Four Multi-GPU Z77 Boards from $280-$350 - PLX PEX 8747 featuring Gigabyte, ASRock, ECS and EVGA

ASRock Z77 Extreme9 In The Box

ASRock boxes can often flip between very good value and perhaps not so much.  On the plus side, they had a phase where even the cheap end boxes contained a USB 3.0 front panel addition, which I thought was quite special.  In terms of the Z77 Extreme9, we get the following:

Driver CD
IO Panel
Manual
Six SATA cables
Two SATA-to-Molex Power Cables
3-way Rigid SLI Bridge
Three 2-way SLI Bridges
Wi-SB Box

While the ASRock Z77 Extreme9 has more SATA ports than the Gigabyte G1.Sniper 3, they have decided to put less SATA cables in the box – we do not get anything eSATA or otherwise either.  The big plus in the box is the ASRock Wi-SB box, which connects to the onboard WiFi.  This Wi-SB box houses two sets of antenna, allowing for better reception of WiFi signals.  The box doubles up as a 2.5” drive storage and two USB 3.0 ports for use on one of the two USB 3.0 headers.

Voltage Readings

After my first publication of OCCT voltage readings, a few readers responded with a more in-depth reasoning behind some of the results we were seeing.  With this in mind, I would like to re-describe what we are doing with this test, and how it comes about.

Much of what an enthusiast overclocker does is monitor CPU temperature and voltage.  Whatever settings a user places in the BIOS or OS is at the mercy of the motherboard - in terms of actually setting the values and reporting the values back.   As an enthusiast, we have to rely on what readings we get back, and hope that motherboard manufacturers are being honest with their readings.

Take CPU voltage.  What we as a user see in CPU-Z or OCCT is a time-averaged value that hides voltage ripple (if any) for power delivery.  It is very easy for a motherboard manufacturer to hide this value, or to disregard slight deviations and report a constant value to the user.  The CPU voltage reading can be taken at a variety of places on the power plane, which can vary between motherboards and manufacturers, meaning that each reading is essentially not comparable with the other.  Nevertheless, as an enthusiast, we will constantly compare value A with value B. 

Whether or not I can achieve 4.7 GHz with 1.175 volts on a particular board is inconsequential - your motherboard may perhaps produce the same result with a reading at 1.200 volts.  The only way to test the actual value is with consistent methodology is via an oscilloscope connected to similar points on each board.  This may sound like taking an OCCT reading is therefore redundant.

However, motherboards have settings relating to load line calibration.  As load is applied to the CPU, the voltage across the processor decreases (VDroop).  Load Line calibration essentially attempts to control this level of droop, by increasing voltage when voltage drops are detected away from a fixed value.  Manufacturers have different ideas on how to modify LLC with respect to load, or whether the level of modification should be controlled by the user.  Some manufacturers offer the option at a variety of levels, such that overclockers can be sure of the applied setting (even if it increases peak voltage, as explained by AnandTech in 2007).

By doing a full load OCCT test, we are essentially determining both how aggressive the motherboard is reporting the CPU voltage under load and how aggressive load line calibration is performing (from the point of view of the user without an oscilloscope or DVM).  If someone has one of the motherboards we have tested and you have a different one, variations in load voltage should describe the offset you may require for overclock comparisons.

As seen on other ASRock motherboards, the CPU at load in an ASRock board tends to be a little jumpy in terms of what is reported to the operating system.  The reports have a 0.008 volt granularity, which could mask a much smaller variation over time.  Though our OCCT recording is actually a smoothing over time, so for the OCCT reading to jitter so much does lead to a mild concern.  I also ran the test in an overclocked setting, with LLC set at Level 1:

There was still mild jitter being recorded on a heavily overclocked system, which leads me to believe that this is something systemic while the system is at load.