RFR(XS) 8224558: x86 Fix replicateB encoding
Deshpande, Vivek R
vivek.r.deshpande at intel.com
Fri May 24 18:22:59 UTC 2019
By Autovectorizer, I was referring to Superword Optimization.
As per earlier discussion with VladimirI, I have a patch which removes the wrong memory based instructs.
Could you all please review it?
I can push the patch, after both of you find it ok.
From: Tobias Hartmann [mailto:tobias.hartmann at oracle.com]
Sent: Thursday, May 23, 2019 5:45 AM
To: Deshpande, Vivek R <vivek.r.deshpande at intel.com>; 'hotspot-compiler-dev at openjdk.java.net compiler' <hotspot-compiler-dev at openjdk.java.net>
Cc: Viswanathan, Sandhya <sandhya.viswanathan at intel.com>
Subject: Re: RFR(XS) 8224558: x86 Fix replicateB encoding
On 22.05.19 19:48, Deshpande, Vivek R wrote:
> I came across this issue with vector API tests.
> I tried to write a reproducer using the autovectorizer test, but it always uses the register based rule(instruct Repl32B) instead of memory based rule (instruct Repl32B_mem) and register based rule gives correct result.
> This is why it never showed up.
Okay, thanks for the explanation.
> Could you please help me with forcing to use memory based rule with autovectorizer based test.
I'm afraid I can't help, I'm not even sure what the autovectorizer is. Is that specific to the vector API?
More information about the hotspot-compiler-dev