Use barrier packets for every profile marker that gets submitted
and use the completion signal to get GPU ts. This gives most accurate
dispatch time. Club cache flushes with profile marker if there is a
pending dispatch that needs cache flush. This optimization saves on
extra barrier and helps wall time
Change-Id: Ib62d6d7aabf4743827b561be6c9c5afa813203da
[ROCm/clr commit: 59c6cb0268]
OCL can't distinguish different copy types, but ROC profiler
expects SDMA transfer visibility. Add extra code to detect
a transfer with the host memory and substitute OCL command
Change-Id: I5290acd0e10bc082e00c1d4ae1474a075de7f165
[ROCm/clr commit: bd340d8cbf]
Enable this optimization when the barrier is disabled, since
reuse requires a signal wait.
Use the size of pending AQL signals as the size of signal pool.
Change-Id: I2754a0f8b67e19d2601c58945e10fdf0e8be1624
[ROCm/clr commit: a5661192b6]
The change reuses HSA signals for dispatches as a wait signal.
Skipping the barrier requires to disable L2 cache for sysmem
allocations and extra tracking for HDP access with the large bar.
ROC_BARRIER_SYNC=0 activates the new logic. Barrier sync is
still used by default.
ROC_ACTIVE_WAIT=1 enables unconditional active wait in ROCr.
The change also consolidated ROCr wait logic under single function.
Change-Id: I6bd1be30aa88258da1b1f9de319ef5a45852afd8
[ROCm/clr commit: d9397590de]
SWDEV-249719 - root cause: queues with custom CU mask are not inserted
into queuePool_ (i.e., queue of reusable HSA queues) of ROC device class
causing a crash when creating hostcall buffers for printf
Change-Id: Ieee7005d9a5a30b3113394ce23ee65927126d0d6
[ROCm/clr commit: 2e199bd492]
When header==0, the legitimate packet->header is wiped out, so also add an assert.
Change-Id: I6b3037d4618719262b0d7c1792bd54f768a63660
[ROCm/clr commit: 19d1497fa2]
root cause - cooperative queue is not inserted into queuePool_ (HSA queues) of ROC device calss causing a crash when creating hostcall buffers for printf
Change-Id: I3f9aceb4e5fe6a7c7a2a549a4bb0a3511fe02799
[ROCm/clr commit: d2b9d267b2]
Fix a typo with the name define, when compilation wasn't enabled.
Force CPU prefetch if system was forced in runtime
Change-Id: Id4b578f9fa44a45426fdb5d8ecb1da803aa42313
[ROCm/clr commit: 6e69258b69]
P2P staging uses device queues for transfer, hence the current
queue must be in sync
Change-Id: I8372a60590eed9dde62cb4c67ef4df5df82a8e8d
[ROCm/clr commit: 0dc47d55d2]
The current implementation creates default reference in the stack and assigns it to class member cuMasks_, so whenever the content of the stack changes, cuMask_ would change.
Change-Id: Iefab63c335d504b83c4ae90bd34ae76c6afb8f3c
[ROCm/clr commit: 8ef5da00c7]
Optimizaiton to remove extra syncs uncovered a bug with the cache
coherency layer, there runtime could lose the track of mem address
if coherency layer performed a sync.
Change-Id: I25647cfa4a4be9cdbd8577ff076a740bbdac79c8
[ROCm/clr commit: 91a25df04f]
When HIP_ENABLE_DEFERRED_LOADING=0, many global variables will be
referenced but they are not initialized in that early time. The patch
will use constexpr to initialze global constant varables in compile
time.
Change-Id: I9d538b7abc6a0ce700ec3332b97fc144db5fc1ef
[ROCm/clr commit: fdef6f722f]
- Expose ROCclr interfaces for HIP usage
- ROCr interfaces aren't available in staging, thus control the
build with AMD_HMM_SUPPORT define
Change-Id: Iadc2bcc230e78d3b0dc22b235189c8cc80843446
[ROCm/clr commit: c5afd5d412]
Make sure runtime waits for the current queue before
synching with device queue
Change-Id: I753b6fc0bb15a3a3d4bf03fef1152842550850c0
[ROCm/clr commit: 86e0f337fc]
Optimization for the fence release removed a sync for mem fill.
Add simple const buffer management forr the filled pattern to avoid
pattern overwriting with the async fills.
Change-Id: I63773ac09ceec31d5396d24570e4647ff096326b
[ROCm/clr commit: 2ce6bbebc4]
SWDEV-234947
SWDEV-236298
Instead of forcing a barrier packet, just inject system scope on the next packet.
Change-Id: If9bcee23e08dfe5db731235e2fcb30582cbd4c1c
[ROCm/clr commit: 6a5af4056e]
Remove queue limitation since we loop through HW queues now.
Add a DevLogError if we fail to create the hsa_queue. A ticket showed a regression there.
Change-Id: I4f58e405f88e75600a762f6d6352838c969cdb5e
[ROCm/clr commit: b54c3f7db9]
[ROCm][TCT][HIP] cooperative stream test case is failing.
Make sure lockXfer() in the blit manager returns a valid value.
Port the latest PAL backend logic into the ROCr backend.
This change doesn't fix the issue, reported in the ticket.
Change-Id: I54101a824f49a2dcfbbf5414cb5b3af41745306d
[ROCm/clr commit: 89133a7301]
- Once device assertion occurs, abort the host execution as well.
- TODO: This's the initial support. As we need to drain hostcall queue
to ensure device assertion message being flushed out, hostcall
listener needs an interface to explicitly drain its queue.
Change-Id: I8a04400aa7109bfd054ae5777c41a4abbf0db4a9
[ROCm/clr commit: 97f55b5c7f]
1. Enable pitch workaround
2. When we use copy image, we don't need to create the custom pitch image
3. wrtBackImageBuffer_ stores device memory object, not amd image object.
Tests:
conformance kernel read / write test pass with this code change.
Change-Id: I7dca3127adde6ac83e78dd270a2256ebed55c60d
[ROCm/clr commit: 43b9863e17]
[hipclang-vdi-rocm][perf]~45% to 50% of Performance drop on
rocBLAS_int8 test
- Enable AMD_OPT_FLUSH optimization by default to match HCC
- Disable CPU writes to GPU memory on boards with large bar,
because it requires HDP flush tracking.
- Enable L2 cache on kernel arguments, because L2 will be
invalidated on memory reuse .
Change-Id: I124cf250bdd4d19c523ce542c163813828f8fbdc
[ROCm/clr commit: 374f612b7c]
Payam
Saleel Kudchadker
German Andryeyev
Aryan Salmanpour
Alex Xie
Jason Tang
Jason Tang
Tao Sang
Jatin Chaudhary
Matt Arsenault
Dittakavi Satyanvesh
Christophe Paquot
Michael LIAO
Laurent Morichetti