Monday, December 11th 2017
Rambus Talks HBM3, DDR5 in Investor Meeting
Rambus, a company that has veered around the line of being an innovative company and a patent troll, has shed some more light on what can be expected from HBM3 memory (when it's finally available). In an investor meeting, representatives from the company shared details regarding HBM3's improvements over HBM2. Details are still scarce, but at least we know Rambus' expectations for the technology: double the memory bandwidth per stack when compared to HBM2 (4000 MB/s), and a more complex design, which leaves behind the 2.5D design due to increased height of the HBM3 memory stacks. An interesting thing to note is that Rambus is counting on HBM3 to be produced on 7 nm technologies. Considering the overall semiconductor manufacturing calendar for the 7 nm process, this should place HBM3 production in 2019, at the earliest.
HBM3 is also expected to bring much lower power consumption compared to HBM2, besides increasing memory density and bandwidth. However, the "complex design architectures" in the Rambus slides should give readers pause. HBM2 production has had some apparent troubles in reaching demand levels, with suspected lower yields than expected being the most likely culprit. Knowing the trouble AMD has had in successful packaging of HBM2 memory with the silicon interposer and its own GPUs, an even more complex implementation of HBM memory in HBM3 could likely signal some more troubles in that area - maybe not just for AMD, but for any other takers of the technology. Here's hoping AMD's woes were due only to one-off snags on their packaging partners' side, and doesn't spell trouble for HBM's implementation itself.
Other details that surfaced in the Rambus investor meeting pertain to DDR5 memory. Rambus says these will also be built under the 7 nm fabrication process, which is reinforced by Micron's assertions that the new memory specifications would be ready for production in 2020. With higher volume being needed for DDR5 production than HBM3, it makes sense that the latter would see production and sale to customers slightly before DDR5, to test the new 7 nm fabrication processes in a lower volume, higher margin product, ensuring yields of DDR5 to be within adequate rates.
Source:
Computerbase
HBM3 is also expected to bring much lower power consumption compared to HBM2, besides increasing memory density and bandwidth. However, the "complex design architectures" in the Rambus slides should give readers pause. HBM2 production has had some apparent troubles in reaching demand levels, with suspected lower yields than expected being the most likely culprit. Knowing the trouble AMD has had in successful packaging of HBM2 memory with the silicon interposer and its own GPUs, an even more complex implementation of HBM memory in HBM3 could likely signal some more troubles in that area - maybe not just for AMD, but for any other takers of the technology. Here's hoping AMD's woes were due only to one-off snags on their packaging partners' side, and doesn't spell trouble for HBM's implementation itself.
17 Comments on Rambus Talks HBM3, DDR5 in Investor Meeting
I understand you want to advocate RDRAM, but there wasn't anything particularly great about RDRAM, besides bandwidth. And even that was beaten, by the time DDR PC-3200 came around.
Grow up a little, the both of you. I was building and working on PC's in the 1980's, which is likely before either of you were born. When sharing information like this, it is at all times based on actual experience, not drivel discovered through Google.
I actually owned one of the systems in question. Socket 423 P4 with RDRAM.
RDRAM was good for next to no time and was attached to a garbage CPU platform aka Intel's socket 423. Socket 423 by the way didn't even make it a year, much like the RDRAM it was equipped with. (to be fair there where a handful of RDRAM equipped s478 boards, but with DDR performing better and being cheaper that lasted next to no time).
You being older doesn't make you know anything. I have dealt with enough older individuals that have trouble turning on a PC let alone knowing what they are talking about with one.
EDIT; There is a reason why Nintendo and Sony chose RDRam over other types for their games system of that time. I wonder what that reason was? Certainly wasn't the cost..