wyj
11e703e33d
Archive fixed catalog subsets and captured events, manifests, reproducible commands, raw timing and regression logs, and device resource evidence. Document distribution-dependent tile reduction gains and independent indexed producer throughput. Update the GPU plan and renderer design while retaining the production atomic path. Preserve historical measurement metadata and exclude generated Python bytecode.
25 lines
1007 B
Plaintext
25 lines
1007 B
Plaintext
1520: .group_segment_fixed_size: 0
|
|
1527: .max_flat_workgroup_size: 1024
|
|
1528: .name: _ZL12splat_kernelPK14PsfCachedEventmiiPKfiidPd
|
|
1529: .private_segment_fixed_size: 0
|
|
1530: .sgpr_count: 18
|
|
1535: .vgpr_count: 62
|
|
1603: .group_segment_fixed_size: 0
|
|
1610: .max_flat_workgroup_size: 1024
|
|
1611: .name: _ZL13prepare_tilesPK14PsfCachedEventmiidP8PreparedPi
|
|
1612: .private_segment_fixed_size: 0
|
|
1613: .sgpr_count: 14
|
|
1618: .vgpr_count: 37
|
|
1669: .group_segment_fixed_size: 0
|
|
1676: .max_flat_workgroup_size: 1024
|
|
1677: .name: _ZL12tile_partialPK8PreparedPKiPKjPK8TileTaskiiiiPKfiiPdSB_
|
|
1678: .private_segment_fixed_size: 0
|
|
1679: .sgpr_count: 46
|
|
1684: .vgpr_count: 21
|
|
1717: .group_segment_fixed_size: 0
|
|
1724: .max_flat_workgroup_size: 1024
|
|
1725: .name: _ZL10tile_mergePKjPK8TileTaskiiiiPKdPd
|
|
1726: .private_segment_fixed_size: 0
|
|
1727: .sgpr_count: 16
|
|
1732: .vgpr_count: 18
|