llvm dev - Feb 2017 - Clang 5.0 support for armv8 64 bit with neon and auto vectorization

Thanks Peter and Tim.

Being that said, can I be sure that for 64 bit arm architectures (e.g. arm
cortex A57) the  neon feature and auto-vectorization is supported as default by
clang 5.0?

Because for us these two features are deal breaking for compiler evaluation.

Mit freundlichen Grüßen / Best regards 

Zeeshan Haider

Chassis Systems Control, Engineering Software Coordination, Software Mainstream
Management, Methods Group 1 (CC/ESM1)
Robert Bosch GmbH | Postfach 16 61 | 71226 Leonberg | GERMANY | www.bosch.com
Tel. +49(711)811-47379 | Fax +49(711)811-0 | Zeeshan.Haider at de.bosch.com

Sitz: Stuttgart, Registergericht: Amtsgericht Stuttgart, HRB 14000;
Aufsichtsratsvorsitzender: Franz Fehrenbach; Geschäftsführung: Dr. Volkmar
Denner,
Dr. Stefan Asenkerschbaumer, Dr. Rolf Bulander, Dr. Stefan Hartung, Dr. Markus
Heyn, Dr. Dirk Hoheisel,
Christoph Kübel, Uwe Raschke, Dr. Werner Struth, Peter Tyroller


-----Original Message-----
From: Tim Northover [mailto:t.p.northover at gmail.com] 
Sent: Freitag, 3. Februar 2017 16:02
To: Haider Zeeshan (CC/ESM1) <Zeeshan.Haider at de.bosch.com>
Cc: llvm-dev at lists.llvm.org
Subject: Re: [llvm-dev] Clang 5.0 support for armv8 64 bit with neon and auto
vectorization

On 3 February 2017 at 00:48, Haider Zeeshan (CC/ESM1) via llvm-dev <llvm-dev
at lists.llvm.org> wrote:
> clang.exe -target armv8 -fslp-vectorize-aggressive  -mfpu=neon 
> -mfloat-abi=hard -c test.cpp
Peter's advice is good (-mfpu and -mfloat-abi aren't needed). But also
note that "-target armv8" actually targets 32-bit ARM (v8 CPUs usually
support both modes).

You probably want to specify a full triple for the target, maybe "-target
aarch64-linux-gnu", otherwise the OS part might default to Windows since
that's where you're running. Clang doesnn't support Windows on
AArch64.

Cheers.

Tim.

Hi Haider,

On 3 February 2017 at 07:13, Haider Zeeshan (CC/ESM1)
<Zeeshan.Haider at de.bosch.com> wrote:
> Being that said, can I be sure that for 64 bit arm architectures (e.g. arm
cortex A57) the  neon feature and auto-vectorization is supported as default by
clang 5.0?
Yes, unless something has gone horribly wrong they will be. The
obvious quick test would be to compile something trivial like

void foo(float *arr) {
  for (int i = 0; i < 128; ++i)
    arr[i] += 1;
}

and look at the output.

Tim.

One more thing, setting up clang 5,0 on windows, I have issues compiling libcxx
project.

Is it supported to be built with Visual studio or MinGW make files? 

Mit freundlichen Grüßen / Best regards

Zeeshan Haider
CC/ESM1  

Tel. +49(711)811-47379 



-----Original Message-----
From: Tim Northover [mailto:t.p.northover at gmail.com] 
Sent: Freitag, 3. Februar 2017 18:05
To: Haider Zeeshan (CC/ESM1) <Zeeshan.Haider at de.bosch.com>
Cc: llvm-dev at lists.llvm.org
Subject: Re: [llvm-dev] Clang 5.0 support for armv8 64 bit with neon and auto
vectorization

Hi Haider,

On 3 February 2017 at 07:13, Haider Zeeshan (CC/ESM1) <Zeeshan.Haider at
de.bosch.com> wrote:
> Being that said, can I be sure that for 64 bit arm architectures (e.g. arm
cortex A57) the  neon feature and auto-vectorization is supported as default by
clang 5.0?
Yes, unless something has gone horribly wrong they will be. The obvious quick
test would be to compile something trivial like

void foo(float *arr) {
  for (int i = 0; i < 128; ++i)
    arr[i] += 1;
}

and look at the output.

Tim.