fbaeb74107
[rocprof-sys] Update nightly CI workflow ( #2263 )
...
Update ROCm version to 7.1.0
Signed-off-by: David Galiffi <David.Galiffi@amd.com >
2025-12-11 12:23:26 -05:00
dd4bee33ff
SWDEV-558848 - Update thunk interface signature for vmm enablement ( #2259 )
...
Co-authored-by: Rahul Manocha <rmanocha@amd.com >
2025-12-11 08:43:28 -08:00
085752d6e5
Add WAIT_PEER NPKIT event ( #2100 )
...
[ROCm/rccl commit: 2cf6a9bb19
2025-12-11 11:18:41 -05:00
2cf6a9bb19
Add WAIT_PEER NPKIT event ( #2100 )
2025-12-11 11:18:41 -05:00
186cdd63c9
[rocpd] Improve summary categories ( #2000 )
...
* Improve summary categories
2025-12-11 16:55:47 +01:00
7b2f68e798
Handle cpu name having colons ( #2155 )
...
* Handle cpu name having colons
* Adding tests to verify
* clang-format fix
---------
Co-authored-by: bgopesh <gopesh.bhardwaj@amd.com >
2025-12-11 16:36:01 +01:00
0c4d08f38d
Revert correcting the VGPR size for GFX 11.5.1 ( #2268 )
...
Although the value is correct; there is no source of truth between
kernel and userspace. This leads to problems if the kernel has strict
restrictions (such as kernel 6.17 or earlier). The restrictions were
lifted in 6.17.9 and and 6.18, but there is no guarantee userspace is
using this.
So short term this value will be wrong. But on newer kernels the kernel
will communicate the right size and rocr-runtime will be adjusted to
use that.
Link: https://github.com/ROCm/TheRock/pull/2505
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org >
2025-12-11 07:59:19 -06:00
6b45657493
update build rccl-tests infrastructure and add getAlgoProtoChannels support ( #2212 )
2025-12-11 18:29:06 +05:30
10635483ad
clr: Fix packet batch write logic ( #2236 )
...
* When writing bulk packets always invalidate packet headers, Its
possible that the CP fetcher can have multiple packets in flight. In
such cases we may end up with a malformed packet because the writes are
not complete yet CP finds a valid header.
2025-12-11 04:26:41 -08:00
a495d1137e
SWDEV-548892 - Make declaration of __ockl_fdot2 always available ( #2229 )
2025-12-11 11:53:11 +01:00
256dd1963a
[hip] Docs: Overhaul HW implementation page ( #1994 )
...
* [hip] Docs: Overhaul HW implementation page
* Update hardware implementation and glossary
* Update programming model
* Add performance optimization
* Split into how-to and understanding
---------
Signed-off-by: Jan Stephan <jan.stephan@amd.com >
Co-authored-by: Jan Stephan <jan.stephan@amd.com >
Co-authored-by: Julia Jiang <julia.jiang@amd.com >
2025-12-11 10:52:34 +01:00
9e06ea8f79
[SWDEV-564696] Structure size mismatch in SOC pstate/XGMI PLPD ( #2207 )
...
* Address PR feedback: consolidate switch cases, move CSV formatting, use direct API calls for error messages
* csv output flattening changes
---------
Signed-off-by: Billakanti, Koushik <Koushik.Billakanti@amd.com >
2025-12-10 23:37:36 -06:00
caecbb4d01
[SWDEV-354749] Added CPU Performance Tests ( #2173 )
...
* CPU Performance testcases
---------
Signed-off-by: Saka, Sitharam Murthy <SitharamMurthy.Saka@amd.com >
2025-12-10 21:57:47 -06:00
e39fe03bcf
[SWDEV-488296] Implemented API Performance test case ( #1903 )
...
Add API performance testing and execution script
---------
Signed-off-by: Sumanth Gavini <sumanth.gavini@amd.com >
Co-authored-by: Sumanth Gavini <sumanth.gavini@amd.com >
2025-12-10 21:33:44 -06:00
91be23b3d0
TheRock compatibility - Devicelib Support ( #684 )
...
* TheRock compatibility - Devicelib Support
* clean up
[ROCm/rocdecode commit: 5784f8cffe
2025-12-10 14:51:43 -08:00
5784f8cffe
TheRock compatibility - Devicelib Support ( #684 )
...
* TheRock compatibility - Devicelib Support
* clean up
2025-12-10 14:51:43 -08:00
20b8575993
TheRock compatibility - Devicelib Support ( #215 )
...
