IPB

Welcome Guest ( Log In | Register )

 
Reply to this topicStart new topic
Increase in LAME performance?, With Intel's recently announced Penryn
Zoom
post Mar 29 2007, 15:48
Post #1





Group: Members (Donating)
Posts: 263
Joined: 23-February 04
From: United States
Member No.: 12219



I was reading a few articles about the new Intel die shrink and core revision and something caught my eye.
QUOTE
Today Intel disclosed that Penryn will feature a 4-bit per cycle divider, that the company claims will offer 4X the performance of current processors for square root operations...
From this article.

Now if I remember correctly, isn't the bottleneck in current versions of LAME the sqrt() function? I was just curious what some of the more technical minded members of HA and/or developers thought this might mean for performance, if anything at all.
Go to the top of the page
+Quote Post
germanjulian
post Mar 29 2007, 16:00
Post #2





Group: Members
Posts: 207
Joined: 8-September 03
Member No.: 8746



mhh that would suck... then i do not even have to wait any more for a song to be encoded since it would be so fast sad.gif

smile.gif
Go to the top of the page
+Quote Post
tcmjr
post Mar 29 2007, 16:54
Post #3





Group: Members
Posts: 142
Joined: 5-January 03
Member No.: 4429



Penryn-based processors also have a much better divider unit, roughly doubling the divider speed using a faster divide technique called Radix 16. Also, the shuffle engine has been improved. Intel's "Super Shuffle Engine" is a 128-bit, single-pass shuffle unit that can perform full-width shuffles in a single cycle, improving performance for SSE2, SSE3 and SSE4 instructions that have shuffle-like operations such as pack, unpack and wider packed shifts.


--------------------
Kind Regards , Tcmjr

Aka HellSnoopy
Go to the top of the page
+Quote Post

Reply to this topicStart new topic
1 User(s) are reading this topic (1 Guests and 0 Anonymous Users)
0 Members:

 



RSS Lo-Fi Version Time is now: 23rd April 2014 - 18:48