AI/rocm-systems
2
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
64,512 Commits 3 Branches 0 Tags
bb1295bcdfd72123700cd66e631326ab38e82db8
Commit Graph
64512 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Jonathan R. Madsen b99b153030 Critical trace updates (#24) 
* Source code restructuring

* Critical trace updates following restructuring

* thread_sampler, timestamps

- thread_sampler
- CPU frequency managed via thread_sampler
- rocm-smi managed via thread_sampler
- Use consistent timestamps for perfetto
- removed hsa_timer_t in favor of wall_clock::record()
- disable KokkosP by default
- re-enable critical-trace testing

* cmake-format

* Fix for defines.hpp.in

* Remove OMNITRACE_ROCM_SMI_FREQ

- thread_sampler freq is set via OMNITRACE_SAMPLING_FREQ w/ max of 1000

* Increase CI Install Dyninst timeout

* Debug macros + omnitrace_init_tooling + config

- new debug macros
- extern "C" omnitrace_init_tooling
- guard get_rocm_smi_devices

* Miscellaneous tweaks

- tweak to transpose
- critical_trace::Device::ANY
- perfetto "critical-trace" category
- OMNITRACE_VERBOSE usage

* Disable key and tid data for HIP API calls

- non-kernels are ignored in activity callback

* critical-trace exe updates

- fix perfetto generation
- improved logging
- improved readability

* timemory submodule update

- lulesh example cmake tweaks

[ROCm/rocprofiler-systems commit: b016c8929f]
 2022-02-19 02:00:59 -06:00
Jonathan R. Madsen b016c8929f Critical trace updates (#24) 
* Source code restructuring

* Critical trace updates following restructuring

* thread_sampler, timestamps

- thread_sampler
- CPU frequency managed via thread_sampler
- rocm-smi managed via thread_sampler
- Use consistent timestamps for perfetto
- removed hsa_timer_t in favor of wall_clock::record()
- disable KokkosP by default
- re-enable critical-trace testing

* cmake-format

* Fix for defines.hpp.in

* Remove OMNITRACE_ROCM_SMI_FREQ

- thread_sampler freq is set via OMNITRACE_SAMPLING_FREQ w/ max of 1000

* Increase CI Install Dyninst timeout

* Debug macros + omnitrace_init_tooling + config

- new debug macros
- extern "C" omnitrace_init_tooling
- guard get_rocm_smi_devices

* Miscellaneous tweaks

- tweak to transpose
- critical_trace::Device::ANY
- perfetto "critical-trace" category
- OMNITRACE_VERBOSE usage

* Disable key and tid data for HIP API calls

- non-kernels are ignored in activity callback

* critical-trace exe updates

- fix perfetto generation
- improved logging
- improved readability

* timemory submodule update

- lulesh example cmake tweaks
 2022-02-19 02:00:59 -06:00
Chauncey Hui b4e97ebccb SWDEV-2 - Change OpenCL version number from 3423 to 3424 
[ROCm/clr commit: f95188ba4c]
 2022-02-19 03:00:07 -05:00
Chauncey Hui f95188ba4c SWDEV-2 - Change OpenCL version number from 3423 to 3424 2022-02-19 03:00:07 -05:00
Saurabh Verma 7a7c73b7d8 SWDEV-299902: merge_traces script from rocprof fails to include GPU / HSA / ROCTX activity in merged trace 
Change-Id: I29cfd6cfaf34bfa588bd90774db6d8ac501e8aa8
 2022-02-18 16:11:08 -06:00
Saurabh Verma 7284cbb59b SWDEV-299902: merge_traces script from rocprof fails to include GPU / HSA / ROCTX activity in merged trace 
Change-Id: I29cfd6cfaf34bfa588bd90774db6d8ac501e8aa8


[ROCm/rocprofiler commit: 7a7c73b7d8]
 2022-02-18 16:11:08 -06:00
Freddy Paul 566a0c794c rocm-smi:Fix cmake target files to reflect correct location 
Change-Id: I86fda8447609c42e0f0615abd837b53ca5fbe717


