|
Advice Beginners BIOS Guide CPUs Links Mainboards Memory Network Storage Video/Sound Cards Contact Forum SiteMap Sponsors WebNews Home
|
. | . |
|
CPU Intel P4 840 D P4 820 D P4 630 P4 640 P4 650 P4 660 P4 670 AMD Athlon64 3500+ 3700+ 3800+ 4000+ X2-3800+ X2-4200+ X2-4400+ X2-4600+ X2-4800+ 1-Way Opteron Opteron 144 Opteron 146 Opteron 148 Opteron 150 Opteron 152 2-Way Opteron Opteron 240 Opteron 242 Opteron 244 Opteron 246 Opteron 248 Opteron 250 Opteron 252 2-Way Dual Core Opteron Opteron 270 Opteron 275 nVidia GF 7800GT GF 6800GT GF 6600GT ATI R X850 XT PE R X850 XT R X800 XT PE R X800 XT R X800 XL Memory Corsair Crucial Kingston Mushkin OCZ |
LOSTCIRCUITS |
|
| ESDRAM a New Memory Technology for Improved Utilization of Bandwidth A preview | |
| (Review by MS) |
"Real Time" Side by Side Comparison of SDRAM and ESDRAM
Just take your time and try to count the little red balls released by the two designs at the same run-time.
![]() |
![]() |
| Conventional SDRAM:
This animation simulates a real life data transfer situation where a continuous stream of information is requested from the DIMMs. The refresh rate of the animation is timed to equal 100 MHz (according to the PC-100 specifications). As you can see, only in 4 out of 9 clock cycles there is actual transfer of data (red balls) from the DIMMs to the system bus (in this case L2 cache), the remaining clock cycles are used for internal movement of the data and their duplication. Autorefresh cycles are not included in this demonstration. |
Enhanced SDRAM (ESDRAM):
Again, we are looking at a simulation of a real life situation in which a large amount of data has to be moved from the DIMMs to the system bus (L2 cache). Situations like this occur e.g. in graphics applications or importing/exporting clipboards. The refresh rate of this animation is timed to equal a 133 MHz bus clock frequency, compared to the 100 MHz in the SDRAM simulation on the left. In situations like this, the hidden autorefresh and the earlier bank activate command enabled by the implementation of the row register cache (RRC) bear full fruit since the available bandwidth can be utilized by 80%. That is, 4 cycles of data output are interrupted only by one cycle without data output. |
Conclusion:
The last and most important questions, of course are:
Answers:
next page: => more =>
If you enjoyed reading this article and found it useful, please consider making a small donation to LostCircuits.