News Bobcat: erste Benchmarks

User-News

Von Onkel_Dithmeyer

Hinweis: Diese "User-News" wurde nicht von der Planet 3DNow! Redaktion veröffentlicht, sondern vom oben genannten Leser, der persönlich für den hier veröffentlichten Inhalt haftet.
Auf dem Financial Analyst Day vor einer Woche hatte AMD bekannt gegeben, dass man noch letzte Woche erste CPUs an die Partner ausliefert. Einige weitere spärliche Informationen machten Lust auf mehr. Kurz darauf war bei Heise zu lesen, dass man in der kommenden Printausgabe erste Benchmarks und die Leistungsaufnahme präsentieren will.
Einen ausführlichen Bericht über Zacate mit CPU- und GPU-Benchmarks sowie Messungen der Leistungsaufnahme bringt c't in der kommenden Ausgabe 25/10.
Doch bereits heute kann man erste Benchmarks im Internet lesen. Genauer gesagt bei Anandtech. Der Autor Anand Lal Shimpi durfte schon vor einiger Zeit testen und nun endlich (Teile) veröffentlichen. Zwar hat man keine finale Hardware in Sachen Leistungsaufnahme bekommen, aber immerhin ist der Takt identisch mit dem finalen Release.


Eine kleine Übersicht:

Leistungsaufnahme (nicht Final):
During my testing I measured a maximum total system power consumption of around 30W (including the 1366 x 768 LCD panel) while playing games and around 25W while encoding H.264 on the two Bobcat cores. The system idled around 15W however AMD cautioned me that this number was unnaturally high. Final Brazos systems will be far more power optimized and AMD expects numbers to drop down to as low as 5.6W.
Er hat während dem Test maximal 30W verbrauch für das Gesamtsystem incl. Display abgelesen. 25W beim encoden auf dem CPU-Teil. Und im Idle ~15W. AMD beteuert aber, dass dieser Wert unnatürlich hoch ist und man mit den Finalen Samples im Idle auf bis zu 5,6W kommt.


CPU-Leistung:
AMD's performance target for Bobcat was 90% of the performance of K8 at the same clock speed and our Photoshop CS4 benchmark shows that AMD can definitely say that it has met that goal. At 1.6GHz the E-350 manages to outperform a pair of K8s running at 1.5GHz in the Athlon X2 3250e.
Man erreicht die von AMD versprochenen rund 90% eines K8 X2 bei gleichem Takt.


Grafikleistung:
Compared to the Radeon HD 5450 the 6310 offers between 66 - 69% of its performance in our GPU bound tests. The performance reduction is entirely due to the 6310's limited memory bandwidth being shared with the dual Bobcat cores on-die
Verglichen mit der Radeon HD 5450, die über die gleiche Shaderzahl verfügt erreicht man ungefähr 2/3 der Leistung mit der On-Chip-GPU. Das ist dem Single-Chanel-Speicherinterface geschuldet, welches von CPU- und GPU-Teil gemeinsam genutzt wird.


Fazit:
The good news is that AMD finally has what looks to be a real contender in the mainstream ultraportable space. While the E-350 won't outperform the Pentium or low end Core i3 systems, you'll get better GPU performance, hopefully in a smaller package. Now we wait for the notebooks.
AMD hat es geschafft etwas im mainstream ultraportable Bereich zu schaffen. Man errreicht zwar nicht die Leistung eines Core-I3 oder Pentium-D aber dabei eine bessere GPU-Performance mit gleichsam kleinerem Package. Man könnte also eher Intels Culv-Platform als Ziel sehen, aber mit besserer Grafik.


Link zum Test (Anandtech)

Des weiteren würde ich jedem der sich für das Thema interessiert den Artikel von Au-Ja empfehlen, der auch regelmäßig aktualisiert wird. Und natürlich auch unsere Foren-internen Spekulationsthreads.
.
EDIT :
.

