Most likely that is just the controller power consumption. Depeding on the type and capacity of NAND, the actual SSD power consumption should be higher than that.
For comparison SK Hynix P31: Idle <50mW, Active 6.3W SK Hynix P41: Idle <50mW, Active 7.5W Kingston KC3000: Avg 0.36W, Max 2.8W Read / 9.9W Write Sabrent Rocket Q4: Idle 76mW, Active 10.58W
Referring to those numbers, 3.5W idle would be high, but it would be very low for peak/max too.
I think it's inaccurate to claim that all Gen 5 SSDs require "massive heatsinks" when in fact most of them run just fine with the mobo supplied flat heatsink. While they might be borderline for laptops, most any consumer performance mobo released in the past few years will run the majority of Gen 5 SSDs without any overheating throttling. For those who don't know the Gen 5 SSD "massive heatsinks" are a gimmick to sway the uninformed.
Most gaming-oriented computer hardware is to some extent gimmicky because said gimmicks land sales. Until that changes (unlikely considering it's been that way for literal decades in PC hardware and far longer in marketing in general) the gimmicks will continue.
>>>capable of delivering sequential read and write speeds of up to 14 GB/s
If you have a LUKS encrypted drive in your Linux laptop (or BitLocker for Windows) I think even a CPU with AES-NI will be unable to reach this data throughput and will be saturated.
A low-power CPU would have no business with four-laned PCIe 5.0 storage—at least not this generation. The PCIe generation support goes hand in hand with the capabilities of the CPU. I highly doubt a CPU with such asymmetrical support would even exist on the market. Those mobile CPUs which are PCIe 5.0 capable are also powerful enough to push more than 14 GB/s of AES encryption/decryption. Those that can’t, support slower generations of PCIe.
You can confirm by perusing a table of CPUs on the market and what PCIe generation they support. Even within the Ryzen 7000 mobile product stack, there are CPUs with support for only PCIe 3.0.
Raptor Lake U series (ie: i7-1355U, i3-1315U), that only supports PCIe Gen4 x8 off the CPU, and Gen3 x12 off the PCH. Alderlake-N (ie n200) only supports up to Gen3 x9 off the PCH. Ryzen 5 7540U (it's a 6 core, but there is no 4 core option) only supports up to Gen4 x16
Is there a general rule for a difference in IOPS from a e.g. 1M to 2.5M on bandwidth (Does this number need transfer block sizes for conversion into bandwidth GB/s)?
With simple conversion bandwidth=iops/block size 512bytes requires 28M IOPS for 14GB/s 4kB ~3.5M above 6kB 2.5M is sufficient for sustained 14GB/s (if heat transfer is capable for 10-15W through 17-35cm^2 towards mainboard pcb and air flow)?
I believe achieving a GEN5 peak power consumption of 3.5W on a 12nm process is not feasible. A reasonable explanation is that firmware can apply proactive power management, such as utilizing LPDDR, specifically tailored for a fixed testing scenario to attain this goal.
"Silicon Motion's move towards PCIe Gen5 SSDs with an astonishingly low 3.5W power consumption is a game-changer! This advancement not only promises blazing-fast speeds but also energy efficiency - a win for both performance enthusiasts and eco-conscious users. It's incredible to see the constant evolution in SSD technology!"
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
19 Comments
Back to Article
NextGen_Gamer - Wednesday, August 9, 2023 - link
Correction to be made to article: "but 3.5W seems to be too high for peak" - I am assuming that should say too high for idle, not peak.qlum - Wednesday, August 9, 2023 - link
I assumed it was to low for peak instead of to high, seems open to interpetation.Kristian Vättö - Wednesday, August 9, 2023 - link
Most likely that is just the controller power consumption. Depeding on the type and capacity of NAND, the actual SSD power consumption should be higher than that.meacupla - Wednesday, August 9, 2023 - link
For comparisonSK Hynix P31: Idle <50mW, Active 6.3W
SK Hynix P41: Idle <50mW, Active 7.5W
Kingston KC3000: Avg 0.36W, Max 2.8W Read / 9.9W Write
Sabrent Rocket Q4: Idle 76mW, Active 10.58W
Referring to those numbers, 3.5W idle would be high, but it would be very low for peak/max too.
yannigr2 - Wednesday, August 9, 2023 - link
Article typo?"but 3.5W seems to be too high for peak"
peak or idle?
