Άρα λοιπόν Q6600 (2+2-πύρηνος)... Και τί άλλο;

[YiannisM]

=> Understanding RAM Timings

Spoiler:

Understanding RAM Timings
Author: Gabriel Torres
Type: Tutorials Last Updated: June 13, 2006


Introduction
DDR and DDR2 memories are classified according to the maximum speed at which they can work. But, besides the speed, there is another information that tells you the memory performance: timings. Timings are numbers like 2-3-2-6-T1, 3-4-4-8 or 2-2-2-5, the lower the better. In this tutorial we will explain you exactly what exactly each one of these numbers mean.

DDR and DDR2 memories follow the DDRxxx/PCyyyy classification. By the way, if you are interested in knowing the difference between DDR and DDR2 memories, read our tutorial on this subject.

The first number, xxx, indicates the maximum clock speed that the memory chips support. For instance, DDR400 memories work at 400 MHz at the most, and DDR2-667 can work up to 667 MHz. It is important to notice that this is not the real clock speed of the memory: the real clock of the DDR and DDR2 memories is half the labeled clock speed. This way, in fact, DDR400 memories work at 200 MHz and DDR2-667 memories work at 333 MHz.

The second number indicates the maximum transfer rate that the memory reaches, in MB/s. DDR400 memories transfer data at 3,200 MB/s at the most, hence they are labeled as PC3200. DDR2-667 memories transfer data at 5,336 MB/s and they are labeled as PC2-5400. As you can see, we use the number “2” after “DDR” or “PC” to indicate that we are talking about DDR2 memory, not DDR.

The first classification, DDRxxx, is the standard used to classify memory chips, while the second classification, PCyyyy, is the standard used to classify memory modules. On Figure 1 you can see a PC2-4200 memory module from Corsair, which uses DDR2-533 memory chips.


click to enlarge
Figure 1: A DDR2-533/PC2-4200 memory module.

The maximum transfer rate for a memory module can be calculated thru the following formula:

Maximum Theoretical Transfer Rate = clock x number of bits / 8
Since DIMM modules transfer 64 bits at a time, “number of bits” will be 64. As 64 / 8 equals to 8, we can simplify this formula to:

Maximum Theoretical Transfer Rate = clock x 8
If the memory module is installed on a system where the memory bus is running at a lower clock rate, the maximum transfer rate the memory module will achieve will be lower than its theoretical maximum transfer rate. Actually, this is a very common misjudgment.

For example, let’s say that you bought a pair of DDR500/PC4000 memories. Even though they are labeled as DDR500, they won’t run at 500 MHz automatically on your system. This is the maximum clock rate they support, not the clock rate at which they will be running. If you install it on a regular PC system supporting DDR memories, they will run at 400 MHz (DDR400) – which the maximum DDR standard speed –, achieving a maximum transfer rate of 3,200 MB/s (or 6,400 MB/s if they are running under dual channel mode, read our tutorial on dual channel to understand more about this subject). So, they won’t automatically run at 500 MHz nor automatically achieve the 4,000 MB/s transfer rate.

So, why someone would buy these modules? For overclocking: since the manufacturer guarantees that these modules will run up to 500 MHz, you know that you can raise the memory bus clock up to 250 MHz to achieve a higher performance with your system. However, your motherboard must support this kind of overclocking (read our tutorial on memory overclocking for more details). So buying a memory module with a labeled clock rate higher than what your system supports is useless if you are not going to overclock your system.

For the average user, that is everything that we have to know about DDR/DDR2 memories. For the advanced user, there is yet another characteristic: the temporization of the memory, a.k.a. timings or latency. Let’s talk about it.


Timings
Because of timings, two memory modules with the same theoretical maximum transfer rate can achieve different performance levels. Why is this possible if both are running at the same clock rate?

Timings measure the time the memory chip delays doing something internally. Let’s give you an example. Consider the most famous parameter, which is called CAS Latency (or CL or “access time”) and tells us how many clock cycles the memory module will delay in returning a data requested by the CPU. A memory module with a CL 4 will delay four clock cycles to deliver a requested data, whereas a memory module with a CL 3 will delay three clock cycles to deliver it. While both modules may run at the same clock rate, the second one will be faster, as it will deliver data sooner than the first one. This issue is known as “latency”. If you pay attention on Figure 1, you will see that the module portrayed there has a CL of 4.

