nissy-core, branch h48-corner-estimateThe "engine" of nissy, including the H48 optimal solver.https://git.tronto.net/nissy-core/atom?h=h48-corner-estimate2025-12-19T06:32:09ZAdd coordinate solvers for corners2025-12-19T06:32:09ZSebastiano Trontosebastiano@tronto.net2025-12-19T06:32:09Zurn:sha1:de04d37e8520079f5bba3b1a87d42313297543dbImprove performance of H48 by 10-30% using interleaved fallback tables.2025-12-17T20:06:12ZSebastiano Trontosebastiano@tronto.net2025-12-17T19:54:23Zurn:sha1:d5c60236c06e67e8da45e63843b37e5d619e9d7b
(See the last 12 commits or so)
H48 now uses interleaved fallback tables, similarly to nxopt / vcube.
This allowed us to simplify the code (we don't use k != 2 anymore for
H48) and gives some nice performance improvement, although repeated
measurements show inconsistent results. The actual speed up depends on
the table, and it is more pronounced on larger versions of the solver.
The nasty part about using interleaved tables is that they are the
most efficient when they are aligned in memory to 512 bits, but the
core library defers memory management to the implementor, so there is
no way to ensure this. For example, any application that wants to save
the tables to a file and then re-load them on a subsequent run (such
as our shell and tools) should make sure to load the data in a 512-bit
aligned memory buffer. The best we can do on the library side having
our main lookup table be 512-bit alinged within the whole solver data
(which includes e.g. cocsepdata and a preamble).
I have also moved some conditionals around in the various checks in the
search dfs hoping to improve the performance further, but the results
have been barely noticeable.
The benchmarks have been updated. Moreover, there is now a way to re-run
them with a single script (see the updates in the benchmarks folder
for details).
Further attempts at optimizing the code via known techniques (such as
prefetching) have failed, but I'll come back to this.
Clarified that results are in a <details>2025-12-17T19:53:14ZSebastiano Trontosebastiano@tronto.net2025-12-17T19:53:14Zurn:sha1:ff68d44aefada070b756a1bdbb0d4d722779440dFix alignment2025-12-17T16:36:16ZSebastiano Trontosebastiano@tronto.net2025-12-17T16:36:16Zurn:sha1:ec9593e2ff0856d78b37df3a977a753be82bfddcImprove pruning value fetching and re-do benchmarks2025-12-17T15:15:02ZSebastiano Trontosebastiano@tronto.net2025-12-17T09:51:34Zurn:sha1:ac3a91f4f173e7a38c70d5cd0caf5a025642312bCleanup md2025-12-17T08:33:41ZSebastiano Trontosebastiano@tronto.net2025-12-17T08:33:41Zurn:sha1:4a2e35f21b07a2abbeddc89c8eda5f1aed6bfb51Remove TODO section in doc2025-12-17T08:28:03ZSebastiano Trontosebastiano@tronto.net2025-12-17T08:28:03Zurn:sha1:e3bb9a1bfee72e83766c86f3cade8259b46c5618Update benchmarks2025-12-17T08:26:53ZSebastiano Trontosebastiano@tronto.net2025-12-17T08:26:53Zurn:sha1:36f37564cd566e91771cd1f92ac3886917c769d1Cleanup2025-12-17T08:15:48ZSebastiano Trontosebastiano@tronto.net2025-12-17T08:15:48Zurn:sha1:c6ab40b1602443938e431b996b28fb3d888365bbMove some checks around, small improvement2025-12-17T06:58:32ZSebastiano Trontosebastiano@tronto.net2025-12-17T06:58:32Zurn:sha1:ad9c99d0274b09b152007332cef589f5e649080a