메뉴
Source the Intel oneAPI environment before running workloads that depend on oneAPI, SYCL, DPC++, or Level Zero. Use this skill when the user needs to set up oneAPI, source setvars.sh, configure the Intel compiler environment, or when icpx/sycl-ls are not found in PATH.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | source-oneapi |
| description | Source the Intel oneAPI environment before running workloads that depend on oneAPI, SYCL, DPC++, or Level Zero. Use this skill when the user needs to set up oneAPI, source setvars.sh, configure the Intel compiler environment, or when icpx/sycl-ls are not found in PATH. |
| license | MIT |
| metadata | {"oneAPI":"Intel oneAPI","SYCL":"Intel DPC++","XPU":"Intel GPU"} |
You MUST source oneAPI components individually. Do NOT use setvars.sh.
source <oneapi_root>/compiler/latest/env/vars.sh
source <oneapi_root>/pti/latest/env/vars.sh
source <oneapi_root>/umf/latest/env/vars.sh
source <oneapi_root>/ccl/latest/env/vars.sh
source <oneapi_root>/mpi/latest/env/vars.sh
which icpx 2>/dev/null && echo "${CMPLR_ROOT:-}"
If CMPLR_ROOT is set and icpx is found, the environment is already initialized. Skip to Step 4.
Check candidates in this order. Use the first one where compiler/latest/env/vars.sh exists:
$HOME/intel/oneapi$HOME/oneapi$HOME:
find "$HOME" -maxdepth 4 -type f -path "*/oneapi/compiler/latest/env/vars.sh" 2>/dev/null | sed 's|/compiler/latest/env/vars.sh||' | sort
/opt/intel/oneapi/opt:
find /opt -maxdepth 4 -type f -path "*/oneapi/compiler/latest/env/vars.sh" 2>/dev/null | sed 's|/compiler/latest/env/vars.sh||' | sort
If no valid root is found, stop and ask the user for the path.
If multiple roots are found at the same priority level, ask the user to choose.
Do NOT fall through to /opt if a valid root exists under $HOME.
source <oneapi_root>/compiler/latest/env/vars.sh
source <oneapi_root>/pti/latest/env/vars.sh
source <oneapi_root>/umf/latest/env/vars.sh
source <oneapi_root>/ccl/latest/env/vars.sh
source <oneapi_root>/mpi/latest/env/vars.sh
Skip any component whose env/vars.sh does not exist. Report skipped components to the user.
which icpx && which sycl-ls && echo "${CMPLR_ROOT:-}"
If sycl-ls is not found, stop and report: "sycl-ls not found. Check whether the oneAPI DPC++/Compiler component is installed."
Run all subsequent commands in the same shell session. Environment variables do not persist across sessions.
If the workload targets a specific GPU, use the "intel-gpu-device-selection" skill to set ZE_AFFINITY_MASK before running.
Analyze UT (unit test) results for a torch-xpu-ops PR. Use when asked to check test results, analyze CI failures, or evaluate test coverage for a PR. Produces a structured report of new failures, failure relevance, and new test coverage.
Rules for automatically determining which disable_* labels to apply to a PR based on the file paths changed. Used by the auto-label workflow.
Extract GPU ISA from oneDNN ngen-JIT kernels. This is the ONLY codegen path that bypasses the standard SYCL/SPIR-V/IGC stack. oneDNN uses its own native code generator (ngen) that directly emits GPU ISA bytes — no SPIR-V, no IGC, no zebin ELF, no .debug_line. Use when extracting ASM from oneDNN kernels (gemm_kernel, gen_conv_kernel), matmul, linear, conv, or SDPA-graph ops dispatched via mkldnn.
Extract GPU ISA from AOT-compiled SYCL binaries using NEO driver runtime dump. Use when the kernel is a SYCL symbol (_ZTS...) from an AOT binary such as libtorch_xpu.so, SYCL-TLA FMHA, or any DPC++ binary compiled with -fsycl-targets=spir64_gen -Xs "-device <gpu>".
Extract GPU ISA from JIT-compiled SYCL kernels. The binary only contains SPIR-V; IGC compiles it to native ISA at first launch. The zebin only exists in memory at runtime, so IGC_ShaderDumpEnable=1 is required to capture it. Use when extracting ASM from SYCL JIT kernels, torch-xpu-ops built with TORCH_XPU_ARCH_LIST=none, or standalone DPC++ without AOT flags.
Extract GPU ISA from Triton kernels on XPU. Triton compiles through the same IGC backend as SYCL (Triton IR → SPIR-V → IGC → zebin). Extraction is identical to sycl-jit: IGC_ShaderDumpEnable=1 captures the zebin at runtime. Use when extracting ASM from torch.compile fusions (triton_per_fused, triton_poi, triton_red), standalone @triton.jit kernels, or Inductor-generated XPU kernels.