[UR] Bump UMF to v0.11.0-dev3 #17188
Conversation
lukaszstolarczuk
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
lukaszstolarczuk
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
|
|
lukaszstolarczuk
force-pushed
the
bump-umf-v0.11.0-dev3
branch
from
045f182 to
3bb9708
Compare
lukaszstolarczuk
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
lukaszstolarczuk
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
lukaszstolarczuk
force-pushed
the
bump-umf-v0.11.0-dev3
branch
from
3bb9708 to
a80ad8b
Compare
lukaszstolarczuk
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
lukaszstolarczuk
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
|
changing to draft, as |
|
Compute Benchmarks level_zero run (with params: ): |
|
Benchmarks level_zero run (): |
|
Compute Benchmarks level_zero run (with params: ): |
|
Benchmarks level_zero run (): Summary(Emphasized values are the best results) Performance change in benchmark groupsVelocity BenchRelative perf in group Other (8)
SYCL-BenchRelative perf in group Other (53)
llama.cpp benchRelative perf in group Other (6)
DetailsBenchmark details - environment, command...Velocity-Bench HashtableCommand:/home/test-user/llvm_bench_workdir/hashtable/hashtable_sycl --no-verify Velocity-Bench BitcrackerCommand:/home/test-user/llvm_bench_workdir/bitcracker/bitcracker -f /home/test-user/llvm_bench_workdir/velocity-bench-repo/bitcracker/hash_pass/img_win8_user_hash.txt -d /home/test-user/llvm_bench_workdir/velocity-bench-repo/bitcracker/hash_pass/user_passwords_60000.txt -b 60000 Velocity-Bench CudaSiftCommand:/home/test-user/llvm_bench_workdir/cudaSift/cudaSift Velocity-Bench QuickSilverCommand:/home/test-user/llvm_bench_workdir/QuickSilver/qs -i /home/test-user/llvm_bench_workdir/velocity-bench-repo/QuickSilver/Examples/AllScattering/scatteringOnly.inp Environment Variables:QS_DEVICE=GPU Velocity-Bench Sobel FilterCommand:/home/test-user/llvm_bench_workdir/sobel_filter/sobel_filter -i /home/test-user/llvm_bench_workdir/data/sobel_filter/sobel_filter_data/silverfalls_32Kx32K.png -n 5 Environment Variables:OPENCV_IO_MAX_IMAGE_PIXELS=1677721600 Velocity-Bench dl-cifarCommand:/home/test-user/llvm_bench_workdir/dl-cifar/dl-cifar_sycl Velocity-Bench dl-mnistCommand:/home/test-user/llvm_bench_workdir/dl-mnist/dl-mnist-sycl -conv_algo ONEDNN_AUTO Environment Variables:NEOReadDebugKeys=1 Velocity-Bench svmCommand:/home/test-user/llvm_bench_workdir/svm/svm_sycl /home/test-user/llvm_bench_workdir/velocity-bench-repo/svm/SYCL/a9a /home/test-user/llvm_bench_workdir/velocity-bench-repo/svm/SYCL/a.m Runtime_IndependentDAGTaskThroughput_SingleTaskCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_IndependentDAGTaskThroughput_BasicParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_IndependentDAGTaskThroughput_HierarchicalParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_IndependentDAGTaskThroughput_NDRangeParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_DAGTaskThroughput_SingleTaskCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 Runtime_DAGTaskThroughput_BasicParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 Runtime_DAGTaskThroughput_HierarchicalParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 Runtime_DAGTaskThroughput_NDRangeParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 MicroBench_HostDeviceBandwidth_1D_H2D_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_H2D_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_H2D_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_1D_D2H_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_D2H_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_D2H_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_1D_H2D_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_H2D_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_H2D_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_1D_D2H_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_D2H_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_D2H_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_LocalMem_int32_4096Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/local_mem --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/LocalMem_multi.csv --size=10240000 MicroBench_LocalMem_fp32_4096Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/local_mem --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/LocalMem_multi.csv --size=10240000 Pattern_Reduction_NDRange_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/reduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_Reduction_multi.csv --size=10240000 Pattern_Reduction_Hierarchical_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/reduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_Reduction_multi.csv --size=10240000 ScalarProduct_NDRange_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_NDRange_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_NDRange_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_Hierarchical_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_Hierarchical_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_Hierarchical_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_int16Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_int16Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 