[ROCm/rocm_smi_lib commit: d0545854dd]
 2022-02-18 09:53:43 -08:00
Freddy Paul d0545854dd rocm-smi:Fix cmake target files to reflect correct location 
Change-Id: I86fda8447609c42e0f0615abd837b53ca5fbe717
 2022-02-18 09:53:43 -08:00
German Andryeyev c52280ae72 SWDEV-323702 - Use active queue for transfer 
Pass active queue for transfers in the cache coherency layer.
That will allow to use device transfer queue only for
cases when active queue isn't available, because using device
transfer queue from another active queue may cause a deadlock

Change-Id: Ifbe7e0303b77dbf6eeda3939ffbc25a3df7472de


[ROCm/clr commit: 95d55fdfa8]
 2022-02-18 09:10:53 -05:00
German Andryeyev 95d55fdfa8 SWDEV-323702 - Use active queue for transfer 
Pass active queue for transfers in the cache coherency layer.
That will allow to use device transfer queue only for
cases when active queue isn't available, because using device
transfer queue from another active queue may cause a deadlock

Change-Id: Ifbe7e0303b77dbf6eeda3939ffbc25a3df7472de
 2022-02-18 09:10:53 -05:00
Chauncey Hui 62dbceb61c SWDEV-2 - Change OpenCL version number from 3422 to 3423 
[ROCm/clr commit: ffbd63e774]
 2022-02-18 03:00:06 -05:00
Chauncey Hui ffbd63e774 SWDEV-2 - Change OpenCL version number from 3422 to 3423 2022-02-18 03:00:06 -05:00
Maneesh Gupta ff8054075a Bump HIP version to 5.1 
[ROCm/hip commit: 15cf839904]
 2022-02-18 07:24:18 +05:30
Maneesh Gupta 15cf839904 Bump HIP version to 5.1 2022-02-18 07:24:18 +05:30
German Andryeyev 7c8a7ddf5e SWDEV-323364 - Fix a typo 
Change-Id: I2031296ab9451342d5930b8b2d3d2e6277946647


[ROCm/clr commit: fbf531398a]
 2022-02-17 20:50:29 -05:00
German Andryeyev fbf531398a SWDEV-323364 - Fix a typo 
Change-Id: I2031296ab9451342d5930b8b2d3d2e6277946647
 2022-02-17 20:50:29 -05:00
TomSang f1ed56ab72 SWDEV-306947 - Add mode combination tests (#2447) 
Address modes are valid for array rather than linear
memory. Comment out codes of address test for linear
memory.
Add tests of mode combination(address, linear and
normorlized coordinates) in 1D, 2D and 3D.

Change-Id: I9e7e97d9bf619743c311f68f51d5bf115fdd534d

[ROCm/hip commit: e05f98967e]
 2022-02-17 13:48:45 -08:00
TomSang e05f98967e SWDEV-306947 - Add mode combination tests (#2447) 
Address modes are valid for array rather than linear
memory. Comment out codes of address test for linear
memory.
Add tests of mode combination(address, linear and
normorlized coordinates) in 1D, 2D and 3D.

Change-Id: I9e7e97d9bf619743c311f68f51d5bf115fdd534d
 2022-02-17 13:48:45 -08:00
Saravanan Solaiyappan 4c1bb19860 SWDEV-323670 - Remove lib/libOpenCL.so* symlinks during upgrade 
During upgrade lib/libOpenCL.so* files/symlinks are not
removed.
This change will remove those symlinks as part of the upgrade
package activity.

Signed-off-by: Saravanan Solaiyappan <saravanan.solaiyappan@amd.com>
Change-Id: Ia12e89e857b358101f93a6044fe090aa7acafbe0


[ROCm/clr commit: c741a808ae]
 2022-02-17 09:43:30 -05:00
Saravanan Solaiyappan c741a808ae SWDEV-323670 - Remove lib/libOpenCL.so* symlinks during upgrade 
During upgrade lib/libOpenCL.so* files/symlinks are not
removed.
This change will remove those symlinks as part of the upgrade
package activity.

