We assessed the heat dissipation of our cooling solution (115 Watts constant), and used it to allow the processor to reach high clock speeds when the workload had modest heat output. If the load became too heavy, the processor's clocks are reduced, to keep within the 115 Watt limit. Although successful, the firmware options are not flexible enough to make the most of every workload presented to the system, and some compromises are associated with each profile.
We do not advocate any activity that would damage your equipment, and will not take responsibility for any consequences caused by following this article.
We take a responsible approach to overclocking, weighing performance gain and efficiency against the effort and risk invested in such a configuration.
We've been running this processor using different profiles, as conditions have allowed:
This article explains the configuration of my current setting: power-limited clocking.
|Motherboard||ASRock Z87 Extreme4|
|Processor||Intel i5-4670K 3.4GHz|
|Cooling||Scythe Mugen 4 PCGH Edition (air cooling, push-pull slow fans)|
|RAM||DDR3 1600 9-9-9-24|
|4.2 GHz||4.3 GHz||4.4 GHz|
|Core multiplier||42x max, all||43x max, all||44x max, all|
|Cache multipler||32x max||43x max||33x max|
|VCore||1.000 V −0.025 V|| ||1.000 V +0.060 V |
|VCache||1.160 V +0.010 V||||1.160 V +0.010 V|
|Load Line Calib.||Level 4||Level 4||Level 3|
|CPU Input||1.88 V||1.90 V ||1.90 V|
|Sys Agent||+0.1 V||+0.1 V||+0.1 V|
|Power limit: short||125 W, 1s|
|125 W, 1s|
|125 W, 1s|
|Power limit: long||115 W|
We felt a little limited by the cooling, and the power throttling at 115W became necessary, particularly above 4.2 GHz, to keep core temperatures from exceeding 85°C.
Performance-wise, the 4.4 GHz profile delivered 6% more speed in POV-Ray than the 4.2 GHz profile. We'd only consider using this if we could keep the processor busy 24/7, with no regard for energy costs. For 'special instruction' work, like the burn-in test, performance at 4.2 GHz was 8% better than at 4.4 GHz, because the voltage offset required to keep the system stable has a side-effect of requiring more power, and this exceeded our defined 115 Watt power limit, and so throttling reduced the core multipliers to 37x, losing 16% of their clock frequency at worst. Incidentally, the 'large' burn-in test at 4.2 GHz yielded 113.2 GFLOPS, exceeding our previous fixed VCore 4.4 GHz result.
We found that the cache multiplier gave no significant performance increase between 32x and 44x. In fact, higher cache speeds contributed significantly to heat output, and we found that lower cache speeds and voltages allowed more flexibility elsewhere (e.g. allowing 4.4 GHz core clocks at modest VCore offset).
Some of the supporting voltages in the 4.2 profile could be lowered a bit more. We'll benchmark that result, to see if performance suffers. Perhaps unsurprisingly, they almost converged with the original "profile 1b", here. Further, this round of tweaks might have increased the margins for stability, to allow efficiencies or gains to be made elsewhere.
The 4.3 GHz profile would benefit from a lower cache clock and voltage. We expect this would increase the throttled clock speed under high load, to between 4.0 GHz and 4.1 GHz.
If our results are below par for this cooling solution, then we'll look at re-seating it.