Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Maslab clr 6.3.3 #142

Closed
wants to merge 119 commits into from
Closed

Conversation

smajidzahedi
Copy link

No description provided.

mangupta and others added 30 commits April 21, 2023 11:30
Change-Id: I9d65880e129eacaa5f3971332a9e1374d1878c9e
Change-Id: Ia9ec1705ce72c025d5ea75f4df56b0988c6f103d
Change-Id: I0a0814d335e8c3d9a80c1217d8d2df62e7baa548
Change-Id: Ia451c84750d33c96c2a435469694794d78fb2725
Change-Id: Ib6b00b7ab1f51fd6d1ea4a6e3d3027d71a0ce63d
For last mainline promotion based on 15-May-2023 build.

Change-Id: Ia2381211df6807df1c8cb265a625c726cd7ab290
Change-Id: I7f5c5e85e6c6bfd05f057350b02f73d03495571b
Change-Id: Ic3916acc6706444717b0c520ed5056e78a76505f
Change-Id: I3279d1c48704e040338bf83debc0588cd90841ee
Change-Id: I85fef1bdc27aea2350ad36184625ebcf3c971c51
Change-Id: I7542839da03d0fe8fb41683acec3a3416716aa57
Change-Id: Ia4fb1f59720c62fc872c0ed7cc4e8625353d7079
Change-Id: Ib6f4af31ac7049997d9f00eafc359846315efa1c
Change-Id: I0bb923950f814052f51d15d59fabaa2cafd679a9
Change-Id: Ib120768cedac894e5fdcb84daff55a8cde8a7167
Change-Id: Icc81cb530ffd2ed10daf1c3cbf4c973ec9ab67f1
Change-Id: I9dc0c086af6c3482001908e3ccfd984ee0d8c420
Change-Id: I7a99a04040e1e1de4f1c9d7ea6e06302f03d5f26
Change-Id: Ie3b9e446a6061aa1dad650c295a17c19a6b1975d
Change-Id: If838e5fb70840574853177fced072cd2620be37a
Change-Id: I8ded4d3a29c3b14d12cc971a334d0d39ceeec84b
Change-Id: I2b99f63785885f1c3a03520af8cb06e184a5c31c
Change-Id: I46ed998eb8a1d6b370029b26ae6b4f00dc1710b9
Change-Id: I257bf31012f300dd4afb10db409dcd588d68503e
…d package

Change-Id: I17643c8d6f66e7a71e2b7385986f5ff654345a62
…m-ocl-icd package"

This reverts commit bfb1ccc.

Reason for revert: to keep stable mainline build

Change-Id: Iccb2f5ce1d35f906e51a8916664f8cfe1999c69c
Change-Id: Id336c34852e02a2952b7fd80bf5ce9cb38e6dd95
Change-Id: I0ff1ab1b5b3a934fb4bdcf744874c2aae86a068d
Change-Id: I42ca288cc40303748c192ec5b18225595d5acbb9
Change-Id: I99c27ab97d3ec54c3de7712e652fd3bda7491926
jaydeeppatel1111 and others added 22 commits November 5, 2024 04:11
Change-Id: I757185e9c7c12f236e266219b67daf5836d2a122
…gfx12

- Default values are being assigned causing occupancy calculation to go
wrong without the right values defined for gfx12 ASICs
- Also added the these values for gfx1105

Change-Id: I611cc3a8ed8c57f2def637310ce1c3a48c16a574
(cherry picked from commit a26dc29)
Change-Id: Ia78b6b9377d99298c68968ef0eddd87534e0f750
(cherry picked from commit b5aab7f)
Change-Id: Ib1538546794194cdce77516ebfa8f5d06da69f1b
…-opencl-icd-loader

Change-Id: Ic659639e3bb55bd90bd50acf28d8079ff7b084bc
The new set tracks only the queues that have a command
submitted to them. This allows for fast iteration
in waitActiveStreams.

Change-Id: I2c832eefa01280d9a87a5f57874d36d2e9441de7
(cherry picked from commit bcc545e)
Change-Id: I1f4744f20a9caeed005ec68da44e5fde737e09f7
- Don't generate callbacks for HIP events
- Don't process profiling info in the callback for HIP events
- Wait for CPU status update of the submitted commands
every 50 calls. That will allow to drain the commands and
destroy HSA signals.

Change-Id: Ib601a350e7e7c2b6c6209a172385389baccf73a9
- Fix typo

Change-Id: If4c68455dcfa03fee18cb4720e8b5b438642703c
Applications may submit commands withoout waits
for GPU. That causes a growth of SW unreleased commands.
Make sure runtime flushes SW queue, if it grows over some
threshold, controlled by DEBUG_CLR_MAX_BATCH_SIZE.

Change-Id: Ia4d85c24210ef91c394f638ab6b53b14323a0396
Add an atomic counter to track the outstanding HSA handlers.
Wait on CPU for the callbacks if the number exceeds the value
in DEBUG_HIP_BLOCK_SYNC env variable.

Change-Id: I95dc8c4bf0258c7e59411b7504220709ed6898c5
Add DEBUG_CLR_SYSMEM_POOL to control sysmempool.

Change-Id: Idb8e2ab32ab33cd65e8b7d61816c028fa44fbc85
(cherry picked from commit 3640722b80b629808788ff52c1092ff3ed409e6d)
Runtime may use checkGpuTime() for the wait and not just for the GPU time queries. Hence, the call can't be skipped if profiling isn't enabled.
More changes are required for this optimization.

Change-Id: I79e8918312e755d75f0d26685f2fdc604a8ffb18
(cherry picked from commit 6189d83817f4196a9e0039a5765d97aea6e76316)
Change-Id: I5e98c34a41434e2f7d2e6406ea30ddcf01b1091c
(cherry picked from commit 39b64b5)
Change-Id: I17fdaf7ac323507f99a7c071066944296537489c
Shared mutex allows to have access to the list of streams  from
multiple threads at the same time.

Change-Id: Ibee64b846cde03321d5b17dbee2829c0bab7e7d6
(cherry picked from commit efd3ea4)
Change-Id: Ib86412255adad172598620ea81214e5eb56020ea
- Remove binning logic, although useful it doesnt work in current
  scenario as there is no upper limit on the size of allocation. If an
app or framework uses entire VRAM and then creates suballocs, binning
would result in failure.

Change-Id: Icc27c13e433bb4a1f03e82028d8718488b43bfa5
(cherry picked from commit e4d29e2)
…isterFatBinary

This is to avoid calling the HIP_INIT macro during the shutdown process.

Change-Id: I2e65f6e10491918a17445ee1e8ddd08286070358
=> GraphExec instance is destroyed before async launch completes,
destroy after all pending graph launches
=> Remove GraphExec destroy during next sync point(hipStreamSync,
hipDeviceSync etc..)

Change-Id: I4df682aae5787fd6e5240a7be936ce50361345d0
(cherry picked from commit f9f995c)
Change-Id: I2942b26b9d49defce0894f60f5fc833842e4928c
Change-Id: Ie2854eeac764fba770b296a63d76d547139d3cc0
@smajidzahedi smajidzahedi deleted the maslab-clr-6.3.3 branch February 26, 2025 05:07
@smajidzahedi smajidzahedi restored the maslab-clr-6.3.3 branch February 26, 2025 05:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.