http://www.xbitlabs.com/news/cpu/display/20120405175642_AMD_to_Formally_Announce_Trinity_Fusion_APUs_for_Notebooks_on_May_15.html
The APU will feature up to four x86 cores powered by enhanced Bulldozer/Piledriver architecture, AMD Radeon HD 7000-series "Southern Islands" graphics core with DirectX 11-class graphics support, DDR3 memory controller and other improvements.
Is it gonna be GCN or Northern Islands.......?
Oh and one more thing,
AMD's current plans, points to May 15 as the formal introduction date of Trinity
From what I have heard, its a HD6000 VLIW4, not GCN unless AMD somehow changed it last minute before they started FABing it but then again it would be delayed.
The current Llano is VLIW5 but carries a HD6K moniker.
They should use real games and real apps to test their new CPU's/GPU's. But I've always hated synthetic benchmarks they always make things seem better then what they are. I'm a little more interested on their power consumption remark how did they get this statement. Under normal browsing(Word,power point) or watching videos/gaming or maybe just a very LONG idle.
But using real games and apps to test wont show their performance gains they want to show. Plus its easier to show improvements with synthetic benchmarks.
I do also hate cherry picking (like how AMD used tests vs the 2600K where the FX-8150 shined and then others where it beat the i7-970). Its annoying.
Im hearing 11% IPC with better clocks, and the IGP is good.
Thats what Ive heard, dont quote me, but sounds reasonable
So the 11% comes from better clocks but not actual per clock IPC increases? That sounds ok to me. Nice to hear a possible IPC increase but I would prefer it be per clock and per core so that any extra MHz IPC is just icing on the cake.
Hmm maybe I should dig out some of my more vintage cards like my x1900xt or 7900gtx duo (massive card) but hte 1900xt has no modern driver support
🙁
Got a Diamond Monster 3D for those who know what card that is
You should. But you are right. 10.2 is the last one for the X1900 but thats ok as that was the last driver that probably would have increased performance.
Nah, just wait on a Steamroller, get the highend CPU and high end GPU for the price of one. Considering the Zambezi's stock idle and load temps and consumption is rather low, certainly the temps are well lower than a Sandybridge, it is difficult to see where the issue is power consumption with AMD. Also consider that a 8core Zambezi litterally halved the consumption from Thuban.
At the end of the day, power consumption is maybe #5 on the list of what is needed.
And going to Intel.......cuts like a knife. 🙁
Zambezis stock power consumption is still higher than a 2600K from Intel and if you knew AFG, you would know she likes low power. If anything she would get the lowest TDP CPU then undervolt the crap out of it to have an even lower power consuption CPU.
Temps are one thing, power consompution is another. A 2600K will stay at under 50c when running normal loads (mine does about 55-60c but thats overclocked to 4.5GHz) and idle around 30-35c. BD is about the same at stock and still doesn't perform as well. Well lower would be 10-20c lower under load.
The major power consumption issue with AMD is that most enthusiasts like to overclock, and AMD has been marketing overclocking to the more budget oriented enthusiasts. Well, BD has major jumps in power usage. At 4.8GHz it uses more power than a 2600K at 5GHz on the same process size. Then again, Intel is on their second gen HK/MG as well as has had time to mature 32nm while AMD has no hand in it and cannot control it.
Here are some leaked Trinity benchmarks: http://amdfx.blogspot.com/2012/05/more-trinity-benchmarks-43-better.html
For the 4M/8T FX 8350, I estimate @ 5.1 Ghz it will match Ivy Bridge i5 3570k single core performance @ 4.3 Ghz. But will scale roughly 85% higher when all threads are used.
While I don't trust this guys numbers, he isn't really anyone with a reputation, if this were true its no big feat for PD. Thats a 800MHz clock speed difference. I doubt PD at 5.1GHz will use less power than IB at 4.3GHz meaning it uses more power to perform the same task.
That aside, his scaling seems a bit high. PD will use the same idea from BD so unless the app is super highly threaded (and efficient at that) I doubt it will scale that well.
I guess time will tell, an price is going to be very important with the performance. Once we start seeing price leaks we will be able to estimate the performance and when we get a final price we can pin it more closley.