USM_Allocation_latency_fp32_deviceCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_allocation_latency --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Allocation_latency_multi.csv --size=1024000000 USM_Allocation_latency_fp32_hostCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_allocation_latency --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Allocation_latency_multi.csv --size=1024000000 USM_Allocation_latency_fp32_sharedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_allocation_latency --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Allocation_latency_multi.csv --size=1024000000 USM_Instr_Mix_fp32_device_1:1mix_with_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 USM_Instr_Mix_fp32_host_1:1mix_with_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 USM_Instr_Mix_fp32_device_1:1mix_no_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 USM_Instr_Mix_fp32_host_1:1mix_no_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 VectorAddition_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/vec_add --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/VectorAddition_multi.csv --size=102400000 VectorAddition_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/vec_add --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/VectorAddition_multi.csv --size=102400000 VectorAddition_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/vec_add --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/VectorAddition_multi.csv --size=102400000 Polybench_2mmCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/2mm --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/2mm.csv --size=512 Polybench_3mmCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/3mm --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/3mm.csv --size=512 Polybench_AtaxCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/atax --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Atax.csv --size=8192 Kmeans_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/kmeans --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Kmeans.csv --size=700000000 MolecularDynamicsCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/mol_dyn --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/MolecularDynamics.csv --size=8196 llama.cpp Prompt Processing Batched 128Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Text Generation Batched 128Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Prompt Processing Batched 256Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Text Generation Batched 256Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Prompt Processing Batched 512Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Text Generation Batched 512Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf |
|
Compute Benchmarks level_zero_v2 run (with params: ): |
|
Benchmarks level_zero_v2 run (): Summary(Emphasized values are the best results) Performance change in benchmark groupsCompute BenchmarksRelative perf in group SubmitKernel (4)
Relative perf in group Other (6)
Relative perf in group SinKernelGraph 5 (3)
Relative perf in group SinKernelGraph 100 (3)
Velocity BenchRelative perf in group Other (8)
SYCL-BenchRelative perf in group Other (54)
llama.cpp benchRelative perf in group Other (6)
DetailsBenchmark details - environment, command...api_overhead_benchmark_l0 SubmitKernel out of orderCommand:/home/test-user/llvm_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 api_overhead_benchmark_l0 SubmitKernel in orderCommand:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_l0 --test=SubmitKernel --csv --noHeaders --Ioq=1 --DiscardEvents=0 --MeasureCompletion=0 --iterations=100000 --Profiling=0 --NumKernels=10 --KernelExecTime=1 api_overhead_benchmark_sycl SubmitKernel out of orderCommand:/home/test-user/llvm_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 api_overhead_benchmark_sycl SubmitKernel in orderCommand:/home/test-user/llvm_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 memory_benchmark_sycl QueueInOrderMemcpy from Device to Device, size 1024Command:/home/test-user/llvm_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 memory_benchmark_sycl QueueInOrderMemcpy from Host to Device, size 1024Command:/home/test-user/llvm_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 memory_benchmark_sycl QueueMemcpy from Device to Device, size 1024Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/memory_benchmark_sycl --test=QueueMemcpy --csv --noHeaders --iterations=10000 --sourcePlacement=Device --destinationPlacement=Device --size=1024 api_overhead_benchmark_sycl ExecImmediateCopyQueue out of order from Device to Device, size 1024Command:/home/test-user/llvm_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 api_overhead_benchmark_sycl ExecImmediateCopyQueue in order from Device to Host, size 1024Command:/home/test-user/llvm_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 miscellaneous_benchmark_sycl VectorSumCommand:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/miscellaneous_benchmark_sycl --test=VectorSum --csv --noHeaders --iterations=1000 --numberOfElementsX=512 --numberOfElementsY=256 --numberOfElementsZ=256 graph_api_benchmark_sycl SinKernelGraph