lkaufman wrote:Thanks. It now appears that the large change in relative speed of Komodo vs. other engines may not be due to the Ivy Bridge technology, but rather it seems that for some unknown reason Komodo's relative speed is lower on my older twelve core machine than on all other machines checked, regardless of Sandy Bridge or Ivy Bridge. I should mention that we are running one match per thread, so that on a normal i7 we run 8 matches, on the twelve core we run 24, and on the 16 core we run 32. Somehow, Komodo slows down much more than other engines when we do this on the Sandy Bridge 12 core machine, though even if we only run one match per core the effect is still substantial. Running just a single game, the problem vanishes.
So my revised question is, why would running many matches at once hurt Komodo's speed more than other engines on a two-processor, 12 core Sandy Bridge machine, as compared to either single processor systems or to a two-processor, 16 core Ivy Bridge machine? This doesn't make any sense to me.
Well,1 match on a 32 core machine in a bit on the lean side of things .
Did you try core-1 matches on the machines?
That would leave a bit of "room" for others things (os,gui etc).
No, but if we do one match per thread (rather than per core) I don't know if it would help anything to leave one thread for other things, would it? In any case the effect of using 31 rather than 32 threads would seem to be minor.
Well,here it would mean using 15 matches,one less than the number of cores.
But you want to keep hyperthreading,did you have the same slowdown with 30 threads too?
lkaufman wrote:So my revised question is, why would running many matches at once hurt Komodo's speed more than other engines on a two-processor, 12 core Sandy Bridge machine, as compared to either single processor systems or to a two-processor, 16 core Ivy Bridge machine? This doesn't make any sense to me.
What kind of machines are these exactly? Dual socket 6-core SB Xeon and a dual socket 8-core IB Xeon? I did not know that Intel has released 8-core IB Xeons.
There are 4-core IB Xeons, but they do not support dual socket. Regular IB does not support dual socket, either.
They are dual socket 6 and 8 core Xeon machines. The 8 cores have been out for some months. I bought mine from JNCS computers, if you want details see their website. My 16 core has a base speed of 2.6 GHz.
At the moment there are no 8-core Ivybridge processors, and there are no Ivybridge processors that support dual socket. So you must have something else.
lkaufman wrote: The 16 core is 1.5 years newer so presumably has somewhat better RAM.
If the old 12 core one is over 1.5 years old, it cannot be Sandybridge. 1.5 years ago, there were no 6-core SB processors, and there were no SB processors supporting dual socket. So it must be something else.
My guess is that your new computer has Sandybridge-EP processors and that your old computer has Westmere-EP / Gulftown processors.
lkaufman wrote:My 16 core has a base speed of 2.6 GHz.
So it must be dual socket with two E5-2670 processors. The E5-2670 is based on Sandybridge. See e.g. here or here. See also its specifications: 32nm lithography, whereas IB is 22nm.
That Ivybridge processors might have been released before the E5-2670 came out (which I have not checked) does not mean the E5-2670 is IB. It is not.
lkaufman wrote:So my revised question is, why would running many matches at once hurt Komodo's speed more than other engines on a two-processor, 12 core Sandy Bridge machine, as compared to either single processor systems or to a two-processor, 16 core Ivy Bridge machine? This doesn't make any sense to me.
What kind of machines are these exactly? Dual socket 6-core SB Xeon and a dual socket 8-core IB Xeon? I did not know that Intel has released 8-core IB Xeons.
There are 4-core IB Xeons, but they do not support dual socket. Regular IB does not support dual socket, either.
They are dual socket 6 and 8 core Xeon machines. The 8 cores have been out for some months. I bought mine from JNCS computers, if you want details see their website. My 16 core has a base speed of 2.6 GHz.
At the moment there are no 8-core Ivybridge processors, and there are no Ivybridge processors that support dual socket. So you must have something else.
lkaufman wrote: The 16 core is 1.5 years newer so presumably has somewhat better RAM.
If the old 12 core one is over 1.5 years old, it cannot be Sandybridge. 1.5 years ago, there were no 6-core SB processors, and there were no SB processors supporting dual socket. So it must be something else.
My guess is that your new computer has Sandybridge-EP processors and that your old computer has Westmere-EP / Gulftown processors.
Do you know the model numbers of the CPUs?
The new one is e5-2670. I don't have the old one handy right now. It was 2.2 Ghz.
lkaufman wrote:My 16 core has a base speed of 2.6 GHz.
So it must be dual socket with two E5-2670 processors. The E5-2670 is based on Sandybridge. See e.g. here or here. See also its specifications: 32nm lithography, whereas IB is 22nm.
That Ivybridge processors might have been released before the E5-2670 came out (which I have not checked) does not mean the E5-2670 is IB. It is not.
OK, my mistake. I know that the E5-2670 has a base speed of 2.6 but a turbo speed of 3.3 (3.0 if all cores in use), and I wrongly associated this turbo as a characteristic of IB, since it was not on my older machine. The new machine is definitely faster than the old by more than the 2.6 to 2.2 GHz, so something has been improved.
lkaufman wrote:The new machine is definitely faster than the old by more than the 2.6 to 2.2 GHz, so something has been improved.
Given that the old one is 1.5 years old and is dual socket, it cannot be Sandybridge. So the old one is Westmere-EP / Gulftown. Sandybridge gave significant performance improvements over Westmere (more than IB over SB).
lkaufman wrote:The new machine is definitely faster than the old by more than the 2.6 to 2.2 GHz, so something has been improved.
Given that the old one is 1.5 years old and is dual socket, it cannot be Sandybridge. So the old one is Westmere-EP / Gulftown. Sandybridge gave significant performance improvements over Westmere (more than IB over SB).
So which technology would be in my standard 4 core I7 from about 2 1/2 years ago?
lkaufman wrote:The new machine is definitely faster than the old by more than the 2.6 to 2.2 GHz, so something has been improved.
Given that the old one is 1.5 years old and is dual socket, it cannot be Sandybridge. So the old one is Westmere-EP / Gulftown. Sandybridge gave significant performance improvements over Westmere (more than IB over SB).
So which technology would be in my standard 4 core I7 from about 2 1/2 years ago?
Westmere-based processors were launched January 7, 2010, but if this overview is correct, there is no regular 4 core i7 based on Westmere. So this 4 core i7 should be based on Nehalem (either Lynnfield or Bloomfield). See also here.
.