RFR: 8286823: Default to UseAVX=2 on all Skylake/Cascade Lake CPUs

[olivergillespie]

On Mon, 16 May 2022 15:52:22 GMT, olivergillespie <duke at openjdk.java.net> wrote:

> The current code already does this for 'older' Skylake processors,
> namely those with _stepping < 5. My testing indicates this is a
> problem for later processors in this family too, so I have removed the
> max stepping condition.
> 
> The original exclusion was added in https://bugs.openjdk.java.net/browse/JDK-8221092.
> 
> A general description of the overall issue is given at
> https://en.wikipedia.org/wiki/Advanced_Vector_Extensions#Downclocking.
> 
> According to https://en.wikichip.org/wiki/intel/microarchitectures/cascade_lake#CPUID,
> stepping values 5..7 indicate Cascade Lake. I have tested on a CPU with stepping=7,
> and I see CPU frequency reduction from 3.1GHz down to 2.7GHz (~23%) when using
> -XX:UseAVX=3, along with a corresponding performance reduction.
> 
> I first saw this issue in a real production workload, where the main AVX3 instructions
> being executed were those generated for various flavours of disjoint_arraycopy.
> 
> I can reproduce a similar effect using SPECjvm2008's xml.transform benchmark.
> 
> 
> java --add-opens=java.xml/com.sun.org.apache.xerces.internal.parsers=ALL-UNNAMED \
> --add-opens=java.xml/com.sun.org.apache.xerces.internal.util=ALL-UNNAMED \
> -jar SPECjvm2008.jar -ikv -ict xml.transform
> 
> 
> Before the change, or with -XX:UseAVX=3:
> 
> 
> Valid run!
> Score on xml.transform: 776.00 ops/m
> 
> 
> After the change, or with -XX:UseAVX=2:
> 
> 
> Valid run!
> Score on xml.transform: 894.07 ops/m
> 
> 
> So, a 15% improvement in this benchmark. It's possible some benchmarks will be negatively
> affected by this change, but I contend that this is still the right move given the stark
> difference in this benchmark combined with the fact that use of AVX3 instructions can
> affect *all* processes/code on the host due to the downclocking, and the fact that this
> effect is very hard to root-cause, for example CPU profiles look very similar before and
> after since all code is equally slowed.

Thanks for the comments, all. I will run all SPECjvm2008 benchmarks before and after the change for us to look at - I'll share the results later today. 

In the application that uncovered this issue for me, minor use of AVX3 instructions (about 3-4% of the overall CPU usage, all in various flavours of disjoint_arraycopy) on my Cascade Lake processor downclocks the whole machine by ~15% - that means all threads/cores/processes slowed by 15% across the board.

The local speedup thanks to AVX3 has to be weighed against the global downclocking overhead, and I contend that most real-world applications will see far more overhead than benefit from AVX3 on Cascade Lake.

-------------

PR: https://git.openjdk.java.net/jdk/pull/8731