graphs:0, numKernels:5Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_sycl --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=5 --withGraphs=0 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_sycl SinKernelGraph graphs:0, numKernels:100Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_sycl --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=100 --withGraphs=0 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_l0 SinKernelGraph graphs:0, numKernels:5Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_l0 --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=5 --withGraphs=0 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_l0 SinKernelGraph graphs:1, numKernels:5Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_l0 --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=5 --withGraphs=1 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_l0 SinKernelGraph graphs:0, numKernels:100Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_l0 --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=100 --withGraphs=0 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_l0 SinKernelGraph graphs:1, numKernels:100Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_l0 --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=100 --withGraphs=1 --withCopyOffload=1 --immediateAppendCmdList=0 Velocity-Bench HashtableCommand:/home/test-user/llvm_bench_workdir/hashtable/hashtable_sycl --no-verify Velocity-Bench BitcrackerCommand:/home/test-user/llvm_bench_workdir/bitcracker/bitcracker -f /home/test-user/llvm_bench_workdir/velocity-bench-repo/bitcracker/hash_pass/img_win8_user_hash.txt -d /home/test-user/llvm_bench_workdir/velocity-bench-repo/bitcracker/hash_pass/user_passwords_60000.txt -b 60000 Velocity-Bench CudaSiftCommand:/home/test-user/llvm_bench_workdir/cudaSift/cudaSift Velocity-Bench QuickSilverCommand:/home/test-user/llvm_bench_workdir/QuickSilver/qs -i /home/test-user/llvm_bench_workdir/velocity-bench-repo/QuickSilver/Examples/AllScattering/scatteringOnly.inp Environment Variables:QS_DEVICE=GPU Velocity-Bench Sobel FilterCommand:/home/test-user/llvm_bench_workdir/sobel_filter/sobel_filter -i /home/test-user/llvm_bench_workdir/data/sobel_filter/sobel_filter_data/silverfalls_32Kx32K.png -n 5 Environment Variables:OPENCV_IO_MAX_IMAGE_PIXELS=1677721600 Velocity-Bench dl-cifarCommand:/home/test-user/llvm_bench_workdir/dl-cifar/dl-cifar_sycl Velocity-Bench dl-mnistCommand:/home/test-user/llvm_bench_workdir/dl-mnist/dl-mnist-sycl -conv_algo ONEDNN_AUTO Environment Variables:NEOReadDebugKeys=1 Velocity-Bench svmCommand:/home/test-user/llvm_bench_workdir/svm/svm_sycl /home/test-user/llvm_bench_workdir/velocity-bench-repo/svm/SYCL/a9a /home/test-user/llvm_bench_workdir/velocity-bench-repo/svm/SYCL/a.m Runtime_IndependentDAGTaskThroughput_SingleTaskCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_IndependentDAGTaskThroughput_BasicParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_IndependentDAGTaskThroughput_HierarchicalParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_IndependentDAGTaskThroughput_NDRangeParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_DAGTaskThroughput_SingleTaskCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 Runtime_DAGTaskThroughput_BasicParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 Runtime_DAGTaskThroughput_HierarchicalParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 Runtime_DAGTaskThroughput_NDRangeParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 MicroBench_HostDeviceBandwidth_1D_H2D_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_H2D_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_H2D_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_1D_D2H_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_D2H_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_D2H_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_1D_H2D_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_H2D_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_H2D_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_1D_D2H_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_D2H_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_D2H_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_LocalMem_int32_4096Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/local_mem --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/LocalMem_multi.csv --size=10240000 MicroBench_LocalMem_fp32_4096Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/local_mem --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/LocalMem_multi.csv --size=10240000 Pattern_Reduction_NDRange_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/reduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_Reduction_multi.csv --size=10240000 Pattern_Reduction_Hierarchical_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/reduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_Reduction_multi.csv --size=10240000 ScalarProduct_NDRange_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_NDRange_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_NDRange_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_Hierarchical_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_Hierarchical_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_Hierarchical_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_int16Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_int16Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 