[ROCm/rocjpeg commit: 62007a9f8b
2025-12-10 14:49:58 -08:00
62007a9f8b
TheRock compatibility - Devicelib Support ( #215 )
2025-12-10 14:49:58 -08:00
195fe4e5ee
GDA docs style edits ( #362 )
...
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/sphinx/_toc.yml.in
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Apply suggestions from code review
Co-authored-by: yugang-amd <yugang.wang@amd.com >
---------
Co-authored-by: Yiltan <ytemucin@amd.com >
[ROCm/rocshmem commit: bbad1d8539
2025-12-10 17:03:58 -05:00
bbad1d8539
GDA docs style edits ( #362 )
...
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/install.rst
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Update docs/sphinx/_toc.yml.in
Co-authored-by: yugang-amd <yugang.wang@amd.com >
* Apply suggestions from code review
Co-authored-by: yugang-amd <yugang.wang@amd.com >
---------
Co-authored-by: Yiltan <ytemucin@amd.com >
2025-12-10 17:03:58 -05:00
0835f2e75a
rocrtst: Updated CMakeFiles to find_package instead of hardcoded ( #2095 )
...
* rocrtst: Updated CMakeFiles to find_package instead of hardcoded
This is to support TheROCK build environment
* rocrtst: Fix CMake to use find_package() instead of hardcoded ENV paths
Fixed CMake style issues from previos first commit's code review
* rocrtst: Fix rocrtst NUMA dependency detection to use find_package
Also added handling of missing headers
* rocrtst: Fix NUMA and hwloc detection for cross-platform builds
---------
Co-authored-by: Shweta Khatri <shweta.khatri@amd.com >
2025-12-10 16:16:25 -05:00
1b4eef8f86
Correct runner name ( #2098 )
...
[ROCm/rccl commit: 5384a8abb2
2025-12-10 11:44:48 -08:00
5384a8abb2
Correct runner name ( #2098 )
2025-12-10 11:44:48 -08:00
70562eb854
Add ROCm 7.1 to workflows ( #2256 )
...
Signed-off-by: David Galiffi <David.Galiffi@amd.com >
2025-12-10 13:41:22 -05:00
e783b47388
Bump version number for post-7.2 devel ( #356 )
...
[ROCm/rocshmem commit: 64460f0ec9
2025-12-10 13:03:20 -05:00
64460f0ec9
Bump version number for post-7.2 devel ( #356 )
2025-12-10 13:03:20 -05:00
3895aadba6
SWDEV-558849 - Make ROCR path in Windows more stable ( #2181 )
2025-12-10 12:37:10 -05:00
1d6b26f829
SWDEV-556684 - HSAIL Cleanup re-apply commit 4abdfe5: ( #2024 )
...
Removed some options
-xnack, -force-wgp-mode, -force-wave-size-32, -round-trip-spirv,
-fe-gen-spirv, -lower-pipe-builtins=0|1, -lower-atomics=0|1,
-set-lds=<value>, -set-scalar-registers=<value>,
-set-vector-registers=<value>, -limit-scalar-registers=<value>,
-limit-vector-registers=<value>, -sc-xnack-iommu,
-faa-for-barrier/-fno-a-for-barrier, -sc-dev-format, -verify-lwspir,
-verify-hwspir, -ffma-enable/-fno-fma-enable,
-fmad-enable/-fno-mad-enable, -fdisable-avx/-fno-disable-avx,
-fforce-llvm/-fno-force-llvm, -print-compile-phases,
-kernel-cache-enforce-miss, -kernel-cache-wipe, -kernel-cache,
-sc[=<filename>]/--load-sc-dll[=<filename>],
-be[=<filename>]/--load-be-dll[=<filename>],
-cg[=<filename>]/--load-cg-dll[=<filename>],
-link[=<filename>]/--load-link-dll[=<filename>],
-opt[=<filename>]/--load-opt-dll[=<filename>],
-fe[=<filename>]/--load-fe-dll[=<filename>],
-cl[=<filename>]/--load-cl-dll[=<filename>], -just-kernel=<kernel-name>,
-use-debugil, -fmulti-level-call/-fno-multi-level-call,
-fdebug-call/-fno-debug-call, -fmacro-call/-fno-macro-call,
-fstack-uav/-fno-stack-uav, -fdef-res-id/-fno-def-res-id,
-wokth=int/--waves-opt-kernel-threshold,
-ilkth=int/--inline-kernel-size-threshold,
-ilsth=int/--inline-size-threshold, -ilcth=int/--inline-cost-threshold,
-scopt=int/--sc-opt-level, -flib-no-inline/-fno-lib-no-inline,