Signed-off-by: Saravanan Solaiyappan <saravanan.solaiyappan@amd.com>
Change-Id: Ia12e89e857b358101f93a6044fe090aa7acafbe0
 2022-02-17 09:43:30 -05:00
Chauncey Hui 867b53ee4e SWDEV-2 - Change OpenCL version number from 3421 to 3422 
[ROCm/clr commit: 0a2baa91b1]
 2022-02-17 03:00:05 -05:00
Chauncey Hui 0a2baa91b1 SWDEV-2 - Change OpenCL version number from 3421 to 3422 2022-02-17 03:00:05 -05:00
Ajay 687298ba1c SWDEV-314982 - hipStreamGetCaptureInfo negative cases 
Change-Id: I98a65fc60610f89184b54152c8e33f59d74e3850


[ROCm/clr commit: 0e94178c03]
 2022-02-16 18:06:12 -05:00
Ajay 0e94178c03 SWDEV-314982 - hipStreamGetCaptureInfo negative cases 
Change-Id: I98a65fc60610f89184b54152c8e33f59d74e3850
 2022-02-16 18:06:12 -05:00
Shweta Khatri 78a6413986 Fixed some errors in rocminfo reported by lint tool 
Change-Id: Ie7852c2003c10847226a5df23c4e85fbe89dad43


[ROCm/rocminfo commit: cf92f649ab]
 2022-02-16 17:05:21 -05:00
Shweta Khatri cf92f649ab Fixed some errors in rocminfo reported by lint tool 
Change-Id: Ie7852c2003c10847226a5df23c4e85fbe89dad43
 2022-02-16 17:05:21 -05:00
Saleel Kudchadker de9a5438b9 SWDEV-322605 - Fix infinite loop condition 
If GlobalMemCacheLine reported is 0, runtime may run into an
infinite loop as the KernelSegmentAlignment is chosen as size of the
cache line.

Change-Id: Ide547940cc0407f16fab10ee210b4fd3ae4eaafc


[ROCm/clr commit: 041ddc0c1c]
 2022-02-16 13:16:18 -05:00
Saleel Kudchadker 041ddc0c1c SWDEV-322605 - Fix infinite loop condition 
If GlobalMemCacheLine reported is 0, runtime may run into an
infinite loop as the KernelSegmentAlignment is chosen as size of the
cache line.

Change-Id: Ide547940cc0407f16fab10ee210b4fd3ae4eaafc
 2022-02-16 13:16:18 -05:00
Payam d0c9d6195f SWDEV-316819 - Adding Graph null check 
Change-Id: I22774109a13c3123e89b82bd6e05e1eea26f80fc


[ROCm/clr commit: dcac099922]
 2022-02-16 04:22:13 -05:00
Payam dcac099922 SWDEV-316819 - Adding Graph null check 
Change-Id: I22774109a13c3123e89b82bd6e05e1eea26f80fc
 2022-02-16 04:22:13 -05:00
Sourabh Betigeri 4e4feda7b3 SWDEV-317017 - hipGraphExecChildGraphNodeSetParams() path to *NodeSetParams 
Change-Id: Iedcbccccb9a2765e08feebd75fb13f3ff83623dc


[ROCm/clr commit: cd4591530d]
 2022-02-16 01:25:23 -05:00
Sourabh Betigeri cd4591530d SWDEV-317017 - hipGraphExecChildGraphNodeSetParams() path to *NodeSetParams 
Change-Id: Iedcbccccb9a2765e08feebd75fb13f3ff83623dc
 2022-02-16 01:25:23 -05:00
Satyanvesh Dittakavi 859d9065cf SWDEV-315981 - make nvidia hiprtc functions static 
Change-Id: I945426c155ed9ce21c308745f384bbf8669d73c4


[ROCm/hipother commit: e3aafb9636]
 2022-02-15 23:38:19 -05:00
Satyanvesh Dittakavi e3aafb9636 SWDEV-315981 - make nvidia hiprtc functions static 
Change-Id: I945426c155ed9ce21c308745f384bbf8669d73c4
 2022-02-15 23:38:19 -05:00
Satyanvesh Dittakavi 0d4a2c78c2 SWDEV-315981 - make nvidia hiprtc functions static 
Change-Id: I945426c155ed9ce21c308745f384bbf8669d73c4


