[L0 v2][CTS] Fix problems reported by SYCL e2e tests #2516
Conversation
github-actions
bot
added
common
|
Compute Benchmarks level_zero_v2 run (with params: --compare baseline-v2): |
|
Compute Benchmarks level_zero_v2 run (--compare baseline-v2): SummaryNo diffs to calculate performance change (result is better) Performance change in benchmark groupsRelative perf in group api (9): cannot calculate
Relative perf in group memory (4): cannot calculate
Relative perf in group miscellaneous (1): cannot calculate
Relative perf in group multithread (10): cannot calculate
Relative perf in group Velocity-Bench (9): cannot calculate
Relative perf in group Runtime (8): cannot calculate
Relative perf in group MicroBench (14): cannot calculate
Relative perf in group Pattern (10): cannot calculate
Relative perf in group ScalarProduct (6): cannot calculate
Relative perf in group USM (7): cannot calculate
Relative perf in group VectorAddition (3): cannot calculate
Relative perf in group Polybench (3): cannot calculate
Relative perf in group Kmeans (1): cannot calculate
Relative perf in group MolecularDynamics (1): cannot calculate
Relative perf in group llama.cpp (6): cannot calculate
Relative perf in group alloc/max (20): cannot calculate
Relative perf in group multiple (12): cannot calculate
Relative perf in group LinearRegressionCoeff (1): cannot calculate
DetailsBenchmark details - environment, command, output...api_overhead_benchmark_l0 SubmitKernel out of orderEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_l0 --test=SubmitKernel --csv --noHeaders --Ioq=0 --DiscardEvents=0 --MeasureCompletion=0 --iterations=100000 --Profiling=0 --NumKernels=10 --KernelExecTime=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type api_overhead_benchmark_sycl SubmitKernel out of orderEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_sycl --test=SubmitKernel --csv --noHeaders --Ioq=0 --DiscardEvents=0 --MeasureCompletion=0 --iterations=100000 --Profiling=0 --NumKernels=10 --KernelExecTime=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type api_overhead_benchmark_sycl SubmitKernel in orderEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_sycl --test=SubmitKernel --csv --noHeaders --Ioq=1 --DiscardEvents=0 --MeasureCompletion=0 --iterations=100000 --Profiling=0 --NumKernels=10 --KernelExecTime=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type memory_benchmark_sycl QueueInOrderMemcpy from Device to Device, size 1024Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/memory_benchmark_sycl --test=QueueInOrderMemcpy --csv --noHeaders --iterations=10000 --IsCopyOnly=0 --sourcePlacement=Device --destinationPlacement=Device --size=1024 --count=100 Output:TestCase,Mean,Median,StdDev,Min,Max,Type memory_benchmark_sycl QueueInOrderMemcpy from Host to Device, size 1024Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/memory_benchmark_sycl --test=QueueInOrderMemcpy --csv --noHeaders --iterations=10000 --IsCopyOnly=0 --sourcePlacement=Host --destinationPlacement=Device --size=1024 --count=100 Output:TestCase,Mean,Median,StdDev,Min,Max,Type memory_benchmark_sycl QueueMemcpy from Device to Device, size 1024Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/memory_benchmark_sycl --test=QueueMemcpy --csv --noHeaders --iterations=10000 --sourcePlacement=Device --destinationPlacement=Device --size=1024 Output:TestCase,Mean,Median,StdDev,Min,Max,Type memory_benchmark_sycl StreamMemory, placement Device, type Triad, size 10240Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/memory_benchmark_sycl --test=StreamMemory --csv --noHeaders --iterations=10000 --type=Triad --size=10240 --memoryPlacement=Device --useEvents=0 --contents=Zeros --multiplier=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type api_overhead_benchmark_sycl ExecImmediateCopyQueue out of order from Device to Device, size 1024Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_sycl --test=ExecImmediateCopyQueue --csv --noHeaders --iterations=100000 --ioq=0 --IsCopyOnly=1 --MeasureCompletionTime=0 --src=Device --dst=Device --size=1024 Output:TestCase,Mean,Median,StdDev,Min,Max,Type api_overhead_benchmark_sycl ExecImmediateCopyQueue in order from Device to Host, size 1024Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_sycl --test=ExecImmediateCopyQueue --csv --noHeaders --iterations=100000 --ioq=1 --IsCopyOnly=1 --MeasureCompletionTime=0 --src=Host --dst=Host --size=1024 Output:TestCase,Mean,Median,StdDev,Min,Max,Type miscellaneous_benchmark_sycl VectorSumEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/miscellaneous_benchmark_sycl --test=VectorSum --csv --noHeaders --iterations=1000 --numberOfElementsX=512 --numberOfElementsY=256 --numberOfElementsZ=256 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:400, numThreads:1, allocSize:102400 srcUSM:1 dstUSM:1Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=1 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=102400 --NumThreads=1 --NumOpsPerThread=400 --iterations=10 --SrcUSM=1 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:100, numThreads:8, allocSize:102400 srcUSM:1 dstUSM:1Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=1 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=102400 --NumThreads=8 --NumOpsPerThread=100 --iterations=10 --SrcUSM=1 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:400, numThreads:8, allocSize:1024 srcUSM:1 