-fuser-no-inline/-fno-user-no-inline,
-scras=int/--sc-si-opt-reg-alloc-strategy, -fsc-post-ra-sched,
-fsc-live-sched/-fno-sc-live-sched, -fsc-use-buffer-for-hsa-global,
-fsc-schedule-no-reorder, -fsc-min-reg-schedule,
-fsc-bias-schedule-to-minimize-insts,
-fsc-bias-schedule-to-minimize-regs, -fsc-disable-merge-memory,
-fsc-disable-loop-unroll, -fsc-use-mubuf/-fno-sc-use-mubuf,
-fsc-selective-inline/-fno-sc-selective-inline,
-fsc-keep-calls/-fno-sc-keep-calls, -slc=0|1/--simplifylibcall,
-stack-alignment=<n>, -fdiv2fmul=0|1, -prt-opt-liveness=0|1,
-liveness=0|1, -SRAE-threshold=<value>, -memcombine-max-vec-gen=<value>,
-small-global-objects, -fast-fmaf, -fast-fma, -bfo=0|1, -ebb=0|1, -aa,
-mem2reg=0|1, -licm=0|1, -unroll-allow-partial,
-unroll-threshold=<positive integer>, -unroll-count=<positive integer>,
-apt/--ap-threshold=<positive integer>, -srt/--sr-threshold=<positive
integer>, -fdebug-linker/-fno-debug-linker, -fbin-gpu64/-fno-bin-gpu64,
-fbin-disasm/-fno-bin-disasm, -fbin-bif30, -fbin-hsail/-fno-bin-hsail,
-fbin-amdil/-fno-bin-amdil, -fbin-spir/-fno-bin-spir, -fonly-bin-source,
-fper-pointer-uav/-fno-per-pointer-uav
Co-authored-by: Konstantin Zhuravlyov <kzhuravl_dev@outlook.com >
2025-12-10 09:09:12 -08:00
de82a18790
Fixed unit-test env var list parsing and improved filtered test run speed ( #1626 )
...
* Fixed parsing of env var lists which were overwriting the mutable env var string and polluting future parses.
* Fixed all tests to obey UT_DATATYPES and UT_REDOPS filters.
* Allow tests to bail early via `GTEST_SKIP` if UT_DATATYPES or UT_REDOPS filters give a test size of zero. This allows tests to run much faster with filters on.
* Wrapped the support checks in helper functions on `TestBed`.
[ROCm/rccl commit: 18e9ad913b
2025-12-10 10:06:44 -07:00
18e9ad913b
Fixed unit-test env var list parsing and improved filtered test run speed ( #1626 )
...
* Fixed parsing of env var lists which were overwriting the mutable env var string and polluting future parses.
* Fixed all tests to obey UT_DATATYPES and UT_REDOPS filters.
* Allow tests to bail early via `GTEST_SKIP` if UT_DATATYPES or UT_REDOPS filters give a test size of zero. This allows tests to run much faster with filters on.
* Wrapped the support checks in helper functions on `TestBed`.
2025-12-10 10:06:44 -07:00
d4fe3f1cc3
[hip-tests] Update API coverage report generator ( #1932 )
...
* [hip-tests] Update API coverage report generator
Updates the HIP API coverage tool. It now takes
extra arguments for the location of the catch test folder
and for the working directory. This avoids issues where the output
of the executable is dependent on the path where it is being
executed from.
Also updates CmakeLists.txt to integrate seamlessly with the
hip-tests project and avoid using commands which rely on
relative paths.
* Remove double new line
* Remove Cmake option to generate coverage
Removes Cmake option to generate coverage. Instead, explicitly removes
the gen_coverage target from all (this is already the default but
doing it explicitly prevents confusion).
2025-12-10 17:53:47 +01:00
258d264ecc
Add default context alltoall API ( #350 )
...
[ROCm/rocshmem commit: fddbe7b15d
2025-12-10 11:43:15 -05:00
fddbe7b15d
Add default context alltoall API ( #350 )
2025-12-10 11:43:15 -05:00
972893bab2
Reenable building test-only with external MPI ( #352 )
...
[ROCm/rocshmem commit: 1a16b3bedc
2025-12-10 11:40:29 -05:00
1a16b3bedc
Reenable building test-only with external MPI ( #352 )
2025-12-10 11:40:29 -05:00
0c1f87a7f6
SWDEV-558848 - vmm api support for rocr on windows ( #1761 )
...