The memory timings are given through a series of numbers, as, for instance 2-3-2-6-T1, 3-4-4-8 or 2-2-2-5. These numbers indicate the amount of clock cycles that it takes the memory to perform a certain operation. The smaller the number, the faster the memory is.


click to enlarge
Figure 2: A DDR2 memory module with 5-5-5-15 timings.

The operations that these numbers indicate are the following: CL-tRCD-tRP-tRAS-CMD. To understand them, bear in mind that the memory is internally organized as a matrix, where the data are stored at the intersection of the lines and columns.

CL: CAS Latency. The time it takes between a command having been sent to the memory and when it begins to reply to it. It is the time it takes between the processor asking for some data from the memory and it returning it.
tRCD: RAS to CAS Delay. The time it takes between the activation of the line (RAS) and the column (CAS) where the data are stored in the matrix.
tRP: RAS Precharge. The time it takes between disabling the access to a line of data and the begin of the access the another line of data.
tRAS: Active to Precharge Delay. How long the memory has to wait until the next access to the memory can be initiated.
CMD: Command Rate. The time it takes between the memory chip having been activated and when the first command may be sent to the memory. Sometimes this value is not informed. It usually is T1 (1 clock cycle) or T2 (2 clock cycles).
Usually you have two options. To configure your PC to use the memory standard timings – usually by setting memory configuration to “Auto” on the motherboard setup – or to manually configure your PC to use lower memory timings, which may increase the performance of your system. Notice that not all motherboards allow you to change the memory timings. Also, some motherboards may not be able to run at very low timings, and they may configure your memory module to run at a higher timing setting because of this.


click to enlarge
Figure 3: Configuration of memory timings at the motherboard setup.

When overclocking your memory you may need to increase the memory timings in order to make the system to run stable. Here is where something very interesting happens. Due to the increased timings, the memory may achieve a lower performance, even though it is now configured to run at a higher clock rate, due to the latency that was introduced.

That is another advantage of memory modules sold specifically for overclocking. The manufacturer, besides guaranteeing you that your memory module will achieve the labeled clock rate, they also guarantee that you will be able to keep the labeled timings up to the labeled clock.

Coming back to the DDR500/PC4000 memory module example, even though you may achieve 500 MHz (250 MHz x2) with DDR400/PC3200 modules, on these modules it may be necessary to increase the memory timings, while on the DDR500/PC4000 ones the manufacturer guarantees that you will be able to achieve 500 MHz keeping the labeled timings.

Now we are going a step further as we will explain in details each one of the memory timing parameters.


CAS Latency (CL)
As mentioned before, CAS Latency (CL) is the most famous memory parameter. It tells us how many clock cycles the memory will delay to return a requested data. A memory with CL = 3 will delay three clock cycles to deliver data, while a memory with CL = 5 will delay five clock cycles to perform the same operation. Thus two memory modules running at the same clock rate the one with the lowest CL will be the faster.

Notice that the clock rate here is the real clock rate under which the memory module is running – i.e. half the rated clock rate. As DDR and DDR2 memories can deliver two data per clock cycle, they are rated with the double of their real clock rate.

On Figure 4 you can see how CL works. We gave two examples, a memory module with CL = 3 and a memory module with CL = 5. The command in blue would be a “read” command.


click to enlarge
Figure 4: CAS Latency (CL).

A memory with CL = 3 will provide a 40% improvement on memory latency over a memory with CL = 5, considering both running at the same clock rate.

You can even calculate the time the memory delays until it starts delivering data. The period of each clock cycle can be easily calculated thru the formula:

T = 1 / f
Thus the period of each clock cycle of a DDR2-533 memory running at 533 MHz (266.66 MHz clock) would be 3.75 ns (ns = nanosecond; 1 ns = 0.000000001 s). Keep in mind that you need to use the real clock rate, which is half the labeled clock rate. So this DDR2-533 memory would delay 18.75 ns to start delivering data, if it had CL =5, or 11.25 ns, if it had CL =3, for example.

SDRAM, DDR and DDR2 memories implement burst mode, where data after the first requested data delays only one clock cycle to exit the memory, if the next requested data is located in the address right after the current requested address. So, while the first data would delay CL clock cycles to exit the memory, the next data would be delivered right after the data that has just came out from the memory, not having to wait another CL cycle.


