bject: Re: Optimizing arithmetic operations on processors with AVX2 support
Such an assumption (in-order execution of statements) would be invalid even
with the current memory model. There's nothing to stop the compilers from
re-ordering the adds and multiplies so that they fill each other&
Java Memory Model.
Date: Thu, 8 Dec 2011 10:08:12 -0800
From: shan...@vmware.com
To: john_pla...@hotmail.com
CC: jdk8-dev@openjdk.java.net
Subject: Re: Optimizing arithmetic operations on processors with AVX2 support
Such an assumption (in-order executi
Shouldn't it be discussed on the hotspot-dev alias?
Thanks,
Artem
On 12/8/2011 9:25 PM, John Platts wrote:
Here is an example of a class with an operation that can be optimized on a
processor with AVX2 support:class ExampleClass {public void
ExampleOperation(ExampleClass y) {a
, 8 Dec 2011 10:08:12 -0800
> From: shan...@vmware.com
> To: john_pla...@hotmail.com
> CC: jdk8-dev@openjdk.java.net
> Subject: Re: Optimizing arithmetic operations on processors with AVX2 support
>
> Such an assumption (in-order execution of statements) would be invalid even
>
Such an assumption (in-order execution of statements) would be invalid even
with the current memory model. There's nothing to stop the compilers from
re-ordering the adds and multiplies so that they fill each other's pipeline
delays.
So I don't think AVX2 brings anything new to the table in ter