[ROCm/clr commit: aee5c48848]
 2022-02-15 23:38:19 -05:00
Satyanvesh Dittakavi aee5c48848 SWDEV-315981 - make nvidia hiprtc functions static 
Change-Id: I945426c155ed9ce21c308745f384bbf8669d73c4
 2022-02-15 23:38:19 -05:00
Payam 60437939e7 SWDEV-313492 - adding Graph null checks 
Change-Id: I00ae51ea8318567b4f6aab1568096d25cc0d373b


[ROCm/clr commit: d27c33aecc]
 2022-02-15 19:34:33 -05:00
Payam d27c33aecc SWDEV-313492 - adding Graph null checks 
Change-Id: I00ae51ea8318567b4f6aab1568096d25cc0d373b
 2022-02-15 19:34:33 -05:00
Sourabh Betigeri 67d88bd915 SWDEV-315225 - Validates parameters of hipGraphExecMemcpyNodeSetParams() 
Change-Id: I7bb5c906f6bca27a8abb7f4f5226e864e9731bae


[ROCm/clr commit: ad19d0957b]
 2022-02-15 17:45:07 -05:00
Sourabh Betigeri ad19d0957b SWDEV-315225 - Validates parameters of hipGraphExecMemcpyNodeSetParams() 
Change-Id: I7bb5c906f6bca27a8abb7f4f5226e864e9731bae
 2022-02-15 17:45:07 -05:00
Ajay 522b62d87a SWDEV-316465 - hipStreamGetCaptureInfo_v2 pointer checks 
Change-Id: I219e16909ddd3fa99cd9a2faefc0f35237ee3b08


[ROCm/clr commit: 57d0acb6d7]
 2022-02-15 16:46:17 -05:00
Ajay 57d0acb6d7 SWDEV-316465 - hipStreamGetCaptureInfo_v2 pointer checks 
Change-Id: I219e16909ddd3fa99cd9a2faefc0f35237ee3b08
 2022-02-15 16:46:17 -05:00
Ranjith Ramakrishnan 9b1793bd39 Merge "SWDEV-291455: Prefer rocm include path to hip include path" into amd-staging 
[ROCm/roctracer commit: c037ccb95e]
 2022-02-15 14:43:32 -05:00
Ranjith Ramakrishnan c037ccb95e Merge "SWDEV-291455: Prefer rocm include path to hip include path" into amd-staging 2022-02-15 14:43:32 -05:00
German Andryeyev a7be0eb56a SWDEV-316824 - Fix P2P compute copy path 
Use device memory object for the GPU VA address look-up.

Change-Id: I76bf58b29205f7b3ba1bf68e9fcca69421267203


[ROCm/clr commit: 3fd4a67670]
 2022-02-15 13:20:13 -05:00
German Andryeyev 3fd4a67670 SWDEV-316824 - Fix P2P compute copy path 
Use device memory object for the GPU VA address look-up.

Change-Id: I76bf58b29205f7b3ba1bf68e9fcca69421267203
 2022-02-15 13:20:13 -05:00
Ajay 7142de77b0 SWDEV-273235 - skip clangRTlib detection in windows sample 
Change-Id: I5a05479c774ce618960ae2578f46f1116b1f93ee


[ROCm/clr commit: a5ee2d2042]
 2022-02-15 12:44:24 -05:00
Ajay a5ee2d2042 SWDEV-273235 - skip clangRTlib detection in windows sample 
Change-Id: I5a05479c774ce618960ae2578f46f1116b1f93ee
 2022-02-15 12:44:24 -05:00
Ajay 8512b5d959 SWDEV-315614 - hipStreamGetCaptureInfo to return seq id based on status 
Change-Id: Ibceeb67fcd60b3ad2272e08a3ee682dc36bda1cb


[ROCm/clr commit: 32b9969db3]
 2022-02-15 12:42:37 -05:00
Ajay 32b9969db3 SWDEV-315614 - hipStreamGetCaptureInfo to return seq id based on status 
Change-Id: Ibceeb67fcd60b3ad2272e08a3ee682dc36bda1cb
 2022-02-15 12:42:37 -05:00