What's your source for Basilisk being 15h?
AMD
Bulldozer pre-2009 had four nodes(20nm/14nm counts as one) with accompanying APUs each.
45-nm SOI; CPU "
Montreal" - Bulldozer // APU "
Swift" - Stars // APU "
Falcon" - Bulldozer
32-nm SOI; CPU "
Sandtiger/Interlagos(Abu Dhabi)/
Terramar" - Piledriver // APU "Llano" - Stars // APU "Trinity/Richland" - Piledriver
At this point is when the roadmap explodes.
28-nm SHP/
22-nm SHP; CPU "
Dublin/Boulder" - Steamroller // APU "Kaveri" - Steamroller
28-nm A/
20-nm SHP/20-nm LPM; CPU "
Austin" - Excavator // APU "Carrizo" - Excavator
14-nm
Bulk/SOI FinFET; CPU "
Gecko" - Excavator // APU "
Basilisk" - Excavator
Underlined equals cancelled, and italics/bolds unconfirmed if being produced.
14nm FinFET Bulldozer is the last Bulldozer(15h) microarchitecture planned.
iGPUs
Swift/Falcon -> 160 ALUs + 40 SFU // Vec4+Scalar1
Llano -> 320 ALUs + 80 SFU // Vec4+Scalar1
Trinity/Richland -> 288 ALUs + 96 SFU // Vec3+Scalar1
Kaveri/Carrizo -> ~512 ALUs // Vec16
Basilisk -> ~1024 ALUs // Vec16
Regardless, end of 2015 to end of 2016 is the range for 1024+ ALU/Shaders.