This is the mail archive of the libc-alpha@sourceware.org mailing list for the glibc project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: [PATCH] Optimized generic expf and exp2f

From: Wilco Dijkstra <Wilco dot Dijkstra at arm dot com>
To: Arjan van de Ven <arjan at linux dot intel dot com>, "libc-alpha at sourceware dot org" <libc-alpha at sourceware dot org>, Szabolcs Nagy <Szabolcs dot Nagy at arm dot com>, "Joseph Myers" <joseph at codesourcery dot com>
Cc: nd <nd at arm dot com>
Date: Wed, 6 Sep 2017 12:55:32 +0000
Subject: Re: [PATCH] Optimized generic expf and exp2f
Authentication-results: sourceware.org; auth=none
Authentication-results: spf=none (sender IP is ) smtp.mailfrom=Wilco dot Dijkstra at arm dot com;
Nodisclaimer: True
References: <DB6PR0801MB2053A12C3A4F7032C0107E1683960@DB6PR0801MB2053.eurprd08.prod.outlook.com> <DB6PR0801MB205311F53E0828F3F0B583F383970@DB6PR0801MB2053.eurprd08.prod.outlook.com>,<1464883d-e2a0-082b-b844-3cd1a4a91820@linux.intel.com>
Spamdiagnosticmetadata: NSPM
Spamdiagnosticoutput: 1:99

Arjan van de Ven wrote:
>> 
>> expf reciprocal-throughput: 1.5x faster
>> expf latency: 1.4x faster
>
> interesting; the fma existing expf for x86_64 is 10 to 11 cycles reciprocal-throughput ;-)
> time to see how you got that 1.5x faster....

Just using a good algorithm :-)  It's not the first time generic C
code beats "optimized" assembler implementations in GLIBC,
and it won't be the last... This shows that optimizing generic
code is a much better strategy overall.

Wilco

Follow-Ups:
- Re: [PATCH] Optimized generic expf and exp2f
  - From: Arjan van de Ven

References:
- Re: [PATCH] Optimized generic expf and exp2f
  - From: Wilco Dijkstra
- Re: [PATCH] Optimized generic expf and exp2f
  - From: Wilco Dijkstra
- Re: [PATCH] Optimized generic expf and exp2f
  - From: Arjan van de Ven

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]