Threska - Wednesday, August 9, 2023 - link
Future NAS are going to be small and interesting.Techie2 - Wednesday, August 9, 2023 - link
I think it's inaccurate to claim that all Gen 5 SSDs require "massive heatsinks" when in fact most of them run just fine with the mobo supplied flat heatsink. While they might be borderline for laptops, most any consumer performance mobo released in the past few years will run the majority of Gen 5 SSDs without any overheating throttling. For those who don't know the Gen 5 SSD "massive heatsinks" are a gimmick to sway the uninformed.PeachNCream - Wednesday, August 9, 2023 - link
Most gaming-oriented computer hardware is to some extent gimmicky because said gimmicks land sales. Until that changes (unlikely considering it's been that way for literal decades in PC hardware and far longer in marketing in general) the gimmicks will continue.cbm80 - Wednesday, August 9, 2023 - link
Typical consumer SSD usage is very bursty. You only get thermal limiting in rare cases, such as bulk copying from/to an equally fast drive.egan_varley - Thursday, August 10, 2023 - link
>>>capable of delivering sequential read and write speeds of up to 14 GB/sIf you have a LUKS encrypted drive in your Linux laptop (or BitLocker for Windows) I think even a CPU with AES-NI will be unable to reach this data throughput and will be saturated.
LiKenun - Thursday, August 10, 2023 - link
The Ryzen 7 5800X3D can push 141,467 MB/s on an AES encryption benchmark. And that’s the slowest of what was measured.The Ryzen 9 7950X hit 386,019 MB/s. Suppose you divided that evenly among the 16 cores, each one could do 24,126 MB/s.
We’re fine until PCIe 6.0.
Source: https://www.tomshardware.com/reviews/amd-ryzen-9-7...
The specific chart: https://cdn.mos.cms.futurecdn.net/ujsvMFT48ZEpZbhB...
egan_varley - Friday, August 11, 2023 - link
I was talking about laptops.Imagine a 4 cores CPU with 15W TDP trying to encode AES at 14GB/s.
LiKenun - Friday, August 11, 2023 - link
A low-power CPU would have no business with four-laned PCIe 5.0 storage—at least not this generation. The PCIe generation support goes hand in hand with the capabilities of the CPU. I highly doubt a CPU with such asymmetrical support would even exist on the market. Those mobile CPUs which are PCIe 5.0 capable are also powerful enough to push more than 14 GB/s of AES encryption/decryption. Those that can’t, support slower generations of PCIe.You can confirm by perusing a table of CPUs on the market and what PCIe generation they support. Even within the Ryzen 7000 mobile product stack, there are CPUs with support for only PCIe 3.0.
meacupla - Saturday, August 12, 2023 - link
4 core 15W TDP?Raptor Lake U series (ie: i7-1355U, i3-1315U), that only supports PCIe Gen4 x8 off the CPU, and Gen3 x12 off the PCH.
Alderlake-N (ie n200) only supports up to Gen3 x9 off the PCH.
Ryzen 5 7540U (it's a 6 core, but there is no 4 core option) only supports up to Gen4 x16
If I had to guess PCI Gen5 eats a lot of power.
back2future - Thursday, August 10, 2023 - link
Is there a general rule for a difference in IOPS from a e.g. 1M to 2.5M on bandwidth (Does this number need transfer block sizes for conversion into bandwidth GB/s)?With simple conversion bandwidth=iops/block size
512bytes requires 28M IOPS for 14GB/s
4kB ~3.5M
above 6kB 2.5M is sufficient for sustained 14GB/s (if heat transfer is capable for 10-15W through 17-35cm^2 towards mainboard pcb and air flow)?
back2future - Thursday, August 10, 2023 - link
sorry formula is wrong for bandwidth:bandwidth(MB/s) = IOPS * (block size for each IO) / 1024
e.g. 2500000*4kB/1024 = 9765.625MB/s
RainbowDash - Thursday, August 10, 2023 - link
Random R/W IOPS implies 4kB block size. I think it’s specified by JESD219.tonsui - Friday, August 11, 2023 - link
I believe achieving a GEN5 peak power consumption of 3.5W on a 12nm process is not feasible. A reasonable explanation is that firmware can apply proactive power management, such as utilizing LPDDR, specifically tailored for a fixed testing scenario to attain this goal.Musclegaragefitness - Tuesday, August 22, 2023 - link
"Silicon Motion's move towards PCIe Gen5 SSDs with an astonishingly low 3.5W power consumption is a game-changer! This advancement not only promises blazing-fast speeds but also energy efficiency - a win for both performance enthusiasts and eco-conscious users. It's incredible to see the constant evolution in SSD technology!"