nissy-core/src/arch/arch.h, branch h48-corner-estimate The "engine" of nissy, including the H48 optimal solver. https://git.tronto.net/nissy-core/atom?h=h48-corner-estimate 2025-07-29T08:00:56Z Optimized some coordinates 2025-07-29T08:00:56Z Sebastiano Tronto sebastiano@tronto.net 2025-07-29T08:00:56Z urn:sha1:38014615238a51f1c0c1f2f96d37cbfbf765520a Turns checks into assertions in utils/math.h 2025-07-28T12:17:42Z Sebastiano Tronto sebastiano@tronto.net 2025-07-28T12:17:42Z urn:sha1:1e5c862d8fa7b76b69b8125d454d8f8d6a9cde25 Working drslice (same results as nissy-classic) 2025-07-17T05:57:18Z Sebastiano Tronto sebastiano@tronto.net 2025-07-17T05:57:18Z urn:sha1:5e741a00a1350477c7d8778cb466c8efa27b152d Neon uint8x8_t corners and minor fixes 2024-10-15T08:34:13Z enricotenuti tenutz_27@outlook.it 2024-10-15T08:34:13Z urn:sha1:8c5f48d61627a986dc9feb8092f1f465b7f90ebc Improved gendata_h48k2 performance 2024-09-07T08:55:30Z Sebastiano Tronto sebastiano@tronto.net 2024-09-07T08:55:30Z urn:sha1:0eba10bf55283acdb687a172404a89e5a72a00c2 Performance for the "real coordinate" case (h0) is ok, but still around 3x slower than the gendata_h48k4 method. Performance for the intermediate tables is not good, but for now I'll keep it like this. This also shows that for h11 we should use the gendata_h48k4 method for h11. For intermediate table, h8, h9 and h10 might be too slow to compute in an acceptable time. We could restrict to h7 (largest with base = 9). Reorganized folder structure 2024-08-18T12:26:45Z Sebastiano Tronto sebastiano@tronto.net 2024-08-18T12:26:45Z urn:sha1:18c9a8b8905304cf5f8fc15825769046a3144866