"36 GB/s (measured by running an MLC workload with a 2:1 read/write ratio on a single module), putting it only slightly behind a DDR5-4800 RDIMM (38.4 GB/s) but orders of magnitude ahead of a NAND-based storage device."
Really? No NAND based storage device can hit 10's of GB/s? Not even PCIe5 x4 drives?
Also, order(s) indicates more than one order of magnitude higher. Even arguing that NAND can only do GB/s instead of 10's of GB/s is a single order of magnitude.
No NAND based storage can hit 10's of GB/s when R/W on 64bit size, which is the word width of current device. Unless you buffer multiple R/W requests but that quickly adds additional latency, like hundreds of times the latency of a single R/W command
Even if it could it wouldn't matter bcuz ram is still 1000's of times lower latency than gen 5 ssds. Hell even the now legacy optane drives absolutely decimate gen 5 drives despite being nearly half the bandwidth bcuz sequential bandwidth hardly matters, it's the iops, particularly at low queue depths and latency where optane is still like 5x faster in low queue depths. Now imagine instead of 5x it's 1000's. V cache is so beneficial because ram takes the cpu like 5x as many cycles to get data from compared to l3. I'm sure the cpu would have ages to fantasise about those sweet, gen 5 sequential bandwidth numbers as it takes the 250000 cycles required to get mere bytes of data from the ssd instead of the 250 needed for ram. Yeah sounds like a bandwidth issue tbh 😂
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
7 Comments
Back to Article
nfriedly - Wednesday, August 9, 2023 - link
> PCIe 5.0 x8 interfaceThat looks more like an x4 just from eyeballing the image(?)
Although I suppose they could fit an x8 if they moved it off-center. Maybe it's just an old photo?
TeXWiller - Thursday, August 10, 2023 - link
The modules are in the E3.S form factor.ballsystemlord - Wednesday, August 9, 2023 - link
> But some applications consume all DRAM they can get and demand more.Like web browsers...
James5mith - Wednesday, August 9, 2023 - link
"36 GB/s (measured by running an MLC workload with a 2:1 read/write ratio on a single module), putting it only slightly behind a DDR5-4800 RDIMM (38.4 GB/s) but orders of magnitude ahead of a NAND-based storage device."Really? No NAND based storage device can hit 10's of GB/s? Not even PCIe5 x4 drives?
Also, order(s) indicates more than one order of magnitude higher. Even arguing that NAND can only do GB/s instead of 10's of GB/s is a single order of magnitude.
lmcd - Wednesday, August 9, 2023 - link
At 4K page size it's multiple orders of magnitude. Thanks for being argumentative though!erinadreno - Friday, August 11, 2023 - link
No NAND based storage can hit 10's of GB/s when R/W on 64bit size, which is the word width of current device. Unless you buffer multiple R/W requests but that quickly adds additional latency, like hundreds of times the latency of a single R/W commandGoku solos - Saturday, August 26, 2023 - link
Even if it could it wouldn't matter bcuz ram is still 1000's of times lower latency than gen 5 ssds. Hell even the now legacy optane drives absolutely decimate gen 5 drives despite being nearly half the bandwidth bcuz sequential bandwidth hardly matters, it's the iops, particularly at low queue depths and latency where optane is still like 5x faster in low queue depths. Now imagine instead of 5x it's 1000's. V cache is so beneficial because ram takes the cpu like 5x as many cycles to get data from compared to l3. I'm sure the cpu would have ages to fantasise about those sweet, gen 5 sequential bandwidth numbers as it takes the 250000 cycles required to get mere bytes of data from the ssd instead of the 250 needed for ram. Yeah sounds like a bandwidth issue tbh 😂