Repository navigation
Conversation
KernelSight: 1,444 H100 GPU counter snapshots (24 channels x 512 bins) with per-segment L1/L2 workload labels, from the pinned Hub release. - One Record per snapshot, 24 Signals in five channel-group Sources, a per-snapshot RegularAxis from the bin edges. - Segment L1/L2 interval annotations, plus multi-hot-only overlap runs (track=multihot) for the 472 cutlass_ws_overlap snapshots. - One ClassificationTask per snapshot on the authors' dominant_l1. - Split grouped by problem (KernelBench dtype/seed variants stay together), stratified by class, 3/1/1, seed 42; the released split memberships are kept in record metadata. - Reads only numeric npz arrays (allow_pickle=False). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
… errors in kernelsight - Group a Variant by its Problem without launch options: the CUTLASS schedule suffix (_rH_s8_b1) and the microbenchmark thread-block size (_T256). No Problem crosses partitions now (0 of 427, was 32 CUTLASS shape groups with 725 snapshots). - Add the workload_l2 annotation (memory_movement_copy) to the 590 multi-hot-only intervals. - Raise TimeNetConnectorError for a missing or corrupt npz or split file, a missing array and segment arrays of different lengths. - Check the data shape in the lazy loader, so convert reads no values. - Test one real snapshot of the pinned release from tests/fixtures. - Card: bin width is 0.2 to 43 ms (not 68), the metadata key is release_splits, and the comment says why the split is 3/1/1. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add
williamhtan/kernelsight: H100 GPU hardware-counter traces with per-segment workload labels, from williamhtan/kernelsight (Apache-2.0). The connector pins the Hub commitd8cd8e804e5b619aadbb082a1fb3a8791b60a680.I cannot add labels from a fork. Could a maintainer add
area:connectors?What it builds
RegularAxistaken from the snapshot's bin edges, so the period differs per snapshot (0.2 ms to 43 ms).workload_l1(12 classes) andworkload_l2(73 classes).ClassificationTaskper snapshot. The target is the authors'dominant_l1field.Notes
docs/connectors.mdsays to preserve official partitions. The released train/val/test split puts dtype and seed variants of one KernelBench problem in different partitions (44 of 200 problems cross it). So the connector assigns its own split withStratifiedSplitter, grouped by problem and stratified bydominant_l1, seed 42.boptions (_rH_s8_b1,_rM,_sw4,_b1) and a microbenchmark's thread-block size (_T256).cutlass_ws_overlapruns the CUTLASS ex48 GEMM ofcutlass_gemmwith device timer markers, so one shape of the two motifs is one problem. A short CUTLASS name (m4096_k2048,kheavy,baseline) leaves the other sizes at a default. The 12 short names whose kernel launch times match a full shape within about 1% join the problem of that shape. No problem crosses partitions (0 of 401).loss,poolingandelementwiseeach lose the validation or the test partition. With 3/1/1, onlysoftmax(2 problems) has no validation snapshot.release_splits(train,val,test,iid,param_ood,composed,length_ood), so the released benchmark stays reproducible.cutlass_ws_overlapsnapshots, an overlappingmemory_movement/memory_movement_copyrun exists only in the release's multi-hot track. Each such run becomes aworkload_l1and aworkload_l2interval with occurrence metadatatrack=multihot.allow_pickle=False. A missing, corrupt or damaged file raisesTimeNetConnectorError.convertreads only the bin edges and labels. The lazy loader reads the counter values and checks their shape.Verified against the real release
timenet-build build williamhtan/kernelsightfrom the Hub at the pinned revision gives 1,444 records and 1,444 tasks, split 862 / 291 / 291. The records carry 45,860 segment intervals for each ofworkload_l1andworkload_l2, plus 590track=multihotintervals for each.verify()passes.Locally,
make check-ci,make test,make test-connectorsandmake license-checkpass. The connector has 35 tests. One of them reads a real snapshot of the pinned release fromtests/fixtures/(16 KB).Part of the TimeNet Online Hackathon: onboard a dataset, then fine-tune a time-series language model on it. This replaces #831, which I closed before rebasing onto the connector API changes (#822, #823, #797, #827).
🤖 Generated with Claude Code