high warlord cavius i ∿(@cavemanloverboy):at 4096 lanes per call, across the set of proposed operations we see a wallclock speedup of 11.7x-47.6x for 64-bit integers and 10.3x-45.1x for 128-bit integers. the proposed cost model results in a 6.1x-20.0x reduction in cu consumption for 64-bit operations and an 11.1x-60.5x reduction for 128-bit operations

high warlord cavius i ∿

@cavemanloverboy

computers. cosmology. caveman. @temporal_xyz @harmonic_gg @humidifi

Joined October 2021

679 Following 8.1K Followers

high warlord cavius i ∿@cavemanloverboy

2026.10.26 20:23

at 4096 lanes per call, across the set of proposed operations we see a wallclock speedup of 11.7x-47.6x for 64-bit integers and 10.3x-45.1x for 128-bit integers. the proposed cost model results in a 6.1x-20.0x reduction in cu consumption for 64-bit operations and an 11.1x-60.5x reduction for 128-bit operations