Habe zwei Weitere Tests aufgetan:

PCPerspective & Hothardware

PCPerspective Schreibt:

Perfomance
Let's tackle the issue of performance from a component stand point. The dual-core Bobcat processor in the Zacate APU from AMD is much faster than the dual-core HyperThreaded Atom D510 processors and is about on par with the performance of the Penryn-based dual-core Celeron SU2300 CULV part. Obviously the in-order architecture of the Atom CPU family is starting to show its age and I have to wonder if Intel doesn't have something else up their sleeve to compete with the obviously fundamentally better design of the Bobcat core.
The 80 stream processors / 2 SIMDs found in the AMD E-350 blow away any graphics performance you might get with the integrated solution on the D510 and the best the Atom designs have to offer today. The Radeon HD 6310 is also faster than the graphics solution found in the NVIDIA ION chipset, sometimes by a notable margin, making the CULV+ION combination that much less impressive in the light of the power efficiency that the AMD Brazos platform provides.

Power
The performance of the E-350 is impressive but even more so is how much better the power efficiency looks with the Brazos platform compared to these Intel offerings. Intel's CULV+ION platform not only uses more than twice as much power at idle than AMD's offering but also requires 30% or so more power at peak performance while still falling behind in many benchmarks. The Intel Atom D510 platform with its integrated graphics does have a good showing in terms of power consumption but at the levels of performance it provides, that is all it can gather credit for.
One of the biggest keys to longer battery life in mobile machines is the idle numbers at with an idle consumption rate of just over 9 watts, the AMD E-350 is 75% better than even the plain vanilla Atom D510. These results bode very well for the Brazos platform being a hit in the ultra-mobile space later this winter.

Zusammengefasst lässt sich sagen, dass der Test von PCPerspective zeigt:
  • Bessere Leistung als Atom D510 mit HT (1,8GHz)
  • Fast identische Leistung wie der Penryn-basierende dual-core Celeron SU2300 CULV
  • Überlegene Grafikleistung auch im Vergleich zum ION mit CULV
  • Einzigartiges Performance/Watt-Verhältnis


Hothardware schreibt:

Performance:
In terms of general CPU performance, this early engineering sample of Zacate proved itself to be faster than a 1.8GHz dual-core Atom processor across the board and in some tests, like our Lame MT audio encoding test, it was significantly faster.
On the GPU side of things, Zacate performs a lot like a dual-core Atom system backed up by NVIDIA's Ion 2 chip, only Zacate does this all on a single chip/die and at decidedly lower power consumption at idle and under load. To us, that looks like a hat-trick.
No matter how you slice it, taking on a combined Intel and NVIDIA solution from a performance standpoint is a tall order in any product segment but to do it successfully and with less power consumption and theoretically lower cost as well, is a proverbial win-win.

System Power Consumption
Also, we should note the AMD Brazos reference platform system we tested was equipped with a USB3 IO chip from NEC, as well as a few other bells and whistles that drive power requirements up by a couple of Watts or so. In reality, if anything, these numbers are on the high side for the Zacate/Brazos test setup.
amd-zacate-power-3.png

In short, AMD's Brazos platform and their Zacate processor consume significantly less power than a dual core Atom/Ion2 solution at idle and under load. In addition, at idle, Zacate even consumes a lot less power than a standard single core Atom design.

In notebooks and netbooks this equates to one thing; extended battery life. We'd also offer that again, the power consumption measurements here are very conservative, comparatively for Zacate. The reference board we tested definitely wasn't optimized for power consumption. Without a doubt, Brazo and AMD's Zacate E-350 processor offer excellent performance-per-watt efficiencies that will likely have Intel on its toes in a big way moving forward.

Anmerkung:
We''ll bring this preview to a close with another reminder that we should call your attention to again. The image below shows you the environment that we tested AMD's new chip in and its reference platform. Obviously, the build you see here is far from retail, though reportedly retail-ready products (notebooks) are not far off and expected to ship this quarter. So, in other words, from here things can only get better for the AMD Brazos mobile platform and their Zacate processor, and they already look really strong.
 
Zuletzt bearbeitet:
Oben Unten