pti-gpu
pti-gpu copied to clipboard
intel
Profiling Tools Interfaces for GPU (PTI for GPU) is a set of Getting Started Documentation and Tools Library to start performance analysis on Intel(R) Processor Graphics easily
onetrace cannot be built due to an error in unified_tracer.h, and the lacking of information on how to build the tool for Windows makes the building process difficult. Fixed unified_tracer.h...
ze_tracer/onetrace: Assertion `call->command != command' failed with simple SYCL Graph application
Trying to trace a simple application which uses SYCL Graphs with ze_tracer or onetrace triggers an internal failed assertion. ```console $ clang++ -fsycl -g test_graph_zetrace.cpp -o test_graph_zetrace $ ONEAPI_DEVICE_SELECTOR=level_zero:0 ~/pti-gpu/tools/ze_tracer/build/ze_tracer...
Heya, I've noticed that the repository recently added an initial draft for a SDK which can be used for profiling / tracing tools to more easily add support for Intel...
Hi all, I use this tool, but I got a problem about execution sysmon don't show running process. Just saying "unknown". How can I do to fix this problem? ...
(llama-17oct) user@BA-ARCH-LAB-SPR-PVC-2T:~/17oct/frameworks.ai.pytorch.gpu-models/LLM/generation$ /home/user/17oct/pti-gpu/tools/oneprof/build/./oneprof -q -o newlog_llama7b_oneprof_q_O_log.txt -p /home/user/17oct/oneprof_temp/ -s 1000 python -u run_generation.py --device xpu --ipex --dtype float16 --input-tokens 32 --max-new-tokens 32 --num-beam 1 --benchmark -m decapoda-research/llama-7b-hf --sub-model-name llama-7b Namespace(model_id='decapoda-research/llama-7b-hf',...
I am trying to build the gpuinfo tool on an ORTCE machine. I am using these modules; Currently Loaded Modulefiles: 1) intel/oneapi/2022.0.1 2) intel-comp-rt/agama-ci-prerelease/475(default) 3) intel/pti-gpu-nda/2021-12-03 I get this compile...
Testing unitrace with ze_peak: ze_peak: a760ae0b52497b73254b2df8b191aa3693a970c7 (pulled 2023.5.13) unitrace --version 0.50.0 (b785677885e062c41405fb8d10812f7e7c0c58d9) unitrace -h -d -v --chrome-call-logging --chrome-device-logging --chrome-kernel-logging ./ze_peak -t dp_compute Device : * name : Intel(R) Data Center...
It is in a single node (localhost in the hostfile), and the command line looks like: oneprof -i -p ~/oneprof_log/ -o ~/oneprof_log/oneprof.log mpirun -n 2 -ppn 2 -hostfile hostfile_mpich python...
Hi, It would be great to have median metric alongside with average or have a choice. Many benchmarks run warm-up trials and then a lot of main trials of the...
Hi! I was looking for a way to kill a GPU process (there was a segfault in the driver and I see my test name show up in the intel-gpu-top...
