threadteam 0.2.0

Scoped CPU thread-team placement token: a Pool and a non-Clone Exec with fork, for_ranges, external and broadcast; no Rayon type in the public API.
Documentation
work,config,run_sections,split_or_fork_regions,gemm_tiled,gemm_below_floor,gemm_one_tile
gemm_sq 64,gf0,1,0,1,0,0
gemm_sq 96,gf0,1,0,1,0,0
gemm_sq 128,gf0,1,0,1,0,0
gemm_sq 256,gf0,1,0,1,0,0
lu 64,pt0_gf0,3,2,3,0,0
lu 64,default,0,0,0,0,0
lu 128,pt0_gf0,11,6,11,0,0
lu 128,default,0,0,0,0,0
lu 192,pt0_gf0,25,11,25,0,0
lu 192,default,0,1,0,0,0
lu 256,pt0_gf0,38,15,38,0,0
lu 256,default,0,1,0,0,0
lu 384,pt0_gf0,72,30,72,20,0
lu 384,default,3,13,3,50,0
lu 512,pt0_gf0,107,38,107,28,0
lu 512,default,5,16,5,76,0
lu 768,pt0_gf0,148,82,148,160,0
lu 768,default,15,57,15,238,0