Article: Medfield, Intel's x86 Phone Chip
By: IntelUser2000 (Intel_user2000.delete@this.yahoo.ca), January 25, 2012 12:56 am
Room: Moderated Discussions
David Kanter (dkanter@realworldtech.com) on 1/25/12 wrote:
---------------------------
>IntelUser2000 (Intel_user2000@yahoo.ca) on 1/24/12 wrote:
>>I've seen >benchmarks of 2 core Atom
>>with Hyperthreading disabled vs Hyperthreading enabled >single core Atom. The 2 core is 30 or so percent faster.
>
>OK. I'm not sure what that says about A9...actually honestly that tells me that
>Intel made a really good choice in terms of hyperthreading.
>
It's that they need a combination of single thread performance(via clock speed for example) and Hyperthreading to match a dual A9. And that A15 improves on clock and IPC.
Though you have a point about process technology giving limited improvents when designs are equal, A15 uses a new architecture.
Sandy Bridge offered both better performance and lower power at same process as Clarkdale. Core 2 Duo did that in 2006 versus Core Duo. A15 chips move to 28nm technology and move to a new architecture.
Perhaps 70% is overkill but 40-50% should be possible, is it not?
---------------------------
>IntelUser2000 (Intel_user2000@yahoo.ca) on 1/24/12 wrote:
>>I've seen >benchmarks of 2 core Atom
>>with Hyperthreading disabled vs Hyperthreading enabled >single core Atom. The 2 core is 30 or so percent faster.
>
>OK. I'm not sure what that says about A9...actually honestly that tells me that
>Intel made a really good choice in terms of hyperthreading.
>
It's that they need a combination of single thread performance(via clock speed for example) and Hyperthreading to match a dual A9. And that A15 improves on clock and IPC.
Though you have a point about process technology giving limited improvents when designs are equal, A15 uses a new architecture.
Sandy Bridge offered both better performance and lower power at same process as Clarkdale. Core 2 Duo did that in 2006 versus Core Duo. A15 chips move to 28nm technology and move to a new architecture.
Perhaps 70% is overkill but 40-50% should be possible, is it not?
Topic | Posted By | Date |
---|---|---|
Medfield article online | David Kanter | 2012/01/23 02:51 PM |
server error | bakaneko | 2012/01/24 04:00 AM |
Fixed | David Kanter | 2012/01/24 05:02 AM |
Fixed | Joel | 2012/01/24 08:43 AM |
Fixed | Ricardo B | 2012/01/24 12:25 PM |
Fixed | David Kanter | 2012/01/24 06:29 PM |
Fixed | Gabriele Svelto | 2012/01/24 02:07 PM |
Fixed | David Kanter | 2012/01/24 06:30 PM |
Reference platform battery life | Doug Siebert | 2012/01/24 03:03 PM |
standby time | Foo_ | 2012/01/25 07:58 AM |
standby time | Anon | 2012/01/26 04:42 AM |
standby time | Foo_ | 2012/01/26 05:02 AM |
standby time | Doug Siebert | 2012/01/26 01:39 PM |
standby time | Anon | 2012/01/26 02:22 PM |
standby time | anon | 2012/01/26 03:08 PM |
standby time | Anon | 2012/01/26 07:03 PM |
standby time | anon | 2012/01/26 09:57 PM |
standby time | anon | 2012/01/26 10:01 PM |
standby time | Anon | 2012/01/27 10:32 PM |
standby time | Doug Siebert | 2012/01/27 03:15 PM |
standby time | anon | 2012/01/27 03:41 PM |
Reference platform battery life | David Kanter | 2012/01/27 11:09 AM |
Performance analysis laughable | Wilco | 2012/01/24 04:23 PM |
Performance analysis laughable | David Kanter | 2012/01/24 06:19 PM |
Performance analysis laughable | IntelUser2000 | 2012/01/24 08:30 PM |
Performance analysis laughable | IntelUser2000 | 2012/01/24 08:32 PM |
Performance analysis laughable | David Kanter | 2012/01/25 12:34 AM |
Performance analysis laughable | IntelUser2000 | 2012/01/25 12:56 AM |
Performance analysis laughable | David Kanter | 2012/01/25 03:07 AM |
Performance analysis laughable | Alberto | 2012/01/25 01:54 PM |
Atom HT gain | Wilco | 2012/01/25 06:43 AM |
Atom HT gain | IntelUser2000 | 2012/01/25 07:53 AM |
Atom HT gain | none | 2012/01/25 08:04 AM |
Atom HT gain | IntelUser2000 | 2012/01/25 08:35 AM |
Atom HT gain | Foo_ | 2012/01/25 08:06 AM |
Performance analysis laughable | Wilco | 2012/01/24 09:21 PM |
Performance analysis laughable | David Kanter | 2012/01/24 11:13 PM |
Performance analysis laughable | Wilco | 2012/01/25 05:30 AM |
Performance analysis laughable | none | 2012/01/25 07:14 AM |
Performance analysis laughable | Wilco | 2012/01/25 08:18 AM |
Performance analysis laughable | observer | 2012/01/26 05:17 AM |
Performance analysis laughable | Wilco | 2012/01/26 07:25 AM |
Process numbers | Alberto | 2012/01/26 10:29 AM |
Performance analysis laughable | David Kanter | 2012/02/02 01:38 AM |
Performance analysis laughable | tupper | 2012/01/25 05:27 PM |
Performance analysis laughable | Linus Torvalds | 2012/01/25 09:37 PM |
Performance analysis laughable | Doug Siebert | 2012/01/26 03:12 PM |
Medfield article online | Andreas | 2012/01/25 04:10 AM |
Medfield article online | Alberto | 2012/01/25 10:44 AM |
Medfield article online | IntelUser2000 | 2012/01/25 11:24 AM |
Medfield article online | David Kanter | 2012/01/25 10:58 PM |
Medfield article online | Doug Siebert | 2012/01/26 02:20 PM |
Medfield article online | Eric | 2012/01/26 07:10 PM |
Medfield article online | Doug Siebert | 2012/01/27 03:40 PM |
64-bit | Ingeneer | 2012/01/25 10:28 AM |
64-bit | Foo_ | 2012/01/25 11:23 AM |
64-bit | Ingeneer | 2012/01/25 03:34 PM |
64-bit | Ungo | 2012/01/25 05:08 PM |
64-bit | EduardoS | 2012/01/26 01:55 PM |
Saltwell memcpy | SHK | 2012/01/26 03:41 AM |
Medfield WiFi & Bluetooth | Rob Thorpe | 2012/01/26 04:09 AM |
Medfield WiFi & Bluetooth | David Kanter | 2012/01/27 06:54 PM |
Medfield WiFi & Bluetooth | Rob Thorpe | 2012/01/28 03:22 PM |
Medfield article online (NT) | Anil | 2012/01/26 06:57 PM |
Medfield article online | Anil | 2012/01/26 07:11 PM |
Medfield article online | Mr. Camel | 2012/01/26 07:26 PM |
Medfield article online | none | 2012/01/27 02:41 AM |