* SWDEV-558848 - vmm api support for rocr on windows
* Fixes to VMM handle Map/Unmap Set/Get Access
* Fix GetShareableHandle to use pointer for shareable handle
* Update os specific map/unmap memory calls
* clang format update
* Minor syntax fixes from code review
Co-authored-by: Yiannis Papadopoulos <102817138+ypapadop-amd@users.noreply.github.com >
---------
Co-authored-by: Rahul Manocha <rmanocha@amd.com >
Co-authored-by: Yiannis Papadopoulos <102817138+ypapadop-amd@users.noreply.github.com >
2025-12-10 08:39:51 -08:00
465633d707
[AQLProfile] Fix sqtt legacy tests due to command buffer size underestimating ( #2194 )
2025-12-10 09:25:38 -06:00
d27bd37042
[rocprof-compute] Fix roofline "test_roof_plot_modes" test case ( #2217 )
...
* fix roof test to be isolated file paths
* fix typo
* addressed comments
* fix typos
2025-12-10 10:01:49 -05:00
252a5e8146
[rocprofiler-compute] Remove TCP_TCP_LATENCY_sum counter for MI300 ( #2174 )
...
* Remove TCP_TCP_LATENCY_sum counter for MI300
* Remove TCP_TCP_LATENCY_sum counter which is unsupported for MI300 per register specification
* Remove VL1 Lat metric from memory chart section (block 3) for MI 300
since it uses TCP_TCP_LATENCY_sum counter which is unsupported
* Remove references to TCP_TCP_LATENCY_sum
* Update CHANGELOG
* reword changelog
2025-12-10 09:41:46 -05:00
9d34098350
[rocprofiler-compute] Roofline runtime compilation patch ( #2232 )
...
* Add install into CMakeLists.txt file- resolves 'no hip module' issues.
* Readd printout line for peak VALU during benchmarking removed on accident in a different commit.
* Add CHANGELOG entry for commit 2bfa9a4#2015 )")
Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com >
* Run formatter checks on rocprof-compute to clear PR checks
Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com >
* Update benchmark.py link in changelog
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Apply suggestions to CHANGELOG from code review
Co-authored-by: Pratik Basyal <pratik.basyal@amd.com >
---------
Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com >
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
Co-authored-by: Pratik Basyal <pratik.basyal@amd.com >
2025-12-10 01:44:28 -05:00
e55a439c13
wsl/librocdxg: Change hsaKmtQueueRingDoorbell interface
...
PR: https://github.com/ROCm/rocm-systems/pull/2068/commits/a87adf6444faf9bd841e9fdd38335aa8008b2d06
Signed-off-by: yangsu13 <Yang.Su2@amd.com >
Reviewed-by: Flora Cui <flora.cui@amd.com >
2025-12-10 14:08:35 +08:00
81c492eba2
CMakeLists - ${CMAKE_CURRENT_SOURCE_DIR} updates ( #683 )
...
* Add ${CMAKE_CURRENT_SOURCE_DIR} over ${CMAKE_SOURCE_DIR} where required
* Address review comments
[ROCm/rocdecode commit: 0ad47c91df
2025-12-09 21:35:46 -08:00
0ad47c91df
CMakeLists - ${CMAKE_CURRENT_SOURCE_DIR} updates ( #683 )
...
* Add ${CMAKE_CURRENT_SOURCE_DIR} over ${CMAKE_SOURCE_DIR} where required
* Address review comments
2025-12-09 21:35:46 -08:00
73778bf83c
Adjust policy for memory display on APUs ( #1967 )
...
* Read the ids_flags when fetching GPU info
The ids_flags contains the flags that can help identify if a GPU
is a dGPU or an APU.
* Show correct memory pool for APUs
The kernel policy for APUs will be to choose the bigger pool of
memory (GTT or VRAM) for KFD work. Adjust the policy for the monitor
and default commands to show the right memory pool when using an APU.
2025-12-09 21:49:06 -06:00
2e0abab81a
[ci] Bumping TheRock CI commit hash ( #2097 )
...
* Bumping TheRock CI commit hasH
* fixing artifact group
[ROCm/rccl commit: 6af9087b0c
2025-12-09 16:25:57 -08:00
6af9087b0c
[ci] Bumping TheRock CI commit hash ( #2097 )
...
