Since hipMemMap can be called for multiple device handles on the same virtual memory, the same is true for hipMemUnmap, meaning that virtual memory can be "partially unmapped".
This means that the unmap function can be called for a specific part of the reserved address, meaning that only the designated subbuffer should be released. If unmap is called on the entire reserved memory, then all subbuffers should be released.
The main point is that for every hsa_amd_vmem_map, there should be a corresponding hsa_amd_vmem_unmap. Otherwise, if entire memory is unmapped by a single unmap call, then HSA will report the memory as "in use" if an attempt is made to delete it.
Change-Id: I039308eafb820decfb1c09f60347f26cdad1a362
[ROCm/clr commit: 3ec1d2d2f1]
Since hipMemMap can be called for multiple device handles on the same virtual memory, the same is true for hipMemUnmap, meaning that virtual memory can be "partially unmapped".
This means that the unmap function can be called for a specific part of the reserved address, meaning that only the designated subbuffer should be released. If unmap is called on the entire reserved memory, then all subbuffers should be released.
The main point is that for every hsa_amd_vmem_map, there should be a corresponding hsa_amd_vmem_unmap. Otherwise, if entire memory is unmapped by a single unmap call, then HSA will report the memory as "in use" if an attempt is made to delete it.
Change-Id: I039308eafb820decfb1c09f60347f26cdad1a362
* misc/msccl: read graphCaptureStatus for every collective call
* fix a bug in checking whether UBR is enabled in MSCCLPP
* cmake: Fix patch reversal order
* misc/msccl: add logging
[ROCm/rccl commit: 23c0b7bd84]
* misc/msccl: read graphCaptureStatus for every collective call
* fix a bug in checking whether UBR is enabled in MSCCLPP
* cmake: Fix patch reversal order
* misc/msccl: add logging
* * rocDecode/VP9: Added VP9 IVF containter detection and picture data parsing.
* * rocDecode/VP9 bitstream reader: Wording changes based on review comment.
* * rocDecode/VP9 IVF parser: Updated change log based on review comment.
* * rocDecode/VP9 IVF parser: Bumped up rocDecode version to 0.11.0.
* * rocDecode/VP9: Added VP9 IVF containter detection and picture data parsing.
* * rocDecode/VP9 bitstream reader: Wording changes based on review comment.
* * rocDecode/VP9 IVF parser: Updated change log based on review comment.
* * rocDecode/VP9 IVF parser: Bumped up rocDecode version to 0.11.0.
* * rocDecode/VP9 IVF parsing: Minor name correction.
* Introduce required frame pts in Video demuxer
* Revert "Support to obtain dts from demuxer and seek (#479)"
This reverts commit 65edd2198d.
---------
Co-authored-by: fgladwin <fgladwin@amd.com>
[ROCm/rocdecode commit: 866ba6699b]
* Introduce required frame pts in Video demuxer
* Revert "Support to obtain dts from demuxer and seek (#479)"
This reverts commit d45cd48001.
---------
Co-authored-by: fgladwin <fgladwin@amd.com>
- Use getBuffer/releaseBuffer in BlitManager
- Cleanup XferBuffer as we use ManagedBuffer for both reads/writes
Change-Id: I2661b85dd012763b17a38a743fec1b1d79125f67
[ROCm/clr commit: 37d606d193]
- Use getBuffer/releaseBuffer in BlitManager
- Cleanup XferBuffer as we use ManagedBuffer for both reads/writes
Change-Id: I2661b85dd012763b17a38a743fec1b1d79125f67
- Add document formatting workflow from ROCm/rocm-docs-core/.github/workflows/linting.yml
- Updated runners to use ubuntu-22.04, since 20.04 is being deprecated.
[ROCm/rocprofiler-systems commit: a18d00d784]
- Add document formatting workflow from ROCm/rocm-docs-core/.github/workflows/linting.yml
- Updated runners to use ubuntu-22.04, since 20.04 is being deprecated.
Modify test case to support XL cards.
Change-Id: I6ad45a290d50a5238804ce7417bcdb33a3912872
Signed-off-by: David Belanger <david.belanger@amd.com>
[ROCm/ROCR-Runtime commit: 3ceb131df5]
* Improve RDMA flushing by write dummy payload with RO=0
* Rename env var for disabling this change to RCCL_GDR_FLUSH_GPU_MEM_NO_RELAXED_ORDERING
[ROCm/rccl commit: 60c1264d27]
- If any kernel uses device heap, the launch needs to be preceeded by an
init kernel, Save on the extra barrier packet launch/flush between the
init heap kernel and user kernel
Change-Id: I8ebc6246188200e5f673dc464bc76a53bcb8b7c6
[ROCm/clr commit: ca530c660b]
- If any kernel uses device heap, the launch needs to be preceeded by an
init kernel, Save on the extra barrier packet launch/flush between the
init heap kernel and user kernel
Change-Id: I8ebc6246188200e5f673dc464bc76a53bcb8b7c6
* Add check to skip counter_storage::write() if internal storage field is destroyed.
* Output warning message if counter data is not available when trying to write out to Timemory
---------
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-systems commit: 43f900d01e]
* Add check to skip counter_storage::write() if internal storage field is destroyed.
* Output warning message if counter data is not available when trying to write out to Timemory
---------
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
* [Samples] - fix the issue of out-of-order processing in the videoDecodeRGB sample
* Add a comment
* Add hipStreamSyncronize
[ROCm/rocdecode commit: 9e0600a2d0]
Change Versioning Scheme to match https://semver.org/
Dropping the year enum and API fields in a future release.
Should not impact library versioning since we are now starting from 25.2.0
---------
Signed-off-by: Joseph Narlo <joseph.narlo@amd.com>
Co-authored-by: Arif, Maisam <Maisam.Arif@amd.com>
Change-Id: Id090e23f156926d08f9c0b781447388adf268cf6
Change Versioning Scheme to match https://semver.org/
Dropping the year enum and API fields in a future release.
Should not impact library versioning since we are now starting from 25.2.0
---------
Signed-off-by: Joseph Narlo <joseph.narlo@amd.com>
Co-authored-by: Arif, Maisam <Maisam.Arif@amd.com>
Change-Id: Id090e23f156926d08f9c0b781447388adf268cf6
[ROCm/amdsmi commit: d7c3ad0886]