[llvm-commits] [llvm] r148658 - in /llvm/trunk: lib/Target/ARM/ARM.td lib/Target/ARM/ARMAsmPrinter.cpp lib/Target/ARM/ARMInstrInfo.td lib/Target/ARM/ARMInstrNEON.td lib/Target/ARM/ARMInstrVFP.td lib/Target/ARM/ARMSchedule.td lib/Target/ARM/ARMSub

[James Molloy]

Hi Anton,

>From my discussions with colleagues we come to a different conclusion - that it is indeed possible to have the NEONv2 vector integer unit without the floating point unit of VFPv4.

We don't think it's possible to have VFPv4 with NEONv1 however.

Cheers,

James
________________________________________
From: anton at korobeynikov.info [anton at korobeynikov.info] On Behalf Of Anton Korobeynikov [asl at math.spbu.ru]
Sent: 24 January 2012 18:15
To: Jim Grosbach
Cc: James Molloy; llvm-commits at cs.uiuc.edu
Subject: Re: [llvm-commits] [llvm] r148658 - in /llvm/trunk: lib/Target/ARM/ARM.td lib/Target/ARM/ARMAsmPrinter.cpp lib/Target/ARM/ARMInstrInfo.td lib/Target/ARM/ARMInstrNEON.td lib/Target/ARM/ARMInstrVFP.td lib/Target/ARM/ARMSchedule.td lib/Target/ARM/ARMSub

Hi Jim,

> If we do keep it, it should be renamed to "neon-vfp4" rather than "neon-vfpv4" to be consistent with the rest of the attributes which reference vfp versions.
ARM docs mentions this as Advances SIMDv2. I just found the following link:
http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ddi0438c/CEGCDBHC.html

So, it's not possible to have just NEONv2 w/o VFPv4.

I will take care about necessary backend changes.

--
With best regards, Anton Korobeynikov
Faculty of Mathematics and Mechanics, Saint Petersburg State University


-- IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium.  Thank you.