Menu
SkillsMP a collecté 27 skills depuis tenstorrent/tt-metal. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 27 skills collectés sur 27.
Generate, refresh, and validate an LLK performance report by running a perf sweep end to end and checking the resulting perf_data CSV. Use when asked to produce or refresh a perf report for an op, run a perf sweep, or when a report is missing, partial, stale,…
Langue du texte source : anglais
Generate, refresh, and validate an LLK performance report by running a perf sweep end to end and checking the resulting perf_data CSV. Use when asked to produce or refresh a perf report for an op, run a perf sweep, or when a report is missing, partial, stale,…
Langue du texte source : anglais
Create, extend, debug, and validate Quasar LLK performance tests, their PerfRunType kernel paths, and tile/dimension sweep coverage. Use when adding perf_[op]_quasar.py, wiring PerfConfig, implementing UNPACK_ISOLATE / MATH_ISOLATE / PACK_ISOLATE /…
Langue du texte source : anglais
Create, extend, debug, and validate Quasar LLK performance tests, their PerfRunType kernel paths, and tile/dimension sweep coverage. Use when adding perf_[op]_quasar.py, wiring PerfConfig, implementing UNPACK_ISOLATE / MATH_ISOLATE / PACK_ISOLATE /…
Langue du texte source : anglais
Compare one LLK perf test between two commits on this machine — by default the branch HEAD against the exact main commit it was branched from (the merge-base, not latest main), or any two refs the user names (hash, tag, origin/main, HEAD~5). Runs the sweep on…
Langue du texte source : anglais
Analyze LLK performance-report CSV files and create evidence-backed parameter-impact reports in a Cursor Canvas. Use when asked how formats, fidelity, dimensions, accumulation, indexing, loop factors, or other parameters affect TILE_LOOP or another marker in…
Langue du texte source : anglais
Analyze LLK performance-report CSV files and create evidence-backed parameter-impact reports in a Cursor Canvas. Use when asked how formats, fidelity, dimensions, accumulation, indexing, loop factors, or other parameters affect TILE_LOOP or another marker in…
Langue du texte source : anglais
Audit LLK code for races on the backend CONFIG register file where differently-named fields share the SAME 32-bit config word — both cross-thread (unpack/math/pack write the same word) and intra-thread (a full-word write clobbers a sibling field the same…
Langue du texte source : anglais
Audit circular-buffer (CB) producer/consumer flow control between data-movement (reader/writer) and compute kernels — cb_reserve_back/cb_push_back/cb_wait_front/cb_pop_front credit balance, data-write-before-credit ordering (NOC flush),…
Langue du texte source : anglais
Audit hand-written Tensix/SFPU instruction sequences for missing pipeline-latency padding — where a dependent instruction consumes a multi-cycle-latency result before it is ready and a NOP (or independent-instruction spacing) is required. Use after touching…
Langue du texte source : anglais
Audit LLK/compute-API use of the RISC↔RISC hardware mailboxes (mailbox_write/mailbox_read/mailbox_not_empty, TENSIX_MAILBOX*) for races/deadlock — push/pop balance per directed channel, call-count symmetry across threads, correct write-dest/read-src…
Langue du texte source : anglais
Audit LLK code for races between a RISC MMIO write to a config/GPR register and a Tensix instruction/MOP/replay that consumes it. Use after touching any raw cfg[...]=/reg_write/cfg_rmw/regfile[]= write near an UNPACR/PACR/MOP/CFGSHIFTMASK, or when adding…
Langue du texte source : anglais
Audit cross-core NoC + L1 synchronization in dataflow kernels — noc_semaphore_wait/set/inc balance and direction, multicast fan-out counts, data-before-signal NoC ordering (noc_async_write_barrier / noc_async_writes_flushed before a remote credit), AND the…
Langue du texte source : anglais
Run all nine LLK hazard audits (mmio-race, reconfig-stall, cfg-word-overlap, semaphore-handshake, mailbox-sync, dataflow-cb-sync, srcreg-bank-sync, noc-sync, instruction-latency) across four synchronization surfaces, and add a cross-class JOIN pass that…
Langue du texte source : anglais
Audit LLK reconfig/uninit/config-write functions for a MISSING stall that drains the execution unit before its config registers are rewritten (packer→PACK, unpacker→UNPACK, math→MATH|WAIT_SFPU). Use after touching cpack/cunpack/cmath, *_reconfig_*, *_uninit,…
Langue du texte source : anglais
Audit LLK inter-thread synchronization (Tensix semaphores + ATGETM/ATRELM mutexes) for races/deadlock — SEMINIT correctness vs usage, post/get balance, wait-direction, RISC-MMIO-vs-Tensix ordering, and mutex acquire/release balance. Use after touching any…
Langue du texte source : anglais
Audit the shared backend DATA registers — SrcA/SrcB bank-valid (AllowedClient) + bank-flip handshake between unpacker and Matrix Unit, and the shared-once Dst/LReg overwrite hazards not already carried by the MATH_PACK semaphore or mutex::SFPU. Use after…
Langue du texte source : anglais
Inspect VCS/FSDB waveforms to localize a Quasar LLK runtime hang, timeout, or mismatch when log/source debugging cannot pin the boundary. Use only after the simulator reaches device-ready; not for compile, pre-device-ready simulator, or confirmed environment…
Langue du texte source : anglais
Convert LLK lib/API tile-size args to ckernel::TensorShape and maintain TRISC TensorShape coverage. Use when adding TensorShape parameters, replacing face_r_dim/num_faces, editing LLK_VALIDATE_TENSOR_SHAPE_*, regenerating tensor_shape_coverage_*.h, or…
Langue du texte source : anglais
Reproduce a flaky/timing-dependent kernel failure (suspected undocumented HW race) by injecting NOPs/delays to shift inter-thread / inter-kernel / inter-core timing until the failure becomes frequent enough to isolate and minimize into a deterministic…
Langue du texte source : anglais
Audit Tensix/SFPU LLK compute kernels for PERFORMANCE — unfilled latency shadows/bubbles and redundant NOPs, redundant Dst/LReg store-load traffic, loop-invariant work, predication that should be branchless arithmetic (min/max/abs/setsgn), un-fused mul+add,…
Langue du texte source : anglais
Run LLK tests using the test runner agent. Never run pytest directly.
Langue du texte source : anglais
Look up Tensix architecture, instruction, or LLK implementation details across architectures. Orchestrates sage agents in parallel.
Langue du texte source : anglais
Debug compilation or runtime errors in LLK kernels. Infers architecture and kernel type from path.
Langue du texte source : anglais
Get structured porting guidance when moving a kernel between architectures. Launches sages for source and target, reads test harness.
Langue du texte source : anglais
Enforce safe bash scripting practices when writing, reviewing, or fixing shell scripts. Covers quoting, arrays, conditionals, arithmetic, redirections, strict mode, and static analysis. Use when editing .sh/.bash files, reviewing shell scripts, fixing…
Langue du texte source : anglais
Guides test-first workflows for bugs and features: write a minimal failing test that encodes contracts and clear failure messages, confirm the gap is not already covered, implement and document the fix, then verify green. Use when fixing bugs with tests,…
Langue du texte source : anglais