Intel Announces New Prime95 Suckage in Skylake

Now we just have to hope that all our Skylake CPUs aren't destined to turn up as paving materials likth FDIV-bug impacted P54C Pentiums were.
 
They claim a BIOS fix can solve this. I'll be interested in what followup tests show.
 
Chewy509 said:
I'm actually a little surprised that Intel don't test internally with Prime95 or a similar application?
Click to expand...

I was thinking the same thing. Then I wondered, am I reading the situation correctly? Maybe I am wrong, but it seems that not every Prime95 instance produces the same results with Skylake. So, could Prime95 be running on a Skylake CPU for 24 hours, and the problem is never encountered?
 
Interesting. I wonder if this explains some of my issues with doing an overclock; I use Prime95 and was having inconsistent results. Looking forward to trying again after the fix.
 
ddrueding said:
Interesting. I wonder if this explains some of my issues with doing an overclock; I use Prime95 and was having inconsistent results. Looking forward to trying again after the fix.
Click to expand...

My understanding is that you need to be careful of what version of Prime95 you are running. Newer versions will push AVX instructions in the fpu in a way that really diverges from actual real world scenarios. IIRC version 27 or something like that is best to avoid AVX. If you are using an AVX version make sure you have adaptive/offset vcore turned off.
 
DrunkenBastard said:
My understanding is that you need to be careful of what version of Prime95 you are running. Newer versions will push AVX instructions in the fpu in a way that really diverges from actual real world scenarios. IIRC version 27 or something like that is best to avoid AVX. If you are using an AVX version make sure you have adaptive/offset vcore turned off.
Click to expand...
Horseshit.
AVX and AVX2 (FMA) instructions are used by Prime95 exactly as they are designed to be used. Idiots who didn't/don't understand the response of the CPU to AVX instructions spread misinformation - usually like "Prime95 caused my overclocked and overvolted CPU to die!" because the additional (and documented) voltage rise triggered by AVX instructions destabilized their CPU.
 
You must log in or register to reply here.
Back
Top