morluto
aa52ff6f4b
fix(gpu): preserve PTX parameter and target facts
...
Fixes #6664
Fixes #6675
Fixes #6680
Fixes #6695
2026-10-23 21:28:10 +08:00
morluto
42086fdba7
fix(gpu): retain resources across entry pragmas
...
Fixes #6651
2026-10-23 19:18:47 +08:00
morluto
8695ca8257
fix(gpu): bound embedded section reads
...
Fixes #6657
2026-10-23 19:18:47 +08:00
morluto
25aa298c61
fix(gpu): preserve parameter and target declarations
...
Decode observed V2 CUDA parameters, retain qualified PTX parameter names and entry resource counts, and preserve family and feature target declarations through selection and consistency checks.
Fixes #6624
Fixes #6625
Fixes #6626
Fixes #6618
Fixes #6613
Fixes #6606
2026-10-23 19:07:46 +08:00
morluto
6442329717
fix(gpu): parse legacy PTX body parameters
...
PTX 1.0 through 1.3 declares kernel parameters inside the entry body. Keep later-version parameter-list parsing unchanged.
Fixes #6594
2026-10-23 18:08:46 +08:00
morluto
f250c8cca5
fix(gpu): accept PTX compute target aliases
...
Preserve the source spelling of NVIDIA's documented compute_xx target synonym.
Fixes #6494
2026-10-23 18:08:46 +08:00
gensokyo-dev
efab044f30
feat(gpu): inspect static CUDA and HIP code objects ( #5813 )
2026-10-21 19:06:44 +08:00