RAS to CAS Delay (tRCD)
Each memory chip is organized internally as a matrix. At the intersection of each row and column we have a small capacitor that is in charge of storing a “0” or a “1” – the data. Inside the memory the process of accessing the stored data is done by activating the row where it is located and then the column where it is located. This activation is done by two control signals called RAS (Row Address Strobe) and CAS (Column Address Strobe). The less time there is between these two signals the better, as the data will be read sooner. RAS to CAS Delay or tRCD measures this time. On Figure 5 we illustrate this, showing a memory with tRCD = 3.


click to enlarge
Figure 5: RAS to CAS Delay (tRCD).

As you can see, RAS to CAS Delay is also the number of clock cycles taken between the “Active” command and a “read” or “write” command.

As it happens with CAS Latency, RAS to CAS Delay works with the memory real clock (which is half the memory labeled clock), and the lower this parameter is, the faster the memory will be, as it will start reading or writing data earlier.


RAS Precharge (tRP)
After data is gathered from the memory, a command called Precharge needs to be issued, closing the memory row that was being used and allowing a new row to be activated. RAS Precharge time (tRP) is the time taken between the Precharge command and the next Active command can be issue. As we learned from the previous page, the “active” command starts a read or write cycle.


click to enlarge
Figure 6: RAS Precharge (tRP).

On Figure 6 we are giving an example of a memory with tRP = 3.

As it happens with the other parameters, RAS Precharge works with the memory real clock (which is half the memory labeled clock), and the lower this parameter is, the faster the memory will be, as it will issue the “active” command earlier.

Adding everything we’ve seen, the time elapsed between issuing the Precharge command and actually getting the data will be tRP + tRCD + CL.


Other Parameters
Let’s take a better look on the other two parameters, Active to Precharge Delay (tRAS) and Command Rate (CMD). As it happens with the other parameters, these two parameters work with the memory real clock (which is half the memory labeled clock), and the lower these parameters are, the faster the memory will be.

Active to Precharge Delay (tRAS): After an “Active” command is issued, another “Precharge” command cannot be issued until tRAS has been elapsed. So this parameter limits when the memory can start reading (or writing) a different row.
Command Rate (CMD): It is the time taken by the memory chip from being activated (thru its CS – Chip Select – pin) and when any command can be issued to the memory. This parameter carries the letter “T” with it and possible values are 1T or 2T, meaning one clock cycle or two clock cycles, respectively.

[wi fi thief]

=> Understanding RAM Timings

Uncomplicating the Complicated!!! ονομα και πραμα

το hardwaresecrets.com βαλτε το ολοι στα bookmark σας!!!

[l_satsok]

να επανελθουμε στο cpu.
οτι παρεις τωρα ειναι step B3 (TDP 105Watt)
το G0 (TDP 90 Watt) θα βγει στην αγορα μετα το δεκεμβρη.

αυτο πιστευω το γνωριζεις.

το eshop τον εχει 257 ευρω,αλλα γιατι ρε παιδια εχει μενει
επι πολλες μερες με μονο 2-3 cpu στον καταλογο του;;
καποιος μου σφυριξε οτι παει για φουντο...

[YiannisM]

να επανελθουμε στο cpu.
οτι παρεις τωρα ειναι step B3 (TDP 105Watt)
το G0 (TDP 90 Watt) θα βγει στην αγορα μετα το δεκεμβρη.

αυτο πιστευω το γνωριζεις.

Όχι δεν το γνώριζα.
Και τι σημαίνει αυτό πρακτικά; Ότι θα καταναλώνει+ζεσταίνεται κάτι παραπάνω;




Επίσης αν κάποιος ξέρει για τις μνήμες, ας μας πει εάν τα ram dims 2x2 GB υποστηρίζονται από 32 bit συστήματα στις καινούριες m/bs που συζητάμε ή όχι.

[l_satsok]

Και τι σημαίνει αυτό πρακτικά; Ότι θα καταναλώνει+ζεσταίνεται κάτι παραπάνω;

αυτο ακριβως.
τωρα πουλανε οτι τσιπακια εχουν μεινει.
αλλα παρτο τωρα,που ξερεις απο δεκεμβρη μπορει να τον ακριβυνουν...

