Re: Popcount optimization using AVX512 - Mailing list pgsql-hackers

From Nathan Bossart
Subject Re: Popcount optimization using AVX512
Date
Msg-id 20240329153515.GA1046039@nathanxps13
Whole thread Raw
In response to RE: Popcount optimization using AVX512  ("Amonson, Paul D" <paul.d.amonson@intel.com>)
Responses RE: Popcount optimization using AVX512
List pgsql-hackers
On Thu, Mar 28, 2024 at 10:03:04PM +0000, Amonson, Paul D wrote:
>> * I think we need to verify there isn't a huge performance regression for
>>   smaller arrays.  IIUC those will still require an AVX512 instruction or
>>   two as well as a function call, which might add some noticeable overhead.
> 
> Not considering your changes, I had already tested small buffers. At less
> than 512 bytes there was no measurable regression (there was one extra
> condition check) and for 512+ bytes it moved from no regression to some
> gains between 512 and 4096 bytes. Assuming you introduced no extra
> function calls, it should be the same.

Cool.  I think we should run the benchmarks again to be safe, though.

>> I forgot to mention that I also want to understand whether we can
>> actually assume availability of XGETBV when CPUID says we support
>> AVX512:
> 
> You cannot assume as there are edge cases where AVX-512 was found on
> system one during compile but it's not actually available in a kernel on
> a second system at runtime despite the CPU actually having the hardware
> feature.

Yeah, I understand that much, but I want to know how portable the XGETBV
instruction is.  Unless I can assume that all x86_64 systems and compilers
support that instruction, we might need an additional configure check
and/or CPUID check.  It looks like MSVC has had support for the _xgetbv
intrinsic for quite a while, but I'm still researching the other cases.

-- 
Nathan Bossart
Amazon Web Services: https://aws.amazon.com



pgsql-hackers by date:

Previous
From: Pavel Borisov
Date:
Subject: Re: Table AM Interface Enhancements
Next
From: Nathan Bossart
Date:
Subject: Re: Popcount optimization using AVX512