USM_Allocation_latency_fp32_deviceCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_allocation_latency --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Allocation_latency_multi.csv --size=1024000000 USM_Allocation_latency_fp32_hostCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_allocation_latency --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Allocation_latency_multi.csv --size=1024000000 USM_Allocation_latency_fp32_sharedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_allocation_latency --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Allocation_latency_multi.csv --size=1024000000 USM_Instr_Mix_fp32_device_1:1mix_with_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 USM_Instr_Mix_fp32_host_1:1mix_with_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 USM_Instr_Mix_fp32_device_1:1mix_no_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 USM_Instr_Mix_fp32_host_1:1mix_no_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 VectorAddition_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/vec_add --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/VectorAddition_multi.csv --size=102400000 VectorAddition_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/vec_add --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/VectorAddition_multi.csv --size=102400000 VectorAddition_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/vec_add --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/VectorAddition_multi.csv --size=102400000 Polybench_2mmCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/2mm --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/2mm.csv --size=512 Polybench_3mmCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/3mm --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/3mm.csv --size=512 Polybench_AtaxCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/atax --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Atax.csv --size=8192 Kmeans_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/kmeans --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Kmeans.csv --size=700000000 LinearRegressionCoeff_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/lin_reg_coeff --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/LinearRegressionCoeff.csv --size=1638400000 MolecularDynamicsCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/mol_dyn --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/MolecularDynamics.csv --size=8196 llama.cpp Prompt Processing Batched 128Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Text Generation Batched 128Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Prompt Processing Batched 256Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Text Generation Batched 256Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Prompt Processing Batched 512Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Text Generation Batched 512Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf |
From now on disjoint_pool is part of libumf, instead of being a separate library.
lukaszstolarczuk
force-pushed
the
bump-umf-v0.11.0-dev3
branch
from
a80ad8b to
2241df2
Compare
lukaszstolarczuk
had a problem deploying
to
WindowsCILock
GitHub Actions
Error
|
Compute Benchmarks level_zero run (with params: --compare baseline): |
|
Benchmarks level_zero run (--compare baseline): Summary(Emphasized values are the best results) Performance change in benchmark groupsCompute BenchmarksRelative perf in group SubmitKernel (4)
Relative perf in group Other (6)
Relative perf in group SinKernelGraph 5 (3)
Relative perf in group SinKernelGraph 100 (3)
Velocity BenchRelative perf in group Other (8)
SYCL-BenchRelative perf in group Other (54)
llama.cpp benchRelative perf in group Other (6)
DetailsBenchmark details - environment, command...api_overhead_benchmark_l0 SubmitKernel out of orderCommand:/home/test-user/llvm_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 api_overhead_benchmark_l0 SubmitKernel in orderCommand:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/api_overhead_benchmark_l0 --test=SubmitKernel --csv --noHeaders --Ioq=1 --DiscardEvents=0 --MeasureCompletion=0 --iterations=100000 --Profiling=0 --NumKernels=10 --KernelExecTime=1 api_overhead_benchmark_sycl SubmitKernel out of orderCommand:/home/test-user/llvm_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 api_overhead_benchmark_sycl SubmitKernel in orderCommand:/home/test-user/llvm_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 memory_benchmark_sycl QueueInOrderMemcpy from Device to Device, size 1024Command:/home/test-user/llvm_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 memory_benchmark_sycl QueueInOrderMemcpy from Host to Device, size 1024Command:/home/test-user/llvm_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 memory_benchmark_sycl QueueMemcpy from Device to Device, size 1024Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/memory_benchmark_sycl --test=QueueMemcpy --csv --noHeaders --iterations=10000 --sourcePlacement=Device --destinationPlacement=Device --size=1024 api_overhead_benchmark_sycl ExecImmediateCopyQueue out of order from Device to Device, size 1024Command:/home/test-user/llvm_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 api_overhead_benchmark_sycl ExecImmediateCopyQueue in order from Device to Host, size 1024Command:/home/test-user/llvm_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 miscellaneous_benchmark_sycl VectorSumCommand:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/miscellaneous_benchmark_sycl --test=VectorSum --csv --noHeaders --iterations=1000 --numberOfElementsX=512 --numberOfElementsY=256 --numberOfElementsZ=256 graph_api_benchmark_sycl SinKernelGraph graphs:0, numKernels:5Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_sycl --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=5 --withGraphs=0 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_sycl SinKernelGraph graphs:0, numKernels:100Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_sycl --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=100 --withGraphs=0 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_l0 SinKernelGraph graphs:0, numKernels:5Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_l0 --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=5 --withGraphs=0 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_l0 SinKernelGraph graphs:1, numKernels:5Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_l0 --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=5 --withGraphs=1 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_l0 SinKernelGraph graphs:0, numKernels:100Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_l0 --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=100 --withGraphs=0 --withCopyOffload=1 --immediateAppendCmdList=0 graph_api_benchmark_l0 SinKernelGraph graphs:1, numKernels:100Command:/home/test-user/llvm_bench_workdir/compute-benchmarks-build/bin/graph_api_benchmark_l0 --test=SinKernelGraph --csv --noHeaders --iterations=10000 --numKernels=100 --withGraphs=1 --withCopyOffload=1 --immediateAppendCmdList=0 Velocity-Bench HashtableCommand:/home/test-user/llvm_bench_workdir/hashtable/hashtable_sycl --no-verify Velocity-Bench BitcrackerCommand:/home/test-user/llvm_bench_workdir/bitcracker/bitcracker -f /home/test-user/llvm_bench_workdir/velocity-bench-repo/bitcracker/hash_pass/img_win8_user_hash.txt -d /home/test-user/llvm_bench_workdir/velocity-bench-repo/bitcracker/hash_pass/user_passwords_60000.txt -b 60000 Velocity-Bench CudaSiftCommand:/home/test-user/llvm_bench_workdir/cudaSift/cudaSift Velocity-Bench QuickSilverCommand:/home/test-user/llvm_bench_workdir/QuickSilver/qs -i /home/test-user/llvm_bench_workdir/velocity-bench-repo/QuickSilver/Examples/AllScattering/scatteringOnly.inp Environment Variables:QS_DEVICE=GPU Velocity-Bench Sobel FilterCommand:/home/test-user/llvm_bench_workdir/sobel_filter/sobel_filter -i /home/test-user/llvm_bench_workdir/data/sobel_filter/sobel_filter_data/silverfalls_32Kx32K.png -n 5 Environment Variables:OPENCV_IO_MAX_IMAGE_PIXELS=1677721600 Velocity-Bench dl-cifarCommand:/home/test-user/llvm_bench_workdir/dl-cifar/dl-cifar_sycl Velocity-Bench dl-mnistCommand:/home/test-user/llvm_bench_workdir/dl-mnist/dl-mnist-sycl -conv_algo ONEDNN_AUTO Environment Variables:NEOReadDebugKeys=1 Velocity-Bench svmCommand:/home/test-user/llvm_bench_workdir/svm/svm_sycl /home/test-user/llvm_bench_workdir/velocity-bench-repo/svm/SYCL/a9a /home/test-user/llvm_bench_workdir/velocity-bench-repo/svm/SYCL/a.m Runtime_IndependentDAGTaskThroughput_SingleTaskCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_IndependentDAGTaskThroughput_BasicParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_IndependentDAGTaskThroughput_HierarchicalParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_IndependentDAGTaskThroughput_NDRangeParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_independent --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/IndependentDAGTaskThroughput_multi.csv --size=32768 Runtime_DAGTaskThroughput_SingleTaskCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 Runtime_DAGTaskThroughput_BasicParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 Runtime_DAGTaskThroughput_HierarchicalParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 Runtime_DAGTaskThroughput_NDRangeParallelForCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/dag_task_throughput_sequential --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/DAGTaskThroughput_multi.csv --size=327680 MicroBench_HostDeviceBandwidth_1D_H2D_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_H2D_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_H2D_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_1D_D2H_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_D2H_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_D2H_ContiguousCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_1D_H2D_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_H2D_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_H2D_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_1D_D2H_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_2D_D2H_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_HostDeviceBandwidth_3D_D2H_StridedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/host_device_bandwidth --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/HostDeviceBandwidth_multi.csv --size=512 MicroBench_LocalMem_int32_4096Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/local_mem --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/LocalMem_multi.csv --size=10240000 MicroBench_LocalMem_fp32_4096Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/local_mem --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/LocalMem_multi.csv --size=10240000 Pattern_Reduction_NDRange_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/reduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_Reduction_multi.csv --size=10240000 Pattern_Reduction_Hierarchical_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/reduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_Reduction_multi.csv --size=10240000 ScalarProduct_NDRange_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_NDRange_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_NDRange_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_Hierarchical_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_Hierarchical_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 ScalarProduct_Hierarchical_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/scalar_prod --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/ScalarProduct_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_int16Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_NDRange_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_int16Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 Pattern_SegmentedReduction_Hierarchical_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/segmentedreduction --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Pattern_SegmentedReduction_multi.csv --size=102400000 USM_Allocation_latency_fp32_deviceCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_allocation_latency --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Allocation_latency_multi.csv --size=1024000000 USM_Allocation_latency_fp32_hostCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_allocation_latency --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Allocation_latency_multi.csv --size=1024000000 USM_Allocation_latency_fp32_sharedCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_allocation_latency --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Allocation_latency_multi.csv --size=1024000000 USM_Instr_Mix_fp32_device_1:1mix_with_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 USM_Instr_Mix_fp32_host_1:1mix_with_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 USM_Instr_Mix_fp32_device_1:1mix_no_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 USM_Instr_Mix_fp32_host_1:1mix_no_init_no_prefetchCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/usm_instr_mix --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/USM_Instr_Mix_multi.csv --size=8192 VectorAddition_int32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/vec_add --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/VectorAddition_multi.csv --size=102400000 VectorAddition_int64Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/vec_add --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/VectorAddition_multi.csv --size=102400000 VectorAddition_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/vec_add --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/VectorAddition_multi.csv --size=102400000 Polybench_2mmCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/2mm --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/2mm.csv --size=512 Polybench_3mmCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/3mm --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/3mm.csv --size=512 Polybench_AtaxCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/atax --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Atax.csv --size=8192 Kmeans_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/kmeans --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/Kmeans.csv --size=700000000 LinearRegressionCoeff_fp32Command:/home/test-user/llvm_bench_workdir/sycl-bench-build/lin_reg_coeff --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/LinearRegressionCoeff.csv --size=1638400000 MolecularDynamicsCommand:/home/test-user/llvm_bench_workdir/sycl-bench-build/mol_dyn --warmup-run --num-runs=3 --output=/home/test-user/llvm_bench_workdir/MolecularDynamics.csv --size=8196 llama.cpp Prompt Processing Batched 128Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Text Generation Batched 128Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Prompt Processing Batched 256Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Text Generation Batched 256Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Prompt Processing Batched 512Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf llama.cpp Text Generation Batched 512Command:/home/test-user/llvm_bench_workdir/llamacpp-build/bin/llama-bench --output csv -n 128 -p 512 -b 128,256,512 --numa isolate -t 56 --model /home/test-user/llvm_bench_workdir/models/Phi-3-mini-4k-instruct-q4.gguf |
|
Replaced with #17468 |
|
replaced with newer version |
From now on disjoint_pool is part of libumf, instead of being a separate library.