Fairly similar. Bandwidth is doubled over GDDR5 by configuring the chip internally as two arrays of GDDR5-like DRAM that can be addressed and read from in parallel, for an effective doubling of the bandwidth compared to GDDR5. Each channel has the same 8n prefetch as DDR4, but there are two channels multiplexed over the bus.
Meh, its still only a press release for a tapeout. Once they have some silicon and have signed up some customers we can start the real conversion. I think its pretty easy to work out from this where this will end up, all the massive processing we are looking at doing in cars and every other device we can think of in coming years, anywhere where GPU like processing could have sped things up, they will be making lower power purpose built SOCs with this attached.
It culd end up in HiSilicon servers as early as next year. Cadence doesn't make products but IP's but list of the partners is long including such as: AMD, Samsung, Mediatek, HiSilicon...
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.
11 Comments
Back to Article
p1esk - Monday, November 26, 2018 - link
So how does GDDR6 compare to DDR4?Ryan Smith - Monday, November 26, 2018 - link
Really fast (14Gbps/pin versus 3.2Gbps/pin). Really power hungry (a few times the power consumption).DanNeely - Monday, November 26, 2018 - link
AFAIK it's also tuned farther in favor of sequential/streaming access than to random IO.saratoga4 - Monday, November 26, 2018 - link
Fairly similar. Bandwidth is doubled over GDDR5 by configuring the chip internally as two arrays of GDDR5-like DRAM that can be addressed and read from in parallel, for an effective doubling of the bandwidth compared to GDDR5. Each channel has the same 8n prefetch as DDR4, but there are two channels multiplexed over the bus.Anymoore - Monday, November 26, 2018 - link
Tapeout is not silicon.saratoga4 - Monday, November 26, 2018 - link
The title of the post makes it pretty clear that they've announced intellectual property, not a product.webdoctors - Monday, November 26, 2018 - link
Author writes this:Traditionally, GDDR memory has been used primarily for graphics cards, but with GDDR6 things look a bit different.
Than doesn't explain why its different, just vendors are advertising it in other markets.
GDDR memory hasn't been used in desktop or mobile since its more expensive, less capacity and uses more power.
The author doesn't explain any technical reason why GDDR6 would differ for these 3 areas. SAD
danielfranklin - Monday, November 26, 2018 - link
Meh, its still only a press release for a tapeout. Once they have some silicon and have signed up some customers we can start the real conversion.I think its pretty easy to work out from this where this will end up, all the massive processing we are looking at doing in cars and every other device we can think of in coming years, anywhere where GPU like processing could have sped things up, they will be making lower power purpose built SOCs with this attached.
ZolaIII - Tuesday, November 27, 2018 - link
It culd end up in HiSilicon servers as early as next year. Cadence doesn't make products but IP's but list of the partners is long including such as: AMD, Samsung, Mediatek, HiSilicon...iwod - Tuesday, November 27, 2018 - link
So what happen to HBM 2/3? Which should have brought us to 1TB/s Memory Bandwidth.Eric Klien - Wednesday, November 28, 2018 - link
Nvidia's V100 uses HBM2 running at 0.9 TB/s memory bandwidth. We're getting there!