News for hackers. Stuff that matters.

A comment on RISC-V Is Sloooow. Parent comment

Re:RISC-V Is Sloooow by twoodfin on Tuesday March 10, 2026 @09:47PM (#47330951)
Hmm? x86 has supported much larger “huge” page sizes for ages.
[ Parent | on HN ]
Re:RISC-V Is Sloooow by ori_b on Wednesday March 11, 2026 @12:43AM (#47331804)
Yes, and Linux. at least historically, has not used them without explicit program opt-in. Often advice is to disable transparent huge pages for performance reasons. Not sure about other operating systems.

See, for example, https://www.pingcap.com/blog/transparent-huge-pages-why-we-d...

[ Parent | on HN ]
Re:RISC-V Is Sloooow by jorvi on Wednesday March 11, 2026 @02:44AM (#47332343)
Huh, no? The usual advice is to enable THPs for performance, you only disable them in specific scenarios.
[ Parent | on HN ]
Re:RISC-V Is Sloooow by wren6991 on Saturday March 14, 2026 @02:58PM (#47379924)
Yep, RISC-V also has these megapages. 4k is the last-level page size. You get larger pages (4M on 32-bit and 2M/1G on 64-bit) by terminating the walk at higher levels of the page table.
[ Parent | on HN ]