Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
AMD Discussion
- Thread starter koyoot
- Start date
- Sort by reaction score
So, they're keeping the Opteron brand.
Naples and Vega would fit like a glove in the mMP. Lots of cores for those who want/need them, loads of PCIe lanes, no PCH, HSA.
Naples and Vega would fit like a glove in the mMP. Lots of cores for those who want/need them, loads of PCIe lanes, no PCH, HSA.
Too bad about Itanium, I still had hopes that it would come back, in some form anyway. x86 seems to not want to go away.
Actually, they are RISC CPUs that have a JIT front end to recompile x64 instructions on the fly into RISC instructions that are executed by the RISC core.
Intel adopted this approach with the P6.
The programmer sees Fortran or Cobol - and they certainly aren't running on Fortran CPUs or Cobol CPUs.
Look up "abstraction".
AMD x64 could be the same, but AMD is more or less irrelevant in the CPU space.
Last edited:
Oh please.
The "assembly programmer"? I'm glad that you used the singular, because there probably aren't two of them still working on the planet.
And that x64 assembly programmer's code will be compiled into µops and executed by a RISC processor.
Your views are distorted by working in a certain application area.
That processor is inaccessible and inside the one that matters to low level programmers.
And you don't realize that since the P6, "low level programmers" are actually writing in a higher level language.
No Intel x64 processor actually executes x64 instructions.
Most low level programmers work in C, eventually C++. That does not mean many do not have to deal with assembly.
Interesting information has been dug up from driver repo for Linux, about Raven Ridge APUs:
https://forums.anandtech.com/thread...-specifications.2479296/page-25#post-38890649
2M3001C3T4MF2_33/30_N + AMD 15DD
2M2000C4T4MF2_33/20_N + AMD 15DD
2M1901C4T4MF2_30/19_N + AMD 15DD
All the 15DD are Raven IDs. Checking the sources it is pretty clear Vega and Raven use GFX9.
I checked out out the agd5f repo, now browsing the branch drm-next-4.13-wip
Some Info from the sources as of this commit
- Max VRAM width is 2048, read from register ranges 128 bit to 2048 bit. VRAM seems to be HBM only for GFX9?
- There are bin files/microcode which are loaded into the asic everytime when driver is loaded?
- Vega and Raven belongs to new chip family unlike Polaris which belong to a big family of chips (Tonga, Fiji, Polaris10/11)
- Vega has many new ip blocks,
- Raven is having many similar ip blocks, including the memory controller for gfx9, but it lacks uvd and vce??? missing code
Ok found the vcn instead, which according to phoronix is doing similar job.
So basically Vega GPUs are designed to work with only HBM2 memory...
https://forums.anandtech.com/thread...-specifications.2479296/page-25#post-38890649
2M3001C3T4MF2_33/30_N + AMD 15DD
2M2000C4T4MF2_33/20_N + AMD 15DD
2M1901C4T4MF2_30/19_N + AMD 15DD
All the 15DD are Raven IDs. Checking the sources it is pretty clear Vega and Raven use GFX9.
I checked out out the agd5f repo, now browsing the branch drm-next-4.13-wip
Some Info from the sources as of this commit
- Max VRAM width is 2048, read from register ranges 128 bit to 2048 bit. VRAM seems to be HBM only for GFX9?
- There are bin files/microcode which are loaded into the asic everytime when driver is loaded?
- Vega and Raven belongs to new chip family unlike Polaris which belong to a big family of chips (Tonga, Fiji, Polaris10/11)
- Vega has many new ip blocks,
- Raven is having many similar ip blocks, including the memory controller for gfx9, but it lacks uvd and vce??? missing code
Ok found the vcn instead, which according to phoronix is doing similar job.
So basically Vega GPUs are designed to work with only HBM2 memory...
http://tieba.baidu.com/p/5116196649
Dem it looks very, very good.
Ryzen 9 1998X: 155W TDP, 16C/32T, 3.5-3.8 GHz.
Ryzen 9 1998: 155W TDP, 16C/32T, 3.2-3.6 GHz.
Ryzen 9 1997X: 155W TDP, 14C/28T, 3.5-3.9 GHz.
Ryzen 9 1977: 140W TDP, 14C/28T, 3.2-3.7 GHz.
Ryzen 9 1976X: 140W TDP, 12C/24T, 3.6-4.0 GHz.
Ryzen 9 1956: 125W TDP, 12C/24T, 3.0-3.7 GHz.
Ryzen 9 1955X: 125W TDP, 10C/20T, 3.6-3.9 GHz.
Ryzen 9 1955: 125W TDP, 10C/20T, 3.1-3.7 GHz.
My sources are suggesting extremely competitive pricing.
Top end model - 1499$. At least this is first rumor that is floating around in retial lines...
If it is correct AMD pretty much has a killer line in CPUs.
Also there might be Ryzen 7 1900X, 8C/16T CPU with higher core clocks, than 1800X. And the suggested price is between 599 and 649$.
Dem it looks very, very good.
Ryzen 9 1998X: 155W TDP, 16C/32T, 3.5-3.8 GHz.
Ryzen 9 1998: 155W TDP, 16C/32T, 3.2-3.6 GHz.
Ryzen 9 1997X: 155W TDP, 14C/28T, 3.5-3.9 GHz.
Ryzen 9 1977: 140W TDP, 14C/28T, 3.2-3.7 GHz.
Ryzen 9 1976X: 140W TDP, 12C/24T, 3.6-4.0 GHz.
Ryzen 9 1956: 125W TDP, 12C/24T, 3.0-3.7 GHz.
Ryzen 9 1955X: 125W TDP, 10C/20T, 3.6-3.9 GHz.
Ryzen 9 1955: 125W TDP, 10C/20T, 3.1-3.7 GHz.
My sources are suggesting extremely competitive pricing.
Top end model - 1499$. At least this is first rumor that is floating around in retial lines...
If it is correct AMD pretty much has a killer line in CPUs.
Also there might be Ryzen 7 1900X, 8C/16T CPU with higher core clocks, than 1800X. And the suggested price is between 599 and 649$.
Last edited:
Different Socket. There will be nothing apart from HEDT CPUs for the socket that will get Ryzen 9 CPUs.
Man, are we starting again the naming war?
Now it's i9 and it couldn't be otherwise but Ryzen 9...
Now it's i9 and it couldn't be otherwise but Ryzen 9...