[llvm-dev] Making LLD PDB generation faster

Alexandre Ganea via llvm-dev llvm-dev at lists.llvm.org
Thu Feb 28 06:32:35 PST 2019


Try enabling large memory pages on your PC: https://support.sisoftware.co.uk/knowledgebase.php?article=52
Get the latest LLVM trunk and ensure the MF_HUGE_HINT is used with your use-case, by tracing Memory::allocateMappedMemory()
Going from 12-byte buckets to 8-buckets only gives mild improvements, you're saving 1/6 cache misses on the hashtable accesses. Most of the gain comes from usage of the large memory pages.

Let me know if that helps,

-----Original Message-----
From: Leonardo Santagada <santagada at gmail.com> 
Sent: Thursday, February 28, 2019 7:36 AM
To: Alexandre Ganea <alexandre.ganea at ubisoft.com>
Cc: Reid Kleckner <rnk at google.com>; Zachary Turner <zturner at google.com>; llvm-dev <llvm-dev at lists.llvm.org>
Subject: Re: [llvm-dev] Making LLD PDB generation faster

Yeah your binary if probably very similar to ours, I work at Guerrilla games, so yeah game engine/editor. I tried extracting just your implementation of densemap from that changelist and it seemed to not give any speedups in our case. I think I will clean up my changes to llvm-objcopy and maybe wait to test your changes.ps: Do you guys hang around on any chat room? I think chatting a bit can be helpful.

More information about the llvm-dev mailing list