Article: AMD's Jaguar Microarchitecture
By: none (none.delete@this.none.com), April 11, 2014 12:49 am
Room: Moderated Discussions
David Kanter (dkanter.delete@this.realworldtech.com) on April 10, 2014 11:24 pm wrote:
[...]
> I suspect a large part of this is because Jaguar doesn't have any turbo capabilities
> and the SoC memory controller and fabric is probably more primitive.
>
> I expect that in a competently designed SoC, Jaguar should beat out Silvermont-based
> designs. Especially in FP. It's strange to see results otherwise.
On the smaller Geekbench (no comment, the aim is to look at a smaller bench :-), J1900 vs 5350: http://browser.primatelabs.com/geekbench3/compare/513198?baseline=514388
As David expected, the FP score is significantly higher despite the frequency deficit.
In Anand review, the 3DPM result is an outlier. A quick disassembly shows it's using x87... I guess Ian Cutress should recompile it with better flags :-)
Ref:
- results: http://anandtech.com/show/7933/the-desktop-kabini-review-part-1-athlon-5350-am1/4
- 3DPM: http://www.borandi.co.uk/3DPM
[...]
> I suspect a large part of this is because Jaguar doesn't have any turbo capabilities
> and the SoC memory controller and fabric is probably more primitive.
>
> I expect that in a competently designed SoC, Jaguar should beat out Silvermont-based
> designs. Especially in FP. It's strange to see results otherwise.
On the smaller Geekbench (no comment, the aim is to look at a smaller bench :-), J1900 vs 5350: http://browser.primatelabs.com/geekbench3/compare/513198?baseline=514388
As David expected, the FP score is significantly higher despite the frequency deficit.
In Anand review, the 3DPM result is an outlier. A quick disassembly shows it's using x87... I guess Ian Cutress should recompile it with better flags :-)
Ref:
- results: http://anandtech.com/show/7933/the-desktop-kabini-review-part-1-athlon-5350-am1/4
- 3DPM: http://www.borandi.co.uk/3DPM