x86, ARM, PARISC, PPC, MIPS and Sparc folks please run this
A message that is not in the archive (sent off-list or not yet received): 20030829053510.GA12663@mail.jlokier.co.uk.suse.lists.linux.kernel
Quoted 3 lines · Jamie Lokier
I already got a surprise (to me): my Athlon MP is much slower accessing multiple mappings which are within 32k of each other, than mappings which are further apart, although it is coherent. The L1
Most x86 and probably most other modern CPUs have virtually addressed L1 caches. It's just too slow to wait for the MMU for an L1 access which is really critical.
So such artifacts are expected
Quoted 2 lines
data cache is 64k. (The explanation is easy: virtually indexed, physically tagged cache moves data among cache lines, possibly via L2).
On x86 L2 is usually physically tagged.
Mostly only ARM,MIPS et.al. have virtually tagged L2.
-Andi
Quoted 7 lines · Andi Kleen
Quoted 2 lines · Jamie Lokier
data cache is 64k. (The explanation is easy: virtually indexed, physically tagged cache moves data among cache lines, possibly via L2).
On x86 L2 is usually physically tagged.
Mostly only ARM,MIPS et.al. have virtually tagged L2.
Correction: ARM L1 is mostly VIVT. L2 cache isn't mandated by the architecture, and therefore generally doesn't exist.
Signature · 2 lines
Russell King ([email protected]) The developer of ARM Linux http://www.arm.linux.org.uk/personal/aboutme.html
Quoted 9 lines · Andi Kleen
Quoted 3 lines
I already got a surprise (to me): my Athlon MP is much slower accessing multiple mappings which are within 32k of each other, than mappings which are further apart, although it is coherent. The L1
Most x86 and probably most other modern CPUs have virtually addressed L1 caches. It's just too slow to wait for the MMU for an L1 access which is really critical.
So such artifacts are expected
I hadn't thought at first because there's no artefact at all (not even a small one) on my Celeron, but you're right. They don't appear on any Intels(*), but they do on all AMDs that I have results for.
(*) With the possible exception of one P4 that reports varying results.
Quoted 5 lines
Quoted 3 lines
data cache is 64k. (The explanation is easy: virtually indexed, physically tagged cache moves data among cache lines, possibly via L2).
On x86 L2 is usually physically tagged.
I'm speculating that L1 is physically tagged, and when there's a virtual alias the CPU moves data from one L1 line to another. L2 only comes into it because the line transfer is slow enough that a MESI-style transfer through L2 (as if another CPU or device requested the line) would account for the slowness.
-- Jamie