x86-64: Optimize e_expf with FMA [BZ #21912]
Commit Message
On Wed, Aug 16, 2017 at 9:00 AM, Carlos O'Donell <carlos@redhat.com> wrote:
> On 08/16/2017 11:57 AM, H.J. Lu wrote:
>> On Wed, Aug 16, 2017 at 8:45 AM, Carlos O'Donell <carlos@redhat.com> wrote:
>>> On 08/16/2017 11:33 AM, H.J. Lu wrote:
>>>> Here is the updated patch I am checking in.
>>>
>>> LGTM. Please include a NEWS entry describing the new optimizations for Intel.
>>>
>>
>> Like this?
>
> You should attribute this to Intel or the particular author who wrote the
> optimization to give them visible credit :-)
>
> Otherwise looks good.
>
I am going to check in this.
Thanks.
From 1eba220f5a2b37fd35d0ec8f7f35dc92d91831ad Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.tools@gmail.com>
Date: Wed, 16 Aug 2017 08:56:24 -0700
Subject: [PATCH] Mention x86-64 FMA optimization in NEWS
* NEWS: Mention x86-64 FMA optimization.
---
NEWS | 3 +++
1 file changed, 3 insertions(+)
@@ -11,6 +11,9 @@ Major new features:
[Add new features here]
+* Optimized x86-64 asin, atan2, exp, expf, log, pow, atan, sin and tan
+ with FMA, contributed by Arjan van de Ven and H.J. Lu from Intel.
+
Deprecated and removed features, and other changes affecting compatibility:
* On GNU/Linux, the obsolete Linux constant PTRACE_SEIZE_DEVEL is no longer
--
2.13.5