[YiannisM]

Μπα, δε νομίζω να ακριβήνουν το Δεκέμβρη, συμπατριώτη.

Μέχρι το Δεκέμβρη όμως, έχουμε αρκετά ψωμιά ακόμα...

[wi fi thief]

Off Topic

μεχρι τον δεκεμβρη μαλλον θα εχουμε και πραγματικους τετραπυρηνους στην αγορα...

[Kapnos]

Από ποιον όμως; Γκουχου γκουχου

[teodor_ch]

Off Topic

αυτό το πραγματικούς μου έχει σπάσει τα νεύρα. έχετε δοκιμάσει "ψεύτικο" τετραπύρηνο και δε σας κάλυψε? (εγώ δεν έχω δοκιμάσει)

[wi fi thief]

Off Topic

αυτό το πραγματικούς μου έχει σπάσει τα νεύρα. έχετε δοκιμάσει "ψεύτικο" τετραπύρηνο και δε σας κάλυψε? (εγώ δεν έχω δοκιμάσει)

εγω δεν εχω δοκιμασει (και μαλλον δεν χρειαζεται και να δοκιμασω), ουτε πραγματικους ουτε ντεμεκ

Το πραγματικους (μενει να δουμε βεβαιως τον αληθινο του χαρακτηρισμου) ειναι εμπνευσμενο απο τον τιτλο του θεματος : 2+2-πυρηνος και εννοει τους αναμενομενους amd (και intel) οι οποιοι δεν θα εχουνε (καθως λεγεται) την ιδια τεχνολογια με τους τωρινους quad

[Sebu]

Οταν σου ερθει ενα φιλαρακι και σου ζητησει να του δωσεις 5-10GB mp3s, απο αυτα που κατεβασες χθες το βραδυ, τι θα κανετε σε αυτη την περιπτωση?
Θα συνδεσετε ασυρματα τον φορητο ή θα περιμενετε 2 ωρες με το κατοσταρι lan των routers?
Αντιθετα με ενα cross καλωδιο κανετε ανετοτατα μια συνδεση pc to pc...

Του τα γραφεις σε ενα dvd σε 5 λεπτακια.Και τα εχει ετοιμα σε backup μορφη και δεν κινδυνευει ποτε να τα χασει!!!Η μαγεια θα ηταν ενα φτηνο 1000αρι ρουτερ ή εστω 1000αρι switch.Εκει θα γινοταν παρτι!!!

[wi fi thief]

Off Topic

Οταν σου ερθει ενα φιλαρακι και σου ζητησει να του δωσεις 5-10GB mp3s, απο αυτα που κατεβασες χθες το βραδυ, τι θα κανετε σε αυτη την περιπτωση?

θα του πεις οτι τα πληρωσες ακριβα (1000 τραγουδια = 100 ευρα) και οτι απαγορευεται απο τους νομους προστασιας της πνευματικης ιδιοκτησιας να του τα δωσεις.
Θα του δωσεις λοιπον τις διευθυνσεις των δισκογραφικων εταιριων και μια πιστωτικη καρτα να παει να τα αγορασει...

χαχαχαχαχαχαχα

φανταστειτε να ερθει η ωρα που θα ζουμε σε μια κοινωνια που θα εφαρμοζει κιολας τους νομους και οχι μονο θα τους θεσπιζει...

[YiannisM]

Το πραγματικους (μενει να δουμε βεβαιως τον αληθινο του χαρακτηρισμου) ειναι εμπνευσμενο απο τον τιτλο του θεματος : 2+2-πυρηνος και εννοει τους αναμενομενους amd (και intel) οι οποιοι δεν θα εχουνε (καθως λεγεται) την ιδια τεχνολογια με τους τωρινους quad

Ο τιτλος του θεματος : 2+2-πυρηνος ήταν για να μην γυρίσουμε ξανά σ αυτήν ακριβώς τη συζήτηση.

Για μένα το 2+2-πυρηνος σημαίνει και κυριολοκτικά 4-πυρηνος, αφού ως γνωστόν 2+2=4 (και όχι 3.9).
Η διαφορά των 2 dies έχει βέβαια κι αυτή τη σημασία της, αλλά δε νομίιζω ότι μπορεί ν αλλάζει την απλή αριθμητική.