![]() |
|
|
#243 |
|
P90 years forever!
Aug 2002
Yeehaw, FL
19·397 Posts |
Oliver, where do I get the latest Linpack for Windows so that I can compare prime95 temps to Linpack temps?
|
|
|
|
|
|
#244 | |
|
Jan 2008
France
2×52×11 Posts |
Quote:
EDIT: Quickly tested IBT (found here). It only outputs 100 GFLOPS and temperature is ~85°C. It seems LinX stresses more the CPU. Last fiddled with by ldesnogu on 2013-09-01 at 08:55 |
|
|
|
|
|
|
#245 |
|
Jan 2008
France
2·52·11 Posts |
As I wanted to know if the cooler is correctly mounted, I ran Prime95 27.9 for Windows 64. I ran stress test with small FFT. Temperature reached 86°C. Blend tests is about 75°C.
Is that good for a high-end air cooler or too high? Last fiddled with by ldesnogu on 2013-09-01 at 11:41 |
|
|
|
|
|
#246 | |||
|
"Oliver"
Mar 2005
Germany
11·101 Posts |
Hello!
Quote:
Quote:
Quote:
Code:
[Worker #1 Sep 1 13:30] Resuming primality test of M30xxxxxx using FMA3 FFT length 1600K, Pass1=640, Pass2=2560 Copied worktodo from one of my machines doing 4 doublechecks, 3 times "FMA3 FFT length 1600K, Pass1=640, Pass2=2560", 1 time "FMA3 FFT length 1728K, Pass1=384, Pass2=4608": v27.9: 10.7xx ms/iter for 1600k FFT, 10.5xx ms/iter for 1728k FFT, package power ~88W v28.1: 9.1xx ms/iter for 1600k FFT, 10.0xx ms/iter for 1728k FFT, package power ~97W Linpack: up to 123-128W package power Oliver Last fiddled with by TheJudger on 2013-09-01 at 12:21 |
|||
|
|
|
|
|
#247 | |
|
Jan 2008
France
55010 Posts |
Hi :)
Quote:
Idle temp is about 30°C which looks correct. BTW, what Linux distro are you running? |
|
|
|
|
|
|
#248 |
|
"Oliver"
Mar 2005
Germany
111110 Posts |
openSUSE 12.3
Yes, you're right. Haswell increases vCore automatically when running AVX code (unless you set a fixed voltage). Oliver |
|
|
|
|
|
#249 |
|
Jan 2008
France
10468 Posts |
Thanks, I'll take a look.
I turned off HT and ASUS 3.9 GHz all core boost, and now LinX reaches 180 GFLOPs and 96°C max. |
|
|
|
|
|
#250 |
|
"Oliver"
Mar 2005
Germany
21278 Posts |
Hello,
yes, HTT is a bad idea for Linpack. With 3.9GHz four core turbo (out of Intel spec but default with Gigabyte BIOS defaults) my system did 203GFLOPS (problem size 44000, 16GiB memory needed) with my handtuned MPI parallel Linpack. Thread parallel might give a small boost but I'm more familar with MPI parallel codes. So your 180GFLOPS is within the same region. And you're facing the same problems, temperature close to thermal throttling, even with a very good heatsink on your system, too. Oliver Last fiddled with by TheJudger on 2013-09-01 at 16:00 |
|
|
|
|
|
#251 |
|
"Oliver"
Mar 2005
Germany
11×101 Posts |
Hello,
currently I'm disapointed with this CPU. The CPU is not bad at all, but for a "k" CPU I would expect more (I know there is no guarantee for overclocking...). The "k" costs a bit more than a "non k" i7-4770.
![]() Currently I aim for a mprime v28.1/Linpack 24/7 stable OC @4000MHz, 4100MHz isn't possible for me. Oliver |
|
|
|
|
|
#252 |
|
"Mr. Meeseeks"
Jan 2012
California, USA
1000011110002 Posts |
On my Haswell quad 4430 3.0 GHz, yes I know it is only 3 GHz.. but I use the stock Intel heatsink and it doesn't go above 60 most of the time. Normal?
EDIT: Intel Rolls Out New Haswell and Ivy Bridge Processors Last fiddled with by kracker on 2013-09-02 at 00:19 |
|
|
|
|
|
#253 |
|
"Mr. Meeseeks"
Jan 2012
California, USA
23·271 Posts |
On 28.1 with one thread, times went from 10 ms to 8 ms.
|
|
|
|
![]() |
| Thread Tools | |
Similar Threads
|
||||
| Thread | Thread Starter | Forum | Replies | Last Post |
| Haswell-E Prelim. Benchmark | sdbardwick | Hardware | 37 | 2015-02-10 18:49 |
| Prime95 and Haswell | Pleco | Information & Answers | 22 | 2014-07-13 16:03 |
| Haswell Rig | Mini-Geek | Hardware | 64 | 2014-05-27 13:22 |
| Prime95 version 27.1 early preview, not-even-close-to-beta release | Prime95 | Software | 126 | 2012-02-09 16:17 |
| Missing mouse-over preview text | retina | Forum Feedback | 1 | 2011-09-12 15:32 |