Fractal Design Focus 2 chassis review
Scythe Mugen 5 Rev.C CPU Cooler review
be quiet Pure Loop 2 FX 280mm LCS review
HP FX900 1 TB NVMe Review
Scythe FUMA2 Rev.B CPU Cooler review
SK Hynix Platinum P41 2TB M.2 NVMe SSD Review
Corsair K70 RGB PRO Mini Wireless review
MSI MPG A1000G - 1000W PSU Review
Goodram IRDM PRO M.2 SSD 2 TB NVMe SSD Review
Samsung T7 Shield Portable 1TB USB SSD review
AMD changes its statements, Ryzen 7000 will consume up to 230W
After constantly assuring the press and fans that the 170W exhibited at Computex 2022 was the maximum power of the socket, the company has officially verified that the amount is, in fact, the maximum TDP specification for the Ryzen CPU.
This does not imply that the Ryzen 7000 CPUs would have a variant with a TDP of 170 W, as AMD's Robert Hallock stated only two days ago that the value of 170 W was from the PPT, which is the maximum power for the socket. The increased maximum power for the socket of 230 W is nearly as high as the Core i9-12900K for Intel's LGA1200 socket, which offers a maximum load of approximately 241 W.
“AMD would like to correct the maximum socket power and TDP limits of the upcoming Socket AM5. Socket AM5 socket supports up to 170W TDP with up to 230W PPT. TDP*1.35 is the standard calculation for TDP vs. PPT for AMD sockets in “Zen”.
“This new TDP will enable significantly higher compute performance for high core count CPUs under heavy workloads, where we will have other 65W and 105W TDP models that Ryzen is known for today. AMD prides itself on providing the enthusiast community with products with the best transparency, and we want to take this opportunity to apologize for our mistake and any confusion we may have caused on this issue."
So in short: Power Specs: 230W Peak Power, 170W TDP.
AMD Changes Wafer Supply Agreement With GLOBALFOUNDRIES - 09/01/2016 08:47 AM
AMD announced that it has entered into a long-term amendment to its Wafer Supply Agreement (WSA) with GLOBALFOUNDRIES Inc. (GF) for the period from Jan. 1, 2016 to Dec. 31, 2020....
AMD changes BF4 bundle, now selected partners only - 11/15/2013 05:17 PM
An email sent to press this Monday that provided details on AMD’s Battlefield 4 promotion was not clear and has led to some confusion in the marketplace. It suggested that all customers who ...
AMD changes Some APU, CPU Prices; New Athlon II - 11/16/2011 01:13 PM
AMD has restructured some of its prices on the FM1 APUs, also a new Athlon was introduced. The A4-3300 and A4-3400 see a price change as well as the A6-3500 and the FX-6100. The six-core FX-6100 sock...
AMD changes CPU schedules - 11/02/2009 07:01 PM
AMD has updated schedule to phase out several Phenom II X4 900 series CPUs, while launch a new model in 2010, according to sources at motherboard makersaccording to digitimes. AMD has already stopped ...
Horus-Anhur
Senior Member
Posts: 4230
Joined: 2013-02-05
Senior Member
Posts: 4230
Joined: 2013-02-05
#6022916 Posted on: 06/04/2022 08:05 PM
From Hallock's interview.
Is it going to support avx 512? 
From Hallock's interview.
Your presentation mentioned "AI acceleration." Is that AVX-512 or something more exotic, like Intel GNA?
Yes. Specifically, AVX 512 VNNI for neural networking and AVX 512 BLOAT16 for inferencing. Both are pretty nice speedups, we're not using a fixed-function acceleration, this could be something we could do with our Xilinx acquisition. We are starting to see more consumer applicability of AI workloads, like video upscaling, which has grown a lot in the last two years. I think there is a general trend for the average enthusiast to take on more AI-type workloads. The time felt right to bring these features into the chip, given we moved to a smaller process node with better performance, power, and area capabilities.
Yes. Specifically, AVX 512 VNNI for neural networking and AVX 512 BLOAT16 for inferencing. Both are pretty nice speedups, we're not using a fixed-function acceleration, this could be something we could do with our Xilinx acquisition. We are starting to see more consumer applicability of AI workloads, like video upscaling, which has grown a lot in the last two years. I think there is a general trend for the average enthusiast to take on more AI-type workloads. The time felt right to bring these features into the chip, given we moved to a smaller process node with better performance, power, and area capabilities.
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 2082
Joined: 2005-08-05
Is it going to support avx 512?