Change-Id: I8d65598fffa4f15f78a64f741fdcb9a4a77af2a0


[ROCm/rocprofiler commit: 25a02fe03e]
 2023-12-27 18:08:39 -05:00
Saurabh Verma 5486b9de3a Fixed format of presenting MI300 counters for individual xccs 
1. Modified rocprofiler_record_profiler_t to include xcc_index
2. Modified file plugin to add additional column XCC_Index to the csv

Change-Id: Ic526c739e16b50dca5704070ccabbcbecd994d6a


[ROCm/rocprofiler commit: b18bc9930b]
 2023-12-20 14:04:10 -05:00
Giovanni LB 0f5bec223e SWDEV-432445: ATT - Adding fixes for symbolic stitch and source reference numbering 
Change-Id: I31d63bd2500155697129c29d7e0bc857e48cad8e


[ROCm/rocprofiler commit: 490ea4c37d]
 2023-12-18 08:53:51 -03:00
Jatin Chaudhary b94af28425 SWDEV-412457 - include assert header in files that use it 
Change-Id: Ie1a947e78c4badc5b07b15fefc8aaedacfc7a02c


[ROCm/rocprofiler commit: 8dd9d9df51]
 2023-12-13 13:37:41 -05:00
Giovanni LB 59537c237c SWDEV-432445: Reorganizing ATT packet start/stop. Bump ATT parser version. 
Change-Id: I979648f8a6a25aa7b499b3eea49978578f6c3f5a


[ROCm/rocprofiler commit: e85c6911aa]
 2023-12-12 17:43:34 -05:00
Giovanni LB f275cdd602 SWDEV-432445: ATT continuous mode update part2. Added codeobj tracking. 
Change-Id: I1b58af70d221bbeb9b4cab960d26357a504045dd


[ROCm/rocprofiler commit: edf93d48ab]
 2023-12-12 17:40:59 -05:00
Giovanni LB 34fd4840d1 SWDEV-432445: ATT continuous mode 
Change-Id: I52732fc1dba41df3373ef6a19a428b00d729bf04


[ROCm/rocprofiler commit: aba6a1d986]
 2023-12-12 10:55:23 -03:00
Giovanni LB ec895dfb2a Added option to control how codeobj is dumped from ATT 
Change-Id: Ie76aeea1193c7ba8fe7f51be159516f8a9eab55f


[ROCm/rocprofiler commit: 99b14fc9f8]
 2023-11-08 17:48:28 -03:00
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
Lancelot Six 929ea5d950 src/core/isa_capture/code_object_track.cpp: remove unused dbgapi import 
The src/core/isa_capture/code_object_track.cpp file includes the
amd-dbgapi header but does not use the library (and is not configured to
use the library).

Remove the unused import.

Change-Id: Icc6c46a1f52355e9e5631395dfad1b44365bdca4


[ROCm/rocprofiler commit: 372fc3910b]
 2023-10-27 00:09:21 -04:00
Mythreya 1471dc8a76 Remove non-functional counters for MI200 and MI300 
Counters removed for MI300 (gfx940)
    TCP_TCC_WRITE_REQ_HOLE_LATENCY
    TCP_TCC_WRITE_REQ_LATENCY
    TCP_TCC_READ_REQ_LATENCY
    TCP_TCP_LATENCY

Counters removed for MI200 and MI300 (gfx90a and gfx940 respectively)
    TA_BUFFER_COALESCABLE_WAVEFRONT
    TA_FLAT_COALESCABLE_WAVEFRONT
    TCC_EA0_WRREQ_IO_CREDIT_STALL
    TCC_EA0_WRREQ_GMI_CREDIT_STALL
    TCC_EA0_WRREQ_DRAM_CREDIT_STALL
    TCC_EA0_RDREQ_IO_CREDIT_STALL
    TCC_EA0_RDREQ_GMI_CREDIT_STALL
    TCC_EA0_RDREQ_DRAM_CREDIT_STALL

Change-Id: Ic3d1e7bf35495f35b1239f03ca6420e949421386


[ROCm/rocprofiler commit: 1fae494b12]
 2023-10-26 12:50:57 -04:00
Saurabh Verma 87654ec8b2 SWDEV-427921: Fixing rocprof v1 counter collection for PAPI on MI300 
Change-Id: I8589fe78fca481ed326e584ea1d01c0f90de655e


[ROCm/rocprofiler commit: 1e1692e6c0]
 2023-10-19 13:40:32 -04:00
gobhardw ea5ecec246 SWDEV-427554 Fixing mainline ASAN build 
Change-Id: I63cd047ceb75dea5f8ed6f84946e1ec209c7d812


[ROCm/rocprofiler commit: 5d390717b5]
 2023-10-18 21:42:47 +05:30
gobhardw 6978569d1f Solving timestamps and serialization merge 
Change-Id: Icd14e49c06b19e4334adbdb98efed54af029b95b


[ROCm/rocprofiler commit: def7fa710a]
 2023-10-16 14:54:50 -04:00
Sriraksha Nagaraj b5be707bcb Enabling -m and --basenames option 
Change-Id: Ic19ac28ab6ec842daf2a93a311ed7690b61b1e2a


[ROCm/rocprofiler commit: a76341e30c]
 2023-10-13 14:44:20 -04:00
Giovanni LB 769f6303d8 SWDEV-423947: Added ATT header option 
Change-Id: I6e9ad213b578d752c865c9f9af4ee0b79d447e1b


[ROCm/rocprofiler commit: e0962d9d63]
 2023-10-12 10:02:30 -04:00
Giovanni LB 92ec86f2d4 Fixing GL2C counter instances 
Change-Id: I37edbdaebe349149e369b21a9e48c302e170941e


[ROCm/rocprofiler commit: 9efd1865c0]
 2023-10-10 12:09:49 -04:00
Giovanni LB 3badb4ba81 SWDEV-423659: Disabling HIP_ACTIVITY when HSA_ACTIVITY is enabled. 
Change-Id: If64fabdcd0d8a718dd0017c2bc821a94c999e87e


[ROCm/rocprofiler commit: 7418c52cc8]
 2023-09-26 01:13:21 -04:00
vlaindic 581bf2cd87 SWDEV-418738: Listing counters of all GPU agents 
Using `gfxip` when listing counters on the system with multi-GPUs
all belonging to the same family results in showing counters
of the first agent multiple times.
Instead, use the agent's `name` to observe counters of all agents.

Change-Id: I7b46c0670bc7c918e2ba0357fa659df9d23379d4


[ROCm/rocprofiler commit: 03a63791b0]
 2023-09-22 17:22:28 +02:00
Sriraksha Nagaraj a157bb93b7 SWDEV-378008: Adding changes to serialize the kernels in rocprofV2 
Change-Id: I82353ba94b3a15fdc5991e6129fe47f6765a9f74


[ROCm/rocprofiler commit: 54f6e2afb7]
 2023-09-14 13:09:09 -04:00
Giovanni LB 00962f5862 SWDEV-421600: Fixing eval_metrics 
Change-Id: I3a41fb6b27d80d84a34ee6461382e512dbecb61f


[ROCm/rocprofiler commit: adc1367c59]
 2023-09-12 16:24:30 -04:00
Giovanni LB 552814f227 SWDEV-419944: Added metrics for gfx1102 
Change-Id: I5c69ff716f530d130710c0687f20e5bc990a60eb


[ROCm/rocprofiler commit: 43e259e5da]
 2023-09-11 13:59:33 -04:00