Today — DEVICES holds two entries: CC 8.6 (A10G) and CC 7.5 (T4) (model/lib.rs:36–58). There is no 8.0 (A100), 8.9 (L4/L40), 9.0 (Hopper: 2048 threads/SM, 64 warps, 32 blocks, 228 KB) or 10.0 (Blackwell). --cc on anything else is a model error, and docs/LIMITATIONS.md correctly says the model is a capacity question — but the capacity table stops at Ampere.
Separately, reconverge's cc.rs carries a 7.0 → 12.0 shared-memory table for the same devices. Two tables of the same facts in two repositories will drift; they already disagree in shape (one has threads/warps/blocks, the other smem per block).
Fix. Complete DEVICES for 8.0, 8.9, 9.0 and 10.0 from the CUDA Programming Guide's compute-capability table, each entry citing the row it came from; then decide with reconverge whether one small shared simt-device-table crate should own both tables. Keep sm_count per named product, since it is a product fact and not a CC fact.
Done when
Today —
DEVICESholds two entries: CC 8.6 (A10G) and CC 7.5 (T4) (model/lib.rs:36–58). There is no 8.0 (A100), 8.9 (L4/L40), 9.0 (Hopper: 2048 threads/SM, 64 warps, 32 blocks, 228 KB) or 10.0 (Blackwell).--ccon anything else is a model error, anddocs/LIMITATIONS.mdcorrectly says the model is a capacity question — but the capacity table stops at Ampere.Separately, reconverge's
cc.rscarries a 7.0 → 12.0 shared-memory table for the same devices. Two tables of the same facts in two repositories will drift; they already disagree in shape (one has threads/warps/blocks, the other smem per block).Fix. Complete
DEVICESfor 8.0, 8.9, 9.0 and 10.0 from the CUDA Programming Guide's compute-capability table, each entry citing the row it came from; then decide with reconverge whether one small sharedsimt-device-tablecrate should own both tables. Keepsm_countper named product, since it is a product fact and not a CC fact.Done when
device("9.0")anddevice("10.0")return parameters with a cited source.