dstUSM:1Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=1 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=1024 --NumThreads=8 --NumOpsPerThread=400 --iterations=1000 --SrcUSM=1 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:10, numThreads:16, allocSize:1024 srcUSM:1 dstUSM:1Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=1 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=1024 --NumThreads=16 --NumOpsPerThread=10 --iterations=10000 --SrcUSM=1 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:400, numThreads:1, allocSize:102400 srcUSM:0 dstUSM:1Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=1 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=102400 --NumThreads=1 --NumOpsPerThread=400 --iterations=10 --SrcUSM=0 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:100, numThreads:8, allocSize:102400 srcUSM:0 dstUSM:1Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=1 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=102400 --NumThreads=8 --NumOpsPerThread=100 --iterations=10 --SrcUSM=0 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:400, numThreads:8, allocSize:1024 srcUSM:0 dstUSM:1Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=1 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=1024 --NumThreads=8 --NumOpsPerThread=400 --iterations=1000 --SrcUSM=0 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:10, numThreads:16, allocSize:1024 srcUSM:0 dstUSM:1Environment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=1 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=1024 --NumThreads=16 --NumOpsPerThread=10 --iterations=10000 --SrcUSM=0 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:4096, numThreads:1, allocSize:1024 srcUSM:0 dstUSM:1 without eventsEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=0 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=1024 --NumThreads=1 --NumOpsPerThread=4096 --iterations=10 --SrcUSM=0 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type multithread_benchmark_ur MemcpyExecute opsPerThread:4096, numThreads:4, allocSize:1024 srcUSM:0 dstUSM:1 without eventsEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/multithread_benchmark_ur --test=MemcpyExecute --csv --noHeaders --Ioq=1 --UseEvents=0 --MeasureCompletion=1 --UseQueuePerThread=1 --AllocSize=1024 --NumThreads=4 --NumOpsPerThread=4096 --iterations=10 --SrcUSM=0 --DstUSM=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type api_overhead_benchmark_ur SubmitKernel out of order CPU countEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_ur --test=SubmitKernel --csv --noHeaders --Ioq=0 --DiscardEvents=0 --MeasureCompletion=0 --iterations=100000 --Profiling=0 --NumKernels=10 --KernelExecTime=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type api_overhead_benchmark_ur SubmitKernel out of orderEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_ur --test=SubmitKernel --csv --noHeaders --Ioq=0 --DiscardEvents=0 --MeasureCompletion=0 --iterations=100000 --Profiling=0 --NumKernels=10 --KernelExecTime=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type api_overhead_benchmark_ur SubmitKernel in order CPU countEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_ur --test=SubmitKernel --csv --noHeaders --Ioq=1 --DiscardEvents=0 --MeasureCompletion=0 --iterations=100000 --Profiling=0 --NumKernels=10 --KernelExecTime=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type api_overhead_benchmark_ur SubmitKernel in orderEnvironment Variables:Command:/home/pmdk/bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_ur --test=SubmitKernel --csv --noHeaders --Ioq=1 --DiscardEvents=0 --MeasureCompletion=0 --iterations=100000 --Profiling=0 --NumKernels=10 --KernelExecTime=1 Output:TestCase,Mean,Median,StdDev,Min,Max,Type Velocity-Bench HashtableEnvironment Variables:Command:/home/pmdk/bench_workdir/hashtable/hashtable_sycl --no-verify Output:hashtable - total time for whole calculation: 0.352291 s Velocity-Bench BitcrackerEnvironment Variables:Command:/home/pmdk/bench_workdir/bitcracker/bitcracker -f /home/pmdk/bench_workdir/velocity-bench-repo/bitcracker/hash_pass/img_win8_user_hash.txt -d /home/pmdk/bench_workdir/velocity-bench-repo/bitcracker/hash_pass/user_passwords_60000.txt -b 60000 Output:---------> BitCracker: BitLocker password cracking tool <--------- ==================================
|
igchor
force-pushed
the
sycl_e2e_fixes
branch
from
2324e67 to
ed1a323
Compare
The check is already done in validation layer
igchor
force-pushed
the
sycl_e2e_fixes
branch
2 times, most recently
from
9ec81a9 to
2a15528
Compare
|
Hm, looks like change in [CTS][L0 v2] adjust urEnqueueMemBufferMap is specific to L0 adapter only (for other adapters SYCL doesn't expect this behavior). I think that for now, I will make the test L0-specific but the proper solution should be to fix the SYCL runtime to not rely on this behavior (it;s not in the spec). |
to match SYCL expectations. When pHost is set in buffer properties, urEnqueueMemBufferMap should map memory to that pointer (instead of creating a new allocation).
event should always be signaled (if provided by the user).
as they can be allocated by the user using L0 API directly (and then UMF will not know about those pointers and umfFree will do nothing).
To support both legacy and v2 adapter in SYCL tests
igchor
force-pushed
the
sycl_e2e_fixes
branch
from
2a15528 to
96a845d
Compare
No description provided.