[HN Gopher] Nested Loops Revisited Again (2023)
       ___________________________________________________________________
        
       Nested Loops Revisited Again (2023)
        
       Author : feeblefakie
       Score  : 34 points
       Date   : 2024-10-28 04:35 UTC (18 hours ago)
        
 (HTM) web link (ieeexplore.ieee.org)
 (TXT) w3m dump (ieeexplore.ieee.org)
        
       | gnabgib wrote:
       | (2023)
        
       | cryptonector wrote:
       | > Hash joins and sort-merge joins have been considered the
       | algorithms of choice for analytical relational queries in most
       | parallel database systems because of their performance robustness
       | and ease of parallelization. On the other hand, nested loop joins
       | have been considered less attractive and are conservatively used.
       | In this paper, we revisit the potential of nested loop joins
       | [...]
       | 
       | Uh, a hash join is basically a nested loop where first you create
       | a hash table index of one side. When I finally realized that I
       | suddenly understood why certain PG queries were slow!
       | 
       | So right off in the abstract I find this paper suspect.
        
       | Log_out_ wrote:
       | Convert all nested loops and funccalls to one large do whilw loop
       | with chacherowsized bundled input and output in the compiler ?
        
       ___________________________________________________________________
       (page generated 2024-10-28 23:02 UTC)