News for hackers. Stuff that matters.
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by tedunangst on Sunday September 08, 2024 @06:50PM (#41483912)
I wonder what workloads would benefit from having an L4 victim cache on another CPU, but that other CPU doesn't need its own L2 cache.
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by kev009 on Sunday September 08, 2024 @08:05PM (#41484340)
The claimed latency for it seems not far off from some other vendor's L3 caches which may be by virtue of rethinking where to share and therefore paying interconnection coherency taxes.

The innovation here seems to be adaptive sizing so if by whatever algorithm/metric a remote core is idle, it can volunteer cache to L4.

Presumably the interconnect is much richer than contemporary processors in typical IBM fashion and they can do all the control at a very low level (hw state machines&microcoding) so it is fast and transparent. It will be interesting to hear how it works in practice and if POWER12 gets a similar feature since it shares a lot of R&D.

Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by _a_a_a_ on Sunday September 08, 2024 @07:25PM (#41484128)
At a guess, a single thread which benefits from as much cache as it can get.
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by tedunangst on Sunday September 08, 2024 @08:29PM (#41484453)
Sure, but having to buy entire CPUs filled with idle cores to scale up cache seems very expensive.
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by kev009 on Sunday September 08, 2024 @08:43PM (#41484521)
These cores are typically licensed with class/restrictions so in absolute terms yes but in the financial engineering of how the system is delivered with excess and restricted hardware no (see core types on the prior/shipping generation here https://www.ibm.com/downloads/cas/6NW3RPQV)

There are probably design reuse and RAS considerations that make it not currently worthwhile to i.e. have a distinct physical design for SAP or whatever cores.

Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by sillywalk on Monday September 09, 2024 @02:25PM (#41491727)
I don't know if it's still the case, but in terms of RAS, the Z/Series CPUs from ~2004 had duplicated/compared instruction-fetch/decode and execution units.

https://pages.cs.wisc.edu/~remzi/Classes/838/Fall2001/Papers...

Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by nxobject on Sunday September 08, 2024 @10:32PM (#41484986)
I wouldn't be surprised as well if there was some binning that occurred – the dies are huge, so why not overprovision in the design? (Although erring on the side of slighlty more surprise in the case of some binning, since IBM mainframes seem to exist beyond the laws of commodity economics, and it looks like they're using a 5nm node.)
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by _a_a_a_ on Sunday September 08, 2024 @08:33PM (#41484480)
I said this is where it would help (AFAICS), not that it was the best solution.
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by nullc on Monday September 09, 2024 @12:52AM (#41485547)
the CPU's only appear to use about 1/3rd of the die area. Most of the space is cache.
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by twic on Monday September 09, 2024 @04:31AM (#41486539)
People buy whole machines to run memcached!
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by unnah on Monday September 09, 2024 @03:06AM (#41486120)
At a basic level, anything with a working set on the order of 360 MB should benefit from 360 MB of combined L3 with a worst-case latency of 11.5 ns, regardless of which parts end up in which L2 slice (and the cache allocation heuristics described in the article look pretty smart to me). Similarly, if you have a total working set of a couple of GB then the 2.8 GB combined L4 at 48.5 ns latency should be great. Is there any other hardware on the market that can offer so much memory at such a low latency?
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by lostmsu on Monday September 09, 2024 @02:53PM (#41492116)
/Uneducated/ these latency numbers seem large to me. DDR5 memory sticks I browsed yesterday for a home PC listed 10ns first word latency.
Re:Telum II at Hot Chips 2024: Mainframe with a Unique Cachi... by unnah on Tuesday September 10, 2024 @04:07AM (#41498390)
If the data is not in cache, it takes quite a while longer from the time the CPU core issues a load instruction for the results to get back to the next instruction. The CPU core has to first try L1 and L2, do a TLB lookup to convert a virtual address to a physical address, send a request to L3 over an on-chip connection, then after L3 lookup fails the memory controller has to transfer a 64-byte cache line from the main memory, and the results are then sent back to the core...

Have a look at the section "Cache setup" at https://chipsandcheese.com/2024/08/14/amds-ryzen-9950x-zen-5... for some real-world latency values. Once we're talking about a 100+ MB working set (i.e. DDR5 instead of cache), a top-of-the-line Ryzen 9950X has an access latency of about 100 ns. There is also some older data for a wider variety of CPUs at https://chipsandcheese.com/memory-latency-data/ - and there the older IBM z15 is in a class of its own.