* Bumping TheRock CI commit hasH
* fixing artifact group
2025-12-09 16:25:57 -08:00
879d010974
Bumping commit hash for TheRock ( #2244 )
2025-12-09 14:56:20 -08:00
63da8d2e08
[SWDEV-568673] Updated Docmentation Examples for Python APIs ( #2017 )
...
* [SWDEV-568673] Updated Docmentation Examples for Python APIs
* amdsmi_get_processor_type
* amdsmi_gpu_create_counter
* amdsmi_gpu_destroy_counter
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com >
* [SWDEV-568997] - Updated Docmentation Examples for Python APIs
* amdsmi_topo_get_p2p_status
Signed-off-by: Sumanth Gavini <sumanth.gavini@amd.com >
* [SWDEV-568997] - Updated Docmentation Examples for Python APIs
* [SWDEV-568997] - amdsmi_topo_get_p2p_status
* [SWDEV-568990] - amdsmi_set_gpu_clk_range
* [SWDEV-568987] - amdsmi_set_gpu_od_clk_info
* [SWDEV-568969] - AmdSmiEventReader
* [SWDEV-568964] - amdsmi_set_gpu_power_profile
* [SWDEV-568953] - amdsmi_gpu_create_counter
* [SWDEV-568939] - amdsmi_set_cpu_pcie_link_rate
* [SWDEV-568937] - amdsmi_get_cpu_socket_lclk_dpm_level
Signed-off-by: Sumanth Gavini <sumanth.gavini@amd.com >
* Fixes:
SWDEV-568716 [TCT][amd-smi]: NameError: name 'handle' is not defined when calling amdsmi_get_processor_handles(handle)
SWDEV-568726 [TCT][amd-smi]: TypeError: list indices must be integers or slices, not str when accessing cache_values['cache_properties']
SWDEV-568526 [TCT][amd-smi]: AMD SMI Python API Documentation Error – Incorrect variable name in sample code
SWDEV-569017 [TCT][amd-smi]: correction required for amdsmi_set_clk_freq API in python API document page
SWDEV-569025 [TCT][amd-smi]: amdsmi_get_link_metrics python API raises key error, correction required in python API sample documentation
Signed-off-by: Joseph Narlo <joseph.narlo@amd.com >
* Fix: SWDEV-568727 [TCT][amd-smi]: Mandatory arguements 'encoding' and 'link_name' needs to be updated in Python API Sample documentation
Signed-off-by: amd-josnarlo <josnarlo.amd.com>
---------
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com >
Signed-off-by: Sumanth Gavini <sumanth.gavini@amd.com >
Signed-off-by: Joseph Narlo <joseph.narlo@amd.com >
Signed-off-by: amd-josnarlo <josnarlo.amd.com>
Co-authored-by: Sumanth Gavini <sumanth.gavini@amd.com >
Co-authored-by: Joseph Narlo <joseph.narlo@amd.com >
Co-authored-by: amd-josnarlo <josnarlo.amd.com>
2025-12-09 16:16:50 -06:00
74cf2a85ec
Fix rocprofiler-sdk CI workflow tarball install errors ( #2225 )
...
* Add ls statement for debugging /opt directory file naming
* Update ROCM_VERSION from 7.0.0 to 7.1.1 in SDK CI
* Update amdgpu debian package for Ubuntu in Dockerfile.ci
* disable HIP/CLR build in codeql (#2242 )
---------
Co-authored-by: Venkateshwar Reddy Kandula <Venkateshwarreddy.Kandula@amd.com >
2025-12-09 16:06:35 -05:00
af5c453551
hip-tests: Enable standalone test targets with cmake ( #2189 )
...
Co-authored-by: Rahul Manocha <rmanocha@amd.com >
2025-12-09 11:07:42 -08:00
David Galiffi
Rahul Manocha
Mustafa Abduljabbar
Aleksei Tumakaev
Marko Crnobrnja Maletić
Mario Limonciello
habajpai-amd
SaleelK
Matt Arsenault
Adel Johar
koushikbillakanti-amd
SakaSitharammurthy
systems-assistant[bot]
Aryan Salmanpour
yugang-amd
shwetakhatri-amd
Geo Min
Aurelien Bouteiller
German Andryeyev
Pengda Xie
corey-derochie-amd
Fábio Mestre
Yiltan
Venkateshwar Reddy Kandula
jamessiddeley-amd
vedithal-amd
cfallows-amd
yangsu13
Zachary Vincze
Maisam Arif
Jason Bonnell