Three HD7970s. Results are consistant. Reports this every time.
1: 76.7%
2: 72.3%
3: 70.1%
I'm curious to know what the other 7xxx series cards report.
Leakage is the manifestation of overclocking headroom. It's the Pentium M principle.How exactly does leaked voltage allow for better overclocking?
Quite possibly the most interesting part of the way Banias was designed, relates to the processor's clock speeds and what it took to achieve them. As we've already mentioned, the CPU features a longer pipeline than the Pentium III which does help it hit higher clocks, but where does the limit exist?
In the course of designing a processor, you will eventually discover that there are certain speed paths in your CPU that will run either faster or slower than your target clock speed. If you run into paths that run slower than your target clock speed, you're in trouble, since it means that you won't be able to reach the clocks you were hoping to without some sort of a redesign. In most cases, if you find that a path is running faster than your target clock speed (e.g. finding a path capable of running at 2.4GHz on a chip with a 1.6GHz target clock speed) then you're in a very good situation, as it means that there are parts of your chip that have fairly high ceilings. For the Israel design team however, this wasn't the case.
The design team actually went in and slowed down paths that were running above Banias' target clock frequencies, because if a path is able to run faster than it should, it means that you're wasting power. The benefit of this is an even more power efficient microprocessor, but the downside is a microprocessor that has a clear clock frequency wall.
The design team actually went in and slowed down paths that were running above Banias' target clock frequencies, because if a path is able to run faster than it should, it means that you're wasting power. The benefit of this is an even more power efficient microprocessor, but the downside is a microprocessor that has a clear clock frequency wall.
Leakage is the manifestation of overclocking headroom. It's the Pentium M principle.
Taken from AnandTech's Pentium M review:
Not wanting to take anyone to task here but this is one of those "rules of thumb" that is only true some of the time for very specific reasons.
Equating leakage to clockspeed headroom is tantamount to equating a car's gas mileage to its maximum drag/transmission-limited speed.
At the device physics level there is no correlation between leakage and clockspeed. Only in practice is there sometimes a correlation that depends on a host of factors.
But not all leakage is created equal. You need leakage in a very specific part of the transistor. I can make leaky transistors by putting the contacts to close to the sidewall, or have too much punchthrough on my Halo implant, and none of that leakage is going to make your GPU clock any faster, its just going to raise the static power consumption and that's it.